From 888443e447cc0dd6b131da21e0103e6ade29e842 Mon Sep 17 00:00:00 2001
From: paulfantom <pawel@krupa.net.pl>
Date: Tue, 25 May 2021 16:03:49 +0200
Subject: [PATCH] manifests: regenerate
---
manifests/grafana-dashboardDefinitions.yaml | 24498 ++++++++--------
manifests/grafana-deployment.yaml | 6 -
.../kube-state-metrics-prometheusRule.yaml | 23 +
manifests/kubernetes-prometheusRule.yaml | 236 +-
manifests/prometheus-prometheusRule.yaml | 10 +
.../setup/prometheus-operator-deployment.yaml | 2 +
6 files changed, 12776 insertions(+), 11999 deletions(-)
diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml
index 2ab0f97b..267433db 100644
--- a/manifests/grafana-dashboardDefinitions.yaml
+++ b/manifests/grafana-dashboardDefinitions.yaml
@@ -7199,124 +7199,10 @@ items:
"showTitle": true,
"title": "Rate of Packets Dropped",
"titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(node_cpu_seconds_total, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Cluster",
- "uid": "efa86fd1d0c121a26444b636a3f509a8",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-cluster
- namespace: monitoring
-- apiVersion: v1
- data:
- k8s-resources-namespace.json: |-
- {
- "annotations": {
- "list": [
-
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
-
- ],
- "refresh": "10s",
- "rows": [
+ },
{
"collapse": false,
- "height": "100px",
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -7326,9 +7212,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "format": "percentunit",
- "id": 1,
+ "decimals": -1,
+ "fill": 10,
+ "id": 20,
"legend": {
"avg": false,
"current": false,
@@ -7339,7 +7225,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -7352,28 +7238,31 @@ items:
],
"spaceLength": 10,
- "span": 3,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
+ "expr": "ceil(sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m])))",
"format": "time_series",
- "instant": true,
"intervalFactor": 2,
- "refId": "A"
+ "legendFormat": "{{namespace}}",
+ "legendLink": null,
+ "step": 10
}
],
- "thresholds": "70,80",
+ "thresholds": [
+
+ ],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Utilisation (from requests)",
+ "title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "singlestat",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -7410,9 +7299,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "format": "percentunit",
- "id": 2,
+ "fill": 10,
+ "id": 21,
"legend": {
"avg": false,
"current": false,
@@ -7423,7 +7311,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -7436,28 +7324,31 @@ items:
],
"spaceLength": 10,
- "span": 3,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
+ "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
"format": "time_series",
- "instant": true,
"intervalFactor": 2,
- "refId": "A"
+ "legendFormat": "{{namespace}}",
+ "legendLink": null,
+ "step": 10
}
],
- "thresholds": "70,80",
+ "thresholds": [
+
+ ],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Utilisation (from limits)",
+ "title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "singlestat",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -7469,7 +7360,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -7485,7 +7376,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Storage IO",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -7495,8 +7398,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "format": "percentunit",
- "id": 3,
+ "id": 22,
"legend": {
"avg": false,
"current": false,
@@ -7519,113 +7421,239 @@ items:
"seriesOverrides": [
],
+ "sort": {
+ "col": 4,
+ "desc": true
+ },
"spaceLength": 10,
- "span": 3,
+ "span": 12,
"stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
- "format": "time_series",
- "instant": true,
- "intervalFactor": 2,
- "refId": "A"
- }
- ],
- "thresholds": "70,80",
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Utilization (from requests)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "singlestat",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "alias": "IOPS(Reads)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {
+ "alias": "IOPS(Writes)",
+ "colorMode": null,
+ "colors": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "format": "percentunit",
- "id": 4,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "IOPS(Reads + Writes)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Throughput(Read)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Throughput(Write)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Throughput(Read + Write)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Namespace",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down to pods",
+ "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
+ "pattern": "namespace",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ ],
+ "type": "string",
+ "unit": "short"
+ }
],
- "spaceLength": 10,
- "span": 3,
- "stack": false,
- "steppedLine": false,
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
- "format": "time_series",
+ "expr": "sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
"instant": true,
"intervalFactor": 2,
- "refId": "A"
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum by(namespace) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
}
],
- "thresholds": "70,80",
+ "thresholds": [
+
+ ],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Utilisation (from limits)",
+ "title": "Current Storage IO",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "singlestat",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -7658,109 +7686,184 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Headlines",
+ "showTitle": true,
+ "title": "Storage IO - Distribution",
"titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 5,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(node_cpu_seconds_total, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Compute Resources / Cluster",
+ "uid": "efa86fd1d0c121a26444b636a3f509a8",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-k8s-resources-cluster
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ k8s-resources-namespace.json: |-
+ {
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "links": [
+
+ ],
+ "refresh": "10s",
+ "rows": [
+ {
+ "collapse": false,
+ "height": "100px",
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "format": "percentunit",
+ "id": 1,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "quota - requests",
- "color": "#F2495C",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "quota - limits",
- "color": "#FF9830",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "quota - requests",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "quota - limits",
- "legendLink": null,
- "step": 10
+ "refId": "A"
}
],
- "thresholds": [
-
- ],
+ "thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
- "title": "CPU Usage",
+ "title": "CPU Utilisation (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -7788,19 +7891,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU Usage",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -7810,7 +7901,8 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 6,
+ "format": "percentunit",
+ "id": 2,
"legend": {
"avg": false,
"current": false,
@@ -7834,206 +7926,112 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 3,
"stack": false,
"steppedLine": false,
- "styles": [
+ "targets": [
{
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
+ "format": "time_series",
+ "instant": true,
+ "intervalFactor": 2,
+ "refId": "A"
+ }
+ ],
+ "thresholds": "70,80",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Utilisation (from limits)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "singlestat",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
{
- "alias": "CPU Usage",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "CPU Limits",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Limits %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
- "pattern": "pod",
- "thresholds": [
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "format": "percentunit",
+ "id": 3,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
- ],
- "type": "string",
- "unit": "short"
- }
],
+ "spaceLength": 10,
+ "span": 3,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
- "format": "table",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
+ "format": "time_series",
"instant": true,
"intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
- "step": 10
+ "refId": "A"
}
],
- "thresholds": [
-
- ],
+ "thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
- "title": "CPU Quota",
+ "title": "Memory Utilisation (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "transform": "table",
- "type": "table",
+ "type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -8061,19 +8059,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU Quota",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -8082,8 +8068,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 7,
+ "fill": 1,
+ "format": "percentunit",
+ "id": 4,
"legend": {
"avg": false,
"current": false,
@@ -8094,7 +8081,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
@@ -8104,36 +8091,131 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
- {
- "alias": "quota - requests",
- "color": "#F2495C",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "quota - limits",
- "color": "#FF9830",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
+
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
+ "format": "time_series",
+ "instant": true,
+ "intervalFactor": 2,
+ "refId": "A"
+ }
+ ],
+ "thresholds": "70,80",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Utilisation (from limits)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "singlestat",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Headlines",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 10,
+ "id": 5,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 0,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "quota - requests",
+ "color": "#F2495C",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ },
+ {
+ "alias": "quota - limits",
+ "color": "#FF9830",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -8141,7 +8223,7 @@ items:
"step": 10
},
{
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - requests",
@@ -8149,7 +8231,7 @@ items:
"step": 10
},
{
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - limits",
@@ -8162,7 +8244,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Usage (w/o cache)",
+ "title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
@@ -8180,7 +8262,7 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -8202,7 +8284,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Memory Usage",
+ "title": "CPU Usage",
"titleSize": "h6"
},
{
@@ -8218,7 +8300,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 8,
+ "id": 6,
"legend": {
"avg": false,
"current": false,
@@ -8253,7 +8335,7 @@ items:
"type": "hidden"
},
{
- "alias": "Memory Usage",
+ "alias": "CPU Usage",
"colorMode": null,
"colors": [
@@ -8269,10 +8351,10 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Requests",
+ "alias": "CPU Requests",
"colorMode": null,
"colors": [
@@ -8288,10 +8370,10 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Requests %",
+ "alias": "CPU Requests %",
"colorMode": null,
"colors": [
@@ -8310,7 +8392,7 @@ items:
"unit": "percentunit"
},
{
- "alias": "Memory Limits",
+ "alias": "CPU Limits",
"colorMode": null,
"colors": [
@@ -8326,10 +8408,10 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Limits %",
+ "alias": "CPU Limits %",
"colorMode": null,
"colors": [
@@ -8347,63 +8429,6 @@ items:
"type": "number",
"unit": "percentunit"
},
- {
- "alias": "Memory Usage (RSS)",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #F",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
- {
- "alias": "Memory Usage (Cache)",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #G",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
- {
- "alias": "Memory Usage (Swap)",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #H",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
{
"alias": "Pod",
"colorMode": null,
@@ -8441,7 +8466,7 @@ items:
],
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8450,7 +8475,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8459,7 +8484,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8468,7 +8493,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8477,40 +8502,13 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
- },
- {
- "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
- },
- {
- "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "G",
- "step": 10
- },
- {
- "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "H",
- "step": 10
}
],
"thresholds": [
@@ -8518,7 +8516,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Quota",
+ "title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
@@ -8559,7 +8557,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Memory Quota",
+ "title": "CPU Quota",
"titleSize": "h6"
},
{
@@ -8574,9 +8572,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 9,
- "interval": "1m",
+ "fill": 10,
+ "id": 7,
"legend": {
"avg": false,
"current": false,
@@ -8587,7 +8584,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -8597,9 +8594,144 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
-
- ],
- "spaceLength": 10,
+ {
+ "alias": "quota - requests",
+ "color": "#F2495C",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ },
+ {
+ "alias": "quota - limits",
+ "color": "#FF9830",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ }
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{pod}}",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "quota - requests",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "quota - limits",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Usage (w/o cache)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Memory Usage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 8,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
@@ -8611,7 +8743,7 @@ items:
"type": "hidden"
},
{
- "alias": "Current Receive Bandwidth",
+ "alias": "Memory Usage",
"colorMode": null,
"colors": [
@@ -8627,10 +8759,10 @@ items:
],
"type": "number",
- "unit": "Bps"
+ "unit": "bytes"
},
{
- "alias": "Current Transmit Bandwidth",
+ "alias": "Memory Requests",
"colorMode": null,
"colors": [
@@ -8646,10 +8778,10 @@ items:
],
"type": "number",
- "unit": "Bps"
+ "unit": "bytes"
},
{
- "alias": "Rate of Received Packets",
+ "alias": "Memory Requests %",
"colorMode": null,
"colors": [
@@ -8665,10 +8797,10 @@ items:
],
"type": "number",
- "unit": "pps"
+ "unit": "percentunit"
},
{
- "alias": "Rate of Transmitted Packets",
+ "alias": "Memory Limits",
"colorMode": null,
"colors": [
@@ -8684,10 +8816,10 @@ items:
],
"type": "number",
- "unit": "pps"
+ "unit": "bytes"
},
{
- "alias": "Rate of Received Packets Dropped",
+ "alias": "Memory Limits %",
"colorMode": null,
"colors": [
@@ -8703,10 +8835,10 @@ items:
],
"type": "number",
- "unit": "pps"
+ "unit": "percentunit"
},
{
- "alias": "Rate of Transmitted Packets Dropped",
+ "alias": "Memory Usage (RSS)",
"colorMode": null,
"colors": [
@@ -8722,7 +8854,45 @@ items:
],
"type": "number",
- "unit": "pps"
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Usage (Cache)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #G",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Usage (Swap)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #H",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "bytes"
},
{
"alias": "Pod",
@@ -8734,7 +8904,7 @@ items:
"decimals": 2,
"link": true,
"linkTargetBlank": false,
- "linkTooltip": "Drill down to pods",
+ "linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@@ -8761,7 +8931,7 @@ items:
],
"targets": [
{
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8770,7 +8940,7 @@ items:
"step": 10
},
{
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8779,7 +8949,7 @@ items:
"step": 10
},
{
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8788,7 +8958,7 @@ items:
"step": 10
},
{
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8797,7 +8967,7 @@ items:
"step": 10
},
{
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -8806,13 +8976,31 @@ items:
"step": 10
},
{
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
+ },
+ {
+ "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "G",
+ "step": 10
+ },
+ {
+ "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "H",
+ "step": 10
}
],
"thresholds": [
@@ -8820,7 +9008,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Current Network Usage",
+ "title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
@@ -8861,7 +9049,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Current Network Usage",
+ "title": "Memory Quota",
"titleSize": "h6"
},
{
@@ -8876,8 +9064,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 10,
+ "fill": 1,
+ "id": 9,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -8888,7 +9077,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
@@ -8901,31 +9090,234 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 12,
+ "stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- }
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
+ {
+ "alias": "Current Receive Bandwidth",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Current Transmit Bandwidth",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Rate of Received Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Received Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Pod",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down to pods",
+ "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+
+ ],
+ "type": "string",
+ "unit": "short"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ }
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
- "title": "Receive Bandwidth",
+ "title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -8937,7 +9329,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -8953,7 +9345,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Current Network Usage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -8963,7 +9367,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 11,
+ "id": 10,
"legend": {
"avg": false,
"current": false,
@@ -8992,7 +9396,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9005,7 +9409,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Transmit Bandwidth",
+ "title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9039,19 +9443,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Bandwidth",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -9061,7 +9453,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 12,
+ "id": 11,
"legend": {
"avg": false,
"current": false,
@@ -9090,7 +9482,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9103,7 +9495,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9137,7 +9529,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Bandwidth",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -9147,7 +9551,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 13,
+ "id": 12,
"legend": {
"avg": false,
"current": false,
@@ -9176,7 +9580,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9189,7 +9593,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets",
+ "title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9223,19 +9627,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -9245,7 +9637,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 14,
+ "id": 13,
"legend": {
"avg": false,
"current": false,
@@ -9274,7 +9666,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9287,7 +9679,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9321,7 +9713,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Rate of Packets",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -9331,7 +9735,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 15,
+ "id": 14,
"legend": {
"avg": false,
"current": false,
@@ -9360,7 +9764,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9373,7 +9777,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
+ "title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9407,160 +9811,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets Dropped",
- "titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
},
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "namespace",
- "options": [
-
- ],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Namespace (Pods)",
- "uid": "85a562078cdf77779eaa1add43ccec1e",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-namespace
- namespace: monitoring
-- apiVersion: v1
- data:
- k8s-resources-node.json: |-
- {
- "annotations": {
- "list": [
-
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
-
- ],
- "refresh": "10s",
- "rows": [
- {
- "collapse": false,
- "height": "250px",
- "panels": [
{
"aliasColors": {
@@ -9570,7 +9821,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 1,
+ "id": 15,
"legend": {
"avg": false,
"current": false,
@@ -9594,12 +9845,12 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9612,7 +9863,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Usage",
+ "title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -9630,7 +9881,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -9652,7 +9903,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "CPU Usage",
+ "title": "Rate of Packets Dropped",
"titleSize": "h6"
},
{
@@ -9667,8 +9918,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 2,
+ "decimals": -1,
+ "fill": 10,
+ "id": 16,
"legend": {
"avg": false,
"current": false,
@@ -9679,7 +9931,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -9692,206 +9944,31 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
- "styles": [
- {
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
- },
+ "targets": [
{
- "alias": "CPU Usage",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "CPU Limits",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Limits %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "pod",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
-
- ],
- "type": "string",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
- "step": 10
- }
- ],
- "thresholds": [
+ "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m])))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{pod}}",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Quota",
+ "title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "transform": "table",
- "type": "table",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -9919,19 +9996,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU Quota",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -9941,7 +10006,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 3,
+ "id": 17,
"legend": {
"avg": false,
"current": false,
@@ -9965,12 +10030,12 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -9983,7 +10048,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Usage (w/o cache)",
+ "title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -10001,7 +10066,7 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -10023,7 +10088,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Memory Usage",
+ "title": "Storage IO",
"titleSize": "h6"
},
{
@@ -10039,7 +10104,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 4,
+ "id": 18,
"legend": {
"avg": false,
"current": false,
@@ -10062,6 +10127,10 @@ items:
"seriesOverrides": [
],
+ "sort": {
+ "col": 4,
+ "desc": true
+ },
"spaceLength": 10,
"span": 12,
"stack": false,
@@ -10074,13 +10143,13 @@ items:
"type": "hidden"
},
{
- "alias": "Memory Usage",
+ "alias": "IOPS(Reads)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
+ "decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
@@ -10090,16 +10159,16 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Requests",
+ "alias": "IOPS(Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
+ "decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
@@ -10109,16 +10178,16 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Requests %",
+ "alias": "IOPS(Reads + Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
+ "decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
@@ -10128,10 +10197,10 @@ items:
],
"type": "number",
- "unit": "percentunit"
+ "unit": "short"
},
{
- "alias": "Memory Limits",
+ "alias": "Throughput(Read)",
"colorMode": null,
"colors": [
@@ -10147,10 +10216,10 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "Bps"
},
{
- "alias": "Memory Limits %",
+ "alias": "Throughput(Write)",
"colorMode": null,
"colors": [
@@ -10166,10 +10235,10 @@ items:
],
"type": "number",
- "unit": "percentunit"
+ "unit": "Bps"
},
{
- "alias": "Memory Usage (RSS)",
+ "alias": "Throughput(Read + Write)",
"colorMode": null,
"colors": [
@@ -10185,84 +10254,46 @@ items:
],
"type": "number",
- "unit": "bytes"
+ "unit": "Bps"
},
{
- "alias": "Memory Usage (Cache)",
+ "alias": "Pod",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
- "link": false,
+ "link": true,
"linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #G",
+ "linkTooltip": "Drill down to pods",
+ "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
"thresholds": [
],
"type": "number",
- "unit": "bytes"
+ "unit": "short"
},
{
- "alias": "Memory Usage (Swap)",
+ "alias": "",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #H",
+ "pattern": "/.*/",
"thresholds": [
],
- "type": "number",
- "unit": "bytes"
- },
+ "type": "string",
+ "unit": "short"
+ }
+ ],
+ "targets": [
{
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "pod",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
-
- ],
- "type": "string",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10271,7 +10302,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10280,7 +10311,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10289,7 +10320,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10298,7 +10329,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10307,31 +10338,13 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
+ "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "G",
- "step": 10
- },
- {
- "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "H",
- "step": 10
}
],
"thresholds": [
@@ -10339,7 +10352,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Quota",
+ "title": "Current Storage IO",
"tooltip": {
"shared": false,
"sort": 0,
@@ -10380,7 +10393,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Memory Quota",
+ "title": "Storage IO - Distribution",
"titleSize": "h6"
}
],
@@ -10444,12 +10457,12 @@ items:
"hide": 0,
"includeAll": false,
"label": null,
- "multi": true,
- "name": "node",
+ "multi": false,
+ "name": "namespace",
"options": [
],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -10493,8 +10506,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Node (Pods)",
- "uid": "200ac8fdbfbb74b39aff88118e4d1c2c",
+ "title": "Kubernetes / Compute Resources / Namespace (Pods)",
+ "uid": "85a562078cdf77779eaa1add43ccec1e",
"version": 0
}
kind: ConfigMap
@@ -10504,11 +10517,11 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-node
+ name: grafana-dashboard-k8s-resources-namespace
namespace: monitoring
- apiVersion: v1
data:
- k8s-resources-pod.json: |-
+ k8s-resources-node.json: |-
{
"annotations": {
"list": [
@@ -10558,24 +10571,7 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
- {
- "alias": "requests",
- "color": "#F2495C",
- "fill": 0,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "limits",
- "color": "#FF9830",
- "fill": 0,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
+
],
"spaceLength": 10,
"span": 12,
@@ -10583,26 +10579,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{container}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "requests",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "limits",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -10662,118 +10642,13 @@ items:
{
"aliasColors": {
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 2,
- "legend": {
- "avg": false,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{container}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
- {
- "colorMode": "critical",
- "fill": true,
- "line": true,
- "op": "gt",
- "value": 0.25,
- "yaxis": "left"
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Throttling",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU Throttling",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 3,
+ "id": 2,
"legend": {
"avg": false,
"current": false,
@@ -10903,7 +10778,7 @@ items:
"unit": "percentunit"
},
{
- "alias": "Container",
+ "alias": "Pod",
"colorMode": null,
"colors": [
@@ -10914,7 +10789,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "container",
+ "pattern": "pod",
"thresholds": [
],
@@ -10939,7 +10814,7 @@ items:
],
"targets": [
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10948,7 +10823,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10957,7 +10832,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10966,7 +10841,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -10975,7 +10850,7 @@ items:
"step": 10
},
{
- "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11046,7 +10921,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 4,
+ "id": 3,
"legend": {
"avg": false,
"current": false,
@@ -11067,26 +10942,7 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
- {
- "alias": "requests",
- "color": "#F2495C",
- "dashes": true,
- "fill": 0,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "limits",
- "color": "#FF9830",
- "dashes": true,
- "fill": 0,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
+
],
"spaceLength": 10,
"span": 12,
@@ -11094,26 +10950,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{container}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "requests",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "limits",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -11123,7 +10963,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Usage",
+ "title": "Memory Usage (w/o cache)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -11179,7 +11019,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 5,
+ "id": 4,
"legend": {
"avg": false,
"current": false,
@@ -11366,7 +11206,7 @@ items:
"unit": "bytes"
},
{
- "alias": "Container",
+ "alias": "Pod",
"colorMode": null,
"colors": [
@@ -11377,7 +11217,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "container",
+ "pattern": "pod",
"thresholds": [
],
@@ -11402,7 +11242,7 @@ items:
],
"targets": [
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11411,7 +11251,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11420,7 +11260,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11429,7 +11269,7 @@ items:
"step": 10
},
{
- "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11438,7 +11278,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11447,7 +11287,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11456,7 +11296,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11465,7 +11305,7 @@ items:
"step": 10
},
{
- "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -11522,7 +11362,148 @@ items:
"showTitle": true,
"title": "Memory Quota",
"titleSize": "h6"
- },
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": true,
+ "name": "node",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Compute Resources / Node (Pods)",
+ "uid": "200ac8fdbfbb74b39aff88118e4d1c2c",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-k8s-resources-node
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ k8s-resources-pod.json: |-
+ {
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "links": [
+
+ ],
+ "refresh": "10s",
+ "rows": [
{
"collapse": false,
"height": "250px",
@@ -11536,8 +11517,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 6,
- "interval": "1m",
+ "id": 1,
"legend": {
"avg": false,
"current": false,
@@ -11558,18 +11538,51 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
-
+ {
+ "alias": "requests",
+ "color": "#F2495C",
+ "fill": 0,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ },
+ {
+ "alias": "limits",
+ "color": "#FF9830",
+ "fill": 0,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ }
],
"spaceLength": 10,
- "span": 6,
+ "span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "{{container}}",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "requests",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "limits",
"legendLink": null,
"step": 10
}
@@ -11579,7 +11592,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Receive Bandwidth",
+ "title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
@@ -11597,7 +11610,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -11613,7 +11626,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "CPU Usage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -11623,12 +11648,11 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 7,
- "interval": "1m",
+ "id": 2,
"legend": {
"avg": false,
- "current": false,
- "max": false,
+ "current": true,
+ "max": true,
"min": false,
"show": true,
"total": false,
@@ -11648,25 +11672,32 @@ items:
],
"spaceLength": 10,
- "span": 6,
+ "span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container)",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
-
+ {
+ "colorMode": "critical",
+ "fill": true,
+ "line": true,
+ "op": "gt",
+ "value": 0.25,
+ "yaxis": "left"
+ }
],
"timeFrom": null,
"timeShift": null,
- "title": "Transmit Bandwidth",
+ "title": "CPU Throttling",
"tooltip": {
"shared": false,
"sort": 0,
@@ -11684,10 +11715,10 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
@@ -11706,7 +11737,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Bandwidth",
+ "title": "CPU Throttling",
"titleSize": "h6"
},
{
@@ -11721,9 +11752,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 8,
- "interval": "1m",
+ "fill": 1,
+ "id": 3,
"legend": {
"avg": false,
"current": false,
@@ -11734,7 +11764,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
@@ -11747,16 +11777,190 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 12,
+ "stack": false,
"steppedLine": false,
+ "styles": [
+ {
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
+ {
+ "alias": "CPU Usage",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "CPU Requests",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "CPU Requests %",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "CPU Limits",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "CPU Limits %",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "Container",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "container",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+
+ ],
+ "type": "string",
+ "unit": "short"
+ }
+ ],
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
- "format": "time_series",
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+ "format": "table",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
"step": 10
}
],
@@ -11765,13 +11969,14 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -11783,7 +11988,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -11799,7 +12004,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "CPU Quota",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -11809,8 +12026,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 9,
- "interval": "1m",
+ "id": 4,
"legend": {
"avg": false,
"current": false,
@@ -11831,117 +12047,53 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Rate of Transmitted Packets",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "alias": "requests",
+ "color": "#F2495C",
+ "dashes": true,
+ "fill": 0,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
+ "alias": "limits",
+ "color": "#FF9830",
+ "dashes": true,
+ "fill": 0,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
}
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 10,
- "interval": "1m",
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
],
"spaceLength": 10,
- "span": 6,
+ "span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "{{container}}",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "requests",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "limits",
"legendLink": null,
"step": 10
}
@@ -11951,7 +12103,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "Memory Usage (WSS)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -11969,7 +12121,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
@@ -11985,7 +12137,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Memory Usage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -11994,9 +12158,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 11,
- "interval": "1m",
+ "fill": 1,
+ "id": 5,
"legend": {
"avg": false,
"current": false,
@@ -12007,7 +12170,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
@@ -12020,441 +12183,153 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 12,
+ "stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
+ {
+ "alias": "Memory Usage (WSS)",
+ "colorMode": null,
+ "colors": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
- ]
- },
- "yaxes": [
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
{
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "alias": "Memory Requests",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "bytes"
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets Dropped",
- "titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
+ "alias": "Memory Requests %",
+ "colorMode": null,
+ "colors": [
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "Memory Limits",
+ "colorMode": null,
+ "colors": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "namespace",
- "options": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
- ],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Limits %",
+ "colorMode": null,
+ "colors": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "pod",
- "options": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
- ],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "Memory Usage (RSS)",
+ "colorMode": null,
+ "colors": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Pod",
- "uid": "6581e46e4e5c7ba40a07646395ef7b23",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-pod
- namespace: monitoring
-- apiVersion: v1
- data:
- k8s-resources-workload.json: |-
- {
- "annotations": {
- "list": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Usage (Cache)",
+ "colorMode": null,
+ "colors": [
- ],
- "refresh": "10s",
- "rows": [
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #G",
+ "thresholds": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 1,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Usage",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU Usage",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 2,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "styles": [
- {
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
- },
- {
- "alias": "CPU Usage",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "CPU Requests %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "CPU Limits",
- "colorMode": null,
- "colors": [
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Usage (Swap)",
+ "colorMode": null,
+ "colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
@@ -12463,15 +12338,15 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #D",
+ "pattern": "Value #H",
"thresholds": [
],
"type": "number",
- "unit": "short"
+ "unit": "bytes"
},
{
- "alias": "CPU Limits %",
+ "alias": "Container",
"colorMode": null,
"colors": [
@@ -12482,26 +12357,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
- "pattern": "pod",
+ "pattern": "container",
"thresholds": [
],
@@ -12526,7 +12382,7 @@ items:
],
"targets": [
{
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -12535,7 +12391,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -12544,7 +12400,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -12553,7 +12409,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -12562,13 +12418,40 @@ items:
"step": 10
},
{
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
+ },
+ {
+ "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ },
+ {
+ "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "G",
+ "step": 10
+ },
+ {
+ "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "H",
+ "step": 10
}
],
"thresholds": [
@@ -12576,7 +12459,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Quota",
+ "title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
@@ -12617,7 +12500,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "CPU Quota",
+ "title": "Memory Quota",
"titleSize": "h6"
},
{
@@ -12633,7 +12516,8 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 3,
+ "id": 6,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -12657,12 +12541,12 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -12675,7 +12559,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Usage",
+ "title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
@@ -12693,7 +12577,7 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -12709,19 +12593,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Memory Usage",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -12730,8 +12602,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 4,
+ "fill": 10,
+ "id": 7,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -12742,7 +12615,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -12755,190 +12628,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
- "styles": [
- {
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
- },
- {
- "alias": "Memory Usage",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
- {
- "alias": "Memory Requests",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
- {
- "alias": "Memory Requests %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "Memory Limits",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "bytes"
- },
- {
- "alias": "Memory Limits %",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "percentunit"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
- "pattern": "pod",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
-
- ],
- "type": "string",
- "unit": "short"
- }
- ],
"targets": [
{
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
- "format": "table",
- "instant": true,
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+ "format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
+ "legendFormat": "{{pod}}",
+ "legendLink": null,
"step": 10
}
],
@@ -12947,14 +12646,13 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Quota",
+ "title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "transform": "table",
- "type": "table",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -12966,7 +12664,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -12988,7 +12686,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Memory Quota",
+ "title": "Bandwidth",
"titleSize": "h6"
},
{
@@ -13003,8 +12701,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 5,
+ "fill": 10,
+ "id": 8,
"interval": "1m",
"legend": {
"avg": false,
@@ -13016,7 +12714,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -13029,234 +12727,31 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
- "styles": [
- {
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
- },
+ "targets": [
{
- "alias": "Current Receive Bandwidth",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Current Transmit Bandwidth",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Rate of Received Packets",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Transmitted Packets",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Received Packets Dropped",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Transmitted Packets Dropped",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #F",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
- "pattern": "pod",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
-
- ],
- "type": "string",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
- "step": 10
- },
- {
- "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
- }
- ],
- "thresholds": [
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{pod}}",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
],
"timeFrom": null,
"timeShift": null,
- "title": "Current Network Usage",
+ "title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "transform": "table",
- "type": "table",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -13268,7 +12763,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -13284,19 +12779,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Current Network Usage",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -13306,7 +12789,8 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 6,
+ "id": 9,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -13335,7 +12819,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -13348,7 +12832,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Receive Bandwidth",
+ "title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13382,7 +12866,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Rate of Packets",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -13392,7 +12888,8 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 7,
+ "id": 10,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -13421,7 +12918,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -13434,7 +12931,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Transmit Bandwidth",
+ "title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13468,19 +12965,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Bandwidth",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -13490,7 +12975,8 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 8,
+ "id": 11,
+ "interval": "1m",
"legend": {
"avg": false,
"current": false,
@@ -13519,7 +13005,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@@ -13532,7 +13018,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Container Bandwidth by Pod: Received",
+ "title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13566,7 +13052,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Rate of Packets Dropped",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -13575,8 +13073,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
+ "decimals": -1,
"fill": 10,
- "id": 9,
+ "id": 12,
"legend": {
"avg": false,
"current": false,
@@ -13605,10 +13104,18 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m])))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "Reads",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m])))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Writes",
"legendLink": null,
"step": 10
}
@@ -13618,7 +13125,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Container Bandwidth by Pod: Transmitted",
+ "title": "IOPS",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13636,7 +13143,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -13652,19 +13159,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Average Container Bandwidth by Pod",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -13674,7 +13169,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 10,
+ "id": 13,
"legend": {
"avg": false,
"current": false,
@@ -13703,10 +13198,18 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "Reads",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Writes",
"legendLink": null,
"step": 10
}
@@ -13716,7 +13219,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "ThroughPut",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13750,7 +13253,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Storage IO - Distribution(Pod - Read & Writes)",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -13759,8 +13274,9 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
+ "decimals": -1,
"fill": 10,
- "id": 11,
+ "id": 14,
"legend": {
"avg": false,
"current": false,
@@ -13789,10 +13305,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "ceil(sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m])))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
@@ -13802,7 +13318,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets",
+ "title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13820,7 +13336,7 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -13836,19 +13352,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -13858,7 +13362,7 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
- "id": 12,
+ "id": 15,
"legend": {
"avg": false,
"current": false,
@@ -13887,10 +13391,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+ "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{pod}}",
+ "legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
@@ -13900,7 +13404,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -13934,7 +13438,19 @@ items:
"show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Storage IO - Distribution(Containers)",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -13943,8 +13459,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 13,
+ "fill": 1,
+ "id": 16,
"legend": {
"avg": false,
"current": false,
@@ -13955,7 +13471,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
@@ -13967,118 +13483,298 @@ items:
"seriesOverrides": [
],
+ "sort": {
+ "col": 4,
+ "desc": true
+ },
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 12,
+ "stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{pod}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
+ {
+ "alias": "IOPS(Reads)",
+ "colorMode": null,
+ "colors": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ ],
+ "type": "number",
+ "unit": "short"
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Rate of Packets Dropped",
- "titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
+ "alias": "IOPS(Writes)",
+ "colorMode": null,
+ "colors": [
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "IOPS(Reads + Writes)",
+ "colorMode": null,
+ "colors": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": -1,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Throughput(Read)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Throughput(Write)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Throughput(Read + Write)",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Container",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "container",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+
+ ],
+ "type": "string",
+ "unit": "short"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum by(container) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Storage IO",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "transform": "table",
+ "type": "table",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Storage IO - Distribution",
+ "titleSize": "h6"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
},
{
"allValue": null,
@@ -14087,15 +13783,15 @@ items:
"value": ""
},
"datasource": "$datasource",
- "hide": 0,
+ "hide": 2,
"includeAll": false,
"label": null,
"multi": false,
- "name": "namespace",
+ "name": "cluster",
"options": [
],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+ "query": "label_values(kube_pod_info, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -14118,11 +13814,11 @@ items:
"includeAll": false,
"label": null,
"multi": false,
- "name": "workload",
+ "name": "namespace",
"options": [
],
- "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -14145,11 +13841,11 @@ items:
"includeAll": false,
"label": null,
"multi": false,
- "name": "type",
+ "name": "pod",
"options": [
],
- "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -14193,8 +13889,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Workload",
- "uid": "a164a7f0339f99e89cea5cb47e9be617",
+ "title": "Kubernetes / Compute Resources / Pod",
+ "uid": "6581e46e4e5c7ba40a07646395ef7b23",
"version": 0
}
kind: ConfigMap
@@ -14204,11 +13900,11 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-workload
+ name: grafana-dashboard-k8s-resources-pod
namespace: monitoring
- apiVersion: v1
data:
- k8s-resources-workloads-namespace.json: |-
+ k8s-resources-workload.json: |-
{
"annotations": {
"list": [
@@ -14258,55 +13954,18 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
{
- "alias": "quota - requests",
- "color": "#F2495C",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "quota - limits",
- "color": "#FF9830",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{workload}} - {{workload_type}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "quota - requests",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "quota - limits",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -14406,25 +14065,6 @@ items:
"pattern": "Time",
"type": "hidden"
},
- {
- "alias": "Running Pods",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 0,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
{
"alias": "CPU Usage",
"colorMode": null,
@@ -14437,7 +14077,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #B",
+ "pattern": "Value #A",
"thresholds": [
],
@@ -14456,7 +14096,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #C",
+ "pattern": "Value #B",
"thresholds": [
],
@@ -14475,7 +14115,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #D",
+ "pattern": "Value #C",
"thresholds": [
],
@@ -14494,7 +14134,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #E",
+ "pattern": "Value #D",
"thresholds": [
],
@@ -14513,7 +14153,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #F",
+ "pattern": "Value #E",
"thresholds": [
],
@@ -14521,7 +14161,7 @@ items:
"unit": "percentunit"
},
{
- "alias": "Workload",
+ "alias": "Pod",
"colorMode": null,
"colors": [
@@ -14531,27 +14171,8 @@ items:
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
- "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
- "pattern": "workload",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "Workload Type",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "workload_type",
+ "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
"thresholds": [
],
@@ -14576,7 +14197,7 @@ items:
],
"targets": [
{
- "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -14585,7 +14206,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -14594,7 +14215,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -14603,7 +14224,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -14612,22 +14233,13 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
- },
- {
- "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
}
],
"thresholds": [
@@ -14713,28 +14325,7 @@ items:
"points": false,
"renderer": "flot",
"seriesOverrides": [
- {
- "alias": "quota - requests",
- "color": "#F2495C",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- },
- {
- "alias": "quota - limits",
- "color": "#FF9830",
- "dashes": true,
- "fill": 0,
- "hiddenSeries": true,
- "hideTooltip": true,
- "legend": true,
- "linewidth": 2,
- "stack": false
- }
+
],
"spaceLength": 10,
"span": 12,
@@ -14742,26 +14333,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{workload}} - {{workload_type}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "quota - requests",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "quota - limits",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -14861,25 +14436,6 @@ items:
"pattern": "Time",
"type": "hidden"
},
- {
- "alias": "Running Pods",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 0,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
{
"alias": "Memory Usage",
"colorMode": null,
@@ -14892,7 +14448,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #B",
+ "pattern": "Value #A",
"thresholds": [
],
@@ -14911,7 +14467,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #C",
+ "pattern": "Value #B",
"thresholds": [
],
@@ -14930,7 +14486,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #D",
+ "pattern": "Value #C",
"thresholds": [
],
@@ -14949,7 +14505,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #E",
+ "pattern": "Value #D",
"thresholds": [
],
@@ -14968,7 +14524,7 @@ items:
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
- "pattern": "Value #F",
+ "pattern": "Value #E",
"thresholds": [
],
@@ -14976,7 +14532,7 @@ items:
"unit": "percentunit"
},
{
- "alias": "Workload",
+ "alias": "Pod",
"colorMode": null,
"colors": [
@@ -14986,27 +14542,8 @@ items:
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
- "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
- "pattern": "workload",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "Workload Type",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "workload_type",
+ "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
"thresholds": [
],
@@ -15031,7 +14568,7 @@ items:
],
"targets": [
{
- "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15040,7 +14577,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15049,7 +14586,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15058,7 +14595,7 @@ items:
"step": 10
},
{
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15067,22 +14604,13 @@ items:
"step": 10
},
{
- "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
- },
- {
- "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
}
],
"thresholds": [
@@ -15297,7 +14825,7 @@ items:
"unit": "pps"
},
{
- "alias": "Workload",
+ "alias": "Pod",
"colorMode": null,
"colors": [
@@ -15306,9 +14834,9 @@ items:
"decimals": 2,
"link": true,
"linkTargetBlank": false,
- "linkTooltip": "Drill down to pods",
- "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
- "pattern": "workload",
+ "linkTooltip": "Drill down",
+ "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
"thresholds": [
],
@@ -15316,43 +14844,24 @@ items:
"unit": "short"
},
{
- "alias": "Workload Type",
+ "alias": "",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "workload_type",
+ "pattern": "/.*/",
"thresholds": [
],
- "type": "number",
+ "type": "string",
"unit": "short"
- },
+ }
+ ],
+ "targets": [
{
- "alias": "",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
-
- ],
- "type": "string",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15361,7 +14870,7 @@ items:
"step": 10
},
{
- "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15370,7 +14879,7 @@ items:
"step": 10
},
{
- "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15379,7 +14888,7 @@ items:
"step": 10
},
{
- "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15388,7 +14897,7 @@ items:
"step": 10
},
{
- "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15397,7 +14906,7 @@ items:
"step": 10
},
{
- "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -15497,10 +15006,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -15583,10 +15092,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -15681,10 +15190,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -15694,7 +15203,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Container Bandwidth by Workload: Received",
+ "title": "Average Container Bandwidth by Pod: Received",
"tooltip": {
"shared": false,
"sort": 0,
@@ -15767,10 +15276,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -15780,7 +15289,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Container Bandwidth by Workload: Transmitted",
+ "title": "Average Container Bandwidth by Pod: Transmitted",
"tooltip": {
"shared": false,
"sort": 0,
@@ -15820,7 +15329,7 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Average Container Bandwidth by Workload",
+ "title": "Average Container Bandwidth by Pod",
"titleSize": "h6"
},
{
@@ -15865,10 +15374,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -15951,10 +15460,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -16049,10 +15558,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -16135,10 +15644,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{workload}}",
+ "legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
@@ -16244,28 +15753,23 @@ items:
},
{
"allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
"current": {
- "text": "deployment",
- "value": "deployment"
+ "text": "",
+ "value": ""
},
"datasource": "$datasource",
- "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
- "name": "type",
+ "name": "namespace",
"options": [
],
- "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
- "skipUrlSync": false,
- "sort": 0,
+ "sort": 1,
"tagValuesQuery": "",
"tags": [
@@ -16285,11 +15789,38 @@ items:
"includeAll": false,
"label": null,
"multi": false,
- "name": "namespace",
+ "name": "workload",
"options": [
],
- "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+ "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "type",
+ "options": [
+
+ ],
+ "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -16333,8 +15864,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / Compute Resources / Namespace (Workloads)",
- "uid": "a87fb0d919ec0ea5f6543124e16c42a5",
+ "title": "Kubernetes / Compute Resources / Workload",
+ "uid": "a164a7f0339f99e89cea5cb47e9be617",
"version": 0
}
kind: ConfigMap
@@ -16344,28 +15875,21 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-k8s-resources-workloads-namespace
+ name: grafana-dashboard-k8s-resources-workload
namespace: monitoring
- apiVersion: v1
data:
- kubelet.json: |-
+ k8s-resources-workloads-namespace.json: |-
{
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
"annotations": {
"list": [
]
},
- "editable": false,
+ "editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
- "id": null,
"links": [
],
@@ -16373,524 +15897,462 @@ items:
"rows": [
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "aliasColors": {
},
- "id": 2,
- "interval": null,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 10,
+ "id": 1,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 0,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
{
- "name": "value to text",
- "value": 1
+ "alias": "quota - requests",
+ "color": "#F2495C",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
+ "alias": "quota - limits",
+ "color": "#FF9830",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
}
],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
"targets": [
{
- "expr": "sum(up{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})",
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
+ "legendFormat": "{{workload}} - {{workload_type}}",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "quota - requests",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "quota - limits",
+ "legendLink": null,
+ "step": 10
}
],
- "thresholds": "",
- "title": "Up",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Usage",
"tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "min"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "gridPos": {
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
},
- "id": 3,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
+ "yaxes": [
{
- "name": "value to text",
- "value": 1
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Running Pods",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "valueName": "min"
- },
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "CPU Usage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "aliasColors": {
},
- "id": 4,
- "interval": null,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 2,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "styles": [
{
- "name": "value to text",
- "value": 1
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "alias": "Running Pods",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 0,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
+ "alias": "CPU Usage",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Running Container",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "alias": "CPU Requests",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "min"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "alias": "CPU Requests %",
+ "colorMode": null,
+ "colors": [
- },
- "id": 5,
- "interval": null,
- "links": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
- ],
- "mappingType": 1,
- "mappingTypes": [
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
{
- "name": "value to text",
- "value": 1
+ "alias": "CPU Limits",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "alias": "CPU Limits %",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
{
- "from": "null",
- "text": "N/A",
- "to": "null"
+ "alias": "Workload",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
+ "pattern": "workload",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Workload Type",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "workload_type",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+
+ ],
+ "type": "string",
+ "unit": "short"
}
],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
"targets": [
{
- "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
- "format": "time_series",
+ "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+ "format": "table",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
}
],
- "thresholds": "",
- "title": "Actual Volume Count",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Quota",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "min"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
-
- },
- "id": 6,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Desired Volume Count",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "min"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "transform": "table",
+ "type": "table",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
},
- "id": 7,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
+ "yaxes": [
{
- "name": "value to text",
- "value": 1
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Config Error Count",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "valueName": "min"
+ ]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "CPU Quota",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -16900,142 +16362,79 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 8,
+ "fill": 10,
+ "id": 3,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
-
+ {
+ "alias": "quota - requests",
+ "color": "#F2495C",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ },
+ {
+ "alias": "quota - limits",
+ "color": "#FF9830",
+ "dashes": true,
+ "fill": 0,
+ "hiddenSeries": true,
+ "hideTooltip": true,
+ "legend": true,
+ "linewidth": 2,
+ "stack": false
+ }
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_type}}",
- "refId": "A"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Operation Rate",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "ops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "legendFormat": "{{workload}} - {{workload_type}}",
+ "legendLink": null,
+ "step": 10
},
{
- "format": "ops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 9,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "quota - requests",
+ "legendLink": null,
+ "step": 10
+ },
{
- "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+ "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_type}}",
- "refId": "A"
+ "legendFormat": "quota - limits",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17043,7 +16442,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Operation Error Rate",
+ "title": "Memory Usage",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17061,7 +16460,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
@@ -17069,12 +16468,12 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -17082,14 +16481,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Memory Usage",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -17100,34 +16498,26 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 10,
+ "id": 4,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
@@ -17135,126 +16525,235 @@ items:
"span": 12,
"stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_type}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
+ },
+ {
+ "alias": "Running Pods",
+ "colorMode": null,
+ "colors": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Operation duration 99th quantile",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 0,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
- ]
- },
- "yaxes": [
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "alias": "Memory Usage",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "bytes"
},
{
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
+ "alias": "Memory Requests",
+ "colorMode": null,
+ "colors": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
- },
- "id": 11,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Requests %",
+ "colorMode": null,
+ "colors": [
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "Memory Limits",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "bytes"
+ },
+ {
+ "alias": "Memory Limits %",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "percentunit"
+ },
+ {
+ "alias": "Workload",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
+ "pattern": "workload",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Workload Type",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "workload_type",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ ],
+ "type": "string",
+ "unit": "short"
+ }
],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
"targets": [
{
- "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
+ "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+ "format": "table",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "{{instance}} pod",
- "refId": "A"
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
},
{
- "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "{{instance}} worker",
- "refId": "B"
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
}
],
"thresholds": [
@@ -17262,13 +16761,14 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Pod Start Rate",
+ "title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -17280,7 +16780,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -17288,15 +16788,27 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Memory Quota",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -17306,69 +16818,278 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 12,
+ "id": 5,
+ "interval": "1m",
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
+ "span": 12,
"stack": false,
"steppedLine": false,
- "targets": [
+ "styles": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} pod",
- "refId": "A"
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
},
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} worker",
- "refId": "B"
- }
- ],
+ "alias": "Current Receive Bandwidth",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Current Transmit Bandwidth",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Rate of Received Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Received Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Workload",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down to pods",
+ "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
+ "pattern": "workload",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Workload Type",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "workload_type",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+
+ ],
+ "type": "string",
+ "unit": "short"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ }
+ ],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
- "title": "Pod Start Duration",
+ "title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -17380,7 +17101,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -17388,12 +17109,12 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -17401,14 +17122,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Current Network Usage",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -17418,51 +17138,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 13,
+ "fill": 10,
+ "id": 6,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
+ "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17470,7 +17181,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Storage Operation Rate",
+ "title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17488,7 +17199,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -17496,12 +17207,12 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
},
@@ -17513,51 +17224,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 14,
+ "fill": 10,
+ "id": 7,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
+ "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17565,7 +17267,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Storage Operation Error Rate",
+ "title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17583,7 +17285,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -17591,12 +17293,12 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -17604,14 +17306,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Bandwidth",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -17621,51 +17322,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 15,
+ "fill": 10,
+ "id": 8,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
+ "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17673,7 +17365,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Storage Operation Duration 99th quantile",
+ "title": "Average Container Bandwidth by Workload: Received",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17691,7 +17383,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -17699,28 +17391,15 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -17729,49 +17408,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 16,
+ "fill": 10,
+ "id": 9,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+ "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{operation_type}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17779,7 +17451,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Cgroup manager operation rate",
+ "title": "Average Container Bandwidth by Workload: Transmitted",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17797,7 +17469,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -17805,15 +17477,27 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Average Container Bandwidth by Workload",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -17822,49 +17506,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 17,
+ "fill": 10,
+ "id": 10,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
+ "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} {{operation_type}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -17872,7 +17549,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Cgroup manager 99th quantile",
+ "title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -17890,7 +17567,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -17898,28 +17575,15 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -17928,143 +17592,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "description": "Pod lifecycle event generator",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 18,
+ "fill": 10,
+ "id": 11,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "PLEG relist rate",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "ops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "ops",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 19,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -18072,7 +17635,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "PLEG relist interval",
+ "title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -18090,7 +17653,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -18098,12 +17661,12 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -18111,14 +17674,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Rate of Packets",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -18128,49 +17690,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 20,
+ "fill": 10,
+ "id": 12,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -18178,7 +17733,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "PLEG relist duration",
+ "title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -18196,7 +17751,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -18204,28 +17759,15 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -18234,70 +17776,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 21,
+ "fill": 10,
+ "id": 13,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "2xx",
- "refId": "A"
- },
- {
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "3xx",
- "refId": "B"
- },
- {
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "4xx",
- "refId": "C"
- },
- {
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+ "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "5xx",
- "refId": "D"
+ "legendFormat": "{{workload}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -18305,7 +17819,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "RPC Rate",
+ "title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
@@ -18323,7 +17837,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
@@ -18331,12 +17845,12 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -18344,1378 +17858,942 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
+ "showTitle": true,
+ "title": "Rate of Packets Dropped",
+ "titleSize": "h6"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "deployment",
+ "value": "deployment"
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "type",
+ "options": [
+
+ ],
+ "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "namespace",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Compute Resources / Namespace (Workloads)",
+ "uid": "a87fb0d919ec0ea5f6543124e16c42a5",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-k8s-resources-workloads-namespace
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ kubelet.json: |-
+ {
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "10s",
+ "rows": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
"gridPos": {
},
- "id": 22,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
+ "id": 2,
+ "interval": null,
"links": [
],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "targets": [
+ "mappingType": 1,
+ "mappingTypes": [
{
- "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{verb}} {{url}}",
- "refId": "A"
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
}
],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Request duration 99th quantile",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
{
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
}
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 23,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
"targets": [
{
- "expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}",
+ "expr": "sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
+ "legendFormat": "",
"refId": "A"
}
],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory",
+ "thresholds": "",
+ "title": "Running Kubelets",
"tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
+ "shared": false
},
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
{
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
}
- ]
+ ],
+ "valueName": "min"
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
"gridPos": {
},
- "id": 24,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
+ "id": 3,
+ "interval": null,
"links": [
],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
"targets": [
{
- "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])",
+ "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU usage",
+ "thresholds": "",
+ "title": "Running Pods",
"tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
+ "shared": false
},
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
}
- ]
+ ],
+ "valueName": "min"
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
"gridPos": {
},
- "id": 25,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
+ "id": 4,
+ "interval": null,
"links": [
],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
"targets": [
{
- "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}",
+ "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Goroutines",
+ "thresholds": "",
+ "title": "Running Container",
"tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
+ "shared": false
},
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "min"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
- ]
},
- "yaxes": [
+ "id": 5,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "name": "value to text",
+ "value": 1
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "name": "range to text",
+ "value": 2
}
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": "cluster",
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "instance",
- "options": [
-
- ],
- "query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, instance)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Kubelet",
- "uid": "3138fa155d5915769fbded898ac09fd9",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-kubelet
- namespace: monitoring
-- apiVersion: v1
- data:
- namespace-by-pod.json: |-
- {
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "type": "dashboard"
- }
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
-
- ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [
-
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Current Bandwidth",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "decimals": 0,
- "format": "time_series",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 1
- },
- "height": 9,
- "id": 3,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "minSpan": 12,
- "nullPointMode": "connected",
- "nullText": null,
- "options": {
- "fieldOptions": {
- "calcs": [
- "last"
],
- "defaults": {
- "max": 10000000000,
- "min": 0,
- "title": "$namespace",
- "unit": "Bps"
- },
- "mappings": [
-
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
],
- "override": {
-
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
},
- "thresholds": [
- {
- "color": "dark-green",
- "index": 0,
- "value": null
- },
+ "tableColumn": "",
+ "targets": [
{
- "color": "dark-yellow",
- "index": 1,
- "value": 5000000000
- },
+ "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Actual Volume Count",
+ "tooltip": {
+ "shared": false
+ },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
{
- "color": "dark-red",
- "index": 2,
- "value": 7000000000
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
}
],
- "values": false
- }
- },
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "valueName": "min"
+ },
{
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 12,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
- "format": "time_series",
- "instant": null,
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Received",
- "type": "gauge",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "decimals": 0,
- "format": "time_series",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 1
- },
- "height": 9,
- "id": 4,
- "interval": null,
- "links": [
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
+ },
+ "id": 6,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Desired Volume Count",
+ "tooltip": {
+ "shared": false
+ },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "min"
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "minSpan": 12,
- "nullPointMode": "connected",
- "nullText": null,
- "options": {
- "fieldOptions": {
- "calcs": [
- "last"
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
],
- "defaults": {
- "max": 10000000000,
- "min": 0,
- "title": "$namespace",
- "unit": "Bps"
+ "datasource": "$datasource",
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
},
- "mappings": [
-
- ],
- "override": {
+ "gridPos": {
},
- "thresholds": [
+ "id": 7,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
{
- "color": "dark-green",
- "index": 0,
- "value": null
+ "name": "value to text",
+ "value": 1
},
{
- "color": "dark-yellow",
- "index": 1,
- "value": 5000000000
- },
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
{
- "color": "dark-red",
- "index": 2,
- "value": 7000000000
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
}
],
- "values": false
- }
- },
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 12,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
- "format": "time_series",
- "instant": null,
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Transmitted",
- "type": "gauge",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "span": 2,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "title": "Config Error Count",
+ "tooltip": {
+ "shared": false
+ },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "min"
}
],
- "valueName": "current"
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
},
{
- "columns": [
- {
- "text": "Time",
- "value": "Time"
- },
- {
- "text": "Value #A",
- "value": "Value #A"
- },
- {
- "text": "Value #B",
- "value": "Value #B"
- },
- {
- "text": "Value #C",
- "value": "Value #C"
- },
- {
- "text": "Value #D",
- "value": "Value #D"
- },
- {
- "text": "Value #E",
- "value": "Value #E"
- },
- {
- "text": "Value #F",
- "value": "Value #F"
- },
- {
- "text": "pod",
- "value": "pod"
- }
- ],
- "datasource": "$datasource",
- "fill": 1,
- "fontSize": "100%",
- "gridPos": {
- "h": 9,
- "w": 24,
- "x": 0,
- "y": 10
- },
- "id": 5,
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "minSpan": 24,
- "nullPointMode": "null as zero",
- "renderer": "flot",
- "scroll": true,
- "showHeader": true,
- "sort": {
- "col": 0,
- "desc": false
- },
- "spaceLength": 10,
- "span": 24,
- "styles": [
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
- "alias": "Time",
- "colorMode": null,
- "colors": [
+ "aliasColors": {
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Time",
- "thresholds": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "type": "hidden",
- "unit": "short"
- },
- {
- "alias": "Bandwidth Received",
- "colorMode": null,
- "colors": [
+ },
+ "id": 8,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Bandwidth Transmitted",
- "colorMode": null,
- "colors": [
-
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_type}}",
+ "refId": "A"
+ }
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
"thresholds": [
],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Rate of Received Packets",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Operation Rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "type": "number",
- "unit": "pps"
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
},
{
- "alias": "Rate of Transmitted Packets",
- "colorMode": null,
- "colors": [
+ "aliasColors": {
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Received Packets Dropped",
- "colorMode": null,
- "colors": [
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
- "thresholds": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Transmitted Packets Dropped",
- "colorMode": null,
- "colors": [
-
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_type}}",
+ "refId": "A"
+ }
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #F",
"thresholds": [
],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Pod",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTooltip": "Drill down",
- "linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell",
- "pattern": "pod",
- "thresholds": [
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Operation Error Rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "type": "number",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
- "step": 10
- },
- {
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
}
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Status",
- "type": "table"
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 19
- },
- "id": 6,
- "panels": [
-
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Bandwidth",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
- "aliasColors": {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 20
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Receive Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 20
- },
- "id": 8,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
-
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Transmit Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 29
- },
- "id": 9,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 10,
- "w": 12,
- "x": 0,
- "y": 30
},
"id": 10,
"legend": {
- "alignAsTable": false,
+ "alignAsTable": true,
"avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
+ "current": true,
"max": false,
"min": false,
- "rightSide": false,
+ "rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -19726,16 +18804,15 @@ items:
],
"spaceLength": 10,
"span": 12,
- "stack": true,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_type}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -19743,10 +18820,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "Operation duration 99th quantile",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -19761,23 +18838,36 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
- "format": "pps",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -19786,37 +18876,30 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 12,
- "y": 30
+
},
"id": 11,
"legend": {
- "alignAsTable": false,
+ "alignAsTable": true,
"avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
+ "current": true,
"max": false,
"min": false,
- "rightSide": false,
+ "rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -19826,17 +18909,23 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} pod",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} worker",
+ "refId": "B"
}
],
"thresholds": [
@@ -19844,10 +18933,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets",
+ "title": "Pod Start Rate",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -19862,7 +18951,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -19870,7 +18959,107 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} pod",
+ "refId": "A"
+ },
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} worker",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Pod Start Duration",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
@@ -19883,21 +19072,14 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Packets",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 30
- },
- "id": 12,
+ "collapse": false,
+ "collapsed": false,
"panels": [
{
"aliasColors": {
@@ -19907,37 +19089,32 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 0,
- "y": 40
+
},
"id": 13,
"legend": {
- "alignAsTable": false,
+ "alignAsTable": true,
"avg": false,
- "current": false,
+ "current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
- "rightSide": false,
+ "rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -19947,17 +19124,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -19965,10 +19141,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "Storage Operation Rate",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -19983,7 +19159,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -19991,7 +19167,7 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -20008,37 +19184,32 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 12,
- "y": 40
+
},
"id": 14,
"legend": {
- "alignAsTable": false,
+ "alignAsTable": true,
"avg": false,
- "current": false,
+ "current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
- "rightSide": false,
+ "rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -20048,17 +19219,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -20066,10 +19236,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
+ "title": "Storage Operation Error Rate",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -20084,7 +19254,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -20092,7 +19262,7 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -20105,863 +19275,554 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Errors",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
- }
- ],
- "refresh": "10s",
- "rows": [
-
- ],
- "schemaVersion": 18,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
+ },
+ "id": 15,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": ".+",
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "kube-system",
- "value": "kube-system"
- },
- "datasource": "$datasource",
- "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "namespace",
- "options": [
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
- ],
- "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Storage Operation Duration 99th quantile",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "resolution",
- "options": [
- {
- "selected": false,
- "text": "30s",
- "value": "30s"
+ ]
},
- {
- "selected": true,
- "text": "5m",
- "value": "5m"
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
+
},
- {
- "selected": false,
- "text": "1h",
- "value": "1h"
- }
- ],
- "query": "30s,5m,1h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "interval",
- "options": [
- {
- "selected": true,
- "text": "4h",
- "value": "4h"
- }
- ],
- "query": "4h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Networking / Namespace (Pods)",
- "uid": "8b7a8b326d7a6f1f04244066368c67af",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-namespace-by-pod
- namespace: monitoring
-- apiVersion: v1
- data:
- namespace-by-workload.json: |-
- {
- "__inputs": [
+ },
+ "id": 16,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "__requires": [
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "type": "dashboard"
- }
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{operation_type}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
- ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Cgroup manager operation rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Current Bandwidth",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "aliasColors": {
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
- },
- "bars": true,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 1
- },
- "id": 3,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": false,
- "linewidth": 1,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "minSpan": 24,
- "nullPointMode": "null",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ },
+ "id": 17,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "spaceLength": 10,
- "span": 24,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{ workload }}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Received",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "series",
- "name": null,
- "show": false,
- "values": [
- "current"
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- },
- "bars": true,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 1
- },
- "id": 4,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": false,
- "linewidth": 1,
- "links": [
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{operation_type}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
- ],
- "minSpan": 24,
- "nullPointMode": "null",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Cgroup manager 99th quantile",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "spaceLength": 10,
- "span": 24,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{ workload }}",
- "refId": "A",
- "step": 10
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
}
],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Transmitted",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "series",
- "name": null,
- "show": false,
- "values": [
- "current"
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
},
{
- "columns": [
- {
- "text": "Time",
- "value": "Time"
- },
- {
- "text": "Value #A",
- "value": "Value #A"
- },
- {
- "text": "Value #B",
- "value": "Value #B"
- },
- {
- "text": "Value #C",
- "value": "Value #C"
- },
- {
- "text": "Value #D",
- "value": "Value #D"
- },
- {
- "text": "Value #E",
- "value": "Value #E"
- },
- {
- "text": "Value #F",
- "value": "Value #F"
- },
- {
- "text": "Value #G",
- "value": "Value #G"
- },
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
- "text": "Value #H",
- "value": "Value #H"
- },
- {
- "text": "workload",
- "value": "workload"
- }
- ],
- "datasource": "$datasource",
- "fill": 1,
- "fontSize": "90%",
- "gridPos": {
- "h": 9,
- "w": 24,
- "x": 0,
- "y": 10
- },
- "id": 5,
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "minSpan": 24,
- "nullPointMode": "null as zero",
- "renderer": "flot",
- "scroll": true,
- "showHeader": true,
- "sort": {
- "col": 0,
- "desc": false
- },
- "spaceLength": 10,
- "span": 24,
- "styles": [
- {
- "alias": "Time",
- "colorMode": null,
- "colors": [
+ "aliasColors": {
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Time",
- "thresholds": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "description": "Pod lifecycle event generator",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "type": "hidden",
- "unit": "short"
- },
- {
- "alias": "Current Bandwidth Received",
- "colorMode": null,
- "colors": [
+ },
+ "id": 18,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Current Bandwidth Transmitted",
- "colorMode": null,
- "colors": [
-
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
"thresholds": [
],
- "type": "number",
- "unit": "Bps"
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "PLEG relist rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
},
{
- "alias": "Average Bandwidth Received",
- "colorMode": null,
- "colors": [
+ "aliasColors": {
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #C",
- "thresholds": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Average Bandwidth Transmitted",
- "colorMode": null,
- "colors": [
+ },
+ "id": 19,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #D",
- "thresholds": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
],
- "type": "number",
- "unit": "Bps"
- },
- {
- "alias": "Rate of Received Packets",
- "colorMode": null,
- "colors": [
-
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #E",
"thresholds": [
],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Transmitted Packets",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #F",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Received Packets Dropped",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #G",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Rate of Transmitted Packets Dropped",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #H",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "pps"
- },
- {
- "alias": "Workload",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": true,
- "linkTooltip": "Drill down",
- "linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell",
- "pattern": "workload",
- "thresholds": [
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "PLEG relist interval",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "type": "number",
- "unit": "short"
- }
- ],
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
- },
- {
- "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "C",
- "step": 10
- },
- {
- "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "D",
- "step": 10
- },
- {
- "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "E",
- "step": 10
- },
- {
- "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "F",
- "step": 10
- },
- {
- "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "G",
- "step": 10
- },
- {
- "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "H",
- "step": 10
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
}
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Status",
- "type": "table"
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
},
{
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 19
- },
- "id": 6,
+ "collapse": false,
+ "collapsed": false,
"panels": [
{
"aliasColors": {
},
- "bars": true,
+ "bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 20
+
},
- "id": 7,
+ "id": 20,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
- "sort": "current",
- "sortDesc": true,
"total": false,
"values": true
},
- "lines": false,
+ "lines": true,
"linewidth": 1,
"links": [
],
- "minSpan": 24,
"nullPointMode": "null",
- "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -20971,17 +19832,16 @@ items:
],
"spaceLength": 10,
- "span": 24,
+ "span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{ workload }}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -20989,25 +19849,25 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Rate of Bytes Received",
+ "title": "PLEG relist duration",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
- "mode": "series",
+ "mode": "time",
"name": null,
- "show": false,
+ "show": true,
"values": [
- "current"
+
]
},
"yaxes": [
{
- "format": "Bps",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
@@ -21015,7 +19875,7 @@ items:
"show": true
},
{
- "format": "Bps",
+ "format": "s",
"label": null,
"logBase": 1,
"max": null,
@@ -21023,48 +19883,52 @@ items:
"show": true
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
},
- "bars": true,
+ "bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 20
+
},
- "id": 8,
+ "id": 21,
"legend": {
- "alignAsTable": true,
+ "alignAsTable": false,
"avg": false,
- "current": true,
- "hideEmpty": true,
- "hideZero": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
+ "rightSide": false,
"show": true,
"sideWidth": null,
- "sort": "current",
- "sortDesc": true,
"total": false,
- "values": true
+ "values": false
},
- "lines": false,
+ "lines": true,
"linewidth": 1,
"links": [
],
- "minSpan": 24,
"nullPointMode": "null",
- "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -21074,17 +19938,37 @@ items:
],
"spaceLength": 10,
- "span": 24,
+ "span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{ workload }}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "2xx",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "3xx",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "4xx",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "5xx",
+ "refId": "D"
}
],
"thresholds": [
@@ -21092,25 +19976,25 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Rate of Bytes Transmitted",
+ "title": "RPC Rate",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
- "mode": "series",
+ "mode": "time",
"name": null,
- "show": false,
+ "show": true,
"values": [
- "current"
+
]
},
"yaxes": [
{
- "format": "Bps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -21118,7 +20002,7 @@ items:
"show": true
},
{
- "format": "Bps",
+ "format": "ops",
"label": null,
"logBase": 1,
"max": null,
@@ -21131,284 +20015,153 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Average Bandwidth",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 29
- },
- "id": 9,
"panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 22,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} {{verb}} {{url}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Request duration 99th quantile",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Bandwidth HIstory",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
- "aliasColors": {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 38
- },
- "id": 10,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Receive Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 38
- },
- "id": 11,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
-
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Transmit Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 39
- },
- "id": 12,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 40
- },
- "id": 13,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
+ },
+ "id": 23,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -21418,17 +20171,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 4,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -21436,10 +20188,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "Memory",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -21454,19 +20206,19 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
- "format": "pps",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
}
]
@@ -21479,21 +20231,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 40
+
},
- "id": 14,
+ "id": 24,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -21503,13 +20250,11 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -21519,138 +20264,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 4,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Rate of Transmitted Packets",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "pps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "pps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Packets",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 40
- },
- "id": 15,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 41
- },
- "id": 16,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
-
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -21658,10 +20281,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "CPU usage",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -21676,7 +20299,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -21684,7 +20307,7 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -21701,21 +20324,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 41
+
},
- "id": 17,
+ "id": 25,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -21725,13 +20343,11 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -21741,17 +20357,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 4,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{workload}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -21759,10 +20374,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
+ "title": "Goroutines",
"tooltip": {
- "shared": true,
- "sort": 2,
+ "shared": false,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -21777,19 +20392,19 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
}
]
@@ -21798,17 +20413,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Errors",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
}
],
- "refresh": "10s",
- "rows": [
-
- ],
- "schemaVersion": 18,
+ "schemaVersion": 14,
"style": "dark",
"tags": [
"kubernetes-mixin"
@@ -21839,7 +20450,7 @@ items:
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
- "label": null,
+ "label": "cluster",
"multi": false,
"name": "cluster",
"options": [
@@ -21848,38 +20459,6 @@ items:
"query": "label_values(kube_pod_info, cluster)",
"refresh": 2,
"regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "kube-system",
- "value": "kube-system"
- },
- "datasource": "$datasource",
- "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "namespace",
- "options": [
-
- ],
- "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@@ -21891,28 +20470,22 @@ items:
},
{
"allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
"current": {
- "text": "deployment",
- "value": "deployment"
+
},
"datasource": "$datasource",
- "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
"hide": 0,
- "includeAll": false,
+ "includeAll": true,
"label": null,
"multi": false,
- "name": "type",
+ "name": "instance",
"options": [
],
- "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, instance)",
"refresh": 2,
"regex": "",
- "skipUrlSync": false,
- "sort": 0,
+ "sort": 1,
"tagValuesQuery": "",
"tags": [
@@ -21920,86 +20493,6 @@ items:
"tagsQuery": "",
"type": "query",
"useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "resolution",
- "options": [
- {
- "selected": false,
- "text": "30s",
- "value": "30s"
- },
- {
- "selected": true,
- "text": "5m",
- "value": "5m"
- },
- {
- "selected": false,
- "text": "1h",
- "value": "1h"
- }
- ],
- "query": "30s,5m,1h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "interval",
- "options": [
- {
- "selected": true,
- "text": "4h",
- "value": "4h"
- }
- ],
- "query": "4h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
}
]
},
@@ -22033,8 +20526,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / Networking / Namespace (Workload)",
- "uid": "bbb2a765a623ae38130206c7d94a160f",
+ "title": "Kubernetes / Kubelet",
+ "uid": "3138fa155d5915769fbded898ac09fd9",
"version": 0
}
kind: ConfigMap
@@ -22044,657 +20537,2121 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-namespace-by-workload
+ name: grafana-dashboard-kubelet
namespace: monitoring
- apiVersion: v1
data:
- node-cluster-rsrc-use.json: |-
+ namespace-by-pod.json: |-
{
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
"annotations": {
"list": [
-
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
+ "id": null,
"links": [
],
- "refresh": "10s",
- "rows": [
+ "panels": [
{
"collapse": false,
- "height": "250px",
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
"panels": [
+
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Current Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "decimals": 0,
+ "format": "time_series",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 1
+ },
+ "height": 9,
+ "id": 3,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "options": {
+ "fieldOptions": {
+ "calcs": [
+ "last"
+ ],
+ "defaults": {
+ "max": 10000000000,
+ "min": 0,
+ "title": "$namespace",
+ "unit": "Bps"
+ },
+ "mappings": [
+
+ ],
+ "override": {
+
+ },
+ "thresholds": [
+ {
+ "color": "dark-green",
+ "index": 0,
+ "value": null
+ },
+ {
+ "color": "dark-yellow",
+ "index": 1,
+ "value": 5000000000
+ },
+ {
+ "color": "dark-red",
+ "index": 2,
+ "value": 7000000000
+ }
+ ],
+ "values": false
+ }
+ },
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 12,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
+ "format": "time_series",
+ "instant": null,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Received",
+ "type": "gauge",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "decimals": 0,
+ "format": "time_series",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 1
+ },
+ "height": 9,
+ "id": 4,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "options": {
+ "fieldOptions": {
+ "calcs": [
+ "last"
+ ],
+ "defaults": {
+ "max": 10000000000,
+ "min": 0,
+ "title": "$namespace",
+ "unit": "Bps"
+ },
+ "mappings": [
+
+ ],
+ "override": {
+
+ },
+ "thresholds": [
+ {
+ "color": "dark-green",
+ "index": 0,
+ "value": null
+ },
+ {
+ "color": "dark-yellow",
+ "index": 1,
+ "value": 5000000000
+ },
+ {
+ "color": "dark-red",
+ "index": 2,
+ "value": 7000000000
+ }
+ ],
+ "values": false
+ }
+ },
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 12,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
+ "format": "time_series",
+ "instant": null,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Transmitted",
+ "type": "gauge",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "columns": [
+ {
+ "text": "Time",
+ "value": "Time"
+ },
+ {
+ "text": "Value #A",
+ "value": "Value #A"
+ },
+ {
+ "text": "Value #B",
+ "value": "Value #B"
+ },
+ {
+ "text": "Value #C",
+ "value": "Value #C"
+ },
+ {
+ "text": "Value #D",
+ "value": "Value #D"
+ },
+ {
+ "text": "Value #E",
+ "value": "Value #E"
+ },
+ {
+ "text": "Value #F",
+ "value": "Value #F"
+ },
+ {
+ "text": "pod",
+ "value": "pod"
+ }
+ ],
+ "datasource": "$datasource",
+ "fill": 1,
+ "fontSize": "100%",
+ "gridPos": {
+ "h": 9,
+ "w": 24,
+ "x": 0,
+ "y": 10
+ },
+ "id": 5,
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "minSpan": 24,
+ "nullPointMode": "null as zero",
+ "renderer": "flot",
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 0,
+ "desc": false
+ },
+ "spaceLength": 10,
+ "span": 24,
+ "styles": [
+ {
+ "alias": "Time",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Time",
+ "thresholds": [
+
+ ],
+ "type": "hidden",
+ "unit": "short"
+ },
+ {
+ "alias": "Bandwidth Received",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Bandwidth Transmitted",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Rate of Received Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Received Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Pod",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTooltip": "Drill down",
+ "linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell",
+ "pattern": "pod",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Status",
+ "type": "table"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 19
+ },
+ "id": 6,
+ "panels": [
+
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 20
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Receive Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 20
+ },
+ "id": 8,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Transmit Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 29
+ },
+ "id": 9,
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 30
+ },
+ "id": 10,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rate of Received Packets",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 30
+ },
+ "id": 11,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rate of Transmitted Packets",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Packets",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 30
+ },
+ "id": 12,
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 40
+ },
+ "id": 13,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rate of Received Packets Dropped",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 40
+ },
+ "id": 14,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rate of Transmitted Packets Dropped",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "pps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Errors",
+ "titleSize": "h6",
+ "type": "row"
+ }
+ ],
+ "refresh": "10s",
+ "rows": [
+
+ ],
+ "schemaVersion": 18,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": ".+",
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "kube-system",
+ "value": "kube-system"
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "namespace",
+ "options": [
+
+ ],
+ "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "resolution",
+ "options": [
+ {
+ "selected": false,
+ "text": "30s",
+ "value": "30s"
+ },
+ {
+ "selected": true,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "1h",
+ "value": "1h"
+ }
+ ],
+ "query": "30s,5m,1h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "interval",
+ "options": [
+ {
+ "selected": true,
+ "text": "4h",
+ "value": "4h"
+ }
+ ],
+ "query": "4h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Networking / Namespace (Pods)",
+ "uid": "8b7a8b326d7a6f1f04244066368c67af",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-namespace-by-pod
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ namespace-by-workload.json: |-
+ {
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "panels": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "panels": [
+
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Current Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": true,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 1
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": false,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "minSpan": 24,
+ "nullPointMode": "null",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 24,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ workload }}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Received",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "series",
+ "name": null,
+ "show": false,
+ "values": [
+ "current"
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": true,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 1
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": false,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "minSpan": 24,
+ "nullPointMode": "null",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 24,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ workload }}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Transmitted",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "series",
+ "name": null,
+ "show": false,
+ "values": [
+ "current"
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "columns": [
+ {
+ "text": "Time",
+ "value": "Time"
+ },
+ {
+ "text": "Value #A",
+ "value": "Value #A"
+ },
+ {
+ "text": "Value #B",
+ "value": "Value #B"
+ },
+ {
+ "text": "Value #C",
+ "value": "Value #C"
+ },
+ {
+ "text": "Value #D",
+ "value": "Value #D"
+ },
+ {
+ "text": "Value #E",
+ "value": "Value #E"
+ },
+ {
+ "text": "Value #F",
+ "value": "Value #F"
+ },
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 1,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "(\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\"}\n*\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
+ "text": "Value #G",
+ "value": "Value #G"
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 2,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ "text": "Value #H",
+ "value": "Value #H"
+ },
+ {
+ "text": "workload",
+ "value": "workload"
+ }
+ ],
+ "datasource": "$datasource",
+ "fill": 1,
+ "fontSize": "90%",
+ "gridPos": {
+ "h": 9,
+ "w": 24,
+ "x": 0,
+ "y": 10
+ },
+ "id": 5,
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
+ ],
+ "minSpan": 24,
+ "nullPointMode": "null as zero",
+ "renderer": "flot",
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 0,
+ "desc": false
+ },
+ "spaceLength": 10,
+ "span": 24,
+ "styles": [
+ {
+ "alias": "Time",
+ "colorMode": null,
+ "colors": [
],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Time",
"thresholds": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Saturation (load1 per CPU)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ "type": "hidden",
+ "unit": "short"
+ },
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 3,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ "alias": "Current Bandwidth Received",
+ "colorMode": null,
+ "colors": [
],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Current Bandwidth Transmitted",
+ "colorMode": null,
+ "colors": [
+
],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
"thresholds": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
+ "type": "number",
+ "unit": "Bps"
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 4,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ "alias": "Average Bandwidth Received",
+ "colorMode": null,
+ "colors": [
],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #C",
+ "thresholds": [
],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
+ "type": "number",
+ "unit": "Bps"
+ },
+ {
+ "alias": "Average Bandwidth Transmitted",
+ "colorMode": null,
+ "colors": [
+
],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #D",
"thresholds": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Saturation (Major Page Faults)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "rps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Memory",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ "type": "number",
+ "unit": "Bps"
+ },
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 5,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ "alias": "Rate of Received Packets",
+ "colorMode": null,
+ "colors": [
],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "/ Receive/",
- "stack": "A"
- },
- {
- "alias": "/ Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #E",
+ "thresholds": [
+
],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Receive",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Transmit",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets",
+ "colorMode": null,
+ "colors": [
+
],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #F",
"thresholds": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Net Utilisation (Bytes Receive/Transmit)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
+ "type": "number",
+ "unit": "pps"
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 6,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
+ "alias": "Rate of Received Packets Dropped",
+ "colorMode": null,
+ "colors": [
],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "/ Receive/",
- "stack": "A"
- },
- {
- "alias": "/ Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #G",
+ "thresholds": [
+
],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Receive",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Transmit",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Rate of Transmitted Packets Dropped",
+ "colorMode": null,
+ "colors": [
+
],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #H",
"thresholds": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Net Saturation (Drops Receive/Transmit)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ "type": "number",
+ "unit": "pps"
+ },
+ {
+ "alias": "Workload",
+ "colorMode": null,
+ "colors": [
- ]
- },
- "yaxes": [
- {
- "format": "rps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTooltip": "Drill down",
+ "linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell",
+ "pattern": "workload",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "C",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "E",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "F",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "G",
+ "step": 10
+ },
+ {
+ "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "H",
+ "step": 10
}
],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Network",
- "titleSize": "h6"
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Status",
+ "type": "table"
},
{
- "collapse": false,
- "height": "250px",
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 19
+ },
+ "id": 6,
"panels": [
{
"aliasColors": {
},
- "bars": false,
+ "bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 20
+ },
"id": 7,
"legend": {
+ "alignAsTable": true,
"avg": false,
- "current": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
+ "rightSide": true,
"show": true,
+ "sideWidth": null,
+ "sort": "current",
+ "sortDesc": true,
"total": false,
- "values": false
+ "values": true
},
- "lines": true,
- "linewidth": 0,
+ "lines": false,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 24,
+ "nullPointMode": "null",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 24,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\"}))\n",
+ "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{device}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "intervalFactor": 1,
+ "legendFormat": "{{ workload }}",
+ "refId": "A",
"step": 10
}
],
@@ -22703,38 +22660,38 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk IO Utilisation",
+ "title": "Average Rate of Bytes Received",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
- "mode": "time",
+ "mode": "series",
"name": null,
- "show": true,
+ "show": false,
"values": [
-
+ "current"
]
},
"yaxes": [
{
- "format": "percentunit",
+ "format": "Bps",
"label": null,
"logBase": 1,
- "max": 1,
+ "max": null,
"min": 0,
"show": true
},
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
},
@@ -22742,45 +22699,62 @@ items:
"aliasColors": {
},
- "bars": false,
+ "bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 20
+ },
"id": 8,
"legend": {
+ "alignAsTable": true,
"avg": false,
- "current": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
+ "rightSide": true,
"show": true,
+ "sideWidth": null,
+ "sort": "current",
+ "sortDesc": true,
"total": false,
- "values": false
+ "values": true
},
- "lines": true,
- "linewidth": 0,
+ "lines": false,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 24,
+ "nullPointMode": "null",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 24,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\"}))\n",
+ "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{device}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "intervalFactor": 1,
+ "legendFormat": "{{ workload }}",
+ "refId": "A",
"step": 10
}
],
@@ -22789,38 +22763,38 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk IO Saturation",
+ "title": "Average Rate of Bytes Transmitted",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
- "mode": "time",
+ "mode": "series",
"name": null,
- "show": true,
+ "show": false,
"values": [
-
+ "current"
]
},
"yaxes": [
{
- "format": "percentunit",
+ "format": "Bps",
"label": null,
"logBase": 1,
- "max": 1,
+ "max": null,
"min": 0,
"show": true
},
{
- "format": "short",
+ "format": "Bps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
}
@@ -22829,197 +22803,243 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Disk IO",
- "titleSize": "h6"
+ "title": "Average Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
},
{
"collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 9,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum without (device) (\n max without (fstype, mountpoint) (\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"} - node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\"}\n )\n) \n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"})))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk Space Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 29
+ },
+ "id": 9,
+ "panels": [
+
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Disk Space",
- "titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
+ "title": "Bandwidth HIstory",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 38
+ },
+ "id": 10,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
+
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Receive Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "utc",
- "title": "USE Method / Cluster",
- "uid": "",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-node-cluster-rsrc-use
- namespace: monitoring
-- apiVersion: v1
- data:
- node-rsrc-use.json: |-
- {
- "annotations": {
- "list": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 38
+ },
+ "id": 11,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Transmit Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "refresh": "10s",
- "rows": [
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
{
- "collapse": false,
- "height": "250px",
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 39
+ },
+ "id": 12,
"panels": [
{
"aliasColors": {
@@ -23029,41 +23049,56 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 1,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 40
+ },
+ "id": 13,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
- "show": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Utilisation",
- "legendLink": null,
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
"step": 10
}
],
@@ -23072,10 +23107,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Utilisation",
+ "title": "Rate of Received Packets",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -23090,7 +23125,7 @@ items:
},
"yaxes": [
{
- "format": "percentunit",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
@@ -23098,12 +23133,12 @@ items:
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
},
@@ -23115,41 +23150,56 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 2,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 40
+ },
+ "id": 14,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
- "show": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Saturation",
- "legendLink": null,
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
"step": 10
}
],
@@ -23158,10 +23208,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Saturation (Load1 per CPU)",
+ "title": "Rate of Transmitted Packets",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -23176,7 +23226,7 @@ items:
},
"yaxes": [
{
- "format": "percentunit",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
@@ -23184,12 +23234,12 @@ items:
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
}
@@ -23198,12 +23248,20 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "CPU",
- "titleSize": "h6"
+ "title": "Packets",
+ "titleSize": "h6",
+ "type": "row"
},
{
- "collapse": false,
- "height": "250px",
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 40
+ },
+ "id": 15,
"panels": [
{
"aliasColors": {
@@ -23213,127 +23271,56 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 3,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Memory",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 4,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 41
+ },
+ "id": 16,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
- "show": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Major page faults",
- "legendLink": null,
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
"step": 10
}
],
@@ -23342,10 +23329,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Saturation (Major Page Faults)",
+ "title": "Rate of Received Packets Dropped",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -23360,7 +23347,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
@@ -23368,27 +23355,15 @@ items:
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Memory",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -23397,57 +23372,56 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 5,
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 41
+ },
+ "id": 17,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null as zero",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
- {
- "alias": "/Receive/",
- "stack": "A"
- },
- {
- "alias": "/Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
+
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Receive",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Transmit",
- "legendLink": null,
+ "intervalFactor": 1,
+ "legendFormat": "{{workload}}",
+ "refId": "A",
"step": 10
}
],
@@ -23456,10 +23430,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Net Utilisation (Bytes Receive/Transmit)",
+ "title": "Rate of Transmitted Packets Dropped",
"tooltip": {
- "shared": false,
- "sort": 0,
+ "shared": true,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -23474,223 +23448,297 @@ items:
},
"yaxes": [
{
- "format": "Bps",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
- "show": false
+ "min": 0,
+ "show": true
}
]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Errors",
+ "titleSize": "h6",
+ "type": "row"
+ }
+ ],
+ "refresh": "10s",
+ "rows": [
+
+ ],
+ "schemaVersion": 18,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
},
- {
- "aliasColors": {
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 6,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "/Receive/",
- "stack": "A"
- },
- {
- "alias": "/Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Receive drops",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Transmit drops",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "kube-system",
+ "value": "kube-system"
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "namespace",
+ "options": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Net Saturation (Drops Receive/Transmit)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- ]
- },
- "yaxes": [
- {
- "format": "rps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Net",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "deployment",
+ "value": "deployment"
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "type",
+ "options": [
+
+ ],
+ "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "resolution",
+ "options": [
+ {
+ "selected": false,
+ "text": "30s",
+ "value": "30s"
},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 7,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
+ {
+ "selected": true,
+ "text": "5m",
+ "value": "5m"
},
- "lines": true,
- "linewidth": 1,
- "links": [
+ {
+ "selected": false,
+ "text": "1h",
+ "value": "1h"
+ }
+ ],
+ "query": "30s,5m,1h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "interval",
+ "options": [
+ {
+ "selected": true,
+ "text": "4h",
+ "value": "4h"
+ }
+ ],
+ "query": "4h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{device}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Networking / Namespace (Workload)",
+ "uid": "bbb2a765a623ae38130206c7d94a160f",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-namespace-by-workload
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ node-cluster-rsrc-use.json: |-
+ {
+ "annotations": {
+ "list": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk IO Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "links": [
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
+ ],
+ "refresh": "10s",
+ "rows": [
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -23699,8 +23747,8 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 8,
+ "fill": 10,
+ "id": 1,
"legend": {
"avg": false,
"current": false,
@@ -23711,7 +23759,7 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -23725,15 +23773,15 @@ items:
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "(\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\"}\n*\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\"}))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{device}}",
- "legendLink": null,
+ "legendFormat": "{{instance}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
"step": 10
}
],
@@ -23742,7 +23790,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk IO Saturation",
+ "title": "CPU Utilisation",
"tooltip": {
"shared": false,
"sort": 0,
@@ -23763,7 +23811,7 @@ items:
"format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
@@ -23776,19 +23824,7 @@ items:
"show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Disk IO",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -23797,19 +23833,19 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "id": 9,
+ "fill": 10,
+ "id": 2,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
- "show": false,
+ "show": true,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
@@ -23822,16 +23858,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "1 -\n(\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n/\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n)\n",
+ "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{device}}",
- "legendLink": null,
+ "legendFormat": "{{instance}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
"step": 10
}
],
@@ -23840,7 +23876,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk Space Utilisation",
+ "title": "CPU Saturation (load1 per CPU)",
"tooltip": {
"shared": false,
"sort": 0,
@@ -23861,7 +23897,7 @@ items:
"format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
@@ -23880,171 +23916,42 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Disk Space",
+ "title": "CPU",
"titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
-
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "prod",
- "value": "prod"
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "instance",
- "multi": false,
- "name": "instance",
- "options": [
-
- ],
- "query": "label_values(up{job=\"node-exporter\"}, instance)",
- "refresh": 1,
- "regex": "",
- "sort": 2,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "utc",
- "title": "USE Method / Node",
- "uid": "",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-node-rsrc-use
- namespace: monitoring
-- apiVersion: v1
- data:
- nodes.json: |-
- {
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
- "annotations": {
- "list": [
-
- ]
- },
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
-
- ],
- "refresh": "",
- "rows": [
+ },
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 2,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 10,
+ "id": 3,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
@@ -24054,12 +23961,12 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"}[$__interval]))\n/ ignoring(cpu) group_left\n count without (cpu)( node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n",
+ "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\"}))\n",
"format": "time_series",
- "interval": "$__rate_interval",
- "intervalFactor": 5,
- "legendFormat": "{{cpu}}",
- "refId": "A"
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24067,9 +23974,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU Usage",
+ "title": "Memory Utilisation",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24093,12 +24000,12 @@ items:
"show": true
},
{
- "format": "percentunit",
+ "format": "short",
"label": null,
"logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
+ "max": null,
+ "min": null,
+ "show": false
}
]
},
@@ -24110,70 +24017,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 3,
+ "fill": 10,
+ "id": 4,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "node_load1{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "1m load average",
- "refId": "A"
- },
- {
- "expr": "node_load5{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "5m load average",
- "refId": "B"
- },
- {
- "expr": "node_load15{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "15m load average",
- "refId": "C"
- },
- {
- "expr": "count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})",
+ "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "logical cores",
- "refId": "D"
+ "legendFormat": "{{instance}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24181,9 +24060,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Load Average",
+ "title": "Memory Saturation (Major Page Faults)",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24199,7 +24078,7 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "rps",
"label": null,
"logBase": 1,
"max": null,
@@ -24211,8 +24090,8 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -24220,14 +24099,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Memory",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -24237,70 +24115,58 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 4,
+ "fill": 10,
+ "id": 5,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
-
+ {
+ "alias": "/ Receive/",
+ "stack": "A"
+ },
+ {
+ "alias": "/ Transmit/",
+ "stack": "B",
+ "transform": "negative-Y"
+ }
],
"spaceLength": 10,
- "span": 9,
+ "span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "memory used",
- "refId": "A"
- },
- {
- "expr": "node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "memory buffers",
- "refId": "B"
- },
- {
- "expr": "node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "memory cached",
- "refId": "C"
+ "legendFormat": "{{instance}} Receive",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
},
{
- "expr": "node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}",
+ "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "memory free",
- "refId": "D"
+ "legendFormat": "{{instance}} Transmit",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24308,9 +24174,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory Usage",
+ "title": "Net Utilisation (Bytes Receive/Transmit)",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24319,124 +24185,30 @@ items:
"buckets": null,
"mode": "time",
"name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "rgba(50, 172, 45, 0.97)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(245, 54, 54, 0.9)"
- ],
- "datasource": "$datasource",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
-
- },
- "id": 5,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "80, 90",
- "title": "Memory Usage",
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "valueName": "current"
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ ]
+ },
{
"aliasColors": {
@@ -24445,73 +24217,58 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
-
- },
+ "fill": 10,
"id": 6,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
{
- "alias": "/ read| written/",
- "yaxis": 1
+ "alias": "/ Receive/",
+ "stack": "A"
},
{
- "alias": "/ io time/",
- "yaxis": 2
+ "alias": "/ Transmit/",
+ "stack": "B",
+ "transform": "negative-Y"
}
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
- "format": "time_series",
- "interval": "$__rate_interval",
- "intervalFactor": 2,
- "legendFormat": "{{device}} read",
- "refId": "A"
- },
- {
- "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
+ "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\"}",
"format": "time_series",
- "interval": "$__rate_interval",
"intervalFactor": 2,
- "legendFormat": "{{device}} written",
- "refId": "B"
+ "legendFormat": "{{instance}} Receive",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
},
{
- "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
+ "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\"}",
"format": "time_series",
- "interval": "$__rate_interval",
"intervalFactor": 2,
- "legendFormat": "{{device}} io time",
- "refId": "C"
+ "legendFormat": "{{instance}} Transmit",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24519,9 +24276,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk I/O",
+ "title": "Net Saturation (Drops Receive/Transmit)",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24537,7 +24294,7 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "rps",
"label": null,
"logBase": 1,
"max": null,
@@ -24545,15 +24302,27 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Network",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -24562,44 +24331,29 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
+ "fill": 10,
"id": 7,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
- {
- "alias": "used",
- "color": "#E0B400"
- },
- {
- "alias": "available",
- "color": "#73BF69"
- }
+
],
"spaceLength": 10,
"span": 6,
@@ -24607,18 +24361,12 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(\n max by (device) (\n node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "used",
- "refId": "A"
- },
- {
- "expr": "sum(\n max by (device) (\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n",
+ "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\"}))\n",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "available",
- "refId": "B"
+ "legendFormat": "{{instance}} {{device}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24626,9 +24374,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Disk Space Usage",
+ "title": "Disk IO Utilisation",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24644,36 +24392,23 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -24682,50 +24417,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
-
- },
+ "fill": 10,
"id": 8,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
+ "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\"}))\n",
"format": "time_series",
- "interval": "$__rate_interval",
"intervalFactor": 2,
- "legendFormat": "{{device}}",
- "refId": "A"
+ "legendFormat": "{{instance}} {{device}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24733,9 +24460,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Network Received",
+ "title": "Disk IO Saturation",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24751,23 +24478,35 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Disk IO",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -24776,50 +24515,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
-
- },
+ "fill": 10,
"id": 9,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
+ "expr": "sum without (device) (\n max without (fstype, mountpoint) (\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"} - node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\"}\n )\n) \n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"})))\n",
"format": "time_series",
- "interval": "$__rate_interval",
"intervalFactor": 2,
- "legendFormat": "{{device}}",
- "refId": "A"
+ "legendFormat": "{{instance}}",
+ "legendLink": "/dashboard/file/node-rsrc-use.json",
+ "step": 10
}
],
"thresholds": [
@@ -24827,9 +24558,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Network Transmitted",
+ "title": "Disk Space Utilisation",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -24845,20 +24576,20 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -24866,10 +24597,9 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Disk Space",
+ "titleSize": "h6"
}
],
"schemaVersion": 14,
@@ -24881,8 +24611,8 @@ items:
"list": [
{
"current": {
- "text": "Prometheus",
- "value": "Prometheus"
+ "text": "default",
+ "value": "default"
},
"hide": 0,
"label": null,
@@ -24894,32 +24624,6 @@ items:
"refresh": 1,
"regex": "",
"type": "datasource"
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "instance",
- "options": [
-
- ],
- "query": "label_values(node_exporter_build_info{job=\"node-exporter\"}, instance)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
}
]
},
@@ -24952,8 +24656,9 @@ items:
"30d"
]
},
- "timezone": "browser",
- "title": "Nodes",
+ "timezone": "utc",
+ "title": "USE Method / Cluster",
+ "uid": "",
"version": 0
}
kind: ConfigMap
@@ -24963,28 +24668,21 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-nodes
+ name: grafana-dashboard-node-cluster-rsrc-use
namespace: monitoring
- apiVersion: v1
data:
- persistentvolumesusage.json: |-
+ node-rsrc-use.json: |-
{
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
"annotations": {
"list": [
]
},
- "editable": false,
+ "editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
- "id": null,
"links": [
],
@@ -24992,204 +24690,7 @@ items:
"rows": [
{
"collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 2,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 9,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "(\n sum without(instance, node) (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Used Space",
- "refId": "A"
- },
- {
- "expr": "sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Free Space",
- "refId": "B"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Volume Space Usage",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "rgba(50, 172, 45, 0.97)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(245, 54, 54, 0.9)"
- ],
- "datasource": "$datasource",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
-
- },
- "id": 3,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "max without(instance,node) (\n(\n kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n -\n kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "80, 90",
- "title": "Volume Space Usage",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "current"
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -25200,55 +24701,41 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 4,
+ "id": 1,
"legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": true,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 9,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "Used inodes",
- "refId": "A"
- },
- {
- "expr": "(\n sum without(instance, node) (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n",
+ "expr": "instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": " Free inodes",
- "refId": "B"
+ "intervalFactor": 2,
+ "legendFormat": "Utilisation",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -25256,7 +24743,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Volume inodes Usage",
+ "title": "CPU Utilisation",
"tooltip": {
"shared": false,
"sort": 0,
@@ -25274,7 +24761,7 @@ items:
},
"yaxes": [
{
- "format": "none",
+ "format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
@@ -25282,795 +24769,915 @@ items:
"show": true
},
{
- "format": "none",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "rgba(50, 172, 45, 0.97)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(245, 54, 54, 0.9)"
- ],
- "datasource": "$datasource",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "aliasColors": {
},
- "id": 5,
- "interval": null,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 2,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "max without(instance,node) (\nkubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100)\n",
+ "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
+ "legendFormat": "Saturation",
+ "legendLink": null,
+ "step": 10
}
],
- "thresholds": "80, 90",
- "title": "Volume inodes Usage",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Saturation (Load1 per CPU)",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "valueName": "current"
+ ]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": "cluster",
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ "showTitle": true,
+ "title": "CPU",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 3,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "Namespace",
- "multi": false,
- "name": "namespace",
- "options": [
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
- ],
- "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Memory",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Utilisation",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
},
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "PersistentVolumeClaim",
- "multi": false,
- "name": "volume",
- "options": [
-
- ],
- "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ {
+ "aliasColors": {
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-7d",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Persistent Volumes",
- "uid": "919b92a8e8041bd567af9edab12c840c",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-persistentvolumesusage
- namespace: monitoring
-- apiVersion: v1
- data:
- pod-total.json: |-
- {
- "__inputs": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 4,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "__requires": [
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
- ],
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": "-- Grafana --",
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "type": "dashboard"
- }
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Major page faults",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
- ],
- "panels": [
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 0
- },
- "id": 2,
- "panels": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Saturation (Major Page Faults)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Current Bandwidth",
- "titleSize": "h6",
- "type": "row"
+ "title": "Memory",
+ "titleSize": "h6"
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "decimals": 0,
- "format": "time_series",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 1
- },
- "height": 9,
- "id": 3,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
- "name": "value to text",
- "value": 1
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 5,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/Receive/",
+ "stack": "A"
+ },
+ {
+ "alias": "/Transmit/",
+ "stack": "B",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Receive",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Transmit",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Net Utilisation (Bytes Receive/Transmit)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "minSpan": 12,
- "nullPointMode": "connected",
- "nullText": null,
- "options": {
- "fieldOptions": {
- "calcs": [
- "last"
- ],
- "defaults": {
- "max": 10000000000,
- "min": 0,
- "title": "$namespace: $pod",
- "unit": "Bps"
+ "aliasColors": {
+
},
- "mappings": [
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 6,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
],
- "override": {
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/Receive/",
+ "stack": "A"
+ },
+ {
+ "alias": "/Transmit/",
+ "stack": "B",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Receive drops",
+ "legendLink": null,
+ "step": 10
+ },
+ {
+ "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "Transmit drops",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Net Saturation (Drops Receive/Transmit)",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
},
- "thresholds": [
- {
- "color": "dark-green",
- "index": 0,
- "value": null
- },
+ "yaxes": [
{
- "color": "dark-yellow",
- "index": 1,
- "value": 5000000000
+ "format": "rps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
},
{
- "color": "dark-red",
- "index": 2,
- "value": 7000000000
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "values": false
- }
- },
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 12,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
- "format": "time_series",
- "instant": null,
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Received",
- "type": "gauge",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
+ ]
}
],
- "valueName": "current"
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Net",
+ "titleSize": "h6"
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "decimals": 0,
- "format": "time_series",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 1
- },
- "height": 9,
- "id": 4,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
- "name": "value to text",
- "value": 1
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 7,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}}",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk IO Utilisation",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "minSpan": 12,
- "nullPointMode": "connected",
- "nullText": null,
- "options": {
- "fieldOptions": {
- "calcs": [
- "last"
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 8,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}}",
+ "legendLink": null,
+ "step": 10
+ }
],
- "defaults": {
- "max": 10000000000,
- "min": 0,
- "title": "$namespace: $pod",
- "unit": "Bps"
- },
- "mappings": [
+ "thresholds": [
],
- "override": {
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk IO Saturation",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+ ]
},
- "thresholds": [
- {
- "color": "dark-green",
- "index": 0,
- "value": null
- },
+ "yaxes": [
{
- "color": "dark-yellow",
- "index": 1,
- "value": 5000000000
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
{
- "color": "dark-red",
- "index": 2,
- "value": 7000000000
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
}
- ],
- "values": false
- }
- },
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 12,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
- "format": "time_series",
- "instant": null,
- "intervalFactor": 1,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Rate of Bytes Transmitted",
- "type": "gauge",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "N/A",
- "value": "null"
+ ]
}
- ],
- "valueName": "current"
- },
- {
- "collapse": false,
- "collapsed": false,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 10
- },
- "id": 5,
- "panels": [
-
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Bandwidth",
- "titleSize": "h6",
- "type": "row"
+ "title": "Disk IO",
+ "titleSize": "h6"
},
{
- "aliasColors": {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 0,
- "y": 11
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 9,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "1 -\n(\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n/\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}}",
+ "legendLink": null,
+ "step": 10
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk Space Utilisation",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
}
],
- "thresholds": [
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Disk Space",
+ "titleSize": "h6"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Receive Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
- ]
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
},
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ {
+ "allValue": null,
+ "current": {
+ "text": "prod",
+ "value": "prod"
},
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "instance",
+ "multi": false,
+ "name": "instance",
+ "options": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 2,
- "fillGradient": 0,
- "gridPos": {
- "h": 9,
- "w": 12,
- "x": 12,
- "y": 11
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "hideEmpty": true,
- "hideZero": true,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [
+ ],
+ "query": "label_values(up{job=\"node-exporter\"}, instance)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 2,
+ "tagValuesQuery": "",
+ "tags": [
- ],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "utc",
+ "title": "USE Method / Node",
+ "uid": "",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-node-rsrc-use
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ nodes.json: |-
+ {
+ "__inputs": [
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
+ ],
+ "__requires": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Transmit Bandwidth",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "annotations": {
+ "list": [
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
+ ]
+ },
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "",
+ "rows": [
{
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 20
- },
- "id": 8,
+ "collapse": false,
+ "collapsed": false,
"panels": [
{
"aliasColors": {
@@ -26080,21 +25687,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 0,
- "y": 21
+
},
- "id": 9,
+ "id": 2,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -26104,13 +25706,11 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -26120,17 +25720,16 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
+ "expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"}[$__rate_interval]))\n/ ignoring(cpu) group_left\n count without (cpu)( node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 5,
+ "legendFormat": "{{cpu}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -26138,10 +25737,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets",
+ "title": "CPU Usage",
"tooltip": {
"shared": true,
- "sort": 2,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -26156,18 +25755,18 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
},
{
- "format": "pps",
+ "format": "percentunit",
"label": null,
"logBase": 1,
- "max": null,
+ "max": 1,
"min": 0,
"show": true
}
@@ -26181,21 +25780,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 0,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 12,
- "y": 21
+
},
- "id": 10,
+ "id": 3,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -26205,13 +25799,11 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -26221,17 +25813,37 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
+ "expr": "node_load1{job=\"node-exporter\", instance=\"$instance\"}",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "1m load average",
+ "refId": "A"
+ },
+ {
+ "expr": "node_load5{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "5m load average",
+ "refId": "B"
+ },
+ {
+ "expr": "node_load15{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "15m load average",
+ "refId": "C"
+ },
+ {
+ "expr": "count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "logical cores",
+ "refId": "D"
}
],
"thresholds": [
@@ -26239,10 +25851,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Transmitted Packets",
+ "title": "Load Average",
"tooltip": {
"shared": true,
- "sort": 2,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -26257,7 +25869,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -26265,7 +25877,7 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -26278,21 +25890,14 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Packets",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
- "collapse": true,
- "collapsed": true,
- "gridPos": {
- "h": 1,
- "w": 24,
- "x": 0,
- "y": 21
- },
- "id": 11,
+ "collapse": false,
+ "collapsed": false,
"panels": [
{
"aliasColors": {
@@ -26302,21 +25907,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 1,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 0,
- "y": 32
+
},
- "id": 12,
+ "id": 4,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -26326,13 +25926,11 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
@@ -26342,17 +25940,37 @@ items:
],
"spaceLength": 10,
- "span": 12,
+ "span": 9,
"stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
+ "expr": "(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n",
"format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
+ "intervalFactor": 2,
+ "legendFormat": "memory used",
+ "refId": "A"
+ },
+ {
+ "expr": "node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "memory buffers",
+ "refId": "B"
+ },
+ {
+ "expr": "node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "memory cached",
+ "refId": "C"
+ },
+ {
+ "expr": "node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "memory free",
+ "refId": "D"
}
],
"thresholds": [
@@ -26360,10 +25978,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate of Received Packets Dropped",
+ "title": "Memory Usage",
"tooltip": {
"shared": true,
- "sort": 2,
+ "sort": 0,
"value_type": "individual"
},
"type": "graph",
@@ -26378,7 +25996,7 @@ items:
},
"yaxes": [
{
- "format": "pps",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
@@ -26386,15 +26004,109 @@ items:
"show": true
},
{
- "format": "pps",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
- ]
- },
+ ]
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": "$datasource",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+
+ },
+ "id": 5,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "80, 90",
+ "title": "Memory Usage",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -26403,21 +26115,16 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 2,
+ "fill": 0,
"fillGradient": 0,
"gridPos": {
- "h": 10,
- "w": 12,
- "x": 12,
- "y": 32
+
},
- "id": 13,
+ "id": 6,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
- "hideEmpty": true,
- "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -26427,352 +26134,209 @@ items:
"values": false
},
"lines": true,
- "linewidth": 2,
+ "linewidth": 1,
"links": [
],
- "minSpan": 12,
- "nullPointMode": "connected",
- "paceLength": 10,
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
- "format": "time_series",
- "intervalFactor": 1,
- "legendFormat": "{{pod}}",
- "refId": "A",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Rate of Transmitted Packets Dropped",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
{
- "format": "pps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "alias": "/ read| written/",
+ "yaxis": 1
},
{
- "format": "pps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
+ "alias": "/ io time/",
+ "yaxis": 2
}
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Errors",
- "titleSize": "h6",
- "type": "row"
- }
- ],
- "refresh": "10s",
- "rows": [
-
- ],
- "schemaVersion": 18,
- "style": "dark",
- "tags": [
- "kubernetes-mixin"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": ".+",
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "kube-system",
- "value": "kube-system"
- },
- "datasource": "$datasource",
- "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "namespace",
- "options": [
-
- ],
- "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": ".+",
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "",
- "value": ""
- },
- "datasource": "$datasource",
- "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "pod",
- "options": [
-
- ],
- "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "resolution",
- "options": [
- {
- "selected": false,
- "text": "30s",
- "value": "30s"
- },
- {
- "selected": true,
- "text": "5m",
- "value": "5m"
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} read",
+ "refId": "A"
+ },
+ {
+ "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} written",
+ "refId": "B"
+ },
+ {
+ "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}} io time",
+ "refId": "C"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk I/O",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
},
- {
- "selected": false,
- "text": "1h",
- "value": "1h"
- }
- ],
- "query": "30s,5m,1h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
- },
- {
- "allValue": null,
- "auto": false,
- "auto_count": 30,
- "auto_min": "10s",
- "current": {
- "text": "5m",
- "value": "5m"
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
},
- "datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": null,
- "multi": false,
- "name": "interval",
- "options": [
- {
- "selected": true,
- "text": "4h",
- "value": "4h"
- }
- ],
- "query": "4h",
- "refresh": 2,
- "regex": "",
- "skipUrlSync": false,
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "interval",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-1h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "UTC",
- "title": "Kubernetes / Networking / Pod",
- "uid": "7a18067ce943a40ae25454675c19ff5c",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-pod-total
- namespace: monitoring
-- apiVersion: v1
- data:
- prometheus-remote-write.json: |-
- {
- "__inputs": [
+ {
+ "aliasColors": {
- ],
- "__requires": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "annotations": {
- "list": [
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+ {
+ "alias": "used",
+ "color": "#E0B400"
+ },
+ {
+ "alias": "available",
+ "color": "#73BF69"
+ }
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(\n max by (device) (\n node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "used",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(\n max by (device) (\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "available",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [
- ],
- "refresh": "60s",
- "rows": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk Space Usage",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
{
"collapse": false,
"collapsed": false,
@@ -26785,12 +26349,12 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
+ "fill": 0,
"fillGradient": 0,
"gridPos": {
},
- "id": 2,
+ "id": 8,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -26823,10 +26387,10 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n",
+ "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "legendFormat": "{{device}}",
"refId": "A"
}
],
@@ -26835,7 +26399,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Highest Timestamp In vs. Highest Timestamp Sent",
+ "title": "Network Received",
"tooltip": {
"shared": true,
"sort": 0,
@@ -26853,23 +26417,248 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{device}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network Transmitted",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
"show": true
}
]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "Prometheus",
+ "value": "Prometheus"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+
},
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "instance",
+ "options": [
+
+ ],
+ "query": "label_values(node_exporter_build_info{job=\"node-exporter\"}, instance)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "browser",
+ "title": "Nodes",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-nodes
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ persistentvolumesusage.json: |-
+ {
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "10s",
+ "rows": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -26883,18 +26672,18 @@ items:
"gridPos": {
},
- "id": 3,
+ "id": 2,
"legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
"linewidth": 1,
@@ -26911,16 +26700,23 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 9,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "clamp_min(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n",
+ "expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "intervalFactor": 1,
+ "legendFormat": "Used Space",
"refId": "A"
+ },
+ {
+ "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Free Space",
+ "refId": "B"
}
],
"thresholds": [
@@ -26928,9 +26724,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate[5m]",
+ "title": "Volume Space Usage",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -26946,29 +26742,113 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "bytes",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
}
]
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": "$datasource",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+
+ },
+ "id": 3,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "80, 90",
+ "title": "Volume Space Usage",
+ "tooltip": {
+ "shared": false
+ },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Timestamps",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
@@ -26991,16 +26871,16 @@ items:
},
"id": 4,
"legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
- "values": false
+ "values": true
},
"lines": true,
"linewidth": 1,
@@ -27017,16 +26897,23 @@ items:
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 9,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) (rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n",
+ "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "intervalFactor": 1,
+ "legendFormat": "Used inodes",
"refId": "A"
+ },
+ {
+ "expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": " Free inodes",
+ "refId": "B"
}
],
"thresholds": [
@@ -27034,9 +26921,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rate, in vs. succeeded or dropped [5m]",
+ "title": "Volume inodes Usage",
"tooltip": {
- "shared": true,
+ "shared": false,
"sort": 0,
"value_type": "individual"
},
@@ -27052,421 +26939,803 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "none",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
"show": true
+ }
+ ]
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": "$datasource",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+
+ },
+ "id": 5,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "80, 90",
+ "title": "Volume inodes Usage",
+ "tooltip": {
+ "shared": false
+ },
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
}
- ]
+ ],
+ "valueName": "current"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": true,
- "title": "Samples",
+ "showTitle": false,
+ "title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
- },
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": "cluster",
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Namespace",
+ "multi": false,
+ "name": "namespace",
+ "options": [
+
+ ],
+ "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "PersistentVolumeClaim",
+ "multi": false,
+ "name": "volume",
+ "options": [
+
+ ],
+ "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-7d",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Persistent Volumes",
+ "uid": "919b92a8e8041bd567af9edab12c840c",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-persistentvolumesusage
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ pod-total.json: |-
+ {
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "panels": [
{
"collapse": false,
"collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
"panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 5,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
- ],
- "minSpan": 6,
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Current Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "decimals": 0,
+ "format": "time_series",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 1
+ },
+ "height": 9,
+ "id": 3,
+ "interval": null,
+ "links": [
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "options": {
+ "fieldOptions": {
+ "calcs": [
+ "last"
],
- "spaceLength": 10,
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ "defaults": {
+ "max": 10000000000,
+ "min": 0,
+ "title": "$namespace: $pod",
+ "unit": "Bps"
+ },
+ "mappings": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Current Shards",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ "override": {
- ]
},
- "yaxes": [
+ "thresholds": [
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "color": "dark-green",
+ "index": 0,
+ "value": null
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "color": "dark-yellow",
+ "index": 1,
+ "value": 5000000000
+ },
+ {
+ "color": "dark-red",
+ "index": 2,
+ "value": 7000000000
}
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ "values": false
+ }
+ },
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 12,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
+ "format": "time_series",
+ "instant": null,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Received",
+ "type": "gauge",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "#299c46",
+ "rgba(237, 129, 40, 0.89)",
+ "#d44a3a"
+ ],
+ "datasource": "$datasource",
+ "decimals": 0,
+ "format": "time_series",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 1
+ },
+ "height": 9,
+ "id": 4,
+ "interval": null,
+ "links": [
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "options": {
+ "fieldOptions": {
+ "calcs": [
+ "last"
],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ "defaults": {
+ "max": 10000000000,
+ "min": 0,
+ "title": "$namespace: $pod",
+ "unit": "Bps"
+ },
+ "mappings": [
],
- "timeFrom": null,
- "timeShift": null,
- "title": "Max Shards",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ "override": {
- ]
},
- "yaxes": [
+ "thresholds": [
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "color": "dark-green",
+ "index": 0,
+ "value": null
},
{
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
+ "color": "dark-yellow",
+ "index": 1,
+ "value": 5000000000
+ },
+ {
+ "color": "dark-red",
+ "index": 2,
+ "value": 7000000000
}
- ]
- },
+ ],
+ "values": false
+ }
+ },
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
{
- "aliasColors": {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 12,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
+ "format": "time_series",
+ "instant": null,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "",
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Rate of Bytes Transmitted",
+ "type": "gauge",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 10
+ },
+ "id": 5,
+ "panels": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Bandwidth",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
- },
- "id": 7,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 0,
+ "y": 11
+ },
+ "id": 6,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Min Shards",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Receive Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
},
{
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
- },
- "id": 8,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 2,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 9,
+ "w": 12,
+ "x": 12,
+ "y": 11
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ],
- "spaceLength": 10,
- "span": 4,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
+ }
+ ],
+ "thresholds": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Desired Shards",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Transmit Bandwidth",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Shards",
- "titleSize": "h6",
- "type": "row"
+ ]
},
{
- "collapse": false,
- "collapsed": false,
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 20
+ },
+ "id": 8,
"panels": [
{
"aliasColors": {
@@ -27476,16 +27745,21 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
+ "fill": 2,
"fillGradient": 0,
"gridPos": {
-
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 21
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -27495,11 +27769,13 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -27509,16 +27785,17 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
}
],
"thresholds": [
@@ -27526,10 +27803,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Shard Capacity",
+ "title": "Rate of Received Packets",
"tooltip": {
"shared": true,
- "sort": 0,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -27544,19 +27821,19 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
}
]
@@ -27569,16 +27846,21 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
+ "fill": 2,
"fillGradient": 0,
"gridPos": {
-
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 21
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -27588,11 +27870,13 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -27602,16 +27886,17 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
}
],
"thresholds": [
@@ -27619,10 +27904,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Pending Samples",
+ "title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
- "sort": 0,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -27637,19 +27922,19 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
}
]
@@ -27659,13 +27944,20 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Shard Details",
+ "title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
- "collapse": false,
- "collapsed": false,
+ "collapse": true,
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 21
+ },
+ "id": 11,
"panels": [
{
"aliasColors": {
@@ -27675,16 +27967,21 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
+ "fill": 2,
"fillGradient": 0,
"gridPos": {
-
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 32
},
- "id": 11,
+ "id": 12,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -27694,11 +27991,13 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -27708,16 +28007,17 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}}",
- "refId": "A"
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
}
],
"thresholds": [
@@ -27725,10 +28025,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "TSDB Current Segment",
+ "title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
- "sort": 0,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -27743,19 +28043,19 @@ items:
},
"yaxes": [
{
- "format": "none",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
}
]
@@ -27768,16 +28068,21 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
+ "fill": 2,
"fillGradient": 0,
"gridPos": {
-
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 32
},
- "id": 12,
+ "id": 13,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
+ "hideEmpty": true,
+ "hideZero": true,
"max": false,
"min": false,
"rightSide": false,
@@ -27787,11 +28092,13 @@ items:
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 2,
"links": [
],
- "nullPointMode": "null",
+ "minSpan": 12,
+ "nullPointMode": "connected",
+ "paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
@@ -27801,16 +28108,17 @@ items:
],
"spaceLength": 10,
- "span": 6,
- "stack": false,
+ "span": 12,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
- "refId": "A"
+ "intervalFactor": 1,
+ "legendFormat": "{{pod}}",
+ "refId": "A",
+ "step": 10
}
],
"thresholds": [
@@ -27818,10 +28126,10 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Remote Write Current Segment",
+ "title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
- "sort": 0,
+ "sort": 2,
"value_type": "individual"
},
"type": "graph",
@@ -27836,19 +28144,19 @@ items:
},
"yaxes": [
{
- "format": "none",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "short",
+ "format": "pps",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
}
]
@@ -27858,107 +28166,282 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Segments",
+ "title": "Errors",
"titleSize": "h6",
"type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
+ }
+ ],
+ "refresh": "10s",
+ "rows": [
+
+ ],
+ "schemaVersion": 18,
+ "style": "dark",
+ "tags": [
+ "kubernetes-mixin"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "default",
+ "value": "default"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "cluster",
+ "options": [
+
+ ],
+ "query": "label_values(kube_pod_info, cluster)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": ".+",
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "kube-system",
+ "value": "kube-system"
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "namespace",
+ "options": [
+
+ ],
+ "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": ".+",
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "",
+ "value": ""
+ },
+ "datasource": "$datasource",
+ "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "pod",
+ "options": [
+
+ ],
+ "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "resolution",
+ "options": [
+ {
+ "selected": false,
+ "text": "30s",
+ "value": "30s"
},
- "id": 13,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
+ {
+ "selected": true,
+ "text": "5m",
+ "value": "5m"
},
- "lines": true,
- "linewidth": 1,
- "links": [
+ {
+ "selected": false,
+ "text": "1h",
+ "value": "1h"
+ }
+ ],
+ "query": "30s,5m,1h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "text": "5m",
+ "value": "5m"
+ },
+ "datasource": "$datasource",
+ "hide": 2,
+ "includeAll": false,
+ "label": null,
+ "multi": false,
+ "name": "interval",
+ "options": [
+ {
+ "selected": true,
+ "text": "4h",
+ "value": "4h"
+ }
+ ],
+ "query": "4h",
+ "refresh": 2,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [
- ],
- "spaceLength": 10,
- "span": 3,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
- "refId": "A"
- }
- ],
- "thresholds": [
+ ],
+ "tagsQuery": "",
+ "type": "interval",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "UTC",
+ "title": "Kubernetes / Networking / Pod",
+ "uid": "7a18067ce943a40ae25454675c19ff5c",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ labels:
+ app.kubernetes.io/component: grafana
+ app.kubernetes.io/name: grafana
+ app.kubernetes.io/part-of: kube-prometheus
+ app.kubernetes.io/version: 7.5.4
+ name: grafana-dashboard-pod-total
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ prometheus-remote-write.json: |-
+ {
+ "__inputs": [
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Dropped Samples",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
+ ],
+ "__requires": [
- ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
+ ],
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": true,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "60s",
+ "rows": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -27972,7 +28455,7 @@ items:
"gridPos": {
},
- "id": 14,
+ "id": 2,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -28000,12 +28483,12 @@ items:
],
"spaceLength": 10,
- "span": 3,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+ "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
@@ -28017,7 +28500,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Failed Samples",
+ "title": "Highest Timestamp In vs. Highest Timestamp Sent",
"tooltip": {
"shared": true,
"sort": 0,
@@ -28065,7 +28548,7 @@ items:
"gridPos": {
},
- "id": 15,
+ "id": 3,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -28093,12 +28576,12 @@ items:
],
"spaceLength": 10,
- "span": 3,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_retried_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+ "expr": "clamp_min(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
@@ -28110,7 +28593,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Retried Samples",
+ "title": "Rate[5m]",
"tooltip": {
"shared": true,
"sort": 0,
@@ -28144,7 +28627,20 @@ items:
"show": true
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Timestamps",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -28158,7 +28654,7 @@ items:
"gridPos": {
},
- "id": 16,
+ "id": 4,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -28186,12 +28682,12 @@ items:
],
"spaceLength": 10,
- "span": 3,
+ "span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+ "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) (rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
@@ -28203,7 +28699,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Enqueue Retries",
+ "title": "Rate, in vs. succeeded or dropped [5m]",
"tooltip": {
"shared": true,
"sort": 0,
@@ -28243,192 +28739,108 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Misc. Rates",
+ "title": "Samples",
"titleSize": "h6",
"type": "row"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
- "prometheus-mixin"
- ],
- "templating": {
- "list": [
- {
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": {
- "selected": true,
- "text": "All",
- "value": "$__all"
},
- "value": {
- "selected": true,
- "text": "All",
- "value": "$__all"
- }
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "instance",
- "options": [
-
- ],
- "query": "label_values(prometheus_build_info, instance)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
- "text": {
- "selected": true,
- "text": "All",
- "value": "$__all"
},
- "value": {
- "selected": true,
- "text": "All",
- "value": "$__all"
- }
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "cluster",
- "options": [
-
- ],
- "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": true,
- "label": null,
- "multi": false,
- "name": "url",
- "options": [
-
- ],
- "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
- "refresh": 2,
- "regex": "",
- "sort": 0,
- "tagValuesQuery": "",
- "tags": [
+ "id": 5,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- }
- ]
- },
- "time": {
- "from": "now-6h",
- "to": "now"
- },
- "timepicker": {
- "refresh_intervals": [
- "5s",
- "10s",
- "30s",
- "1m",
- "5m",
- "15m",
- "30m",
- "1h",
- "2h",
- "1d"
- ],
- "time_options": [
- "5m",
- "15m",
- "1h",
- "6h",
- "12h",
- "24h",
- "2d",
- "7d",
- "30d"
- ]
- },
- "timezone": "browser",
- "title": "Prometheus / Remote Write",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- labels:
- app.kubernetes.io/component: grafana
- app.kubernetes.io/name: grafana
- app.kubernetes.io/part-of: kube-prometheus
- app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-prometheus-remote-write
- namespace: monitoring
-- apiVersion: v1
- data:
- prometheus.json: |-
- {
- "annotations": {
- "list": [
+ ],
+ "minSpan": 6,
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
- ],
- "refresh": "60s",
- "rows": [
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Current Shards",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
{
"aliasColors": {
@@ -28438,13 +28850,20 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 6,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
@@ -28453,154 +28872,119 @@ items:
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 12,
+ "span": 4,
"stack": false,
"steppedLine": false,
- "styles": [
- {
- "alias": "Time",
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "pattern": "Time",
- "type": "hidden"
- },
- {
- "alias": "Count",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #A",
- "thresholds": [
-
- ],
- "type": "hidden",
- "unit": "short"
- },
- {
- "alias": "Uptime",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "Value #B",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
- },
+ "targets": [
{
- "alias": "Instance",
- "colorMode": null,
- "colors": [
+ "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "instance",
- "thresholds": [
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Max Shards",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
- ],
- "type": "number",
- "unit": "short"
- },
+ ]
+ },
+ "yaxes": [
{
- "alias": "Job",
- "colorMode": null,
- "colors": [
-
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "job",
- "thresholds": [
-
- ],
- "type": "number",
- "unit": "short"
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
},
{
- "alias": "Version",
- "colorMode": null,
- "colors": [
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "link": false,
- "linkTargetBlank": false,
- "linkTooltip": "Drill down",
- "linkUrl": "",
- "pattern": "version",
- "thresholds": [
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
- ],
- "type": "number",
- "unit": "short"
- },
- {
- "alias": "",
- "colorMode": null,
- "colors": [
+ },
+ "id": 7,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
- ],
- "dateFormat": "YYYY-MM-DD HH:mm:ss",
- "decimals": 2,
- "pattern": "/.*/",
- "thresholds": [
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
- ],
- "type": "string",
- "unit": "short"
- }
],
+ "spaceLength": 10,
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "count by (job, instance, version) (prometheus_build_info{job=~\"$job\", instance=~\"$instance\"})",
- "format": "table",
- "instant": true,
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A",
- "step": 10
- },
- {
- "expr": "max by (job, instance) (time() - process_start_time_seconds{job=~\"$job\", instance=~\"$instance\"})",
- "format": "table",
- "instant": true,
+ "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
+ "format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
- "refId": "B",
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -28608,14 +28992,13 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Prometheus Stats",
+ "title": "Min Shards",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
- "transform": "table",
- "type": "table",
+ "type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -28631,7 +29014,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -28640,22 +29023,10 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Prometheus Stats",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -28665,13 +29036,20 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 2,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 8,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
@@ -28680,26 +29058,26 @@ items:
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
+ "span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m])) by (scrape_job) * 1e3",
+ "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{scrape_job}}",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -28707,9 +29085,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Target Sync",
+ "title": "Desired Shards",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -28725,11 +29103,11 @@ items:
},
"yaxes": [
{
- "format": "ms",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -28738,10 +29116,23 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Shards",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -28750,42 +29141,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 3,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 9,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": true,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(prometheus_sd_discovered_targets{job=~\"$job\",instance=~\"$instance\"})",
+ "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "Targets",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -28793,9 +29191,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Targets",
+ "title": "Shard Capacity",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -28815,7 +29213,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -28824,22 +29222,10 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Discovery",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -28849,13 +29235,20 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "id": 4,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 10,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
@@ -28864,26 +29257,26 @@ items:
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_target_interval_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3",
+ "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{interval}} configured",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -28891,9 +29284,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Average Scrape Interval Duration",
+ "title": "Pending Samples",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -28909,11 +29302,11 @@ items:
},
"yaxes": [
{
- "format": "ms",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -28922,10 +29315,23 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Shard Details",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -28934,66 +29340,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 5,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 11,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total[1m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "exceeded sample limit: {{job}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total[1m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "duplicate timestamp: {{job}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total[1m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "out of bounds: {{job}}",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total[1m]))",
+ "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "out of order: {{job}}",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29001,9 +29390,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Scrape failures",
+ "title": "TSDB Current Segment",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29019,11 +29408,11 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "none",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29032,7 +29421,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
},
@@ -29044,42 +29433,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 6,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 12,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
- "stack": true,
+ "span": 6,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=~\"$job\",instance=~\"$instance\"}[5m])",
+ "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{job}} {{instance}}",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29087,9 +29483,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Appended Samples",
+ "title": "Remote Write Current Segment",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29105,11 +29501,11 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "none",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29118,7 +29514,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
}
@@ -29127,12 +29523,13 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Retrieval",
- "titleSize": "h6"
+ "title": "Segments",
+ "titleSize": "h6",
+ "type": "row"
},
{
"collapse": false,
- "height": "250px",
+ "collapsed": false,
"panels": [
{
"aliasColors": {
@@ -29142,42 +29539,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 7,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 13,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"}",
+ "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{job}} {{instance}} head series",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29185,9 +29589,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Head Series",
+ "title": "Dropped Samples",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29207,7 +29611,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29216,7 +29620,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
},
@@ -29228,42 +29632,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 8,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 14,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"}",
+ "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{job}} {{instance}} head chunks",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29271,9 +29682,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Head Chunks",
+ "title": "Failed Samples",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29293,7 +29704,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29302,22 +29713,10 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Storage",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
+ },
{
"aliasColors": {
@@ -29326,42 +29725,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 9,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 15,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "rate(prometheus_engine_query_duration_seconds_count{job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])",
+ "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_retried_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{job}} {{instance}}",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29369,9 +29775,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Query Rate",
+ "title": "Retried Samples",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29391,7 +29797,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29400,7 +29806,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
},
@@ -29412,42 +29818,49 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 10,
- "id": 10,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 16,
"legend": {
+ "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
+ "rightSide": false,
"show": true,
+ "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 0,
+ "linewidth": 1,
"links": [
],
- "nullPointMode": "null as zero",
+ "nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
+ "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
- "stack": true,
+ "span": 3,
+ "stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",job=~\"$job\",instance=~\"$instance\"}) * 1e3",
+ "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{slice}}",
- "legendLink": null,
- "step": 10
+ "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+ "refId": "A"
}
],
"thresholds": [
@@ -29455,9 +29868,9 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Stage Duration",
+ "title": "Enqueue Retries",
"tooltip": {
- "shared": false,
+ "shared": true,
"sort": 0,
"value_type": "individual"
},
@@ -29473,11 +29886,11 @@ items:
},
"yaxes": [
{
- "format": "ms",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -29486,7 +29899,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": false
+ "show": true
}
]
}
@@ -29495,8 +29908,9 @@ items:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
- "title": "Query",
- "titleSize": "h6"
+ "title": "Misc. Rates",
+ "titleSize": "h6",
+ "type": "row"
}
],
"schemaVersion": 14,
@@ -29507,10 +29921,6 @@ items:
"templating": {
"list": [
{
- "current": {
- "text": "default",
- "value": "default"
- },
"hide": 0,
"label": null,
"name": "datasource",
@@ -29523,25 +29933,67 @@ items:
"type": "datasource"
},
{
- "allValue": ".+",
+ "allValue": null,
"current": {
- "selected": true,
- "text": "All",
- "value": "$__all"
+ "text": {
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
+ },
+ "value": {
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
+ }
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": true,
+ "label": null,
+ "multi": false,
+ "name": "instance",
+ "options": [
+
+ ],
+ "query": "label_values(prometheus_build_info, instance)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": {
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
+ },
+ "value": {
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
+ }
},
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
- "label": "job",
- "multi": true,
- "name": "job",
+ "label": null,
+ "multi": false,
+ "name": "cluster",
"options": [
],
- "query": "label_values(prometheus_build_info, job)",
- "refresh": 1,
+ "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)",
+ "refresh": 2,
"regex": "",
- "sort": 2,
+ "sort": 0,
"tagValuesQuery": "",
"tags": [
@@ -29551,25 +30003,23 @@ items:
"useTags": false
},
{
- "allValue": ".+",
+ "allValue": null,
"current": {
- "selected": true,
- "text": "All",
- "value": "$__all"
+
},
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
- "label": "instance",
- "multi": true,
- "name": "instance",
+ "label": null,
+ "multi": false,
+ "name": "url",
"options": [
],
- "query": "label_values(prometheus_build_info, instance)",
- "refresh": 1,
+ "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
+ "refresh": 2,
"regex": "",
- "sort": 2,
+ "sort": 0,
"tagValuesQuery": "",
"tags": [
@@ -29581,7 +30031,7 @@ items:
]
},
"time": {
- "from": "now-1h",
+ "from": "now-6h",
"to": "now"
},
"timepicker": {
@@ -29609,9 +30059,8 @@ items:
"30d"
]
},
- "timezone": "utc",
- "title": "Prometheus / Overview",
- "uid": "",
+ "timezone": "browser",
+ "title": "Prometheus / Remote Write",
"version": 0
}
kind: ConfigMap
@@ -29621,172 +30070,202 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-prometheus
+ name: grafana-dashboard-prometheus-remote-write
namespace: monitoring
- apiVersion: v1
data:
- proxy.json: |-
+ prometheus.json: |-
{
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
"annotations": {
"list": [
]
},
- "editable": false,
+ "editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
- "id": null,
"links": [
],
- "refresh": "10s",
+ "refresh": "60s",
"rows": [
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
+ "aliasColors": {
},
- "id": 2,
- "interval": null,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "id": 1,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "styles": [
{
- "name": "value to text",
- "value": 1
+ "alias": "Time",
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "pattern": "Time",
+ "type": "hidden"
},
{
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "alias": "Count",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #A",
+ "thresholds": [
+
+ ],
+ "type": "hidden",
+ "unit": "short"
+ },
{
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 2,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
- "targets": [
+ "alias": "Uptime",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "Value #B",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "expr": "sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "Up",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "alias": "Instance",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "instance",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
{
- "op": "=",
- "text": "N/A",
- "value": "null"
- }
- ],
- "valueName": "min"
- },
- {
- "aliasColors": {
+ "alias": "Job",
+ "colorMode": null,
+ "colors": [
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "job",
+ "thresholds": [
+
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "Version",
+ "colorMode": null,
+ "colors": [
+
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "linkTargetBlank": false,
+ "linkTooltip": "Drill down",
+ "linkUrl": "",
+ "pattern": "version",
+ "thresholds": [
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "alias": "",
+ "colorMode": null,
+ "colors": [
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ ],
+ "type": "string",
+ "unit": "short"
+ }
],
- "spaceLength": 10,
- "span": 5,
- "stack": false,
- "steppedLine": false,
"targets": [
{
- "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
- "format": "time_series",
+ "expr": "count by (job, instance, version) (prometheus_build_info{job=~\"$job\", instance=~\"$instance\"})",
+ "format": "table",
+ "instant": true,
"intervalFactor": 2,
- "legendFormat": "rate",
- "refId": "A"
+ "legendFormat": "",
+ "refId": "A",
+ "step": 10
+ },
+ {
+ "expr": "max by (job, instance) (time() - process_start_time_seconds{job=~\"$job\", instance=~\"$instance\"})",
+ "format": "table",
+ "instant": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
}
],
"thresholds": [
@@ -29794,13 +30273,14 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rules Sync Rate",
+ "title": "Prometheus Stats",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
- "type": "graph",
+ "transform": "table",
+ "type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
@@ -29812,7 +30292,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -29820,15 +30300,27 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Prometheus Stats",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -29838,48 +30330,41 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 4,
+ "id": 2,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 5,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+ "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m])) by (scrape_job) * 1e3",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{scrape_job}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -29887,7 +30372,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Rule Sync Latency 99th Quantile",
+ "title": "Target Sync",
"tooltip": {
"shared": false,
"sort": 0,
@@ -29905,7 +30390,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "ms",
"label": null,
"logBase": 1,
"max": null,
@@ -29913,28 +30398,15 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -29943,49 +30415,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 5,
+ "fill": 10,
+ "id": 3,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+ "expr": "sum(prometheus_sd_discovered_targets{job=~\"$job\",instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "rate",
- "refId": "A"
+ "legendFormat": "Targets",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -29993,7 +30458,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Network Programming Rate",
+ "title": "Targets",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30011,7 +30476,7 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -30019,15 +30484,27 @@ items:
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Discovery",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -30037,48 +30514,41 @@ items:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 6,
+ "id": 4,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 6,
+ "span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m])) by (instance, le))",
+ "expr": "rate(prometheus_target_interval_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{interval}} configured",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30086,7 +30556,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Network Programming Latency 99th Quantile",
+ "title": "Average Scrape Interval Duration",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30104,7 +30574,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "ms",
"label": null,
"logBase": 1,
"max": null,
@@ -30112,100 +30582,83 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 7,
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 10,
+ "id": 5,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
- "stack": false,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+ "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total[1m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "2xx",
- "refId": "A"
+ "legendFormat": "exceeded sample limit: {{job}}",
+ "legendLink": null,
+ "step": 10
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+ "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total[1m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "3xx",
- "refId": "B"
+ "legendFormat": "duplicate timestamp: {{job}}",
+ "legendLink": null,
+ "step": 10
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+ "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total[1m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "4xx",
- "refId": "C"
+ "legendFormat": "out of bounds: {{job}}",
+ "legendLink": null,
+ "step": 10
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+ "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total[1m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "5xx",
- "refId": "D"
+ "legendFormat": "out of order: {{job}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30213,7 +30666,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Kube API Request Rate",
+ "title": "Scrape failures",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30231,20 +30684,20 @@ items:
},
"yaxes": [
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "ops",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
},
@@ -30256,49 +30709,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 8,
+ "fill": 10,
+ "id": 6,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 8,
- "stack": false,
+ "span": 4,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
+ "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=~\"$job\",instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{verb}} {{url}}",
- "refId": "A"
+ "legendFormat": "{{job}} {{instance}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30306,7 +30752,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Post Request Latency 99th Quantile",
+ "title": "Appended Samples",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30324,7 +30770,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -30332,12 +30778,12 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
}
@@ -30345,14 +30791,13 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Retrieval",
+ "titleSize": "h6"
},
{
"collapse": false,
- "collapsed": false,
+ "height": "250px",
"panels": [
{
"aliasColors": {
@@ -30362,49 +30807,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 9,
+ "fill": 10,
+ "id": 7,
"legend": {
- "alignAsTable": true,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
"show": true,
- "sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 12,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+ "expr": "prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{verb}} {{url}}",
- "refId": "A"
+ "legendFormat": "{{job}} {{instance}} head series",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30412,7 +30850,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Get Request Latency 99th Quantile",
+ "title": "Head Series",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30430,7 +30868,7 @@ items:
},
"yaxes": [
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -30438,28 +30876,15 @@ items:
"show": true
},
{
- "format": "s",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ },
{
"aliasColors": {
@@ -30468,49 +30893,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 10,
+ "fill": 10,
+ "id": 8,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
+ "expr": "prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{job}} {{instance}} head chunks",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30518,7 +30936,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Memory",
+ "title": "Head Chunks",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30536,23 +30954,35 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
- },
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": true,
+ "title": "Storage",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": false,
+ "height": "250px",
+ "panels": [
{
"aliasColors": {
@@ -30561,49 +30991,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 11,
+ "fill": 10,
+ "id": 9,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[5m])",
+ "expr": "rate(prometheus_engine_query_duration_seconds_count{job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{job}} {{instance}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30611,7 +31034,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "CPU usage",
+ "title": "Query Rate",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30641,8 +31064,8 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
- "show": true
+ "min": null,
+ "show": false
}
]
},
@@ -30654,49 +31077,42 @@ items:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
- "fill": 1,
- "fillGradient": 0,
- "gridPos": {
-
- },
- "id": 12,
+ "fill": 10,
+ "id": 10,
"legend": {
- "alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
- "rightSide": false,
"show": true,
- "sideWidth": null,
"total": false,
"values": false
},
"lines": true,
- "linewidth": 1,
+ "linewidth": 0,
"links": [
],
- "nullPointMode": "null",
+ "nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
- "repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
- "span": 4,
- "stack": false,
+ "span": 6,
+ "stack": true,
"steppedLine": false,
"targets": [
{
- "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
+ "expr": "max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",job=~\"$job\",instance=~\"$instance\"}) * 1e3",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "refId": "A"
+ "legendFormat": "{{slice}}",
+ "legendLink": null,
+ "step": 10
}
],
"thresholds": [
@@ -30704,7 +31120,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Goroutines",
+ "title": "Stage Duration",
"tooltip": {
"shared": false,
"sort": 0,
@@ -30722,11 +31138,11 @@ items:
},
"yaxes": [
{
- "format": "short",
+ "format": "ms",
"label": null,
"logBase": 1,
"max": null,
- "min": null,
+ "min": 0,
"show": true
},
{
@@ -30735,7 +31151,7 @@ items:
"logBase": 1,
"max": null,
"min": null,
- "show": true
+ "show": false
}
]
}
@@ -30743,16 +31159,15 @@ items:
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
+ "showTitle": true,
+ "title": "Query",
+ "titleSize": "h6"
}
],
"schemaVersion": 14,
"style": "dark",
"tags": [
- "kubernetes-mixin"
+ "prometheus-mixin"
],
"templating": {
"list": [
@@ -30773,23 +31188,25 @@ items:
"type": "datasource"
},
{
- "allValue": null,
+ "allValue": ".+",
"current": {
-
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
},
"datasource": "$datasource",
- "hide": 2,
- "includeAll": false,
- "label": "cluster",
- "multi": false,
- "name": "cluster",
+ "hide": 0,
+ "includeAll": true,
+ "label": "job",
+ "multi": true,
+ "name": "job",
"options": [
],
- "query": "label_values(kube_pod_info, cluster)",
- "refresh": 2,
+ "query": "label_values(prometheus_build_info, job)",
+ "refresh": 1,
"regex": "",
- "sort": 1,
+ "sort": 2,
"tagValuesQuery": "",
"tags": [
@@ -30799,23 +31216,25 @@ items:
"useTags": false
},
{
- "allValue": null,
+ "allValue": ".+",
"current": {
-
+ "selected": true,
+ "text": "All",
+ "value": "$__all"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
- "label": null,
- "multi": false,
+ "label": "instance",
+ "multi": true,
"name": "instance",
"options": [
],
- "query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\"}, instance)",
- "refresh": 2,
+ "query": "label_values(prometheus_build_info, instance)",
+ "refresh": 1,
"regex": "",
- "sort": 1,
+ "sort": 2,
"tagValuesQuery": "",
"tags": [
@@ -30855,9 +31274,9 @@ items:
"30d"
]
},
- "timezone": "UTC",
- "title": "Kubernetes / Proxy",
- "uid": "632e265de029684c40b21cb76bca4f94",
+ "timezone": "utc",
+ "title": "Prometheus / Overview",
+ "uid": "",
"version": 0
}
kind: ConfigMap
@@ -30867,11 +31286,11 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-proxy
+ name: grafana-dashboard-prometheus
namespace: monitoring
- apiVersion: v1
data:
- scheduler.json: |-
+ proxy.json: |-
{
"__inputs": [
@@ -30959,7 +31378,7 @@ items:
"tableColumn": "",
"targets": [
{
- "expr": "sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})",
+ "expr": "sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@@ -30975,13 +31394,212 @@ items:
"valueFontSize": "80%",
"valueMaps": [
{
- "op": "=",
- "text": "N/A",
- "value": "null"
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "min"
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 5,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "rate",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rules Sync Rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 5,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Rule Sync Latency 99th Quantile",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "valueName": "min"
- },
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"aliasColors": {
@@ -30995,18 +31613,18 @@ items:
"gridPos": {
},
- "id": 3,
+ "id": 5,
"legend": {
- "alignAsTable": true,
+ "alignAsTable": false,
"avg": false,
- "current": true,
+ "current": false,
"max": false,
"min": false,
- "rightSide": true,
+ "rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
- "values": true
+ "values": false
},
"lines": true,
"linewidth": 1,
@@ -31023,37 +31641,16 @@ items:
],
"spaceLength": 10,
- "span": 5,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
+ "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} e2e",
+ "legendFormat": "rate",
"refId": "A"
- },
- {
- "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} binding",
- "refId": "B"
- },
- {
- "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} scheduling algorithm",
- "refId": "C"
- },
- {
- "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} volume",
- "refId": "D"
}
],
"thresholds": [
@@ -31061,7 +31658,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Scheduling Rate",
+ "title": "Network Programming Rate",
"tooltip": {
"shared": false,
"sort": 0,
@@ -31109,7 +31706,7 @@ items:
"gridPos": {
},
- "id": 4,
+ "id": 6,
"legend": {
"alignAsTable": true,
"avg": false,
@@ -31137,37 +31734,16 @@ items:
],
"spaceLength": 10,
- "span": 5,
+ "span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "{{instance}} e2e",
+ "legendFormat": "{{instance}}",
"refId": "A"
- },
- {
- "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} binding",
- "refId": "B"
- },
- {
- "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} scheduling algorithm",
- "refId": "C"
- },
- {
- "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} volume",
- "refId": "D"
}
],
"thresholds": [
@@ -31175,7 +31751,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Scheduling latency 99th Quantile",
+ "title": "Network Programming Latency 99th Quantile",
"tooltip": {
"shared": false,
"sort": 0,
@@ -31236,7 +31812,7 @@ items:
"gridPos": {
},
- "id": 5,
+ "id": 7,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -31269,28 +31845,28 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
- "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
@@ -31324,7 +31900,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
},
{
@@ -31332,7 +31908,7 @@ items:
"label": null,
"logBase": 1,
"max": null,
- "min": 0,
+ "min": null,
"show": true
}
]
@@ -31350,7 +31926,7 @@ items:
"gridPos": {
},
- "id": 6,
+ "id": 8,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -31383,7 +31959,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
+ "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@@ -31456,7 +32032,7 @@ items:
"gridPos": {
},
- "id": 7,
+ "id": 9,
"legend": {
"alignAsTable": true,
"avg": false,
@@ -31489,7 +32065,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+ "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@@ -31562,7 +32138,7 @@ items:
"gridPos": {
},
- "id": 8,
+ "id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -31595,7 +32171,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}",
+ "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@@ -31655,7 +32231,7 @@ items:
"gridPos": {
},
- "id": 9,
+ "id": 11,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -31688,7 +32264,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])",
+ "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@@ -31718,7 +32294,7 @@ items:
},
"yaxes": [
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -31726,7 +32302,7 @@ items:
"show": true
},
{
- "format": "bytes",
+ "format": "short",
"label": null,
"logBase": 1,
"max": null,
@@ -31748,7 +32324,7 @@ items:
"gridPos": {
},
- "id": 10,
+ "id": 12,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -31781,7 +32357,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}",
+ "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@@ -31901,7 +32477,7 @@ items:
"options": [
],
- "query": "label_values(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\"}, instance)",
+ "query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -31945,8 +32521,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / Scheduler",
- "uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
+ "title": "Kubernetes / Proxy",
+ "uid": "632e265de029684c40b21cb76bca4f94",
"version": 0
}
kind: ConfigMap
@@ -31956,120 +32532,37 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-scheduler
- namespace: monitoring
-- apiVersion: v1
- data:
- statefulset.json: |-
- {
- "__inputs": [
-
- ],
- "__requires": [
-
- ],
- "annotations": {
- "list": [
-
- ]
- },
- "editable": false,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "id": null,
- "links": [
-
- ],
- "refresh": "",
- "rows": [
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
-
- },
- "id": 2,
- "interval": null,
- "links": [
-
- ],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "cores",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
- ],
- "span": 4,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "lineColor": "rgb(31, 120, 193)",
- "show": true
- },
- "tableColumn": "",
- "targets": [
- {
- "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "",
- "title": "CPU",
- "tooltip": {
- "shared": false
- },
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
- {
- "op": "=",
- "text": "0",
- "value": "null"
- }
- ],
- "valueName": "current"
- },
+ name: grafana-dashboard-proxy
+ namespace: monitoring
+- apiVersion: v1
+ data:
+ scheduler.json: |-
+ {
+ "__inputs": [
+
+ ],
+ "__requires": [
+
+ ],
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "10s",
+ "rows": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
"cacheTimeout": null,
"colorBackground": false,
@@ -32091,7 +32584,7 @@ items:
"gridPos": {
},
- "id": 3,
+ "id": 2,
"interval": null,
"links": [
@@ -32110,7 +32603,7 @@ items:
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
- "postfix": "GB",
+ "postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
@@ -32121,16 +32614,17 @@ items:
"to": "null"
}
],
- "span": 4,
+ "span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
"lineColor": "rgb(31, 120, 193)",
- "show": true
+ "show": false
},
"tableColumn": "",
"targets": [
{
- "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3",
+ "expr": "sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@@ -32138,7 +32632,7 @@ items:
}
],
"thresholds": "",
- "title": "Memory",
+ "title": "Up",
"tooltip": {
"shared": false
},
@@ -32147,94 +32641,239 @@ items:
"valueMaps": [
{
"op": "=",
- "text": "0",
+ "text": "N/A",
"value": "null"
}
],
- "valueName": "current"
+ "valueName": "min"
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "aliasColors": {
+
},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
"gridPos": {
},
- "id": 4,
- "interval": null,
+ "id": 3,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 5,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
{
- "name": "value to text",
- "value": 1
+ "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} e2e",
+ "refId": "A"
},
{
- "name": "range to text",
- "value": 2
+ "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} binding",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} scheduling algorithm",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} volume",
+ "refId": "D"
}
],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "Bps",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Scheduling Rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "from": "null",
- "text": "N/A",
- "to": "null"
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "span": 4,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "lineColor": "rgb(31, 120, 193)",
- "show": true
+ ]
+ },
+ {
+ "aliasColors": {
+
},
- "tableColumn": "",
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 4,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 5,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",pod=~\"$statefulset.*\"}[3m]))",
+ "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
+ "legendFormat": "{{instance}} e2e",
"refId": "A"
+ },
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} binding",
+ "refId": "B"
+ },
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} scheduling algorithm",
+ "refId": "C"
+ },
+ {
+ "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "{{instance}} volume",
+ "refId": "D"
}
],
- "thresholds": "",
- "title": "Network",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Scheduling latency 99th Quantile",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "0",
- "value": "null"
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "valueName": "current"
+ ]
}
],
"repeat": null,
@@ -32248,357 +32887,519 @@ items:
{
"collapse": false,
"collapsed": false,
- "height": "100px",
"panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "aliasColors": {
+
},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
"gridPos": {
},
"id": 5,
- "interval": null,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
{
- "name": "value to text",
- "value": 1
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "2xx",
+ "refId": "A"
},
{
- "name": "range to text",
- "value": 2
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "3xx",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "4xx",
+ "refId": "C"
+ },
+ {
+ "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "5xx",
+ "refId": "D"
}
],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Kube API Request Rate",
+ "tooltip": {
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "from": "null",
- "text": "N/A",
- "to": "null"
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "ops",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
+ ]
+ },
+ {
+ "aliasColors": {
+
},
- "tableColumn": "",
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+
+ },
+ "id": 6,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 8,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
+ "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
+ "legendFormat": "{{verb}} {{url}}",
"refId": "A"
}
],
- "thresholds": "",
- "title": "Desired Replicas",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Post Request Latency 99th Quantile",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
{
- "op": "=",
- "text": "0",
- "value": "null"
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "valueName": "current"
- },
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "aliasColors": {
+
},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
"gridPos": {
},
- "id": 6,
- "interval": null,
+ "id": 7,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
+ "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
+ "legendFormat": "{{verb}} {{url}}",
"refId": "A"
}
],
- "thresholds": "",
- "title": "Replicas of current version",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Get Request Latency 99th Quantile",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "0",
- "value": "null"
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "valueName": "current"
- },
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "aliasColors": {
+
},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
"gridPos": {
},
- "id": 7,
- "interval": null,
+ "id": 8,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
+ "spaceLength": 10,
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
+ "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
+ "legendFormat": "{{instance}}",
"refId": "A"
}
],
- "thresholds": "",
- "title": "Observed Generation",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "0",
- "value": "null"
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
}
- ],
- "valueName": "current"
+ ]
},
{
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "#299c46",
- "rgba(237, 129, 40, 0.89)",
- "#d44a3a"
- ],
- "datasource": "$datasource",
- "format": "none",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": false,
- "thresholdLabels": false,
- "thresholdMarkers": true
+ "aliasColors": {
+
},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "fillGradient": 0,
"gridPos": {
},
- "id": 8,
- "interval": null,
+ "id": 9,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
"links": [
],
- "mappingType": 1,
- "mappingTypes": [
- {
- "name": "value to text",
- "value": 1
- },
- {
- "name": "range to text",
- "value": 2
- }
- ],
- "maxDataPoints": 100,
- "nullPointMode": "connected",
- "nullText": null,
- "postfix": "",
- "postfixFontSize": "50%",
- "prefix": "",
- "prefixFontSize": "50%",
- "rangeMaps": [
- {
- "from": "null",
- "text": "N/A",
- "to": "null"
- }
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
],
- "span": 3,
- "sparkline": {
- "fillColor": "rgba(31, 118, 189, 0.18)",
- "full": false,
- "lineColor": "rgb(31, 120, 193)",
- "show": false
- },
- "tableColumn": "",
+ "spaceLength": 10,
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
"targets": [
{
- "expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
+ "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "",
+ "legendFormat": "{{instance}}",
"refId": "A"
}
],
- "thresholds": "",
- "title": "Metadata Generation",
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU usage",
"tooltip": {
- "shared": false
+ "shared": false,
+ "sort": 0,
+ "value_type": "individual"
},
- "type": "singlestat",
- "valueFontSize": "80%",
- "valueMaps": [
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
{
- "op": "=",
- "text": "0",
- "value": "null"
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
}
- ],
- "valueName": "current"
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
+ ]
+ },
{
"aliasColors": {
@@ -32612,7 +33413,7 @@ items:
"gridPos": {
},
- "id": 9,
+ "id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
@@ -32640,43 +33441,16 @@ items:
],
"spaceLength": 10,
+ "span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
- "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
+ "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
- "legendFormat": "replicas specified",
+ "legendFormat": "{{instance}}",
"refId": "A"
- },
- {
- "expr": "max(kube_statefulset_status_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "replicas created",
- "refId": "B"
- },
- {
- "expr": "min(kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "ready",
- "refId": "C"
- },
- {
- "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "replicas of current version",
- "refId": "D"
- },
- {
- "expr": "min(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "updated",
- "refId": "E"
}
],
"thresholds": [
@@ -32684,7 +33458,7 @@ items:
],
"timeFrom": null,
"timeShift": null,
- "title": "Replicas",
+ "title": "Goroutines",
"tooltip": {
"shared": false,
"sort": 0,
@@ -32766,33 +33540,7 @@ items:
"options": [
],
- "query": "label_values(kube_statefulset_metadata_generation, cluster)",
- "refresh": 2,
- "regex": "",
- "sort": 1,
- "tagValuesQuery": "",
- "tags": [
-
- ],
- "tagsQuery": "",
- "type": "query",
- "useTags": false
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$datasource",
- "hide": 0,
- "includeAll": false,
- "label": "Namespace",
- "multi": false,
- "name": "namespace",
- "options": [
-
- ],
- "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
+ "query": "label_values(kube_pod_info, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -32811,14 +33559,14 @@ items:
},
"datasource": "$datasource",
"hide": 0,
- "includeAll": false,
- "label": "Name",
+ "includeAll": true,
+ "label": null,
"multi": false,
- "name": "statefulset",
+ "name": "instance",
"options": [
],
- "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)",
+ "query": "label_values(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -32862,8 +33610,8 @@ items:
]
},
"timezone": "UTC",
- "title": "Kubernetes / StatefulSets",
- "uid": "a31c1f46e6f727cb37c0d731a7245005",
+ "title": "Kubernetes / Scheduler",
+ "uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
"version": 0
}
kind: ConfigMap
@@ -32873,7 +33621,7 @@ items:
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 7.5.4
- name: grafana-dashboard-statefulset
+ name: grafana-dashboard-scheduler
namespace: monitoring
- apiVersion: v1
data:
diff --git a/manifests/grafana-deployment.yaml b/manifests/grafana-deployment.yaml
index c69b637b..edb6623e 100644
--- a/manifests/grafana-deployment.yaml
+++ b/manifests/grafana-deployment.yaml
@@ -116,9 +116,6 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/scheduler
name: grafana-dashboard-scheduler
readOnly: false
- - mountPath: /grafana-dashboard-definitions/0/statefulset
- name: grafana-dashboard-statefulset
- readOnly: false
- mountPath: /grafana-dashboard-definitions/0/workload-total
name: grafana-dashboard-workload-total
readOnly: false
@@ -201,9 +198,6 @@ spec:
- configMap:
name: grafana-dashboard-scheduler
name: grafana-dashboard-scheduler
- - configMap:
- name: grafana-dashboard-statefulset
- name: grafana-dashboard-statefulset
- configMap:
name: grafana-dashboard-workload-total
name: grafana-dashboard-workload-total
diff --git a/manifests/kube-state-metrics-prometheusRule.yaml b/manifests/kube-state-metrics-prometheusRule.yaml
index 9b4541f6..824d8132 100644
--- a/manifests/kube-state-metrics-prometheusRule.yaml
+++ b/manifests/kube-state-metrics-prometheusRule.yaml
@@ -40,3 +40,26 @@ spec:
for: 15m
labels:
severity: critical
+ - alert: KubeStateMetricsShardingMismatch
+ annotations:
+ description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all.
+ runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubestatemetricsshardingmismatch
+ summary: kube-state-metrics sharding is misconfigured.
+ expr: |
+ stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) != 0
+ for: 15m
+ labels:
+ severity: critical
+ - alert: KubeStateMetricsShardsMissing
+ annotations:
+ description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed.
+ runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubestatemetricsshardsmissing
+ summary: kube-state-metrics shards are missing.
+ expr: |
+ 2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) - 1
+ -
+ sum( 2 ^ max by (shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) )
+ != 0
+ for: 15m
+ labels:
+ severity: critical
diff --git a/manifests/kubernetes-prometheusRule.yaml b/manifests/kubernetes-prometheusRule.yaml
index fda06912..0434a676 100644
--- a/manifests/kubernetes-prometheusRule.yaml
+++ b/manifests/kubernetes-prometheusRule.yaml
@@ -699,26 +699,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1d]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1d]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1d]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
labels:
verb: read
record: apiserver_request:burnrate1d
@@ -726,26 +726,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1h]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1h]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1h]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
labels:
verb: read
record: apiserver_request:burnrate1h
@@ -753,26 +753,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[2h]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[2h]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[2h]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
labels:
verb: read
record: apiserver_request:burnrate2h
@@ -780,26 +780,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30m]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30m]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30m]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
labels:
verb: read
record: apiserver_request:burnrate30m
@@ -807,26 +807,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[3d]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[3d]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[3d]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
labels:
verb: read
record: apiserver_request:burnrate3d
@@ -834,26 +834,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[5m]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[5m]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[5m]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
record: apiserver_request:burnrate5m
@@ -861,26 +861,26 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h]))
-
(
(
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[6h]))
or
vector(0)
)
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[6h]))
+
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[6h]))
)
)
+
# errors
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
labels:
verb: read
record: apiserver_request:burnrate6h
@@ -888,15 +888,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1d]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
labels:
verb: write
record: apiserver_request:burnrate1d
@@ -904,15 +904,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1h]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
labels:
verb: write
record: apiserver_request:burnrate1h
@@ -920,15 +920,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[2h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[2h]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
labels:
verb: write
record: apiserver_request:burnrate2h
@@ -936,15 +936,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[30m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[30m]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
labels:
verb: write
record: apiserver_request:burnrate30m
@@ -952,15 +952,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[3d]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[3d]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
labels:
verb: write
record: apiserver_request:burnrate3d
@@ -968,15 +968,15 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[5m]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[5m]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
verb: write
record: apiserver_request:burnrate5m
@@ -984,36 +984,36 @@ spec:
(
(
# too slow
- sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
-
- sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[6h]))
+ sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[6h]))
)
+
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
)
/
- sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
+ sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
labels:
verb: write
record: apiserver_request:burnrate6h
- expr: |
- sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
+ sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
record: code_resource:apiserver_request_total:rate5m
- expr: |
- sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
+ sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
verb: write
record: code_resource:apiserver_request_total:rate5m
- expr: |
- histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET"}[5m]))) > 0
+ histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET"}[5m]))) > 0
labels:
quantile: "0.99"
verb: read
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
- histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0
+ histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0
labels:
quantile: "0.99"
verb: write
@@ -1040,56 +1040,56 @@ spec:
1 - (
(
# write too slow
- sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
-
- sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
) +
(
# read too slow
- sum(increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d]))
-
(
(
- sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
or
vector(0)
)
+
- sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
+
- sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
)
) +
# errors
- sum(code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
+ sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
)
/
- sum(code:apiserver_request_total:increase30d)
+ sum by (cluster) (code:apiserver_request_total:increase30d)
labels:
verb: all
record: apiserver_request:availability30d
- expr: |
1 - (
- sum(increase(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30d]))
-
(
# too slow
(
- sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
or
vector(0)
)
+
- sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
+
- sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
)
+
# errors
- sum(code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
+ sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
)
/
- sum(code:apiserver_request_total:increase30d{verb="read"})
+ sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"})
labels:
verb: read
record: apiserver_request:availability30d
@@ -1097,16 +1097,16 @@ spec:
1 - (
(
# too slow
- sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
-
- sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
+ sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
)
+
# errors
- sum(code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
+ sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
)
/
- sum(code:apiserver_request_total:increase30d{verb="write"})
+ sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"})
labels:
verb: write
record: apiserver_request:availability30d
@@ -1114,84 +1114,84 @@ spec:
avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30
record: code_verb:apiserver_request_total:increase30d
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[1h]))
+ sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: |
- sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
+ sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels:
verb: read
record: code:apiserver_request_total:increase30d
- expr: |
- sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
+ sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels:
verb: write
record: code:apiserver_request_total:increase30d
diff --git a/manifests/prometheus-prometheusRule.yaml b/manifests/prometheus-prometheusRule.yaml
index 681219fb..51f857d6 100644
--- a/manifests/prometheus-prometheusRule.yaml
+++ b/manifests/prometheus-prometheusRule.yaml
@@ -211,6 +211,16 @@ spec:
for: 15m
labels:
severity: warning
+ - alert: PrometheusLabelLimitHit
+ annotations:
+ description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit.
+ runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheuslabellimithit
+ summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit.
+ expr: |
+ increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+ for: 15m
+ labels:
+ severity: warning
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
diff --git a/manifests/setup/prometheus-operator-deployment.yaml b/manifests/setup/prometheus-operator-deployment.yaml
index 23992a03..a87ecacc 100644
--- a/manifests/setup/prometheus-operator-deployment.yaml
+++ b/manifests/setup/prometheus-operator-deployment.yaml
@@ -17,6 +17,8 @@ spec:
app.kubernetes.io/part-of: kube-prometheus
template:
metadata:
+ annotations:
+ kubectl.kubernetes.io/default-container: prometheus-operator
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
--
GitLab