DEV-563: added hetzner dashboard + svennes dashboard + refactoring alert for hetzner_api_rate_limit

feature/DEV-655
friedrich goerz 3 years ago
parent c424c1edb4
commit 9e6f28c62a

@ -164,7 +164,7 @@
- name: "Create cronjob to exec hetzner-metrics script" - name: "Create cronjob to exec hetzner-metrics script"
ansible.builtin.cron: ansible.builtin.cron:
name: "update hetzner metrics" name: "update hetzner metrics"
minute: "*" minute: "*/5"
job: /root/hetzner_unattached_volumes.py job: /root/hetzner_unattached_volumes.py
tags: tags:
- update-hetzner-metrics - update-hetzner-metrics

@ -0,0 +1,420 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 22,
"links": [],
"liveNow": false,
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 9,
"panels": [],
"title": "Rate Limits",
"type": "row"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "remaining rate limit",
"axisPlacement": "auto",
"axisSoftMax": 100,
"axisSoftMin": 0,
"axisWidth": 40,
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "percentage",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "(hetzner_api_ratelimit_remaining / hetzner_api_ratelimit_limit) * 100",
"hide": false,
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{env}}",
"refId": "A"
}
],
"title": "Hetzner",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "remaining rate limit",
"axisPlacement": "auto",
"axisSoftMax": 100,
"axisSoftMin": 0,
"axisWidth": 40,
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "percentage",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"id": 3,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "(digitalocean_api_ratelimit_remaining / digitalocean_api_ratelimit_limit) * 100",
"hide": false,
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{env}}",
"refId": "A"
}
],
"title": "Digital Ocean",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 10
},
"id": 7,
"panels": [],
"title": "Errors",
"type": "row"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "Count/5m",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 11
},
"id": 5,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "changes(awx_status_total{status=\"failed\"}[5m])",
"interval": "",
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Failed AWX Jobs",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "Count/5m",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 11
},
"id": 10,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "irate(logback_events_total{level=\"error\"}[5m])",
"interval": "",
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Application Errors",
"type": "timeseries"
}
],
"refresh": "",
"schemaVersion": 34,
"style": "dark",
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-2d",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Stage Overview",
"uid": "NXk5Nk74k",
"version": 7,
"weekStart": ""
}

@ -0,0 +1,357 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 21,
"links": [],
"liveNow": false,
"panels": [
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "max_requests"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-red",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "hetzner_api_ratelimit_limit",
"interval": "",
"legendFormat": "max_requests",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "hetzner_api_ratelimit_remaining",
"hide": false,
"interval": "",
"legendFormat": "remaining requests",
"refId": "B"
}
],
"title": "API requests",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "max_requests"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-red",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "hetzner_api_unattached_volumes",
"interval": "",
"legendFormat": "locked servers",
"refId": "A"
}
],
"title": "unattached volumes",
"type": "timeseries"
},
{
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "max_requests"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-red",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"id": 3,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"exemplar": true,
"expr": "hetzner_api_locked_servers",
"interval": "",
"legendFormat": "locked servers",
"refId": "A"
}
],
"title": "locked servers",
"type": "timeseries"
}
],
"schemaVersion": 34,
"style": "dark",
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-30m",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "hetzner metrics",
"uid": "DClNWkn4k",
"version": 2,
"weekStart": ""
}

@ -333,7 +333,7 @@ groups:
description: "offsite metrics unavailable." description: "offsite metrics unavailable."
- alert: DO_API_REQUEST_usage - alert: DO_API_REQUEST_usage
expr: (digitalocean_api_ratelimit_remaining * 100)/digitalocean_api_ratelimit_limit < 50 expr: (digitalocean_api_ratelimit_remaining * 100)/digitalocean_api_ratelimit_limit < 50 or absent(digitalocean_api_ratelimit_remaining)
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@ -390,14 +390,14 @@ groups:
- alert: hetzner ratelimit_remaining low - alert: hetzner ratelimit_remaining low
expr: hetzner_api_ratelimit_remaining < 720 or absent(hetzner_api_ratelimit_remaining) expr: (hetzner_api_ratelimit_remaining * 100)/ hetzner_api_ratelimit_remaining < 50 or absent(hetzner_api_ratelimit_remaining)
for: 1h for: 10m
labels: labels:
severity: critical severity: critical
annotations: annotations:
identifier: '{{ '{{' }} $labels.instance {{ '}}' }}' identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
summary: "hetzner ratelimit_remaining below 720" summary: "hetzner ratelimit_remaining below 50%"
description: "hetzner ratelimit_remaining below 720" description: "hetzner ratelimit_remaining below 50%"
- alert: hetzner locked server exists - alert: hetzner locked server exists
expr: hetzner_api_locked_servers > 0 or absent(hetzner_api_locked_servers) expr: hetzner_api_locked_servers > 0 or absent(hetzner_api_locked_servers)

Loading…
Cancel
Save