diff --git a/jsonnet/kube-prometheus/alertmanager/alertmanager.libsonnet b/jsonnet/kube-prometheus/alertmanager/alertmanager.libsonnet
index 320e8223c93e8208a4fffac9c1d2885764bda9ac..6f7ca1c6f056e4b4979a2277c697ba75852ec999 100644
--- a/jsonnet/kube-prometheus/alertmanager/alertmanager.libsonnet
+++ b/jsonnet/kube-prometheus/alertmanager/alertmanager.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
diff --git a/jsonnet/kube-prometheus/jsonnetfile.json b/jsonnet/kube-prometheus/jsonnetfile.json
index 20aedb5c5a6cad31571713b375bb41e47654821c..30e7f660b8910c119767acfefacaa77238d779e2 100644
--- a/jsonnet/kube-prometheus/jsonnetfile.json
+++ b/jsonnet/kube-prometheus/jsonnetfile.json
@@ -13,7 +13,7 @@
{
"source": {
"git": {
- "remote": "https://github.com/coreos/etcd",
+ "remote": "https://github.com/etcd-io/etcd",
"subdir": "Documentation/etcd-mixin"
}
},
diff --git a/jsonnet/kube-prometheus/ksm-autoscaler/ksm-autoscaler.libsonnet b/jsonnet/kube-prometheus/ksm-autoscaler/ksm-autoscaler.libsonnet
index 56406efbd41af68e250f357bbde886af2ccf8f0f..1fed631ded7d73d74342a8711b7e4bcef6aa18a4 100644
--- a/jsonnet/kube-prometheus/ksm-autoscaler/ksm-autoscaler.libsonnet
+++ b/jsonnet/kube-prometheus/ksm-autoscaler/ksm-autoscaler.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
diff --git a/jsonnet/kube-prometheus/kube-prometheus-all-namespaces.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-all-namespaces.libsonnet
index 468420fd1f636d7fd237769c82eebc56962adaf3..e6ab55486fbc2af8d35b90cd494dfdaaaba7467d 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-all-namespaces.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-all-namespaces.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
prometheus+:: {
diff --git a/jsonnet/kube-prometheus/kube-prometheus-anti-affinity.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-anti-affinity.libsonnet
index 51b3c19b3a1a728ab29913f0ef4bfa2533baa119..59014d551ad7957da1ce60c1889d2165d0e67d07 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-anti-affinity.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-anti-affinity.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local statefulSet = k.apps.v1.statefulSet;
local affinity = statefulSet.mixin.spec.template.spec.affinity.podAntiAffinity.preferredDuringSchedulingIgnoredDuringExecutionType;
local matchExpression = affinity.mixin.podAffinityTerm.labelSelector.matchExpressionsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-bootkube.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-bootkube.libsonnet
index 6281c664f85c11dd953eba5838df684e35d7db0b..05c6a4d2408bfbfa44bd4fd547547b2e03db81db 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-bootkube.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-bootkube.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-custom-metrics.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-custom-metrics.libsonnet
index 7c5b41661c1b6151172d00a6afa09d7c5fe8de65..bbbd7a69767068e53283a2f7f02a8c6de82ebea7 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-custom-metrics.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-custom-metrics.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
// Custom metrics API allows the HPA v2 to scale based on arbirary metrics.
// For more details on usage visit https://github.com/DirectXMan12/k8s-prometheus-adapter#quick-links
diff --git a/jsonnet/kube-prometheus/kube-prometheus-eks.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-eks.libsonnet
index f064bda469fdbb73ed7036d2a70f742d7ff3fb9a..a3f59958901e53fa2063feb2516c82fcef7e4083 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-eks.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-eks.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-kops-coredns.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-kops-coredns.libsonnet
index 8a309d284f13873629db2eff640d693c03472150..37760404511b502fe96488ae267d3ab6aff28d82 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-kops-coredns.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-kops-coredns.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-kops.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-kops.libsonnet
index b5cb1f84c889586ca019965d6f892cbdda50689c..9f9bb9503c0c6f0480ea9ae25431f1a7d5e1aa86 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-kops.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-kops.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-ksonnet.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-ksonnet.libsonnet
index 664e19125b72419a58e79bf108fe981d6ae1826a..ad13373fda32dadc392e6f88df587ccc74de2e1c 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-ksonnet.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-ksonnet.libsonnet
@@ -1,4 +1,4 @@
-local kp = (import 'kube-prometheus/kube-prometheus.libsonnet');
+local kp = (import './kube-prometheus/kube-prometheus.libsonnet');
{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } +
{ ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } +
diff --git a/jsonnet/kube-prometheus/kube-prometheus-kube-aws.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-kube-aws.libsonnet
index 7a3326c23818528859b0d0388fa0dd4dde6e117f..bd7ea6caa845d8fe7170503cde85277f71d3d0af 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-kube-aws.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-kube-aws.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-kubeadm.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-kubeadm.libsonnet
index e981a1286a8650197d599694b84e1fd88483246e..1481c596842b2a29a9189584b95c8b6bb04de481 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-kubeadm.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-kubeadm.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-kubespray.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-kubespray.libsonnet
index 9889963ad084c5242782b937451ba8a14c91bdc8..fbda4a9eb432b2dfc98417f15d73220e7882b300 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-kubespray.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-kubespray.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-node-ports.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-node-ports.libsonnet
index b10a1bb4925a886d32a0018fe38d51f3a1e9e7c2..13901307363277b123474be706422cbf7c9f2a77 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-node-ports.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-node-ports.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-static-etcd.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-static-etcd.libsonnet
index 63094f157198d6a5e27e0e7222a831e8376b7cdb..7b017e74eebd630c22af4c6fbe02222feff13ae1 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-static-etcd.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-static-etcd.libsonnet
@@ -1,6 +1,6 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
-(import 'etcd-mixin/mixin.libsonnet') + {
+(import 'github.com/etcd-io/etcd/Documentation/etcd-mixin/mixin.libsonnet') + {
_config+:: {
etcd: {
ips: [],
diff --git a/jsonnet/kube-prometheus/kube-prometheus-thanos-sidecar.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-thanos-sidecar.libsonnet
index a6f54bd0fc6bfaf99b29bb5aae6abd786f15311c..210207ba5cba077675ff1d06d876ec2d54751537 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-thanos-sidecar.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-thanos-sidecar.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
diff --git a/jsonnet/kube-prometheus/kube-prometheus-weave-net.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-weave-net.libsonnet
index c75587ab6fbab0ba63e67e64f09abc5f02623e18..2a8e7980f8062b22d6537c23e3094d42d7128bb4 100644
--- a/jsonnet/kube-prometheus/kube-prometheus-weave-net.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus-weave-net.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;
@@ -183,7 +183,7 @@ local servicePort = k.core.v1.service.mixin.spec.portsType;
],
},
grafanaDashboards+:: {
- 'weave-net.json': (import 'grafana-weave-net.json'),
- 'weave-net-cluster.json': (import 'grafana-weave-net-cluster.json'),
+ 'weave-net.json': (import './grafana-weave-net.json'),
+ 'weave-net-cluster.json': (import './grafana-weave-net-cluster.json'),
},
}
diff --git a/jsonnet/kube-prometheus/kube-prometheus.libsonnet b/jsonnet/kube-prometheus/kube-prometheus.libsonnet
index d04ec890cf0e79a99333ca58d1275b75fd2ea822..1907d9f02fbba4145554b5bd762c32284914f414 100644
--- a/jsonnet/kube-prometheus/kube-prometheus.libsonnet
+++ b/jsonnet/kube-prometheus/kube-prometheus.libsonnet
@@ -1,20 +1,20 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
-local k3 = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
+local k3 = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.3/k.libsonnet';
local configMapList = k3.core.v1.configMapList;
-(import 'grafana/grafana.libsonnet') +
-(import 'kube-state-metrics/kube-state-metrics.libsonnet') +
-(import 'kube-state-metrics-mixin/mixin.libsonnet') +
-(import 'node-exporter/node-exporter.libsonnet') +
-(import 'node-mixin/mixin.libsonnet') +
-(import 'alertmanager/alertmanager.libsonnet') +
-(import 'prometheus-operator/prometheus-operator.libsonnet') +
-(import 'prometheus/prometheus.libsonnet') +
-(import 'prometheus-adapter/prometheus-adapter.libsonnet') +
-(import 'kubernetes-mixin/mixin.libsonnet') +
-(import 'prometheus/mixin.libsonnet') +
-(import 'alerts/alerts.libsonnet') +
-(import 'rules/rules.libsonnet') + {
+(import 'github.com/brancz/kubernetes-grafana/grafana/grafana.libsonnet') +
+(import './kube-state-metrics/kube-state-metrics.libsonnet') +
+(import 'github.com/kubernetes/kube-state-metrics/jsonnet/kube-state-metrics-mixin/mixin.libsonnet') +
+(import './node-exporter/node-exporter.libsonnet') +
+(import 'github.com/kubernetes/kube-state-metrics/jsonnet/kube-state-metrics-mixin/mixin.libsonnet') +
+(import './alertmanager/alertmanager.libsonnet') +
+(import 'github.com/prometheus-operator/prometheus-operator/jsonnet/prometheus-operator/prometheus-operator.libsonnet') +
+(import './prometheus/prometheus.libsonnet') +
+(import './prometheus-adapter/prometheus-adapter.libsonnet') +
+(import 'github.com/kubernetes-monitoring/kubernetes-mixin/mixin.libsonnet') +
+(import 'github.com/prometheus/prometheus/documentation/prometheus-mixin/mixin.libsonnet') +
+(import './alerts/alerts.libsonnet') +
+(import './rules/rules.libsonnet') + {
kubePrometheus+:: {
namespace: k.core.v1.namespace.new($._config.namespace),
},
diff --git a/jsonnet/kube-prometheus/kube-rbac-proxy/container.libsonnet b/jsonnet/kube-prometheus/kube-rbac-proxy/container.libsonnet
index c5934732b172db290e3858b045d425938f3864f5..e1d3dc0e93cc6bcce9a178f1d194c51a5e1f296c 100644
--- a/jsonnet/kube-prometheus/kube-rbac-proxy/container.libsonnet
+++ b/jsonnet/kube-prometheus/kube-rbac-proxy/container.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local deployment = k.apps.v1.deployment;
local container = deployment.mixin.spec.template.spec.containersType;
local containerPort = container.portsType;
diff --git a/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet b/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet
index 2c21905cfe52c47ca2c782d98a14fe9ddabe613a..a313e7b1f4ec471504fd45ed157bf4d29ec25628 100644
--- a/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet
+++ b/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet
@@ -11,7 +11,7 @@
scrapeTimeout: '30s',
},
},
- kubeStateMetrics+:: (import 'kube-state-metrics/kube-state-metrics.libsonnet') +
+ kubeStateMetrics+:: (import 'github.com/kubernetes/kube-state-metrics/jsonnet/kube-state-metrics/kube-state-metrics.libsonnet') +
{
local ksm = self,
name:: 'kube-state-metrics',
diff --git a/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet b/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet
index a162c9664c3cb682751e37125e73256967867b01..a6fb05875acfd6f828b7c6aa6f3418bd57d401e9 100644
--- a/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet
+++ b/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
diff --git a/jsonnet/kube-prometheus/prometheus-adapter/prometheus-adapter.libsonnet b/jsonnet/kube-prometheus/prometheus-adapter/prometheus-adapter.libsonnet
index 682f3015621e642543a87644d61e212fe3cf4520..ecbfb2c698e449561f31a71407ad976003118a81 100644
--- a/jsonnet/kube-prometheus/prometheus-adapter/prometheus-adapter.libsonnet
+++ b/jsonnet/kube-prometheus/prometheus-adapter/prometheus-adapter.libsonnet
@@ -1,4 +1,4 @@
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
diff --git a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet
index e4f102c72997493325b2d4c17b250984b921b389..a1a52d8f69772cab77aa90d08fe83eecdf39281a 100644
--- a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet
+++ b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet
@@ -1,5 +1,5 @@
-local k3 = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
-local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
+local k3 = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.3/k.libsonnet';
+local k = import 'github.com/ksonnet/ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json
index 5b25845ed1ff4c26b61a9246c1fe8aad85f6a576..6c0add96906f087d001541a0e5a8760ecc903454 100644
--- a/jsonnetfile.lock.json
+++ b/jsonnetfile.lock.json
@@ -14,7 +14,7 @@
{
"source": {
"git": {
- "remote": "https://github.com/coreos/etcd.git",
+ "remote": "https://github.com/etcd-io/etcd.git",
"subdir": "Documentation/etcd-mixin"
}
},
diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml
index 36a422490451bb9b2271ab5d64427eb3b27d94f7..2c4847be5f3b0ba94a8b035a179a9f0787585a5d 100644
--- a/manifests/grafana-dashboardDefinitions.yaml
+++ b/manifests/grafana-dashboardDefinitions.yaml
@@ -22022,2907 +22022,6 @@ items:
metadata:
name: grafana-dashboard-namespace-by-workload
namespace: monitoring
-- apiVersion: v1
- data:
- node-cluster-rsrc-use.json: |-
- {
- "annotations": {
- "list": [
-
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
-
- ],
- "refresh": "10s",
- "rows": [
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "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:rate1m{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
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 2,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "CPU Saturation (load1 per CPU)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "CPU",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$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": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "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
- }
- ],
- "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
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 4,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Saturation (Major Page Faults)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "rps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Memory",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$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": "/ Receive/",
- "stack": "A"
- },
- {
- "alias": "/ Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_bytes_excluding_lo:rate1m{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:rate1m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Transmit",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "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
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 6,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "/ Receive/",
- "stack": "A"
- },
- {
- "alias": "/ Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_drop_excluding_lo:rate1m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Receive",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_drop_excluding_lo:rate1m{job=\"node-exporter\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} Transmit",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Net Saturation (Drops Receive/Transmit)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "rps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Network",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 7,
- "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": "instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{device}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "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": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 10,
- "id": 8,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 0,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\"}))\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{instance}} {{device}}",
- "legendLink": "/dashboard/file/node-rsrc-use.json",
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk IO Saturation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Disk IO",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$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
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Disk Space",
- "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"
- }
- ]
- },
- "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": "3e97d1d02672cdd0861f4c97c64f89b2",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- name: grafana-dashboard-node-cluster-rsrc-use
- namespace: monitoring
-- apiVersion: v1
- data:
- node-rsrc-use.json: |-
- {
- "annotations": {
- "list": [
-
- ]
- },
- "editable": true,
- "gnetId": null,
- "graphTooltip": 0,
- "hideControls": false,
- "links": [
-
- ],
- "refresh": "10s",
- "rows": [
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 1,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_cpu_utilisation:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Utilisation",
- "legendLink": null,
- "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": 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": "$datasource",
- "fill": 1,
- "id": 2,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Saturation",
- "legendLink": null,
- "step": 10
- }
- ],
- "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": 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",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 3,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", job=\"node-exporter\", instance=\"$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": "$datasource",
- "fill": 1,
- "id": 4,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Major page faults",
- "legendLink": null,
- "step": 10
- }
- ],
- "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": "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": "Memory",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 5,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
- {
- "alias": "/Receive/",
- "stack": "A"
- },
- {
- "alias": "/Transmit/",
- "stack": "B",
- "transform": "negative-Y"
- }
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance:node_network_receive_bytes_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Receive",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_bytes_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Transmit",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Net Utilisation (Bytes Receive/Transmit)",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "Bps",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$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": [
-
- ],
- "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:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "Receive drops",
- "legendLink": null,
- "step": 10
- },
- {
- "expr": "instance:node_network_transmit_drop_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$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": [
-
- ]
- },
- "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": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 7,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\", instance=\"$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
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 8,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{device}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "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": [
-
- ]
- },
- "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
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Disk IO",
- "titleSize": "h6"
- },
- {
- "collapse": false,
- "height": "250px",
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "id": 9,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": false,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null as zero",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "1 -\n(\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n/\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "{{device}}",
- "legendLink": null,
- "step": 10
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk Space Utilisation",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": false
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": true,
- "title": "Disk Space",
- "titleSize": "h6"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
-
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "default",
- "value": "default"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
- "text": "prod",
- "value": "prod"
- },
- "datasource": "$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": "fac67cfbe174d3ef53eb473d73d9212f",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- 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,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
-
- },
- "id": 2,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": true,
- "steppedLine": false,
- "targets": [
- {
- "expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"}[$__interval]))\n/ ignoring(cpu) group_left\n count without (cpu)( node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 5,
- "legendFormat": "{{cpu}}",
- "refId": "A"
- }
- ],
- "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": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- },
- {
- "format": "percentunit",
- "label": null,
- "logBase": 1,
- "max": 1,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
-
- },
- "id": 3,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "node_load1{job=\"node-exporter\", instance=\"$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=\"$instance\", mode=\"idle\"})",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "logical cores",
- "refId": "D"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Load Average",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
-
- },
- "id": 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,
- "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 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\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "memory cached",
- "refId": "C"
- },
- {
- "expr": "node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "memory free",
- "refId": "D"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Memory Usage",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- },
- {
- "cacheTimeout": null,
- "colorBackground": false,
- "colorValue": false,
- "colors": [
- "rgba(50, 172, 45, 0.97)",
- "rgba(237, 129, 40, 0.89)",
- "rgba(245, 54, 54, 0.9)"
- ],
- "datasource": "$datasource",
- "format": "percent",
- "gauge": {
- "maxValue": 100,
- "minValue": 0,
- "show": true,
- "thresholdLabels": false,
- "thresholdMarkers": true
- },
- "gridPos": {
-
- },
- "id": 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 node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n* 100\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "thresholds": "80, 90",
- "title": "Memory Usage",
- "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,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
-
- },
- "id": 6,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
- {
- "alias": "/ read| written/",
- "yaxis": 1
- },
- {
- "alias": "/ io time/",
- "yaxis": 2
- }
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 2,
- "legendFormat": "{{device}} read",
- "refId": "A"
- },
- {
- "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 2,
- "legendFormat": "{{device}} written",
- "refId": "B"
- },
- {
- "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 2,
- "legendFormat": "{{device}} io time",
- "refId": "C"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk I/O",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "s",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 1,
- "gridPos": {
-
- },
- "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": [
-
- ],
- "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=\"$instance\", fstype!=\"\"}\n )\n)\n",
- "format": "time_series",
- "intervalFactor": 2,
- "legendFormat": "available",
- "refId": "B"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Disk Space Usage",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- },
- {
- "collapse": false,
- "collapsed": false,
- "panels": [
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 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
- },
- "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_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 2,
- "legendFormat": "{{device}}",
- "refId": "A"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network Received",
- "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
- }
- ]
- },
- {
- "aliasColors": {
-
- },
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": "$datasource",
- "fill": 0,
- "gridPos": {
-
- },
- "id": 9,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": false,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 1,
- "links": [
-
- ],
- "nullPointMode": "null",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "repeat": null,
- "seriesOverrides": [
-
- ],
- "spaceLength": 10,
- "span": 6,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
- "format": "time_series",
- "interval": "1m",
- "intervalFactor": 2,
- "legendFormat": "{{device}}",
- "refId": "A"
- }
- ],
- "thresholds": [
-
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Network Transmitted",
- "tooltip": {
- "shared": false,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "buckets": null,
- "mode": "time",
- "name": null,
- "show": true,
- "values": [
-
- ]
- },
- "yaxes": [
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- },
- {
- "format": "bytes",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": 0,
- "show": true
- }
- ]
- }
- ],
- "repeat": null,
- "repeatIteration": null,
- "repeatRowId": null,
- "showTitle": false,
- "title": "Dashboard Row",
- "titleSize": "h6",
- "type": "row"
- }
- ],
- "schemaVersion": 14,
- "style": "dark",
- "tags": [
-
- ],
- "templating": {
- "list": [
- {
- "current": {
- "text": "Prometheus",
- "value": "Prometheus"
- },
- "hide": 0,
- "label": null,
- "name": "datasource",
- "options": [
-
- ],
- "query": "prometheus",
- "refresh": 1,
- "regex": "",
- "type": "datasource"
- },
- {
- "allValue": null,
- "current": {
-
- },
- "datasource": "$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": "UTC",
- "title": "Nodes",
- "uid": "fa49a4706d07a042595b664c87fb33ea",
- "version": 0
- }
- kind: ConfigMap
- metadata:
- name: grafana-dashboard-nodes
- namespace: monitoring
- apiVersion: v1
data:
persistentvolumesusage.json: |-
diff --git a/manifests/grafana-deployment.yaml b/manifests/grafana-deployment.yaml
index 589b1ade56cc53f4e2d0a174427919b1418df86d..7b7dc791f94f9aec4ecd5aca135ba0718c019e45 100644
--- a/manifests/grafana-deployment.yaml
+++ b/manifests/grafana-deployment.yaml
@@ -81,15 +81,6 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/namespace-by-workload
name: grafana-dashboard-namespace-by-workload
readOnly: false
- - mountPath: /grafana-dashboard-definitions/0/node-cluster-rsrc-use
- name: grafana-dashboard-node-cluster-rsrc-use
- readOnly: false
- - mountPath: /grafana-dashboard-definitions/0/node-rsrc-use
- name: grafana-dashboard-node-rsrc-use
- readOnly: false
- - mountPath: /grafana-dashboard-definitions/0/nodes
- name: grafana-dashboard-nodes
- readOnly: false
- mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage
name: grafana-dashboard-persistentvolumesusage
readOnly: false
@@ -166,15 +157,6 @@ spec:
- configMap:
name: grafana-dashboard-namespace-by-workload
name: grafana-dashboard-namespace-by-workload
- - configMap:
- name: grafana-dashboard-node-cluster-rsrc-use
- name: grafana-dashboard-node-cluster-rsrc-use
- - configMap:
- name: grafana-dashboard-node-rsrc-use
- name: grafana-dashboard-node-rsrc-use
- - configMap:
- name: grafana-dashboard-nodes
- name: grafana-dashboard-nodes
- configMap:
name: grafana-dashboard-persistentvolumesusage
name: grafana-dashboard-persistentvolumesusage
diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml
index 166f21596af3281a1d7a630c2bea792b613396be..dcb52653fe8b4efe7bc01693c17517a9e96e5824 100644
--- a/manifests/prometheus-rules.yaml
+++ b/manifests/prometheus-rules.yaml
@@ -8,63 +8,6 @@ metadata:
namespace: monitoring
spec:
groups:
- - name: node-exporter.rules
- rules:
- - expr: |
- count without (cpu) (
- count without (mode) (
- node_cpu_seconds_total{job="node-exporter"}
- )
- )
- record: instance:node_num_cpu:sum
- - expr: |
- 1 - avg without (cpu, mode) (
- rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[1m])
- )
- record: instance:node_cpu_utilisation:rate1m
- - expr: |
- (
- node_load1{job="node-exporter"}
- /
- instance:node_num_cpu:sum{job="node-exporter"}
- )
- record: instance:node_load1_per_cpu:ratio
- - expr: |
- 1 - (
- node_memory_MemAvailable_bytes{job="node-exporter"}
- /
- node_memory_MemTotal_bytes{job="node-exporter"}
- )
- record: instance:node_memory_utilisation:ratio
- - expr: |
- rate(node_vmstat_pgmajfault{job="node-exporter"}[1m])
- record: instance:node_vmstat_pgmajfault:rate1m
- - expr: |
- rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
- record: instance_device:node_disk_io_time_seconds:rate1m
- - expr: |
- rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
- record: instance_device:node_disk_io_time_weighted_seconds:rate1m
- - expr: |
- sum without (device) (
- rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[1m])
- )
- record: instance:node_network_receive_bytes_excluding_lo:rate1m
- - expr: |
- sum without (device) (
- rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[1m])
- )
- record: instance:node_network_transmit_bytes_excluding_lo:rate1m
- - expr: |
- sum without (device) (
- rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[1m])
- )
- record: instance:node_network_receive_drop_excluding_lo:rate1m
- - expr: |
- sum without (device) (
- rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
- )
- record: instance:node_network_transmit_drop_excluding_lo:rate1m
- name: kube-apiserver.rules
rules:
- expr: |
@@ -816,234 +759,38 @@ spec:
for: 15m
labels:
severity: critical
- - name: node-exporter
+ - name: kube-state-metrics
rules:
- - alert: NodeFilesystemSpaceFillingUp
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available space left and is filling
- up.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
- summary: Filesystem is predicted to run out of space within the next 24 hours.
- expr: |
- (
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40
- and
- predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: warning
- - alert: NodeFilesystemSpaceFillingUp
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available space left and is filling
- up fast.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
- summary: Filesystem is predicted to run out of space within the next 4 hours.
- expr: |
- (
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15
- and
- predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: critical
- - alert: NodeFilesystemAlmostOutOfSpace
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available space left.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
- summary: Filesystem has less than 5% space left.
- expr: |
- (
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: warning
- - alert: NodeFilesystemAlmostOutOfSpace
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available space left.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
- summary: Filesystem has less than 3% space left.
- expr: |
- (
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: critical
- - alert: NodeFilesystemFilesFillingUp
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available inodes left and is filling
- up.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
- summary: Filesystem is predicted to run out of inodes within the next 24 hours.
- expr: |
- (
- node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40
- and
- predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: warning
- - alert: NodeFilesystemFilesFillingUp
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available inodes left and is filling
- up fast.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
- summary: Filesystem is predicted to run out of inodes within the next 4 hours.
- expr: |
- (
- node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20
- and
- predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: critical
- - alert: NodeFilesystemAlmostOutOfFiles
- annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available inodes left.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
- summary: Filesystem has less than 5% inodes left.
- expr: |
- (
- node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
- labels:
- severity: warning
- - alert: NodeFilesystemAlmostOutOfFiles
+ - alert: KubeStateMetricsListErrors
annotations:
- description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
- has only {{ printf "%.2f" $value }}% available inodes left.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
- summary: Filesystem has less than 3% inodes left.
+ description: kube-state-metrics is experiencing errors at an elevated rate
+ in list operations. This is likely causing it to not be able to expose metrics
+ about Kubernetes objects correctly or at all.
+ runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricslisterrors
+ summary: kube-state-metrics is experiencing errors in list operations.
expr: |
- (
- node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3
- and
- node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
- )
- for: 1h
+ (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m]))
+ /
+ sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])))
+ > 0.01
+ for: 15m
labels:
severity: critical
- - alert: NodeNetworkReceiveErrs
- annotations:
- description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
- {{ printf "%.0f" $value }} receive errors in the last two minutes.'
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworkreceiveerrs
- summary: Network interface is reporting many receive errors.
- expr: |
- increase(node_network_receive_errs_total[2m]) > 10
- for: 1h
- labels:
- severity: warning
- - alert: NodeNetworkTransmitErrs
- annotations:
- description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
- {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworktransmiterrs
- summary: Network interface is reporting many transmit errors.
- expr: |
- increase(node_network_transmit_errs_total[2m]) > 10
- for: 1h
- labels:
- severity: warning
- - alert: NodeHighNumberConntrackEntriesUsed
- annotations:
- description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodehighnumberconntrackentriesused
- summary: Number of conntrack are getting close to the limit.
- expr: |
- (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
- labels:
- severity: warning
- - alert: NodeTextFileCollectorScrapeError
- annotations:
- description: Node Exporter text file collector failed to scrape.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodetextfilecollectorscrapeerror
- summary: Node Exporter text file collector failed to scrape.
- expr: |
- node_textfile_scrape_error{job="node-exporter"} == 1
- labels:
- severity: warning
- - alert: NodeClockSkewDetected
- annotations:
- message: Clock on {{ $labels.instance }} is out of sync by more than 300s.
- Ensure NTP is configured correctly on this host.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclockskewdetected
- summary: Clock skew detected.
- expr: |
- (
- node_timex_offset_seconds > 0.05
- and
- deriv(node_timex_offset_seconds[5m]) >= 0
- )
- or
- (
- node_timex_offset_seconds < -0.05
- and
- deriv(node_timex_offset_seconds[5m]) <= 0
- )
- for: 10m
- labels:
- severity: warning
- - alert: NodeClockNotSynchronising
- annotations:
- message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP
- is configured on this host.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclocknotsynchronising
- summary: Clock not synchronising.
- expr: |
- min_over_time(node_timex_sync_status[5m]) == 0
- for: 10m
- labels:
- severity: warning
- - alert: NodeRAIDDegraded
+ - alert: KubeStateMetricsWatchErrors
annotations:
- description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is
- in degraded state due to one or more disks failures. Number of spare drives
- is insufficient to fix issue automatically.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddegraded
- summary: RAID Array is degraded
+ description: kube-state-metrics is experiencing errors at an elevated rate
+ in watch operations. This is likely causing it to not be able to expose
+ metrics about Kubernetes objects correctly or at all.
+ runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricswatcherrors
+ summary: kube-state-metrics is experiencing errors in watch operations.
expr: |
- node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0
+ (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m]))
+ /
+ sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])))
+ > 0.01
for: 15m
labels:
severity: critical
- - alert: NodeRAIDDiskFailure
- annotations:
- description: At least one device in RAID array on {{ $labels.instance }} failed.
- Array '{{ $labels.device }}' needs attention and possibly a disk swap.
- runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddiskfailure
- summary: Failed device in RAID array
- expr: |
- node_md_disks{state="fail"} > 0
- labels:
- severity: warning
- name: kubernetes-apps
rules:
- alert: KubePodCrashLooping