github-personal/typhoon
1
0
Fork 0
mirror of https://github.com/outbackdingo/typhoon.git synced 2026-01-27 18:20:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Refresh Prometheus alerts and Grafana dashboards

Browse Source 
* Add 2 min wait before KubeNodeUnreachable to be less
noisy on premeptible clusters
* Add a BlackboxProbeFailure alert for any failing probes
for services annotated `prometheus.io/probe: true`
This commit is contained in:
Dalton Hubble
2020-03-01 23:20:33 -08:00
parent 51cee6d5a4
commit c4683c5bad
7 changed files with 2289 additions and 2219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGES.md
View File

@@ -27,9 +27,12 @@ Notable changes between versions.
* Update nginx-ingress from v0.28.0 to [v0.30.0](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.30.0)
* Update Prometheus from v2.15.2 to [v2.16.0](https://github.com/prometheus/prometheus/releases/tag/v2.16.0)
* Refresh Prometheus rules and alerts
* Add a BlackboxProbeFailure alert
* Update kube-state-metrics from v1.9.4 to v1.9.5
* Update node-exporter from v0.18.1 to [v1.0.0-rc.0](https://github.com/prometheus/node_exporter/releases/tag/v1.0.0-rc.0)
* Update Grafana from v6.6.1 to v6.6.2
* Refresh Grafana dashboards
## v1.17.3

194
addons/grafana/dashboards-k8s-nodes.yaml
View File

@@ -21,7 +21,7 @@ data:
"links": [
],
"refresh": "",
"refresh": "10s",
"rows": [
{
"collapse": false,
@@ -558,15 +558,15 @@ data:
},
"id": 8,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -649,15 +649,15 @@ data:
},
"id": 9,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -753,15 +753,15 @@ data:
},
"id": 10,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -857,15 +857,15 @@ data:
},
"id": 11,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -955,15 +955,15 @@ data:
},
"id": 12,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1066,17 +1066,17 @@ data:
},
"id": 13,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"hideEmpty": "true",
"hideZero": "true",
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1159,17 +1159,17 @@ data:
},
"id": 14,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"hideEmpty": "true",
"hideZero": "true",
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1265,17 +1265,17 @@ data:
},
"id": 15,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"hideEmpty": "true",
"hideZero": "true",
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1371,15 +1371,15 @@ data:
},
"id": 16,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1462,15 +1462,15 @@ data:
},
"id": 17,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1567,15 +1567,15 @@ data:
},
"id": 18,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1658,15 +1658,15 @@ data:
},
"id": 19,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1762,15 +1762,15 @@ data:
},
"id": 20,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1991,15 +1991,15 @@ data:
},
"id": 22,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -2373,8 +2373,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -2427,7 +2427,7 @@ data:
"options": [
],
"query": "label_values(kubelet_runtime_operations{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
"query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@@ -2496,7 +2496,7 @@ data:
"links": [
],
"refresh": "",
"refresh": "10s",
"rows": [
{
"collapse": false,
@@ -2691,15 +2691,15 @@ data:
},
"id": 4,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -2886,15 +2886,15 @@ data:
},
"id": 6,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -3206,15 +3206,15 @@ data:
},
"id": 9,
"legend": {
"alignAsTable": "true",
"alignAsTable": true,
"avg": false,
"current": "true",
"current": true,
"max": false,
"min": false,
"rightSide": "true",
"show": "true",
"rightSide": true,
"show": true,
"total": false,
"values": "true"
"values": true
},
"lines": true,
"linewidth": 1,
@@ -3588,8 +3588,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,

646
addons/grafana/dashboards-k8s-resources-1.yaml
View File

@@ -2458,8 +2458,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -2508,7 +2508,7 @@ data:
"text": "5m",
"value": "5m"
},
"datasource": "prometheus",
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
@@ -2533,6 +2533,33 @@ data:
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(node_cpu_seconds_total, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
@@ -2586,6 +2613,354 @@ data:
],
"refresh": "10s",
"rows": [
{
"collapse": false,
"height": "100px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"format": "percentunit",
"id": 1,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
"title": "CPU Utilisation (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"format": "percentunit",
"id": 2,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
"title": "CPU Utilisation (from limits)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"format": "percentunit",
"id": 3,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
"title": "Memory Utilization (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"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": "$datasource",
"fill": 1,
"format": "percentunit",
"id": 4,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
"title": "Memory Utilisation (from limits)",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "singlestat",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Headlines",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
@@ -2599,7 +2974,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 1,
"id": 5,
"legend": {
"avg": false,
"current": false,
@@ -2620,7 +2995,26 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "quota - requests",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
},
{
"alias": "quota - limits",
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -2634,6 +3028,22 @@ data:
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - requests",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - limits",
"legendLink": null,
"step": 10
}
],
"thresholds": [
@@ -2697,7 +3107,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 2,
"id": 6,
"legend": {
"avg": false,
"current": false,
@@ -2964,7 +3374,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 3,
"id": 7,
"legend": {
"avg": false,
"current": false,
@@ -2985,7 +3395,26 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "quota - requests",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
},
{
"alias": "quota - limits",
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -2999,6 +3428,22 @@ data:
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - requests",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - limits",
"legendLink": null,
"step": 10
}
],
"thresholds": [
@@ -3062,7 +3507,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 4,
"id": 8,
"legend": {
"avg": false,
"current": false,
@@ -3410,7 +3855,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 5,
"id": 9,
"legend": {
"avg": false,
"current": false,
@@ -3704,7 +4149,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 6,
"id": 10,
"legend": {
"avg": false,
"current": false,
@@ -3802,7 +4247,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 7,
"id": 11,
"legend": {
"avg": false,
"current": false,
@@ -3900,7 +4345,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 8,
"id": 12,
"legend": {
"avg": false,
"current": false,
@@ -3998,7 +4443,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 9,
"id": 13,
"legend": {
"avg": false,
"current": false,
@@ -4096,7 +4541,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 10,
"id": 14,
"legend": {
"avg": false,
"current": false,
@@ -4194,7 +4639,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 11,
"id": 15,
"legend": {
"avg": false,
"current": false,
@@ -4289,8 +4734,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -4303,60 +4748,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "namespace",
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
@@ -4366,7 +4757,7 @@ data:
"text": "5m",
"value": "5m"
},
"datasource": "prometheus",
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
@@ -4391,6 +4782,60 @@ data:
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
@@ -5265,8 +5710,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -5281,14 +5726,49 @@ data:
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "prod",
"value": "prod"
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
@@ -5297,7 +5777,7 @@ data:
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@@ -5309,13 +5789,13 @@ data:
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "node",
"label": null,
"multi": false,
"name": "node",
"options": [
@@ -5324,7 +5804,7 @@ data:
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
"refresh": 1,
"regex": "",
"sort": 2,
"sort": 1,
"tagValuesQuery": "",
"tags": [

769
addons/grafana/dashboards-k8s-resources-2.yaml
View File

@@ -50,7 +50,24 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "requests",
"color": "#F2495C",
"fill": 0,
"hideTooltip": true,
"legend": true,
"linewidth": 2,
"stack": false
},
{
"alias": "limits",
"color": "#FF9830",
"fill": 0,
"hideTooltip": true,
"legend": true,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -64,6 +81,22 @@ data:
"legendFormat": "{{container}}",
"legendLink": null,
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "requests",
"legendLink": null,
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "limits",
"legendLink": null,
"step": 10
}
],
"thresholds": [
@@ -126,8 +159,113 @@ data:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fill": 10,
"id": 2,
"legend": {
"avg": false,
"current": true,
"max": true,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
{
"colorMode": "critical",
"fill": true,
"line": true,
"op": "gt",
"value": 1,
"yaxis": "left"
}
],
"timeFrom": null,
"timeShift": null,
"title": "CPU Throttling",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": 1,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "CPU Throttling",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 3,
"legend": {
"avg": false,
"current": false,
@@ -394,7 +532,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 3,
"id": 4,
"legend": {
"avg": false,
"current": false,
@@ -415,7 +553,26 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "requests",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
},
{
"alias": "limits",
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -423,26 +580,26 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}} (RSS)",
"legendFormat": "{{container}}",
"legendLink": null,
"step": 10
},
{
"expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}} (Cache)",
"legendFormat": "requests",
"legendLink": null,
"step": 10
},
{
"expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}} (Swap)",
"legendFormat": "limits",
"legendLink": null,
"step": 10
}
@@ -508,7 +665,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 4,
"id": 5,
"legend": {
"avg": false,
"current": false,
@@ -856,7 +1013,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 5,
"id": 6,
"legend": {
"avg": false,
"current": false,
@@ -954,7 +1111,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 6,
"id": 7,
"legend": {
"avg": false,
"current": false,
@@ -1052,7 +1209,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 7,
"id": 8,
"legend": {
"avg": false,
"current": false,
@@ -1150,7 +1307,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 8,
"id": 9,
"legend": {
"avg": false,
"current": false,
@@ -1248,7 +1405,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 9,
"id": 10,
"legend": {
"avg": false,
"current": false,
@@ -1346,7 +1503,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 10,
"id": 11,
"legend": {
"avg": false,
"current": false,
@@ -1441,8 +1598,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -1455,87 +1612,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "namespace",
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "pod",
"multi": false,
"name": "pod",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
@@ -1545,7 +1621,7 @@ data:
"text": "5m",
"value": "5m"
},
"datasource": "prometheus",
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
@@ -1570,6 +1646,87 @@ data:
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "pod",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
@@ -3441,8 +3598,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -3455,114 +3612,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "namespace",
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "workload",
"multi": false,
"name": "workload",
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "type",
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
@@ -3572,7 +3621,7 @@ data:
"text": "5m",
"value": "5m"
},
"datasource": "prometheus",
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
@@ -3597,6 +3646,114 @@ data:
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "workload",
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
@@ -3684,7 +3841,26 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "quota - requests",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
},
{
"alias": "quota - limits",
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -3698,6 +3874,22 @@ data:
"legendFormat": "{{workload}} - {{workload_type}}",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - requests",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - limits",
"legendLink": null,
"step": 10
}
],
"thresholds": [
@@ -4094,7 +4286,26 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "quota - requests",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
},
{
"alias": "quota - limits",
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@@ -4108,6 +4319,22 @@ data:
"legendFormat": "{{workload}} - {{workload_type}}",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - requests",
"legendLink": null,
"step": 10
},
{
"expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "quota - limits",
"legendLink": null,
"step": 10
}
],
"thresholds": [
@@ -5576,8 +5803,8 @@ data:
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
@@ -5590,60 +5817,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "namespace",
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
@@ -5653,7 +5826,7 @@ data:
"text": "5m",
"value": "5m"
},
"datasource": "prometheus",
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
@@ -5706,6 +5879,60 @@ data:
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",

1739
addons/grafana/dashboards-k8s.yaml
View File

File diff suppressed because it is too large Load Diff

854
addons/grafana/dashboards-prom.yaml
View File

File diff suppressed because it is too large Load Diff

303
addons/prometheus/rules.yaml
View File

@@ -42,10 +42,10 @@ data:
{
"alert": "etcdHighNumberOfLeaderChanges",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last 30 minutes."
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated."
},
"expr": "rate(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}[15m]) > 3\n",
"for": "15m",
"expr": "increase((max by (job) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 3\n",
"for": "5m",
"labels": {
"severity": "warning"
}
@@ -145,25 +145,132 @@ data:
kube.yaml: |-
{
"groups": [
{
"name": "kube-apiserver-error",
"rules": [
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[5m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate5m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[30m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate30m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[2h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate2h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[6h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate6h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1d"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[3d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate3d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate5m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate5m{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate5m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate30m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate30m{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate30m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate2h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate2h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate2h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate6h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate6h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate6h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1d{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate3d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate3d{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate3d"
}
]
},
{
"name": "kube-apiserver.rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"expr": "sum(rate(apiserver_request_duration_seconds_sum{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[5m])) without(instance, pod)\n/\nsum(rate(apiserver_request_duration_seconds_count{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[5m])) without(instance, pod)\n",
"record": "cluster:apiserver_request_duration_seconds:mean5m"
},
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.99"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.9"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.5"
},
@@ -179,23 +286,23 @@ data:
"record": "namespace:container_cpu_usage_seconds_total:sum_rate"
},
{
"expr": "sum by (namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"expr": "sum by (cluster, namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate"
},
{
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_memory_working_set_bytes"
},
{
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_memory_rss"
},
{
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_memory_cache"
},
{
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_memory_swap"
},
{
@@ -203,29 +310,29 @@ data:
"record": "namespace:container_memory_usage_bytes:sum"
},
{
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)) by (namespace, pod)\n * on (namespace, pod)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace:kube_pod_container_resource_requests_memory_bytes:sum"
},
{
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)) by (namespace, pod)\n * on (namespace, pod)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace:kube_pod_container_resource_requests_cpu_cores:sum"
},
{
"expr": "sum(\n label_replace(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"},\n \"replicaset\", \"$1\", \"owner_name\", \"(.*)\"\n ) * on(replicaset, namespace) group_left(owner_name) kube_replicaset_owner{job=\"kube-state-metrics\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"},\n \"replicaset\", \"$1\", \"owner_name\", \"(.*)\"\n ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (\n 1, max by (replicaset, namespace, owner_name) (\n kube_replicaset_owner{job=\"kube-state-metrics\"}\n )\n ),\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "deployment"
},
"record": "mixin_pod_workload"
},
{
"expr": "sum(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "daemonset"
},
"record": "mixin_pod_workload"
},
{
"expr": "sum(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "statefulset"
},
@@ -305,23 +412,49 @@ data:
"name": "node.rules",
"rules": [
{
"expr": "sum(min(kube_pod_info) by (node))",
"expr": "sum(min(kube_pod_info) by (cluster, node))\n",
"record": ":kube_pod_info_node_count:"
},
{
"expr": "max(label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")) by (node, namespace, pod)\n",
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
"record": "node_namespace_pod:kube_pod_info:"
},
{
"expr": "count by (node) (sum by (node, cpu) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n))\n",
"expr": "count by (cluster, node) (sum by (node, cpu) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n))\n",
"record": "node:node_num_cpu:sum"
},
{
"expr": "sum(\n node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"} +\n node_memory_Cached_bytes{job=\"node-exporter\"} +\n node_memory_MemFree_bytes{job=\"node-exporter\"} +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n)\n",
"expr": "sum(\n node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"} +\n node_memory_Cached_bytes{job=\"node-exporter\"} +\n node_memory_MemFree_bytes{job=\"node-exporter\"} +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n) by (cluster)\n",
"record": ":node_memory_MemAvailable_bytes:sum"
}
]
},
{
"name": "kubelet.rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.99"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.9"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.5"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
}
]
},
{
"name": "kubernetes-apps",
"rules": [
@@ -343,7 +476,7 @@ data:
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
},
"expr": "sum by (namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Failed|Pending|Unknown\"} * on(namespace, pod) group_left(owner_kind) kube_pod_owner{owner_kind!=\"Job\"}) > 0\n",
"expr": "sum by (namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}) * on(namespace, pod) group_left(owner_kind) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})) > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
@@ -367,7 +500,7 @@ data:
"message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
},
"expr": "kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\nkube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n",
"expr": "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
@@ -379,7 +512,7 @@ data:
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch"
},
"expr": "kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n",
"expr": "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
@@ -528,7 +661,7 @@ data:
"message": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
},
"expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum)\n /\nsum(kube_node_status_allocatable_cpu_cores)\n >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n",
"expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n",
"for": "5m",
"labels": {
"severity": "warning"
@@ -540,7 +673,7 @@ data:
"message": "Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
},
"expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum)\n /\nsum(kube_node_status_allocatable_memory_bytes)\n >\n(count(kube_node_status_allocatable_memory_bytes)-1)\n /\ncount(kube_node_status_allocatable_memory_bytes)\n",
"expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})\n /\nsum(kube_node_status_allocatable_memory_bytes)\n >\n(count(kube_node_status_allocatable_memory_bytes)-1)\n /\ncount(kube_node_status_allocatable_memory_bytes)\n",
"for": "5m",
"labels": {
"severity": "warning"
@@ -618,7 +751,7 @@ data:
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
},
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n",
"for": "5m",
"for": "1h",
"labels": {
"severity": "critical"
}
@@ -666,17 +799,44 @@ data:
}
]
},
{
"name": "kube-apiserver-error-alerts",
"rules": [
{
"alert": "ErrorBudgetBurn",
"annotations": {
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1h{job=\"apiserver\"} > (14.4*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate5m{job=\"apiserver\"} > (14.4*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (6*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate30m{job=\"apiserver\"} > (6*0.010000)\n)\n",
"labels": {
"job": "apiserver",
"severity": "critical"
}
},
{
"alert": "ErrorBudgetBurn",
"annotations": {
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1d{job=\"apiserver\"} > (3*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate2h{job=\"apiserver\"} > (3*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate3d{job=\"apiserver\"} > (0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (0.010000)\n)\n",
"labels": {
"job": "apiserver",
"severity": "warning"
}
}
]
},
{
"name": "kubernetes-system-apiserver",
"rules": [
{
"alert": "KubeAPILatencyHigh",
"annotations": {
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"message": "The API server has an abnormal latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 1\n",
"for": "10m",
"expr": "(\n cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"}\n >\n on (verb) group_left()\n (\n avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n +\n 2*stddev by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n )\n) > on (verb) group_left()\n1.2 * avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\nand on (verb,resource)\ncluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"}\n>\n1\n",
"for": "5m",
"labels": {
"severity": "warning"
}
@@ -687,7 +847,7 @@ data:
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 4\n",
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"} > 4\n",
"for": "10m",
"labels": {
"severity": "critical"
@@ -747,7 +907,7 @@ data:
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
},
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
"labels": {
"severity": "warning"
}
@@ -758,11 +918,34 @@ data:
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
},
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
"labels": {
"severity": "critical"
}
},
{
"alert": "AggregatedAPIErrors",
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors"
},
"expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "AggregatedAPIDown",
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} is down. It has not been available at least for the past five minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown"
},
"expr": "sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeAPIDown",
"annotations": {
@@ -799,6 +982,7 @@ data:
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable"
},
"expr": "kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} == 1\n",
"for": "2m",
"labels": {
"severity": "warning"
}
@@ -815,6 +999,42 @@ data:
"severity": "warning"
}
},
{
"alert": "KubeNodeReadinessFlapping",
"annotations": {
"message": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping"
},
"expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletPlegDurationHigh",
"annotations": {
"message": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh"
},
"expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletPodStartUpLatencyHigh",
"annotations": {
"message": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh"
},
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 5\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletDown",
"annotations": {
@@ -1124,7 +1344,7 @@ data:
{
"alert": "PrometheusRemoteStorageFailures",
"annotations": {
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to queue {{$labels.queue}}.",
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"summary": "Prometheus fails to send samples to remote storage."
},
"expr": "(\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n (\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n +\n rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n )\n)\n* 100\n> 1\n",
@@ -1136,7 +1356,7 @@ data:
{
"alert": "PrometheusRemoteWriteBehind",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for queue {{$labels.queue}}.",
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"summary": "Prometheus remote write is behind."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
@@ -1148,10 +1368,10 @@ data:
{
"alert": "PrometheusRemoteWriteDesiredShards",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ printf $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n> on(job, instance) group_right\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
"for": "15m",
"labels": {
"severity": "warning"
@@ -1201,6 +1421,17 @@ data:
"labels": {
"severity": "warning"
}
},
{
"alert": "BlackboxProbeFailure",
"annotations": {
"message": "Blackbox probe {{$labels.instance}} failed"
},
"expr": "probe_success == 0",
"for": "2m",
"labels": {
"severity": "critical"
}
}
]
},