Add Telegraf Role

roles/telegraf/README.md

@@ -0,0 +1,56 @@
+Telegraf
+========
+
+An Ansible role to install, configure, and manage [Telegraf](https://github.com/influxdb/telegraf), the plugin-driven server agent for reporting metrics into InfluxDB.
+
+Requirements
+------------
+
+Prior knowledge/experience with InfluxDB and Telegraf is highly recommended. Full documentation is available [here](https://docs.influxdata.com).
+
+Installation
+------------
+
+Either clone this repository, or install through Ansible Galaxy directly using the command:
+
+```
+ansible-galaxy install rossmcdonald.telegraf
+```
+
+Role Variables
+--------------
+
+The high-level variables are stored in the `defaults/main.yml` file. The most important ones being:
+
+```
+# Channel of Telegraf to install (currently only 'stable' is supported)
+telegraf_install_version: stable
+```
+
+More advanced configuration options are stored in the `vars/main.yml` file, which includes all of the necessary bells and whistles to tweak your configuration.
+
+Dependencies
+------------
+
+No other Ansible dependencies are required. This role was tested and developed with Ansible 1.9.4.
+
+Example Playbook
+----------------
+
+An example playbook is included in the `test.yml` file. There is also a `Vagrantfile`, which can be used for quick local testing leveraging [Vagrant](https://www.vagrantup.com/).
+
+Contributions and Feedback
+--------------------------
+
+Any contributions are welcome. For any bugs or feature requests, please open an issue through Github.
+
+License
+-------
+
+MIT
+
+Author
+------
+
+Created by [Ross McDonald](https://github.com/rossmcdonald).
+

roles/telegraf/Vagrantfile

@@ -0,0 +1,40 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+
+Vagrant.configure(2) do |config|
+  config.vm.box = "ubuntu/trusty64"
+  # config.vm.box = "ubuntu/vivid64"
+  # config.vm.box = "relativkreativ/centos-7-minimal"
+  # config.vm.box = "box-cutter/fedora22"
+  # config.vm.box = "puppetlabs/centos-6.6-64-nocm"
+  # config.vm.box = "debian/jessie64"
+
+  BOX_COUNT = 1
+  (1..BOX_COUNT).each do |machine_id|
+    config.vm.define "telegraf#{machine_id}" do |machine|
+      machine.vm.hostname = "telegraf#{machine_id}"
+      # machine.vm.network "private_network", ip: "10.0.3.#{1+machine_id}", virtualbox__intnet: true
+      # machine.vm.network "public_network"
+      machine.vm.network "public_network", :bridge => 'en0: Wi-Fi (AirPort)'
+      
+      machine.vm.provider "virtualbox" do |v|
+        v.memory = 512
+        v.cpus = 1
+      end
+
+      if machine_id == BOX_COUNT
+        machine.vm.provision "ansible" do |ansible|
+          # ansible.verbose = 'vvvv'
+          ansible.limit = 'all'
+          ansible.playbook = "test.yml"
+          ansible.sudo = true
+          ansible.host_key_checking = false
+          ansible.extra_vars = {
+            is_vagrant: true,
+          }
+        end
+      end
+      
+    end
+  end
+end

roles/telegraf/defaults/main.yml

@@ -0,0 +1,85 @@
+---
+# Channel of Telegraf to install
+telegraf_install_version: stable
+
+# The user and group telegraf should run under (should be set to telegraf unless needed otherwise)
+telegraf_runas_user: telegraf
+telegraf_runas_group: telegraf
+
+# Configuration Template
+telegraf_configuration_template: telegraf.conf.j2
+
+# Configuration Variables
+telegraf_tags:
+telegraf_aws_tags: false
+telegraf_aws_tags_prefix:
+
+telegraf_agent_interval: 10s
+telegraf_round_interval: "true"
+telegraf_metric_batch_size: "1000"
+telegraf_metric_buffer_limit: "10000"
+
+telegraf_collection_jitter: 0s
+telegraf_flush_interval: 10s
+telegraf_flush_jitter: 0s
+telegraf_debug: "false"
+telegraf_quiet: "false"
+telegraf_hostname:
+telegraf_omit_hostname: "false"
+telegraf_install_url:
+
+
+telegraf_influxdb_url: http://stats.regensburg.freifunk.net:8086
+telegraf_influxdb_database: telegraf
+telegraf_influxdb_precision: s
+telegraf_influxdb_retention_policy: autogen
+telegraf_influxdb_write_consistency: any
+telegraf_influxdb_ssl_ca:
+telegraf_influxdb_ssl_cert:
+telegraf_influxdb_ssl_key:
+telegraf_influxdb_insecure_skip_verify:
+
+telegraf_influxdb_timeout: 5s
+telegraf_influxdb_username: telegraf
+telegraf_influxdb_password:
+telegraf_influxdb_user_agent:
+telegraf_influxdb_udp_payload:
+
+telegraf_plugins_base:
+  - name: swap
+  - name: processes
+  - name: kernel
+  - name: netstat
+  - name: mem
+  - name: system
+  - name: cpu
+    options:
+      percpu: "true"
+      totalcpu: "true"
+      collect_cpu_time: "false"
+      report_active: "false"
+      fielddrop:
+        - "time_*"
+  - name: disk
+    options:
+      mountpoints:
+        - "/"
+      ignore_fs:
+        - "tmpfs"
+        - "devtmpfs"
+        - "devfs"
+  - name: diskio
+    options:
+      skip_serial_number: "true"
+  - name: procstat
+    options:
+      exe: "influxd"
+      prefix: "influxdb"
+  - name: net
+    options:
+      interfaces:
+        - "eth0"
+
+telegraf_plugins: "{{ telegraf_plugins_base }} + {{ telegraf_plugins_extra | default([]) }}"
+
+telegraf_influxdata_base_url: "https://repos.influxdata.com"

roles/telegraf/handlers/main.yml

@@ -0,0 +1,30 @@
+---
+# The order here matters
+- name: restart telegraf
+  service:
+    name: telegraf
+    state: restarted
+  become: true
+  when: telegraf_start_service
+
+- name: pause
+  pause:
+    seconds: "{{ telegraf_start_delay }}"
+  when: telegraf_start_service
+
+## After version 2.2 of ansible 'listen' could be used to
+## group 'check status' and 'assert running' into a single listener
+- name: check status
+  command: service telegraf status
+  args:
+    warn: false
+  ignore_errors: yes
+  register: telegraf_service_status
+  become: true
+  when: telegraf_start_service
+
+- name: assert running
+  assert:
+    that:
+      - "telegraf_service_status.rc == 0"
+  when: telegraf_start_service

roles/telegraf/meta/main.yml

@@ -0,0 +1,24 @@
+---
+galaxy_info:
+  author: Ross McDonald
+  description: Install and configure Telegraf, the plugin-driven server agent for reporting metrics into InfluxDB
+  company: InfluxData
+  license: MIT
+  min_ansible_version: 1.2
+  platforms:
+    - name: EL
+      versions:
+        - 6
+        - 7
+    - name: Ubuntu
+      versions:
+        - trusty
+        - utopic
+        - vivid
+    - name: Debian
+      versions:
+        - jessie
+        - wheezy
+  categories:
+    - monitoring
+dependencies: []

roles/telegraf/tasks/configure.yml

@@ -0,0 +1,70 @@
+---
+- name: Retrieve ec2 facts
+  ec2_metadata_facts:
+  when: telegraf_aws_tags
+
+- name: Retrieve all ec2 tags on the instance
+  ec2_tag:
+    region: "{{ ansible_ec2_placement_region }}"
+    resource: "{{ ansible_ec2_instance_id }}"
+    state: list
+  when: telegraf_aws_tags
+  register: ec2_tags
+
+- name: get the rpm or apt package facts
+  package_facts:
+    manager: "auto"
+
+- name: Set templatized Telegraf configuration
+  template:
+    src: "{{ telegraf_configuration_template }}"
+    dest: "{{ telegraf_configuration_dir }}/telegraf.conf"
+    force: yes
+    backup: yes
+    owner: telegraf
+    group: telegraf
+    mode: 0744
+  when: telegraf_template_configuration
+  # If config changes, restart telegraf and confirm it remained running
+  notify:
+    - "restart telegraf"
+    - "pause"
+    - "check status"
+    - "assert running"
+
+- name: Test for sysvinit script
+  stat:
+    path: /etc/init.d/telegraf
+  register: telegraf_sysvinit_script
+
+- name: Modify user Telegraf should run as [sysvinit]
+  replace:
+    path: /etc/init.d/telegraf
+    regexp: USER=.*
+    replace: USER={{ telegraf_runas_user }}
+  when: telegraf_runas_user != "telegraf" and telegraf_sysvinit_script.stat.exists
+
+- name: Modify group Telegraf should run as [sysvinit]
+  replace:
+    path: /etc/init.d/telegraf
+    regexp: GROUP=.*
+    replace: GROUP={{ telegraf_runas_group }}
+  when: telegraf_runas_group != "telegraf" and telegraf_sysvinit_script.stat.exists
+
+- name: Create systemd service directory [systemd]
+  file:
+    path: /etc/systemd/system/telegraf.service.d
+    state: directory
+  when: telegraf_runas_user != "telegraf" and not telegraf_sysvinit_script.stat.exists
+
+- name: Modify user Telegraf should run as [systemd]
+  template:
+    src: systemd/system/telegraf.service.d/override.conf
+    dest: /etc/systemd/system/telegraf.service.d/override.conf
+  when: telegraf_runas_user != "telegraf" and not telegraf_sysvinit_script.stat.exists
+  register: telegraf_unit_file_updated
+
+- name: Reload systemd configuration [systemd]
+  systemd:
+    daemon_reload: yes
+  when: telegraf_unit_file_updated is defined and telegraf_unit_file_updated.changed

roles/telegraf/tasks/install-debian.yml

@@ -0,0 +1,55 @@
+---
+- name: Install any necessary dependencies [Debian/Ubuntu]
+  apt:
+    name:
+      - python-httplib2
+      - python-apt
+      - curl
+      - apt-transport-https
+    state: present
+    update_cache: yes
+    cache_valid_time: 3600
+  register: apt_result
+  until: apt_result is success
+  retries: 2
+  delay: 5
+
+- name: Import InfluxData GPG signing key [Debian/Ubuntu]
+  apt_key:
+    url: "{{ telegraf_influxdata_base_url }}/influxdb.key"
+    state: present
+  when: telegraf_install_url is not defined or telegraf_install_url == None
+
+- name: Add InfluxData repository [Debian/Ubuntu]
+  apt_repository:
+    repo: deb {{ telegraf_influxdata_base_url }}/{{ ansible_distribution | lower }} {{ ansible_distribution_release }} {{ telegraf_install_version }}
+    state: present
+  when: telegraf_install_url is not defined or telegraf_install_url == None
+
+- name: Install Telegraf packages [Debian/Ubuntu]
+  apt:
+    name: telegraf
+    state: latest
+    update_cache: yes
+    cache_valid_time: 3600
+  register: apt_result
+  until: apt_result is success
+  retries: 2
+  delay: 5
+  when: telegraf_install_url is not defined or telegraf_install_url == None
+
+- name: Download Telegraf package via URL [Debian/Ubuntu]
+  get_url:
+    url: "{{ telegraf_install_url }}"
+    dest: /tmp/telegraf-ansible-download.deb
+  when: telegraf_install_url is defined and telegraf_install_url != None
+
+- name: Install downloaded Telegraf package [Debian/Ubuntu]
+  apt:
+    deb: /tmp/telegraf-ansible-download.deb
+    state: present
+  register: apt_result
+  until: apt_result is success
+  retries: 2
+  delay: 5
+  when: telegraf_install_url is defined and telegraf_install_url != None

roles/telegraf/tasks/install-redhat.yml

@@ -0,0 +1,21 @@
+---
+- name: Add InfluxData repository file [RHEL/CentOS]
+  template:
+    src: etc/yum.repos.d/influxdata.repo.j2
+    dest: /etc/yum.repos.d/influxdata.repo
+    force: yes
+    backup: yes
+  when: telegraf_install_url is not defined or telegraf_install_url == None
+
+- name: Install Telegraf packages [RHEL/CentOS]
+  yum:
+    name: telegraf
+    state: latest
+    update_cache: yes
+  when: telegraf_install_url is not defined or telegraf_install_url == None
+
+- name: Install Telegraf from URL [RHEL/CentOS]
+  yum:
+    name: "{{ telegraf_install_url }}"
+    state: present
+  when: telegraf_install_url is defined and telegraf_install_url != None

roles/telegraf/tasks/install.yml

@@ -0,0 +1,6 @@
+---
+- include: install-redhat.yml
+  when: ansible_os_family == "RedHat"
+
+- include: install-debian.yml
+  when: ansible_os_family == "Debian"

roles/telegraf/tasks/main.yml

@@ -0,0 +1,10 @@
+---
+- include: install.yml
+  tags: [telegraf, install]
+
+- include: configure.yml
+  tags: [telegraf, configure]
+
+- include: start.yml
+  tags: [telegraf, start]
+  when: telegraf_start_service

roles/telegraf/tasks/start.yml

@@ -0,0 +1,12 @@
+---
+- name: Start the Telegraf service
+  service:
+    name: telegraf
+    state: started
+    enabled: yes
+  # Only care to check the status if the state changed to 'started'
+  notify:
+    - "pause"
+    - "check status"
+    - "assert running"
+  become: true

roles/telegraf/templates/etc/yum.repos.d/influxdata.repo.j2

@@ -0,0 +1,13 @@
+[influxdb]
+name = InfluxDB Repository - {{ ansible_distribution }} $releasever
+{% if ansible_distribution|lower == "amazon" %}
+baseurl = "{{ telegraf_influxdata_base_url }}/centos/6/amd64/{{ telegraf_install_version }}"
+{% elif ansible_distribution|lower == "redhat" %}
+baseurl = {{ telegraf_influxdata_base_url }}/rhel/$releasever/$basearch/{{ telegraf_install_version }}
+{% else %}
+baseurl = {{ telegraf_influxdata_base_url }}/{{ ansible_distribution|lower }}/$releasever/$basearch/{{ telegraf_install_version }}
+{% endif %}
+enabled = 1
+gpgcheck = 1
+gpgkey = {{ telegraf_influxdata_base_url }}/influxdb.key
+sslverify = 1

roles/telegraf/templates/systemd/system/telegraf.service.d/override.conf

@@ -0,0 +1,2 @@
+[Service]
+User={{ telegraf_runas_user }}

roles/telegraf/templates/telegraf.conf.j2

@@ -0,0 +1,181 @@
+# Telegraf configuration
+
+# Telegraf is entirely plugin driven. All metrics are gathered from the
+# declared plugins.
+
+# Even if a plugin has no configuration, it must be declared in here
+# to be active. Declaring a plugin means just specifying the name
+# as a section with no variables. To deactivate a plugin, comment
+# out the name and any variables.
+
+# Use 'telegraf -config telegraf.toml -test' to see what metrics a config
+# file would generate.
+
+# One rule that plugins conform to is wherever a connection string
+# can be passed, the values '' and 'localhost' are treated specially.
+# They indicate to the plugin to use their own builtin configuration to
+# connect to the local system.
+
+# NOTE: The configuration has a few required parameters. They are marked
+# with 'required'. Be sure to edit those to make this configuration work.
+
+# Tags can also be specified via a normal map, but only one form at a time:
+[global_tags]
+{% if telegraf_tags is defined and telegraf_tags != None %}
+{% for key, value in telegraf_tags.items()%}
+   {{ key }} = "{{ value }}"
+{% endfor %}
+{% endif %}
+{% if telegraf_aws_tags == true and ec2_tags is defined and ec2_tags != None %}
+{% for key, value in ec2_tags.tags.items()%}
+   {{ telegraf_aws_tags_prefix }}{{ key }} = "{{ value }}"
+{% endfor %}
+{% endif %}
+
+# Configuration for telegraf agent
+[agent]
+  ## Default data collection interval for all inputs
+  interval = "{{ telegraf_agent_interval }}"
+  ## Rounds collection interval to 'interval'
+  ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
+  round_interval = {{ telegraf_round_interval }}
+
+  ## Telegraf will send metrics to outputs in batches of at
+  ## most metric_batch_size metrics.
+  metric_batch_size = {{ telegraf_metric_batch_size }}
+  ## 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.
+  metric_buffer_limit = {{ telegraf_metric_buffer_limit }}
+
+  ## 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 = "{{ telegraf_collection_jitter }}"
+
+  ## Default flushing interval for all outputs. You shouldn't set this below
+  ## interval. Maximum flush_interval will be flush_interval + flush_jitter
+  flush_interval = "{{ telegraf_flush_interval }}"
+  ## 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 = "{{ telegraf_flush_jitter }}"
+
+  ## Run telegraf in debug mode
+  debug = {{ telegraf_debug }}
+  ## Run telegraf in quiet mode
+  quiet = {{ telegraf_quiet }}
+
+  hostname = "{{ ansible_fqdn }}"
+
+  ## If set to true, do no set the "host" tag in the telegraf agent.
+  omit_hostname = {{ telegraf_omit_hostname }}
+
+###############################################################################
+#                                  OUTPUTS                                    #
+###############################################################################
+
+[outputs]
+
+# Configuration for influxdb server to send metrics to
+[[outputs.influxdb]]
+  # The full HTTP or UDP endpoint URL for your InfluxDB instance.
+  # Multiple urls can be specified but it is assumed that they are part of the same
+  # cluster, this means that only ONE of the urls will be written to each interval.
+  # urls = ["udp://localhost:8089"] # UDP endpoint example
+  ## urls = [ "" ] # required
+  urls = ["{{ telegraf_influxdb_url }}"]
+  # The target database for metrics (telegraf will create it if not exists)
+  database = "{{ telegraf_influxdb_database }}" # required
+  # Precision of writes, valid values are n, u, ms, s, m, and h
+  # note: using second precision greatly helps InfluxDB compression
+  precision = "{{ telegraf_influxdb_precision }}"
+
+  ## Retention policy to write to.
+  retention_policy = "{{ telegraf_influxdb_retention_policy }}"
+  ## Write consistency (clusters only), can be: "any", "one", "quorom", "all"
+  write_consistency = "{{ telegraf_influxdb_write_consistency }}"
+
+  # Connection timeout (for the connection with InfluxDB), formatted as a string.
+  # If not provided, will default to 0 (no timeout)
+  timeout = "{{ telegraf_influxdb_timeout }}"
+{% if telegraf_influxdb_username is defined and telegraf_influxdb_username != None %}
+  username = "{{ telegraf_influxdb_username }}"
+{% endif %}
+  password = "{{ telegraf_influxdb_password }}"
+  # Set the user agent for HTTP POSTs (can be useful for log differentiation)
+{% if telegraf_influxdb_user_agent is defined and telegraf_influxdb_user_agent != None %}
+  user_agent = "{{ telegraf_influxdb_user_agent }}"
+{% endif %}
+  # Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
+{% if telegraf_influxdb_udp_payload is defined and telegraf_influxdb_udp_payload != None %}
+  udp_payload = {{ telegraf_influxdb_udp_payload }}
+{% endif %}
+
+  ## Optional SSL Config
+{% if telegraf_influxdb_ssl_ca is defined and telegraf_influxdb_ssl_ca != None %}
+  # ssl_ca = "{{ telegraf_influxdb_ssl_ca }}"
+{% endif %}
+{% if telegraf_influxdb_ssl_cert is defined and telegraf_influxdb_ssl_cert != None %}
+  # ssl_cert = "{{ telegraf_influxdb_ssl_cert }}"
+{% endif %}
+{% if telegraf_influxdb_ssl_key is defined and telegraf_influxdb_ssl_key != None %}
+  # ssl_key = "{{ telegraf_influxdb_ssl_key }}"
+{% endif %}
+
+{% if telegraf_influxdb_insecure_skip_verify is defined and telegraf_influxdb_insecure_skip_verify != None %}
+  ## Use SSL but skip chain & host verification
+  insecure_skip_verify = {{ telegraf_influxdb_insecure_skip_verify }}
+{% endif %}
+
+###############################################################################
+#                                  PLUGINS                                    #
+###############################################################################
+
+{% for plugin in telegraf_plugins %}
+[[inputs.{{ plugin.name }}]]
+{% if plugin.options is defined %}
+{% for key, value in plugin.options.items() %}
+{% if value is not mapping %}
+{% if value is sequence and value is not string %}
+{% if value[0] is number %}
+    {{ key }} = [ {{ value|join(', ') }} ]
+{% else %}
+    {{ key }} = [ "{{ value|join('", "') }}" ]
+{% endif %}
+{% else %}
+{% if value == "true" or value == "false" or value is number %}
+    {{ key }} = {{ value | lower }}
+{% else %}
+    {{ key }} = "{{ value }}"
+{% endif %}
+{% endif %}
+{% endif %}
+{% endfor %}
+{% for key, value in plugin.options.items() %}
+{% if value is mapping %}
+    [inputs.{{ plugin.name }}.{{ key }}]
+{% for lv2_key, lv2_value in value.items() %}
+{% if lv2_value is sequence and lv2_value is not string %}
+{% if lv2_value[0] is number %}
+      {{ lv2_key }} = [ {{ lv2_value|join(', ') }} ]
+{% else %}
+      {{ lv2_key }} = [ "{{ lv2_value|join('", "') }}" ]
+{% endif %}
+{% else %}
+{% if lv2_value == "true" or lv2_value == "false" or lv2_value is number %}
+      {{ lv2_key }} = {{ lv2_value | lower }}
+{% else %}
+      {{ lv2_key }} = "{{ lv2_value }}"
+{% endif %}
+{% endif %}
+{% endfor %}
+{% endif %}
+{% endfor %}
+{% endif %}
+{% endfor %}
+
+###############################################################################
+#                              service PLUGINS                                #
+###############################################################################

roles/telegraf/test.yml

@@ -0,0 +1,8 @@
+- hosts: all
+  vars_files:
+    - defaults/main.yml
+    - vars/main.yml
+  tasks:
+    - include: tasks/main.yml
+  handlers:
+    - include: handlers/main.yml

roles/telegraf/vars/main.yml

@@ -0,0 +1,16 @@
+---
+
+# Whether or not the playbook is run locally
+# This should only be set in the Vagrantfile and not modified elsewhere
+is_vagrant: no
+
+# If yes, service will be started. Will not be started if set to no.
+telegraf_start_service: yes
+telegraf_start_delay: 6
+
+# If yes, will overwrite the packaged configuration with an Asnible/jinja2 template
+telegraf_template_configuration: yes
+
+# Path for finding Telegraf data. Added for backwards-compatibility.
+telegraf_binary_path: /usr/bin/telegraf
+telegraf_configuration_dir: /etc/telegraf