Update config

.env

@@ -1,2 +0,0 @@
-GF_SECURITY_ADMIN_USER=admin
-GF_SECURITY_ADMIN_PASSWORD=adminpass

.gitignore

@@ -1,4 +1,6 @@
 data/*
 
+data/grafana
 !data/grafana/grafana.ini
+data/telegra
 !data/telegraf/telegraf.conf

clean.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+sudo rm -rf ./data/grafana/data
+sudo rm -rf ./data/grafana/provisioning
+mkdir -p ./data/grafana/data
+chmod 757 ./data/grafana/data
+
+sudo rm -rf ./data/influxdb/data

data/telegraf/telegraf.conf

@@ -0,0 +1,143 @@
+# Configuration for telegraf agent
+[agent]
+  ## Default data collection interval for all inputs
+  interval = "10s"
+  ## Rounds collection interval to 'interval'
+  ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
+  round_interval = true
+
+  ## Telegraf will send metrics to outputs in batches of at most
+  ## metric_batch_size metrics.
+  ## This controls the size of writes that Telegraf sends to output plugins.
+  metric_batch_size = 1000
+
+  ## For failed writes, telegraf will cache metric_buffer_limit metrics for each
+  ## output, and will flush this buffer on a successful write. Oldest metrics
+  ## are dropped first when this buffer fills.
+  ## This buffer only fills when writes fail to output plugin(s).
+  metric_buffer_limit = 10000
+
+  ## Collection jitter is used to jitter the collection by a random amount.
+  ## Each plugin will sleep for a random time within jitter before collecting.
+  ## This can be used to avoid many plugins querying things like sysfs at the
+  ## same time, which can have a measurable effect on the system.
+  collection_jitter = "0s"
+
+  ## Default flushing interval for all outputs. Maximum flush_interval will be
+  ## flush_interval + flush_jitter
+  flush_interval = "10s"
+  ## Jitter the flush interval by a random amount. This is primarily to avoid
+  ## large write spikes for users running a large number of telegraf instances.
+  ## ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
+  flush_jitter = "0s"
+
+  ## By default or when set to "0s", precision will be set to the same
+  ## timestamp order as the collection interval, with the maximum being 1s.
+  ##   ie, when interval = "10s", precision will be "1s"
+  ##       when interval = "250ms", precision will be "1ms"
+  ## Precision will NOT be used for service inputs. It is up to each individual
+  ## service input to set the timestamp at the appropriate precision.
+  ## Valid time units are "ns", "us" (or "µs"), "ms", "s".
+  precision = ""
+
+  ## Logging configuration:
+  ## Run telegraf with debug log messages.
+  debug = false
+  ## Run telegraf in quiet mode (error log messages only).
+  quiet = false
+  ## Specify the log file name. The empty string means to log to stderr.
+  logfile = ""
+
+  ## Override default hostname, if empty use os.Hostname()
+  hostname = ""
+  ## If set to true, do no set the "host" tag in the telegraf agent.
+  omit_hostname = false
+
+[[outputs.influxdb_v2]]
+  ## The URLs of the InfluxDB cluster nodes.
+  ##
+  ## Multiple URLs can be specified for a single cluster, only ONE of the
+  ## urls will be written to each interval.
+  ## urls exp: http://127.0.0.1:8086
+  urls = ["http://influxdb:8086"]
+
+  ## Token for authentication.
+  token = "2uY3YEm_n1jw1BLnPV0TL-xdF3xYEZwy85bMdry_fOQhOWoVc99jrwEf5N2PkeQec0ELCt8xMpgVc0EyXCCp2A=="
+
+  ## Organization is the name of the organization you wish to write to; must exist.
+  organization = "awin"
+
+  ## Destination bucket to write into.
+  bucket = "main"
+
+# Read metrics about cpu usage
+[[inputs.cpu]]
+  ## Whether to report per-cpu stats or not
+  percpu = true
+  ## Whether to report total system cpu stats or not
+  totalcpu = true
+  ## If true, collect raw CPU time metrics
+  collect_cpu_time = false
+  ## If true, compute and report the sum of all non-idle CPU states
+  report_active = false
+  ## If true and the info is available then add core_id and physical_id tags
+  core_tags = false
+
+[[inputs.disk]]
+  ## By default stats will be gathered for all mount points.
+  ## Set mount_points will restrict the stats to only the specified mount points.
+  # mount_points = ["/"]
+  ## Ignore mount points by filesystem type.
+  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "overlay", "aufs", "squashfs"]
+
+[[inputs.diskio]]
+
+[[inputs.mem]]
+
+[[inputs.net]]
+
+[[inputs.processes]]
+
+[[inputs.swap]]
+
+[[inputs.system]]
+
+[[inputs.docker]]
+  ## Docker Endpoint
+  ##   To use TCP, set endpoint = "tcp://[ip]:[port]"
+  ##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
+  ##   exp: unix:///var/run/docker.sock
+  endpoint = "unix:///var/run/docker.sock"
+
+  ## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
+  gather_services = false
+
+  ## Only collect metrics for these containers, collect all if empty
+  container_names = []
+
+  ## Containers to include and exclude. Globs accepted.
+  ## Note that an empty array for both will include all containers
+  container_name_include = []
+  container_name_exclude = []
+
+  ## Container states to include and exclude. Globs accepted.
+  ## When empty only containers in the "running" state will be captured.
+  # 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...) and
+  ## network (eth0, eth1, ...) stats or not
+  perdevice = true
+
+  ## Whether to report for each container total blkio and network stats or not
+  total = false
+
+  ## Which environment variables should we use as a tag
+  ##tag_env = ["JAVA_HOME", "HEAP_SIZE"]
+  ## 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 = []

docker-compose.yml

@@ -7,12 +7,50 @@ services:
     restart: always
     user: "1000" # needs to be `id -u` // alternatively chown the grafana/data dir to 472:472
     ports:
-      - "3000:3000" # expose for localhost
+      - "8081:3000" # expose for localhost
+    links:
+      - influxdb
     volumes:
-      - $HOME/docker/grafana/data:/var/lib/grafana # data path
-      - $HOME/docker/grafana/grafana.ini:/etc/grafana/grafana.ini
-      - $HOME/docker/grafana/provisioning:/etc/grafana/provisioning
+      - ./data/grafana/data:/var/lib/grafana # data path
+      - ./data/grafana/provisioning:/etc/grafana/provisioning
+      - ./data/grafana/grafana.ini:/etc/grafana/grafana.ini
     environment:
       - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
-      - GF_SECURITY_ADMIN_USER=${GF_SECURITY_ADMIN_USER}
-      - GF_SECURITY_ADMIN_PASSWORD=${GF_SECURITY_ADMIN_PASSWORD}
+      # - GF_SECURITY_ADMIN_USER=admin
+      # - GF_SECURITY_ADMIN_PASSWORD=adminpass
+
+  influxdb:
+    image: influxdb
+    ports:
+      - "8082:8086"
+    volumes:
+      - ./data/influxdb/data:/var/lib/influxdb2
+    # environment:
+    #   - INFLUXDB_DB=main
+    #   - DOCKER_INFLUXDB_INIT_MODE=setup
+    #   - DOCKER_INFLUXDB_INIT_USERNAME=admin
+    #   - DOCKER_INFLUXDB_INIT_PASSWORD=adminpass
+    #   - DOCKER_INFLUXDB_INIT_ORG=awin
+    #   - DOCKER_INFLUXDB_INIT_BUCKET=main
+
+  telegraf:
+    image: telegraf
+    user: telegraf:992
+    depends_on:
+      - influxdb
+    links:
+      - influxdb
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./data/telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
+    environment:
+      - HOST_PROC=/proc
+      - HOST_SYS=/sys
+      - HOST_ETC=/etc
+    #   - HOST_ETC=/hostfs/etc
+    #   - HOST_PROC=/hostfs/proc
+    #   - HOST_SYS=/hostfs/sys
+    #   - HOST_VAR=/hostfs/var
+    #   - HOST_RUN=/hostfs/run
+    #   - HOST_MOUNT_PREFIX=/hostfs
+