diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json
index 87e216584d0d74045b951500d02bd8d1039ba5ba..d3dac64f6c056735d42412c2dbc9f55348204639 100644
--- a/jsonnetfile.lock.json
+++ b/jsonnetfile.lock.json
@@ -8,7 +8,7 @@
"subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
}
},
- "version": "360f5ad835e12f3627a45f2df0487f73ec8969e3"
+ "version": "8582fcce481d4302a9c29e9b5e4182c5d98d67ed"
},
{
"name": "ksonnet",
@@ -28,7 +28,7 @@
"subdir": ""
}
},
- "version": "64a06754786ca1a28929b9fb05c381085dcdd44c"
+ "version": "4c23c06fff9ef50744f5ed306c9ab0c4bd78a144"
},
{
"name": "grafonnet",
@@ -38,7 +38,7 @@
"subdir": "grafonnet"
}
},
- "version": "eea8b5ba6b8883cf2df5a17c39a42c4b57c0d63e"
+ "version": "d05a9bd3adfba39ed3b1987a428d9e9863428df5"
},
{
"name": "grafana-builder",
@@ -48,7 +48,7 @@
"subdir": "grafana-builder"
}
},
- "version": "d60a39a5c01f651fdfef2db7a710bb5319b0dbc4"
+ "version": "c6932cf90bce4fef218b4308effc9f15c4219a01"
},
{
"name": "grafana",
@@ -68,7 +68,7 @@
"subdir": "jsonnet/prometheus-operator"
}
},
- "version": "72ec4b9b16ef11700724dc71fec77112536eed40"
+ "version": "174c9bf17bec78b055e8e63c6ae3a3dc9bb0a3a8"
},
{
"name": "etcd-mixin",
@@ -78,7 +78,7 @@
"subdir": "Documentation/etcd-mixin"
}
},
- "version": "dedae6eb7c253635e70403a1fb04842700277b23"
+ "version": "b04633fd8e67c65d4fe4929333fb4856f25da189"
}
]
}
diff --git a/manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml b/manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml
index d5c94fc9867958cdd41b229fa10cfd2759aa6149..89748f1acddcf97c265ded69bf350f4de7e3f8be 100644
--- a/manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml
+++ b/manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml
@@ -1378,6 +1378,12 @@ spec:
under. This is necessary to generate correct URLs. This is necessary
if Alertmanager is not served from root of a DNS name.
type: string
+ image:
+ description: Image if specified has precedence over baseImage, tag and
+ sha combinations. Specifying the version is still necessary to ensure
+ the Prometheus Operator knows what version of Alertmanager is being
+ configured.
+ type: string
imagePullSecrets:
description: An optional list of references to secrets in the same namespace
to use for pulling prometheus and alertmanager images from registries
diff --git a/manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml b/manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml
index d825277ebe0cf38eae542c2489f2be959094190f..627ce96d4be312855b1265ef59dc52008562215b 100644
--- a/manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml
+++ b/manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml
@@ -1550,6 +1550,12 @@ spec:
under. This is necessary to generate correct URLs. This is necessary
if Prometheus is not served from root of a DNS name.
type: string
+ image:
+ description: Image if specified has precedence over baseImage, tag and
+ sha combinations. Specifying the version is still necessary to ensure
+ the Prometheus Operator knows what version of Prometheus is being
+ configured.
+ type: string
imagePullSecrets:
description: An optional list of references to secrets in the same namespace
to use for pulling prometheus and alertmanager images from registries
@@ -1863,6 +1869,21 @@ spec:
priorityClassName:
description: Priority class assigned to the Pods
type: string
+ query:
+ description: QuerySpec defines the query command line flags when starting
+ Prometheus.
+ properties:
+ lookbackDelta:
+ description: The delta difference allowed for retrieving metrics
+ during expression evaluations.
+ type: string
+ maxConcurrency:
+ description: Number of concurrent queries that can be run at once.
+ format: int32
+ type: integer
+ timeout:
+ description: Maximum time a query may take before being aborted.
+ type: string
remoteRead:
description: If specified, the remote_read spec. This is an experimental
feature, it may change in any upcoming release in a breaking way.
@@ -2943,6 +2964,12 @@ spec:
type: boolean
required:
- key
+ image:
+ description: Image if specified has precedence over baseImage, tag
+ and sha combinations. Specifying the version is still necessary
+ to ensure the Prometheus Operator knows what version of Thanos
+ is being configured.
+ type: string
peers:
description: Peers is a DNS name for Thanos to discover peers through.
type: string
diff --git a/manifests/0prometheus-operator-deployment.yaml b/manifests/0prometheus-operator-deployment.yaml
index 1ddbae2f94f3f2f188b33be5a3114cab8f3f962d..55ad90434f568cbdb3d888d137adf354f9ba8cb9 100644
--- a/manifests/0prometheus-operator-deployment.yaml
+++ b/manifests/0prometheus-operator-deployment.yaml
@@ -20,8 +20,8 @@ spec:
- --kubelet-service=kube-system/kubelet
- --logtostderr=true
- --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1
- - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.26.0
- image: quay.io/coreos/prometheus-operator:v0.26.0
+ - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.27.0
+ image: quay.io/coreos/prometheus-operator:v0.27.0
name: prometheus-operator
ports:
- containerPort: 8080
diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml
index e4364aa65b258b43f90d1c78077580eb0d5e495a..f2c1ba403def7972c917d3b81faec83237aaf6aa 100644
--- a/manifests/grafana-dashboardDefinitions.yaml
+++ b/manifests/grafana-dashboardDefinitions.yaml
@@ -796,7 +796,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(max(node_filesystem_size_bytes{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"} - node_filesystem_avail_bytes{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"}) by (device,pod,namespace)) by (pod,namespace)\n/ scalar(sum(max(node_filesystem_size_bytes{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"}) by (device,pod,namespace)))\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:\n",
+ "expr": "sum(max(node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"} - node_filesystem_avail_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"}) by (device,pod,namespace)) by (pod,namespace)\n/ scalar(sum(max(node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"}) by (device,pod,namespace)))\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{node}}",
@@ -5064,7 +5064,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "avg by (cpu) (irate(node_cpu_seconds_total{job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[5m])) * 100",
+ "expr": "sum by (cpu) (irate(node_cpu_seconds_total{job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cpu}}",
@@ -5775,7 +5775,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "max(rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!\u007e\"lo\"}[5m]))",
+ "expr": "max(rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"lo\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{device}}",
@@ -5866,7 +5866,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "max(rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!\u007e\"lo\"}[5m]))",
+ "expr": "max(rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"lo\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{device}}",
@@ -5921,6 +5921,198 @@ items:
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
+ },
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "gridPos": {
+
+ },
+ "id": 12,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 9,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max(\n node_filesystem_files{job=\"node-exporter\", instance=\"$instance\"}\n - node_filesystem_files_free{job=\"node-exporter\", instance=\"$instance\"}\n)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "inodes used",
+ "refId": "A"
+ },
+ {
+ "expr": "max(node_filesystem_files_free{job=\"node-exporter\", instance=\"$instance\"})",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "inodes free",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Inodes Usage",
+ "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
+ }
+ ]
+ },
+ {
+ "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": "$datasource",
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "gridPos": {
+
+ },
+ "id": 13,
+ "interval": null,
+ "links": [
+
+ ],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "max(\n (\n (\n node_filesystem_files{job=\"node-exporter\", instance=\"$instance\"}\n - node_filesystem_files_free{job=\"node-exporter\", instance=\"$instance\"}\n )\n / node_filesystem_files{job=\"node-exporter\", instance=\"$instance\"}\n ) * 100)\n",
+ "format": "time_series",
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": "80, 90",
+ "title": "Inodes 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"
}
],
"schemaVersion": 14,
@@ -6012,6 +6204,349 @@ items:
metadata:
name: grafana-dashboard-nodes
namespace: monitoring
+- apiVersion: v1
+ data:
+ persistentvolumesusage.json: |-
+ {
+ "annotations": {
+ "list": [
+
+ ]
+ },
+ "editable": false,
+ "gnetId": null,
+ "graphTooltip": 0,
+ "hideControls": false,
+ "id": null,
+ "links": [
+
+ ],
+ "refresh": "",
+ "rows": [
+ {
+ "collapse": false,
+ "collapsed": false,
+ "panels": [
+ {
+ "aliasColors": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "gridPos": {
+
+ },
+ "id": 2,
+ "legend": {
+ "alignAsTable": false,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", persistentvolumeclaim=\"$volume\"} - kubelet_volume_stats_available_bytes{job=\"kubelet\", persistentvolumeclaim=\"$volume\"}) / kubelet_volume_stats_capacity_bytes{job=\"kubelet\", persistentvolumeclaim=\"$volume\"} * 100\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ Usage }}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Volume Space Usage",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": null,
+ "logBase": 1,
+ "max": 100,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "percent",
+ "label": null,
+ "logBase": 1,
+ "max": 100,
+ "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": {
+
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "$datasource",
+ "fill": 1,
+ "gridPos": {
+
+ },
+ "id": 3,
+ "legend": {
+ "alignAsTable": false,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": true,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [
+
+ ],
+ "nullPointMode": "null",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "repeat": null,
+ "seriesOverrides": [
+
+ ],
+ "spaceLength": 10,
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "kubelet_volume_stats_inodes_used{job=\"kubelet\", persistentvolumeclaim=\"$volume\"} / kubelet_volume_stats_inodes{job=\"kubelet\", persistentvolumeclaim=\"$volume\"} * 100\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ Usage }}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [
+
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Volume inodes Usage",
+ "tooltip": {
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": [
+
+ ]
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": null,
+ "logBase": 1,
+ "max": 100,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "percent",
+ "label": null,
+ "logBase": 1,
+ "max": 100,
+ "min": 0,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Dashboard Row",
+ "titleSize": "h6",
+ "type": "row"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [
+
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "text": "Prometheus",
+ "value": "Prometheus"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "datasource",
+ "options": [
+
+ ],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Namespace",
+ "multi": false,
+ "name": "namespace",
+ "options": [
+
+ ],
+ "query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}, exported_namespace)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": "",
+ "tags": [
+
+ ],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+
+ },
+ "datasource": "$datasource",
+ "hide": 0,
+ "includeAll": false,
+ "label": "PersistentVolumeClaim",
+ "multi": false,
+ "name": "volume",
+ "options": [
+
+ ],
+ "query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", exported_namespace=\"$namespace\"}, persistentvolumeclaim)",
+ "refresh": 2,
+ "regex": "",
+ "sort": 0,
+ "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": "",
+ "title": "Persistent Volumes",
+ "uid": "919b92a8e8041bd567af9edab12c840c",
+ "version": 0
+ }
+ kind: ConfigMap
+ metadata:
+ name: grafana-dashboard-persistentvolumesusage
+ namespace: monitoring
- apiVersion: v1
data:
pods.json: |-
@@ -6078,21 +6613,21 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum by(container_name) (container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\"$pod\", container_name=\u007e\"$container\", container_name!=\"POD\"})",
+ "expr": "sum by(container_name) (container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\"$pod\", container_name=~\"$container\", container_name!=\"POD\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Current: {{ container_name }}",
"refId": "A"
},
{
- "expr": "sum by(container) (kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\", namespace=\"$namespace\", pod=\"$pod\", container=\u007e\"$container\"})",
+ "expr": "sum by(container) (kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Requested: {{ container }}",
"refId": "B"
},
{
- "expr": "sum by(container) (kube_pod_container_resource_limits_memory_bytes{job=\"kube-state-metrics\", namespace=\"$namespace\", pod=\"$pod\", container=\u007e\"$container\"})",
+ "expr": "sum by(container) (kube_pod_container_resource_limits_memory_bytes{job=\"kube-state-metrics\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Limit: {{ container }}",
@@ -6418,7 +6953,7 @@ items:
"options": [
],
- "query": "label_values(kube_pod_info{namespace=\u007e\"$namespace\"}, pod)",
+ "query": "label_values(kube_pod_info{namespace=~\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"sort": 0,
@@ -6579,7 +7114,7 @@ items:
"tableColumn": "",
"targets": [
{
- "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m]))",
+ "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}[3m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@@ -6659,7 +7194,7 @@ items:
"tableColumn": "",
"targets": [
{
- "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}) / 1024^3",
+ "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}) / 1024^3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@@ -6739,7 +7274,7 @@ items:
"tableColumn": "",
"targets": [
{
- "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=\u007e\"$statefulset.*\"}[3m]))",
+ "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=~\"$statefulset.*\"}[3m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
diff --git a/manifests/grafana-deployment.yaml b/manifests/grafana-deployment.yaml
index 6816ce2f4126b14b53c89e832a3ccbe8761ccfbb..aa5814eb2db4e6355cd30890a239ad171e550f97 100644
--- a/manifests/grafana-deployment.yaml
+++ b/manifests/grafana-deployment.yaml
@@ -60,6 +60,9 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/nodes
name: grafana-dashboard-nodes
readOnly: false
+ - mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage
+ name: grafana-dashboard-persistentvolumesusage
+ readOnly: false
- mountPath: /grafana-dashboard-definitions/0/pods
name: grafana-dashboard-pods
readOnly: false
@@ -97,6 +100,9 @@ spec:
- configMap:
name: grafana-dashboard-nodes
name: grafana-dashboard-nodes
+ - configMap:
+ name: grafana-dashboard-persistentvolumesusage
+ name: grafana-dashboard-persistentvolumesusage
- configMap:
name: grafana-dashboard-pods
name: grafana-dashboard-pods
diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml
index 01ca8ddbf8e9bb44edea994deb591e7419110a64..05e0debf10d0392cfde9e0f9ea3763ccbec94383 100644
--- a/manifests/prometheus-rules.yaml
+++ b/manifests/prometheus-rules.yaml
@@ -264,6 +264,28 @@ spec:
node_namespace_pod:kube_pod_info:
)
record: node:node_net_saturation:sum_irate
+ - expr: |
+ max(
+ max(
+ kube_pod_info{job="kube-state-metrics", host_ip!=""}
+ ) by (node, host_ip)
+ * on (host_ip) group_right (node)
+ label_replace(
+ (max(node_filesystem_files{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*"
+ )
+ ) by (node)
+ record: 'node:node_inodes_total:'
+ - expr: |
+ max(
+ max(
+ kube_pod_info{job="kube-state-metrics", host_ip!=""}
+ ) by (node, host_ip)
+ * on (host_ip) group_right (node)
+ label_replace(
+ (max(node_filesystem_files_free{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*"
+ )
+ ) by (node)
+ record: 'node:node_inodes_free:'
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[3m])) BY (instance)
@@ -680,7 +702,7 @@ spec:
}}' is experiencing {{ printf "%0.0f" $value }}% errors.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
expr: |
- (sum(rate(rest_client_requests_total{code!~"2..|404"}[5m])) by (instance, job)
+ (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job)
/
sum(rate(rest_client_requests_total[5m])) by (instance, job))
* 100 > 1
diff --git a/manifests/prometheus-serviceMonitorCoreDNS.yaml b/manifests/prometheus-serviceMonitorCoreDNS.yaml
index 14a245459fee6cff374468d6766875ad5b7ba12d..633aa18cf1d4d352e4f527b726a1127393da6f4d 100644
--- a/manifests/prometheus-serviceMonitorCoreDNS.yaml
+++ b/manifests/prometheus-serviceMonitorCoreDNS.yaml
@@ -10,6 +10,7 @@ spec:
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
interval: 15s
port: metrics
+ jobLabel: k8s-app
namespaceSelector:
matchNames:
- kube-system