dashboard
This commit is contained in:
parent
88bb561b39
commit
01baaa951f
@ -6,3 +6,16 @@ networks:
|
||||
|
||||
#### SERVICES
|
||||
services:
|
||||
picoshare:
|
||||
image: mtlynch/picoshare
|
||||
environment:
|
||||
- PORT=4001
|
||||
- PS_SHARED_SECRET=GolDoRak # Changez_moi!
|
||||
networks:
|
||||
- back_network
|
||||
ports:
|
||||
- 4001:4001
|
||||
command: -db /data/store.db
|
||||
volumes:
|
||||
- ./picoshare/data:/data
|
||||
restart: unless-stopped
|
@ -7,5 +7,6 @@ providers:
|
||||
type: file
|
||||
disableDeletion: false
|
||||
editable: true
|
||||
allowUiUpdates: true
|
||||
options:
|
||||
path: /etc/grafana/provisioning/dashboards
|
||||
|
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
@ -0,0 +1,398 @@
|
||||
{
|
||||
"id": null,
|
||||
"title": "Nginx",
|
||||
"description": "Nginx exporter metrics",
|
||||
"tags": [
|
||||
"nginx"
|
||||
],
|
||||
"style": "dark",
|
||||
"timezone": "browser",
|
||||
"editable": true,
|
||||
"hideControls": false,
|
||||
"sharedCrosshair": true,
|
||||
"rows": [
|
||||
{
|
||||
"collapse": false,
|
||||
"editable": true,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {},
|
||||
"bars": false,
|
||||
"datasource": "Prometheus",
|
||||
"decimals": 2,
|
||||
"editable": true,
|
||||
"error": false,
|
||||
"fill": 1,
|
||||
"grid": {
|
||||
"threshold1": null,
|
||||
"threshold1Color": "rgba(216, 200, 27, 0.27)",
|
||||
"threshold2": null,
|
||||
"threshold2Color": "rgba(234, 112, 112, 0.22)"
|
||||
},
|
||||
"id": 3,
|
||||
"isNew": true,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 2,
|
||||
"links": [],
|
||||
"nullPointMode": "connected",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [],
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(nginx_connections_processed_total{stage=\"any\"}[5m])) by (stage)",
|
||||
"hide": false,
|
||||
"interval": "",
|
||||
"intervalFactor": 10,
|
||||
"legendFormat": "requests",
|
||||
"metric": "",
|
||||
"refId": "B",
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Requests/sec",
|
||||
"tooltip": {
|
||||
"msResolution": false,
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "cumulative"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"show": true
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {},
|
||||
"bars": false,
|
||||
"datasource": "Prometheus",
|
||||
"decimals": 2,
|
||||
"editable": true,
|
||||
"error": false,
|
||||
"fill": 1,
|
||||
"grid": {
|
||||
"threshold1": null,
|
||||
"threshold1Color": "rgba(216, 200, 27, 0.27)",
|
||||
"threshold2": null,
|
||||
"threshold2Color": "rgba(234, 112, 112, 0.22)"
|
||||
},
|
||||
"id": 2,
|
||||
"isNew": true,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 2,
|
||||
"links": [],
|
||||
"nullPointMode": "connected",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [],
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(nginx_connections_current) by (state)",
|
||||
"interval": "",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{state}}",
|
||||
"metric": "",
|
||||
"refId": "A",
|
||||
"step": 2
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Connections",
|
||||
"tooltip": {
|
||||
"msResolution": false,
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "cumulative"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"show": true
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {},
|
||||
"bars": false,
|
||||
"datasource": "Prometheus",
|
||||
"decimals": 2,
|
||||
"editable": true,
|
||||
"error": false,
|
||||
"fill": 1,
|
||||
"grid": {
|
||||
"threshold1": null,
|
||||
"threshold1Color": "rgba(216, 200, 27, 0.27)",
|
||||
"threshold2": null,
|
||||
"threshold2Color": "rgba(234, 112, 112, 0.22)"
|
||||
},
|
||||
"id": 1,
|
||||
"isNew": true,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 2,
|
||||
"links": [],
|
||||
"nullPointMode": "connected",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [],
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(irate(nginx_connections_processed_total{stage!=\"any\"}[5m])) by (stage)",
|
||||
"hide": false,
|
||||
"interval": "",
|
||||
"intervalFactor": 10,
|
||||
"legendFormat": "{{stage}}",
|
||||
"metric": "",
|
||||
"refId": "B",
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Connections rate",
|
||||
"tooltip": {
|
||||
"msResolution": false,
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "cumulative"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"show": true
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"title": "Nginx exporter metrics"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"editable": true,
|
||||
"height": "250px",
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {},
|
||||
"bars": false,
|
||||
"datasource": null,
|
||||
"editable": true,
|
||||
"error": false,
|
||||
"fill": 1,
|
||||
"grid": {
|
||||
"threshold1": null,
|
||||
"threshold1Color": "rgba(216, 200, 27, 0.27)",
|
||||
"threshold2": null,
|
||||
"threshold2Color": "rgba(234, 112, 112, 0.22)"
|
||||
},
|
||||
"id": 4,
|
||||
"isNew": true,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": true,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 2,
|
||||
"links": [],
|
||||
"nullPointMode": "connected",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [],
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(container_cpu_usage_seconds_total{name=~\"nginx\"}[5m])) / count(node_cpu_seconds_total{mode=\"system\"}) * 100",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "nginx",
|
||||
"refId": "A",
|
||||
"step": 2
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "CPU usage",
|
||||
"tooltip": {
|
||||
"msResolution": false,
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "cumulative"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"show": true
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"title": "Nginx container metrics"
|
||||
}
|
||||
],
|
||||
"time": {
|
||||
"from": "now-15m",
|
||||
"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"
|
||||
]
|
||||
},
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 12,
|
||||
"version": 9,
|
||||
"links": [],
|
||||
"gnetId": null
|
||||
}
|
@ -2,6 +2,57 @@ groups:
|
||||
- name: example
|
||||
rules:
|
||||
|
||||
- name: targets
|
||||
rules:
|
||||
- alert: monitor_service_down
|
||||
expr: up == 0
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Monitor service non-operational"
|
||||
description: "Service {{ $labels.instance }} is down."
|
||||
|
||||
- name: host
|
||||
rules:
|
||||
- alert: high_cpu_load
|
||||
expr: node_load1 > 1.5
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server under high load"
|
||||
description: "Docker host is under high load, the avg load 1m is at {{ $value}}. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- alert: high_memory_load
|
||||
expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server memory is almost full"
|
||||
description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- alert: high_storage_load
|
||||
expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"} * 100 > 85
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server storage is almost full"
|
||||
description: "Docker host storage usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- name: containers
|
||||
rules:
|
||||
- alert: jenkins_down
|
||||
expr: absent(container_memory_usage_bytes{name="jenkins"})
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Jenkins down"
|
||||
description: "Jenkins container is down for more than 30 seconds."
|
||||
|
||||
# Alert for any instance that is unreachable for >2 minutes.
|
||||
- alert: service_down
|
||||
expr: up == 0
|
||||
|
Loading…
x
Reference in New Issue
Block a user