Add telegraf

And input to ping and output via prometheus

ansible/roles/forrest/files/docker-compose-telegraf.yml

@@ -0,0 +1,15 @@
+version: "2.3"
+
+services:
+  telegraf:
+    image: telegraf:alpine
+    restart: unless-stopped
+    networks:
+      - default
+      - prometheus
+    volumes:
+      - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
+
+networks:
+  prometheus:
+    external: true

ansible/roles/forrest/files/prometheus.yml

@@ -0,0 +1,5 @@
+scrape_configs:
+  - job_name: telegraf
+    static_configs:
+      - targets:
+          - telegraf:9273

ansible/roles/forrest/files/telegraf.conf

@@ -0,0 +1,98 @@
+# Global tags can be specified here in key="value" format.
+[global_tags]
+  # dc = "us-east-1" # will tag all metrics with dc=us-east-1
+  # rack = "1a"
+  ## Environment variables can be used as tags, and throughout the config file
+  # user = "$USER"
+
+
+# Configuration for telegraf agent
+[agent]
+  ## Default data collection interval for all inputs
+  interval = "60s"
+  ## 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
+
+  ## Maximum number of unwritten metrics per output.  Increasing this value
+  ## allows for longer periods of output downtime without dropping metrics at the
+  ## cost of higher maximum memory usage.
+  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 = ""
+
+  ## Log at debug level.
+  # debug = false
+  ## Log only error level messages.
+  # quiet = false
+
+  ## Log target controls the destination for logs and can be one of "file",
+  ## "stderr" or, on Windows, "eventlog".  When set to "file", the output file
+  ## is determined by the "logfile" setting.
+  # logtarget = "file"
+
+  ## Name of the file to be logged to when using the "file" logtarget.  If set to
+  ## the empty string then logs are written to stderr.
+  # logfile = ""
+
+  ## The logfile will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.  Logs are rotated only when
+  ## written to, if there is no log activity rotation may be delayed.
+  # logfile_rotation_interval = "0d"
+
+  ## The logfile will be rotated when it becomes larger than the specified
+  ## size.  When set to 0 no size based rotation is performed.
+  # logfile_rotation_max_size = "0MB"
+
+  ## Maximum number of rotated archives to keep, any older logs are deleted.
+  ## If set to -1, no archives are removed.
+  # logfile_rotation_max_archives = 5
+
+  ## Override default hostname, if empty use os.Hostname()
+  hostname = "{{ ansible_fqdn }}"
+  ## If set to true, do no set the "host" tag in the telegraf agent.
+  omit_hostname = false
+
+
+###############################################################################
+#                            OUTPUT PLUGINS                                   #
+###############################################################################
+
+[[outputs.prometheus_client]]
+  listen = ":9273"
+  metric_version = 2
+
+
+###############################################################################
+#                            INPUT PLUGINS                                    #
+###############################################################################
+
+[[inputs.ping]]
+  urls = ["192.168.1.1", "1.1.1.1"]
+  ping_interval = 60.0

ansible/roles/forrest/handlers/main.yml

@@ -12,3 +12,8 @@
   shell:
     chdir: /opt/prometheus
     cmd: "{{ docker_update_command }}"
+
+- name: restart telegraf
+  shell:
+    chdir: /opt/telegraf
+    cmd: "{{ docker_update_command }}"

ansible/roles/forrest/tasks/main.yml

@@ -6,3 +6,6 @@
 
 - name: Prometheus
   include: prometheus.yml
+
+- name: Telegraf
+  include: telegraf.yml

ansible/roles/forrest/tasks/prometheus.yml

@@ -10,6 +10,15 @@
     mode: "{{ docker_compose_directory_mask }}"
   become: true
 
+- name: Install prometheus config
+  template:
+    src: files/prometheus.yml
+    dest: /opt/prometheus/prometheus.yml
+    mode: "{{ docker_compose_file_mask }}"
+    owner: "{{ docker_user.name }}"
+  notify: restart prometheus
+  become: true
+
 - name: Install prometheus compose file
   template:
     src: files/docker-compose-prometheus.yml

ansible/roles/forrest/tasks/telegraf.yml

@@ -0,0 +1,26 @@
+- name: Create telegraf install directory
+  file:
+    path: /opt/telegraf
+    state: directory
+    owner: "{{ docker_user.name }}"
+    mode: "{{ docker_compose_directory_mask }}"
+  become: true
+
+- name: Install telegraf config
+  template:
+    src: files/telegraf.conf
+    dest: /opt/telegraf/telegraf.conf
+    mode: "{{ docker_compose_file_mask }}"
+    owner: "{{ docker_user.name }}"
+  notify: restart telegraf
+  become: true
+
+- name: Install telegraf compose file
+  template:
+    src: files/docker-compose-telegraf.yml
+    dest: /opt/telegraf/docker-compose.yml
+    mode: "{{ docker_compose_file_mask }}"
+    owner: "{{ docker_user.name }}"
+    validate: docker-compose -f %s config
+  notify: restart telegraf
+  become: true