ajout docker plugin for telegraf

README.md

@@ -18,6 +18,11 @@ urls = ["http://SERVER-IP:8086"] # required
 
 ## Usage
 
+- get docker UID for telegraf (agent only)
+```bash
+./get-docker-id.sh
+```
+
 - start stack
 ```bash
 docker-compose up -d
@@ -56,4 +61,4 @@ docker-compose logs -f
 # To do:
 
 - [ ] script install
-- [ ] ajout Cadvisor + Prometheus
+- [ ] Prometheus + Alertmanager

docker-compose-telegraf-agent.yml

@@ -4,22 +4,28 @@ services:
 
   telegraf:
     image: telegraf:1.18-alpine
-    # image: telegraf:latest #(for arm64)
+    # image: telegraf:latest #(for amd64)
+    container_name: telegraf
+    restart: unless-stopped
+    # for docker
+    hostname: ${HOSTNAME}
+    user: "telegraf:${DOCKER_GID}"
     volumes:
       - ./telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
+      - /var/run/docker.sock:/var/run/docker.sock
     ports:
     - '8125:8125/udp'
 
-  cadvisor:
+  # cadvisor:
-    image: gcr.io/cadvisor/cadvisor
+  #   image: gcr.io/cadvisor/cadvisor
-    # + image arm64
+  #   # + image arm64
-    container_name: cadvisor
+  #   container_name: cadvisor
-    volumes:
+  #   volumes:
-      - /:/rootfs:ro
+  #     - /:/rootfs:ro
-      - /var/run:/var/run:rw
+  #     - /var/run:/var/run:rw
-      - /sys:/sys:ro
+  #     - /sys:/sys:ro
-      - /var/lib/docker:/var/lib/docker:ro
+  #     - /var/lib/docker:/var/lib/docker:ro
-      - /cgroup:/cgroup:ro
+  #     - /cgroup:/cgroup:ro
-    restart: unless-stopped
+  #   restart: unless-stopped
-    ports:
+  #   ports:
-      - '8080:8080'
+  #     - '8080:8080'

docker-compose.yml

@@ -12,6 +12,7 @@ services:
     volumes:
       - influxdb_data:/var/lib/influxdb
       - ./influxdb/imports:/imports
+      - ./influxdb/config:/etc/influxdb/
 
 # Dashboard
   grafana:
@@ -36,8 +37,12 @@ services:
     # image: telegraf:latest #(for amd64)
     container_name: telegraf
     restart: unless-stopped
+    # for docker
+    hostname: ${HOSTNAME}
+    user: "telegraf:${DOCKER_GID}"
     volumes:
       - ./telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
+      - /var/run/docker.sock:/var/run/docker.sock
     depends_on:
       - influxdb
     links:
@@ -45,20 +50,21 @@ services:
     ports:
     - '8125:8125/udp'
 
-# containers metrics
+# # containers metrics
-  cadvisor:
+#   cadvisor:
-    image: gcr.io/cadvisor/cadvisor
+#     image: gcr.io/cadvisor/cadvisor
-    # + image arm64
+#     # + image arm64
-    container_name: cadvisor
+#     container_name: cadvisor
-    restart: unless-stopped
+#     restart: unless-stopped
-    volumes:
+#     volumes:
-      - /:/rootfs:ro
+#       - /:/rootfs:ro
-      - /var/run:/var/run:rw
+#       - /var/run:/var/run:rw
-      - /sys:/sys:ro
+#       - /sys:/sys:ro
-      - /var/lib/docker:/var/lib/docker:ro
+#       - /var/lib/docker:/var/lib/docker:ro
-      - /cgroup:/cgroup:ro
+#       - /cgroup:/cgroup:ro
-    ports:
+#     ports:
-      - '8080:8080'
+#       - '8080:8080'
+
 # gather metrics and launch alerts
   prometheus:
     image: prom/prometheus:v2.17.1
@@ -101,3 +107,4 @@ services:
 volumes:
   grafana_data: {}
   influxdb_data: {}
+  prometheus_data: {}

get-docker-id.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+DOCKER_GID=`stat -c '%g' /var/run/docker.sock`
+REPORT_HOSTNAME=`hostname`
+
+echo "DOCKER_GID=${DOCKER_GID}" >> ${SCRIPT_DIR}/.env
+echo "HOSTNAME=${HOSTNAME}" >> ${SCRIPT_DIR}/.env

influxdb/influxdb.conf

@@ -0,0 +1,15 @@
+[meta]
+  dir = "/var/lib/influxdb/meta"
+
+[data]
+  dir = "/var/lib/influxdb/data"
+  engine = "tsm1"
+  wal-dir = "/var/lib/influxdb/wal"
+
+[http]
+  enabled = true
+  bind-address = ":8086"
+  auth-enabled = true # Set to true
+  log-enabled = true
+  username = ""
+  password = ""

telegraf/telegraf.conf

@@ -70,8 +70,8 @@
   ## Write timeout (for the InfluxDB client), formatted as a string.
   ## If not provided, will default to 5s. 0s means no timeout (not recommended).
   timeout = "5s"
-  # username = "telegraf"
+  username = ""
-  # password = "metricsmetricsmetricsmetrics"
+  password = ""
   # Set the user agent for HTTP POSTs (can be useful for log differentiation)
   # user_agent = "telegraf"
   # Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
@@ -212,3 +212,76 @@
 
 [[inputs.linux_sysctl_fs]]
   # no configuration
+
+# Read metrics about docker containers
+[[inputs.docker]]
+  ## Docker Endpoint
+  ##   To use TCP, set endpoint = "tcp://[ip]:[port]"
+  ##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
+  endpoint = "unix:///var/run/docker.sock"
+
+  ## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
+  ## Note: configure this in one of the manager nodes in a Swarm cluster.
+  ## configuring in multiple Swarm managers results in duplication of metrics.
+  gather_services = false
+
+  ## Only collect metrics for these containers. Values will be appended to
+  ## container_name_include.
+  ## Deprecated (1.4.0), use container_name_include
+  #container_names = []
+
+  ## Set the source tag for the metrics to the container ID hostname, eg first 12 chars
+  source_tag = false
+
+  ## Containers to include and exclude. Collect all if empty. Globs accepted.
+  container_name_include = []
+  container_name_exclude = ["prometheus", "cadvisor", "grafana", "telegraf", "influxdb", "pushgateway"]
+
+  ## Container states to include and exclude. Globs accepted.
+  ## When empty only containers in the "running" state will be captured.
+  ## example: container_state_include = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+  ## example: container_state_exclude = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+  # container_state_include = []
+  # container_state_exclude = []
+
+  ## Timeout for docker list, info, and stats commands
+  timeout = "5s"
+
+  ## Whether to report for each container per-device blkio (8:0, 8:1...),
+  ## network (eth0, eth1, ...) and cpu (cpu0, cpu1, ...) stats or not.
+  ## Usage of this setting is discouraged since it will be deprecated in favor of 'perdevice_include'.
+  ## Default value is 'true' for backwards compatibility, please set it to 'false' so that 'perdevice_include' setting
+  ## is honored.
+  perdevice = true
+
+  ## Specifies for which classes a per-device metric should be issued
+  ## Possible values are 'cpu' (cpu0, cpu1, ...), 'blkio' (8:0, 8:1, ...) and 'network' (eth0, eth1, ...)
+  ## Please note that this setting has no effect if 'perdevice' is set to 'true'
+  # perdevice_include = ["cpu"]
+
+  ## Whether to report for each container total blkio and network stats or not.
+  ## Usage of this setting is discouraged since it will be deprecated in favor of 'total_include'.
+  ## Default value is 'false' for backwards compatibility, please set it to 'true' so that 'total_include' setting
+  ## is honored.
+  total = false
+
+  ## Specifies for which classes a total metric should be issued. Total is an aggregated of the 'perdevice' values.
+  ## Possible values are 'cpu', 'blkio' and 'network'
+  ## Total 'cpu' is reported directly by Docker daemon, and 'network' and 'blkio' totals are aggregated by this plugin.
+  ## Please note that this setting has no effect if 'total' is set to 'false'
+  # total_include = ["cpu", "blkio", "network"]
+
+  ## docker labels to include and exclude as tags.  Globs accepted.
+  ## Note that an empty array for both will include all labels as tags
+  docker_label_include = []
+  docker_label_exclude = []
+
+  ## Which environment variables should we use as a tag
+  #tag_env = ["JAVA_HOME", "HEAP_SIZE"]
+
+  ## Optional TLS Config
+  # tls_ca = "/etc/telegraf/ca.pem"
+  # tls_cert = "/etc/telegraf/cert.pem"
+  # tls_key = "/etc/telegraf/key.pem"
+  ## Use TLS but skip chain & host verification
+  # insecure_skip_verify = false