Compare commits

..

5 Commits

Author SHA1 Message Date
Digital Studium d3d3b431cd Add web.external-url 2023-02-26 19:13:48 +03:00
digitalstudium c20c412019
Update README.md 2023-02-25 08:24:06 +03:00
Digital Studium 1fda4c6fff Refactored alertmanager 2023-02-24 20:55:21 +03:00
digitalstudium d374a3af1f Added alertmanager-bot 2021-08-06 21:30:10 +03:00
digitalstudium 1cd2337453 Added alertmanager 2021-07-30 14:08:09 +03:00
10 changed files with 24157 additions and 25 deletions

View File

@ -1,24 +1,15 @@
# grafana-docker-stack # grafana-docker-stack
For deploying Grafana, Prometheus and Node Exporter, make these steps: For deploying Grafana, Prometheus and Node Exporter, make these steps:
1. Deploy stack 1. Clone repo
``` ```
git clone https://github.com/digitalstudium/grafana-docker-stack.git git clone https://github.com/digitalstudium/grafana-docker-stack.git
```
2. Change configs if necessary (at least `configs/alertmanager.yml` to configure notification receivers)
3. Deploy stack
```bash
docker stack deploy -c grafana-docker-stack/docker-compose.yml monitoring docker stack deploy -c grafana-docker-stack/docker-compose.yml monitoring
``` ```
2. Add prometheus datasource with address `http://prometheus:9090` to grafana
3. Add these three lines to the bottom of `/var/lib/docker/volumes/monitoring_prom-configs/_data/prometheus.yml` file, to `scrape_configs:` section:
```
- job_name: 'node-exporter'
static_configs:
- targets: ['node-exporter:9100']
```
4. Reload prometheus config via this command:
```
docker ps | grep prometheus | awk '{print $1}' | xargs docker kill -s SIGHUP
```
5. Import this dashboard: https://grafana.com/grafana/dashboards/1860 to grafana.
That's it! That's it!
@ -28,8 +19,8 @@ If you want to add more servers to prometheus, make these steps:
git clone https://github.com/digitalstudium/grafana-docker-stack.git git clone https://github.com/digitalstudium/grafana-docker-stack.git
docker stack deploy -c grafana-docker-stack/node-exporter.yml node-exporter docker stack deploy -c grafana-docker-stack/node-exporter.yml node-exporter
``` ```
2. Add these servers to `/var/lib/docker/volumes/monitoring_prom-configs/_data/prometheus.yml` file to `- targets: ['node-exporter:9100']` list of `- job_name: 'node-exporter'` section, like `- targets: ['node-exporter:9100', 'server1:9100', 'server2:9100', '...']` 2. Add these servers to `configs/prometheus/prometheus.yml` file to `- targets: ['node-exporter:9100']` list of `- job_name: 'node-exporter'` section, like `- targets: ['node-exporter:9100', 'server1:9100', 'server2:9100', '...']`
3. Reload prometheus config via this command: 3. Reload prometheus config via this command:
``` ```bash
docker ps | grep prometheus | awk '{print $1}' | xargs docker kill -s SIGHUP docker ps | grep prometheus | awk '{print $1}' | xargs docker kill -s SIGHUP
```

18
configs/alertmanager.yml Normal file
View File

@ -0,0 +1,18 @@
route:
receiver: 'telegram'
routes:
# All alerts with severity=warning or severity=critical
# are dispatched to the telegram receiver.
- receiver: 'telegram'
group_wait: 10s
matchers:
- severity=~"warning|critical"
receivers:
- name: 'telegram'
telegram_configs:
- bot_token: "00000:ddddddddddddddddddd"
chat_id: -3453435345
# https://api.telegram.org/botINSERT_BOT_ID_HERE/getUpdates - to get chat_id
# amtool --alertmanager.url=http://localhost:9093/ alert add alertname="Test alert" severity="warning" job="test-job" - to send test alert

View File

@ -0,0 +1,799 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "Simple exporter for cadvisor only",
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": 14282,
"graphTooltip": 0,
"links": [],
"liveNow": false,
"panels": [
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 8,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"refId": "A"
}
],
"title": "CPU",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 1
},
"hiddenSeries": false,
"id": 15,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.3.6",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(rate(container_cpu_usage_seconds_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name) *100",
"hide": false,
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "CPU Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:606",
"format": "percent",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:607",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 8
},
"id": 11,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"refId": "A"
}
],
"title": "Memory",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 9
},
"hiddenSeries": false,
"id": 9,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.3.6",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(container_memory_rss{instance=~\"$host\",name=~\"$container\",name=~\".+\"}) by (name)",
"hide": false,
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Memory Usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:606",
"format": "bytes",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:607",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 9
},
"hiddenSeries": false,
"id": 14,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.3.6",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(container_memory_cache{instance=~\"$host\",name=~\"$container\",name=~\".+\"}) by (name)",
"hide": false,
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Memory Cached",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:606",
"format": "bytes",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:607",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 17
},
"id": 2,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"refId": "A"
}
],
"title": "Network",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 18
},
"hiddenSeries": false,
"id": 4,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"hideEmpty": false,
"hideZero": false,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.3.6",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(rate(container_network_receive_bytes_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name)",
"hide": false,
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Received Network Traffic",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:674",
"format": "Bps",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:675",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 18
},
"hiddenSeries": false,
"id": 6,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.3.6",
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "sum(rate(container_network_transmit_bytes_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name)",
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"thresholds": [],
"timeRegions": [],
"title": "Sent Network Traffic",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:832",
"format": "Bps",
"logBase": 1,
"show": true
},
{
"$$hashKey": "object:833",
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 26
},
"id": 19,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"refId": "A"
}
],
"title": "Misc",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"custom": {
"filterable": false
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "id"
},
"properties": [
{
"id": "custom.width",
"value": 260
}
]
},
{
"matcher": {
"id": "byName",
"options": "Running"
},
"properties": [
{
"id": "unit",
"value": "d"
},
{
"id": "decimals",
"value": 1
},
{
"id": "custom.displayMode",
"value": "color-text"
},
{
"id": "color",
"value": {
"fixedColor": "dark-green",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 27
},
"id": 17,
"options": {
"showHeader": true,
"sortBy": []
},
"pluginVersion": "7.4.5",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"expr": "(time() - container_start_time_seconds{instance=~\"$host\",name=~\"$container\",name=~\".+\"})/86400",
"format": "table",
"instant": true,
"interval": "",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"title": "Containers Info",
"transformations": [
{
"id": "filterFieldsByName",
"options": {
"include": {
"names": [
"container_label_com_docker_compose_project",
"container_label_com_docker_compose_project_working_dir",
"image",
"instance",
"name",
"Value",
"container_label_com_docker_compose_service"
]
}
}
},
{
"id": "organize",
"options": {
"excludeByName": {},
"indexByName": {},
"renameByName": {
"Value": "Running",
"container_label_com_docker_compose_project": "Label",
"container_label_com_docker_compose_project_working_dir": "Working dir",
"container_label_com_docker_compose_service": "Service",
"image": "Registry Image",
"instance": "Instance",
"name": "Name"
}
}
}
],
"type": "table"
}
],
"schemaVersion": 37,
"style": "dark",
"tags": [
"cadvisor",
"docker"
],
"templating": {
"list": [
{
"allValue": ".*",
"current": {
"selected": false,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"definition": "label_values({__name__=~\"container.*\"},instance)",
"hide": 0,
"includeAll": true,
"label": "Host",
"multi": false,
"name": "host",
"options": [],
"query": {
"query": "label_values({__name__=~\"container.*\"},instance)",
"refId": "Prometheus-host-Variable-Query"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 5,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".*",
"current": {
"selected": false,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"definition": "label_values({__name__=~\"container.*\", instance=~\"$host\"},name)",
"hide": 0,
"includeAll": true,
"label": "Container",
"multi": false,
"name": "container",
"options": [],
"query": {
"query": "label_values({__name__=~\"container.*\", instance=~\"$host\"},name)",
"refId": "Prometheus-container-Variable-Query"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-5m",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Cadvisor exporter",
"uid": "pMEd7m0Mz",
"version": 1,
"weekStart": ""
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,22 @@
apiVersion: 1
providers:
# <string> an unique provider name
- name: 'Unknown_provider'
# <int> org id. will default to orgId 1 if not specified
orgId: 1
# <string, required> name of the dashboard folder. Required
folder: ''
# <string> folder UID. will be automatically generated if not specified
folderUid: ''
# <string, required> provider type. Required
type: file
# <bool> disable dashboard deletion
disableDeletion: false
# <bool> enable dashboard editing
editable: true
# <int> how often Grafana will scan for changed dashboards
updateIntervalSeconds: 10
options:
# <string, required> path to dashboard files on disk. Required
path: /etc/grafana/provisioning/dashboards

View File

@ -0,0 +1,16 @@
# config file version
apiVersion: 1
# list of datasources to insert/update depending
# whats available in the database
datasources:
# <string, required> name of the datasource. Required
- name: Prometheus
# <string, required> datasource type. Required
type: prometheus
# <string, required> access mode. direct or proxy. Required
access: proxy
# <int> org id. will default to orgId 1 if not specified
orgId: 1
# <string> url
url: http://prometheus:9090

View File

@ -0,0 +1,57 @@
groups:
- name: Prometheus self-monitoring
rules:
- alert: Prometheus target missing
expr: 'up == 0'
annotations:
description: A Prometheus target has disappeared. An exporter might be crashed.
labels:
severity: critical
- alert: Prometheus AlertManager config not synced
expr: 'count(count_values("config_hash", alertmanager_config_hash)) > 1'
annotations:
description: Configurations of AlertManager cluster instances are out of sync
labels:
severity: warning
- alert: Prometheus target scraping slow
expr: 'prometheus_target_interval_length_seconds{quantile="0.9"} > 60'
annotations:
description: Prometheus is scraping exporters slowly
labels:
severity: warning
for: 5m
- name: Host and hardware
rules:
- alert: Host out of memory
expr: 'node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10'
annotations:
description: Node memory is filling up (< 10% left)
labels:
severity: warning
for: 2m
- alert: Host out of disk space
expr: '(node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
annotations:
description: Disk is almost full (< 10% left)
labels:
severity: warning
for: 2m
- alert: Host high CPU load
expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80'
annotations:
description: CPU load is > 80%
labels:
severity: warning
- alert: Host OOM kill detected
expr: 'increase(node_vmstat_oom_kill[1m]) > 0'
annotations:
description: OOM kill detected
labels:
severity: warning
- alert: Host clock skew
expr: '(node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)'
annotations:
description: 'Clock skew detected. Clock is out of sync.'
labels:
severity: warning
for: 2m

View File

@ -0,0 +1,36 @@
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
- alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
- "alert_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: "prometheus"
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ["localhost:9090"]
- job_name: "node-exporter"
static_configs:
- targets: ["node-exporter:9100"]
- job_name: "cadvisor"
static_configs:
- targets: ["cadvisor:8080"]

View File

@ -1,21 +1,47 @@
version: "3.9" version: "3.9"
services: services:
grafana: grafana:
image: grafana/grafana:8.5.3-ubuntu image: grafana/grafana:9.3.6-ubuntu
ports: ports:
- "3000:3000" - "3000:3000"
volumes: volumes:
- grafana-data:/var/lib/grafana - grafana-data:/var/lib/grafana
- grafana-configs:/etc/grafana - ./configs/grafana/datasources:/etc/grafana/provisioning/datasources/
- ./configs/grafana/dashboards:/etc/grafana/provisioning/dashboards/
prometheus: prometheus:
image: prom/prometheus:v2.36.0 image: prom/prometheus:v2.42.0
ports: ports:
- "9090:9090" - "9090:9090"
# Change 127.0.0.1 to ip address of node where docker satck is deployed
command:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus"
- "--web.external-url=http://127.0.0.1:9090"
- "--web.console.libraries=/usr/share/prometheus/console_libraries"
- "--web.console.templates=/usr/share/prometheus/consoles"
volumes: volumes:
- prom-data:/prometheus - prom-data:/prometheus
- prom-configs:/etc/prometheus - ./configs/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml
- ./configs/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
alertmanager:
image: prom/alertmanager:v0.25.0
ports:
- "9093:9093"
# Change 127.0.0.1 to ip address of node where docker satck is deployed
command:
- "--config.file=/etc/alertmanager/alertmanager.yml"
- "--storage.path=/alertmanager"
- "--web.external-url=http://127.0.0.1:9093"
volumes:
- alert-data:/alertmanager
- ./configs/alertmanager.yml:/etc/alertmanager/alertmanager.yml
node-exporter: node-exporter:
image: prom/node-exporter:v1.3.1 image: prom/node-exporter:v1.5.0
ports: ports:
- "9100:9100" - "9100:9100"
volumes: volumes:
@ -27,8 +53,18 @@ services:
- '--path.sysfs=/host/sys' - '--path.sysfs=/host/sys'
- '--collector.filesystem.mount-points-exclude' - '--collector.filesystem.mount-points-exclude'
- '^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)' - '^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)'
cadvisor:
image: gcr.io/cadvisor/cadvisor:v0.47.0
ports:
- 8080:8080
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
volumes: volumes:
grafana-data: grafana-data:
grafana-configs:
prom-data: prom-data:
prom-configs: alert-data:

View File

@ -1,7 +1,7 @@
version: "3.9" version: "3.9"
services: services:
node-exporter: node-exporter:
image: prom/node-exporter:v1.3.1 image: prom/node-exporter:v1.5.0
ports: ports:
- "9100:9100" - "9100:9100"
volumes: volumes: