Fusion de prometheus et granafa

This commit is contained in:
Adrien Reslinger 2020-04-20 18:03:28 +02:00
parent 82c43339cb
commit 2c57657fc9
39 changed files with 26968 additions and 57 deletions

View file

@ -0,0 +1,36 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-config
namespace: monitoring
data:
custom.ini: |+
[server]
http_port = 8080
[paths]
data = /var/lib/grafana
plugins = /var/lib/grafana/plugins
provisioning = /etc/grafana/provisioning
[users]
allow_sign_up = false
allow_org_create = false
# viewers can edit/inspect, but not save
viewers_can_edit = true
# Disable login form, since Grafana always creates an admin user
[auth]
disable_login_form = true
# Disable the user/pass login system
[auth.basic]
enabled = false
# Allow anonymous authentication with view-only authorization
[auth.anonymous]
enabled = true
org_role = Viewer
[analytics]
reporting_enabled = false

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,968 @@
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": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 2,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$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": true,
"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": "$datasource",
"fill": 0,
"gridPos": {
},
"id": 3,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_load1{job=\"node-exporter\", instance=\"$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=\"$instance\", mode=\"idle\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "logical cores",
"refId": "D"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Load Average",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 4,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"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=\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "memory free",
"refId": "D"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Memory Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "$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",
"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": "$datasource",
"fill": 0,
"gridPos": {
},
"id": 6,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
{
"alias": "/ read| written/",
"yaxis": 1
},
{
"alias": "/ io time/",
"yaxis": 2
}
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} read",
"refId": "A"
},
{
"expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} written",
"refId": "B"
},
{
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} io time",
"refId": "C"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Disk I/O",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 7,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"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=\"$instance\", fstype!~\"tmpfs|nsfs|vfat\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!~\"tmpfs|nsfs|vfat\"}\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=\"$instance\", fstype!~\"tmpfs|nsfs|vfat\"}\n )\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "available",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Disk Space Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"gridPos": {
},
"id": 8,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"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": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"gridPos": {
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Network Transmitted",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
}
],
"schemaVersion": 14,
"style": "dark",
"tags": [
],
"templating": {
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
},
"hide": 0,
"label": null,
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "instance",
"options": [
],
"query": "label_values(node_exporter_build_info{job=\"node-exporter\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "",
"title": "Nodes",
"uid": "fa49a4706d07a042595b664c87fb33ea",
"version": 0
}
kind: ConfigMap
metadata:
name: grafana-dashboards-node-exporter
namespace: monitoring

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,24 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-datasources
namespace: monitoring
data:
prometheus.yaml: |+
apiVersion: 1
datasources:
- name: prometheus
type: prometheus
access: proxy
url: http://prometheus.monitoring.svc.cluster.local
version: 1
editable: false
loki.yaml: |+
apiVersion: 1
datasources:
- name: loki
type: loki
access: proxy
url: http://loki.monitoring.svc.cluster.local
version: 1
editable: false

View file

@ -0,0 +1,112 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: grafana
namespace: monitoring
spec:
replicas: 1
strategy:
type: RollingUpdate
rollingUpdate:
maxUnavailable: 1
selector:
matchLabels:
name: grafana
phase: prod
template:
metadata:
labels:
name: grafana
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
containers:
- name: grafana
image: docker.io/grafana/grafana:6.7.2
env:
- name: GF_PATHS_CONFIG
value: "/etc/grafana/custom.ini"
ports:
- name: http
containerPort: 8080
livenessProbe:
httpGet:
path: /metrics
port: 8080
initialDelaySeconds: 10
readinessProbe:
httpGet:
path: /api/health
port: 8080
initialDelaySeconds: 10
resources:
requests:
cpu: 100m
memory: 100Mi
limits:
cpu: 200m
memory: 200Mi
volumeMounts:
- name: config
mountPath: /etc/grafana
- name: datasources
mountPath: /etc/grafana/provisioning/datasources
- name: providers
mountPath: /etc/grafana/provisioning/dashboards
- name: dashboards-etcd
mountPath: /etc/grafana/dashboards/etcd
- name: dashboards-node-exporter
mountPath: /etc/grafana/dashboards/node-exporter
- name: dashboards-prom
mountPath: /etc/grafana/dashboards/prom
- name: dashboards-k8s
mountPath: /etc/grafana/dashboards/k8s
- name: dashboards-k8s-nodes
mountPath: /etc/grafana/dashboards/k8s-nodes
- name: dashboards-k8s-resources-1
mountPath: /etc/grafana/dashboards/k8s-resources-1
- name: dashboards-k8s-resources-2
mountPath: /etc/grafana/dashboards/k8s-resources-2
- name: dashboards-coredns
mountPath: /etc/grafana/dashboards/coredns
- name: dashboards-nginx-ingress
mountPath: /etc/grafana/dashboards/nginx-ingress
volumes:
- name: config
configMap:
name: grafana-config
- name: datasources
configMap:
name: grafana-datasources
- name: providers
configMap:
name: grafana-providers
- name: dashboards-etcd
configMap:
name: grafana-dashboards-etcd
- name: dashboards-node-exporter
configMap:
name: grafana-dashboards-node-exporter
- name: dashboards-prom
configMap:
name: grafana-dashboards-prom
- name: dashboards-k8s
configMap:
name: grafana-dashboards-k8s
- name: dashboards-k8s-nodes
configMap:
name: grafana-dashboards-k8s-nodes
- name: dashboards-k8s-resources-1
configMap:
name: grafana-dashboards-k8s-resources-1
- name: dashboards-k8s-resources-2
configMap:
name: grafana-dashboards-k8s-resources-2
- name: dashboards-coredns
configMap:
name: grafana-dashboards-coredns
- name: dashboards-nginx-ingress
configMap:
name: grafana-dashboards-nginx-ingress

View file

@ -0,0 +1,15 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-providers
namespace: monitoring
data:
providers.yaml: |+
apiVersion: 1
providers:
- name: 'default'
ordId: 1
folder: ''
type: file
options:
path: /etc/grafana/dashboards

View file

@ -0,0 +1,18 @@
apiVersion: v1
kind: Service
metadata:
name: grafana
namespace: monitoring
annotations:
prometheus.io/scrape: 'true'
prometheus.io/port: '8080'
spec:
type: ClusterIP
selector:
name: grafana
phase: prod
ports:
- name: http
protocol: TCP
port: 80
targetPort: 8080

View file

@ -20,7 +20,7 @@ spec:
serviceAccountName: prometheus
containers:
- name: prometheus
image: quay.io/prometheus/prometheus:v2.17.0
image: quay.io/prometheus/prometheus:v2.17.1
args:
- --web.listen-address=0.0.0.0:9090
- --config.file=/etc/prometheus/prometheus.yaml

View file

@ -252,25 +252,25 @@ data:
"name": "kube-apiserver.rules",
"rules": [
{
"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",
"expr": "sum(rate(apiserver_request_duration_seconds_sum{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n/\nsum(rate(apiserver_request_duration_seconds_count{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|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",
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|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\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[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|DELETECOLLECTION|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\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"}[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|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.5"
},
@ -805,6 +805,7 @@ data:
{
"alert": "ErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"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",
@ -816,6 +817,7 @@ data:
{
"alert": "ErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"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",
@ -853,30 +855,6 @@ data:
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.03\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.01\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
@ -993,7 +971,7 @@ data:
"message": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods"
},
"expr": "max(max(kubelet_running_pod_count{job=\"kubelet\"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"}) by(node) / max(kube_node_status_capacity_pods{job=\"kube-state-metrics\"}) by(node) > 0.95\n",
"expr": "max(max(kubelet_running_pod_count{job=\"kubelet\"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"}) by(node) / max(kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1) by(node) > 0.95\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -1029,7 +1007,7 @@ data:
"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",
"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 > 60\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -1085,9 +1063,167 @@ data:
}
]
}
loki.yaml: |-
{
"groups": [
{
"name": "loki_rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))",
"record": "job:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))",
"record": "job:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job) / sum(rate(loki_request_duration_seconds_count[1m])) by (job)",
"record": "job:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job)",
"record": "job:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job)",
"record": "job:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job)",
"record": "job:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))",
"record": "job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))",
"record": "job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route)",
"record": "job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))",
"record": "namespace_job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))",
"record": "namespace_job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_count:sum_rate"
}
]
},
{
"name": "loki_alerts",
"rules": [
{
"alert": "LokiRequestErrors",
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n"
},
"expr": "100 * sum(rate(loki_request_duration_seconds_count{status_code=~\"5..\"}[1m])) by (namespace, job, route)\n /\nsum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)\n > 10\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "LokiRequestLatency",
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n"
},
"expr": "namespace_job_route:loki_request_duration_seconds:99quantile{route!~\"(?i).*tail.*\"} > 1\n",
"for": "15m",
"labels": {
"severity": "critical"
}
}
]
}
]
}
node-exporter.yaml: |-
{
"groups": [
{
"name": "node-exporter.rules",
"rules": [
{
"expr": "count without (cpu) (\n count without (mode) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n )\n)\n",
"record": "instance:node_num_cpu:sum"
},
{
"expr": "1 - avg without (cpu, mode) (\n rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\"}[1m])\n)\n",
"record": "instance:node_cpu_utilisation:rate1m"
},
{
"expr": "(\n node_load1{job=\"node-exporter\"}\n/\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n",
"record": "instance:node_load1_per_cpu:ratio"
},
{
"expr": "1 - (\n node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n",
"record": "instance:node_memory_utilisation:ratio"
},
{
"expr": "rate(node_vmstat_pgmajfault{job=\"node-exporter\"}[1m])\n",
"record": "instance:node_vmstat_pgmajfault:rate1m"
},
{
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n",
"record": "instance_device:node_disk_io_time_seconds:rate1m"
},
{
"expr": "rate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n",
"record": "instance_device:node_disk_io_time_weighted_seconds:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_receive_bytes_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_transmit_bytes_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_receive_drop_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_transmit_drop_excluding_lo:rate1m"
}
]
},
{
"name": "node-exporter",
"rules": [
@ -1210,6 +1346,41 @@ data:
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeHighNumberConntrackEntriesUsed",
"annotations": {
"description": "{{ $value | humanizePercentage }} of conntrack entries are used",
"summary": "Number of conntrack are getting close to the limit"
},
"expr": "(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75\n",
"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.",
"summary": "Clock skew detected."
},
"expr": "(\n node_timex_offset_seconds > 0.05\nand\n deriv(node_timex_offset_seconds[5m]) >= 0\n)\nor\n(\n node_timex_offset_seconds < -0.05\nand\n deriv(node_timex_offset_seconds[5m]) <= 0\n)\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeClockNotSynchronising",
"annotations": {
"message": "Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.",
"summary": "Clock not synchronising."
},
"expr": "min_over_time(node_timex_sync_status[5m]) == 0\n",
"for": "10m",
"labels": {
"severity": "warning"
}
}
]
}