Skip to content

Instantly share code, notes, and snippets.

@ratulbasak
Created September 17, 2017 09:22
Show Gist options
  • Save ratulbasak/46d3de3c22d3c4a1a451f5a14d6d8029 to your computer and use it in GitHub Desktop.
Save ratulbasak/46d3de3c22d3c4a1a451f5a14d6d8029 to your computer and use it in GitHub Desktop.
monitoring docker swarm using influxdb, grafana, cadvisor
{
"__inputs": [
{
"name": "DS_INFLUX",
"label": "influx",
"description": "",
"type": "datasource",
"pluginId": "influxdb",
"pluginName": "InfluxDB"
}
],
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "4.2.0"
},
{
"type": "panel",
"id": "graph",
"name": "Graph",
"version": ""
},
{
"type": "datasource",
"id": "influxdb",
"name": "InfluxDB",
"version": "1.0.0"
}
],
"annotations": {
"list": []
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": 2,
"links": [],
"refresh": "5s",
"rows": [
{
"collapse": false,
"height": 250,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "influx",
"fill": 1,
"id": 1,
"interval": "",
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"show": true,
"total": true,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"alias": "Memory {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$__interval"
],
"type": "time"
},
{
"params": [
"machine"
],
"type": "tag"
},
{
"params": [
"container_name"
],
"type": "tag"
}
],
"measurement": "memory_usage",
"orderByTime": "ASC",
"policy": "default",
"query": "SELECT \"value\" FROM \"memory_usage\" WHERE \"container_name\" =~ /^$container$/ AND \"machine\" =~ /^$host$/ AND $timeFilter",
"rawQuery": false,
"refId": "A",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
}
]
],
"tags": [
{
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
},
{
"condition": "AND",
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
}
]
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Memory",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "decbytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "influx",
"fill": 1,
"id": 2,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": true,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"alias": "CPU {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$interval"
],
"type": "time"
},
{
"params": [
"machine"
],
"type": "tag"
},
{
"params": [
"container_name"
],
"type": "tag"
}
],
"measurement": "cpu_usage_total",
"orderByTime": "ASC",
"policy": "default",
"refId": "A",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
},
{
"params": [
"10s"
],
"type": "derivative"
}
]
],
"tags": [
{
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
},
{
"condition": "AND",
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
}
]
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "CPU",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "hertz",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6"
},
{
"collapse": false,
"height": 250,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "influx",
"fill": 1,
"id": 3,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": true,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"alias": "Usage {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$interval"
],
"type": "time"
},
{
"params": [
"container_name"
],
"type": "tag"
},
{
"params": [
"machine"
],
"type": "tag"
}
],
"measurement": "fs_usage",
"orderByTime": "ASC",
"policy": "default",
"refId": "A",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
}
]
],
"tags": [
{
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
},
{
"condition": "AND",
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
}
]
},
{
"alias": "Limit {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$interval"
],
"type": "time"
},
{
"params": [
"container_name"
],
"type": "tag"
},
{
"params": [
"machine"
],
"type": "tag"
}
],
"measurement": "fs_limit",
"orderByTime": "ASC",
"policy": "default",
"refId": "B",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
}
]
],
"tags": [
{
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
},
{
"condition": "AND",
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
}
]
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "File System",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "decbytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "influx",
"fill": 1,
"id": 4,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"show": true,
"total": true,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"alias": "RX {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$interval"
],
"type": "time"
},
{
"params": [
"container_name"
],
"type": "tag"
},
{
"params": [
"machine"
],
"type": "tag"
}
],
"measurement": "rx_bytes",
"orderByTime": "ASC",
"policy": "default",
"refId": "A",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
},
{
"params": [
"10s"
],
"type": "derivative"
}
]
],
"tags": [
{
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
},
{
"condition": "AND",
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
}
]
},
{
"alias": "TX {host: $tag_machine, container: $tag_container_name}",
"dsType": "influxdb",
"groupBy": [
{
"params": [
"$interval"
],
"type": "time"
},
{
"params": [
"container_name"
],
"type": "tag"
},
{
"params": [
"machine"
],
"type": "tag"
}
],
"measurement": "tx_bytes",
"orderByTime": "ASC",
"policy": "default",
"refId": "B",
"resultFormat": "time_series",
"select": [
[
{
"params": [
"value"
],
"type": "field"
},
{
"params": [],
"type": "mean"
},
{
"params": [
"10s"
],
"type": "derivative"
}
]
],
"tags": [
{
"key": "machine",
"operator": "=~",
"value": "/^$host$/"
},
{
"condition": "AND",
"key": "container_name",
"operator": "=~",
"value": "/^$container$*/"
}
]
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Network",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6"
}
],
"schemaVersion": 14,
"style": "dark",
"tags": [],
"templating": {
"list": [
{
"allValue": "",
"current": {
"text": "backbox.corde.org",
"value": "backbox.corde.org"
},
"datasource": "influx",
"hide": 0,
"includeAll": true,
"label": "Host",
"multi": false,
"name": "host",
"options": [],
"query": "show tag values with key = \"machine\"",
"refresh": 1,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "/",
"value": "/"
},
"datasource": "influx",
"hide": 0,
"includeAll": false,
"label": "Container",
"multi": false,
"name": "container",
"options": [],
"query": "show tag values with key = \"container_name\" WHERE machine =~ /^$host$/",
"refresh": 1,
"regex": "/([^.]+)/",
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-6h",
"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": "browser",
"title": "cAdvisor Copy",
"version": 2
}
  1. Install docker, docker-machine,docker-compose

  2. Create a manager node and 3 worker nodes

  3. ssh into manager node and create swarm :

    $ docker-machine ssh manager $ docker swarm init --advertise-addr docker-machine ip manager

  4. Add worker nodes to the swarm :

    $ docker-machine ssh agent1 docker swarm join --token docker swarm join-token -q worker docker-machine ip manager:2377 $ docker-machine ssh agent2 docker swarm join --token docker swarm join-token -q worker docker-machine ip manager:2377

  5. Copy the docker-compose file to install Influxdb, Grafana and cAdvisor :

    $ vi docker-compose.yml

  6. run docker-compose.yml:

    $ docker stack deploy -c docker-stack.yml monitor

  7. create database named cadvisor in influxdb to store the metrics :

    $ docker exec docker ps | grep -i influx | awk '{print $1}' influx -execute 'CREATE DATABASE cadvisor'

  8. goto browser : http://docker-machine ip manager username: admin password: admin

  9. create a datasource in Grafana from above dashboard.json.

version: '3'
services:
influx:
image: influxdb
volumes:
- influx:/var/lib/influxdb
deploy:
replicas: 1
placement:
constraints:
- node.role == manager
grafana:
image: grafana/grafana
ports:
- 0.0.0.0:3000:3000
volumes:
- grafana:/var/lib/grafana
depends_on:
- influx
deploy:
replicas: 1
placement:
constraints:
- node.role == manager
cadvisor:
image: google/cadvisor
hostname: '{{.Node.ID}}'
command: -logtostderr -docker_only -storage_driver=influxdb -storage_driver_db=cadvisor -storage_driver_host=influx:8086
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
depends_on:
- influx
deploy:
mode: global
volumes:
influx:
driver: local
grafana:
driver: local
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment