first commit

README.md

@@ -0,0 +1,47 @@
+Openstack-Ansible Telegraf
+==========================
+
+This role is used to create and manage telegraf in an openstack-ansible-based deployment.
+
+Requirements
+------------
+
+An openstack-ansible deployment is required.
+
+Role Variables
+--------------
+
+By default, the role does not configure any output. The available choices are Graphite / InfluxDB over AMQP or InfluxDB.
+
+Dependencies
+------------
+
+None.
+
+Example Playbook
+----------------
+
+Including an example of how to use your role (for instance, with variables passed in as parameters) is always nice for users too:
+
+    - hosts: all
+      gather_facts: "{{ gather_facts | default(True) }}"
+      user: root
+      roles:
+         - { role: ansible-telegraf }
+      vars:
+         telegraf_output: amqp
+         telegraf_output_amqp_user: metrics
+         telegraf_output_amqp_password: secret # should be in user_secrets.yml
+         telegraf_output_amqp_server: my-mq.local
+         telegraf_output_amqp_vhost: /
+         telegraf_output_amqp_url: "amqp://{{ telegraf_output_amqp_user }}:{{ telegraf_output_amqp_password }}@{{ telegraf_output_amqp_server }}:5672/{{ telegraf_output_amqp_vhost }}"
+
+License
+-------
+
+GPL-3+
+
+Author Information
+------------------
+
+Mathieu GRZYBEK

defaults/main.yml

@@ -0,0 +1,51 @@
+---
+
+influxdb_repo_root: https://repos.influxdata.com
+influxdb_repo_key: https://repos.influxdata.com/influxdb.key
+
+telegraf_server_package_state: latest
+cache_timeout: 600
+
+telegraf_global_tags_dc: None
+telegraf_global_tags_rack: None
+telegraf_global_tags_add_node_type: false
+
+telegraf_agent_interval: 60
+
+telegraf_metric_batch_size: 1024
+telegraf_metric_buffer_limit: 10240
+telegraf_collection_jitter: 8s
+
+telegraf_output: amqp # influxdb
+telegraf_output_amqp_url: None
+telegraf_output_amqp_exchange: None
+telegraf_output_amqp_auth_method: PLAIN
+telegraf_output_amqp_routing_tag: field
+telegraf_output_amqp_data_format: graphite
+telegraf_output_amqp_template: host.measurement.tags.field
+
+telegraf_output_influxdb_targets:
+  - "http://localhost:8086"
+
+telegraf_output_influxdb_database: telegraf
+telegraf_output_influxdb_retention_policy:
+telegraf_output_influxdb_write_consistency: any # any, one, quorum, all
+telegraf_output_influxdb_timeout: 5s
+telegraf_output_influxdb_username: None
+telegraf_output_influxdb_password: None
+telegraf_output_influxdb_user_agent: telegraf
+telegraf_output_influxdb_udp_payload: 512
+telegraf_output_influxdb_ssl_ca:
+telegraf_output_influxdb_ssl_cert:
+telegraf_output_influxdb_ssl_key:
+telegraf_output_influxdb_insecure_skip_verify: false
+telegraf_output_influxdb_http_proxy: None
+telegraf_output_influxdb_http_headers_key: None
+telegraf_output_influxdb_http_headers_value: None
+
+telegraf_openstack_scripts:
+  - glance-stats.sh
+  - hypervisors-stats.sh
+  - instances-stats.sh
+  - neutron-stats.sh
+  - usage-stats.sh

files/glance-stats.sh

@@ -0,0 +1,7 @@
+#! /usr/bin/env bash
+
+source /root/openrc
+
+# Number of images in the catalog
+openstack image list -c ID -f value|wc -l|awk '{print "openstack.images.available "$1,systime()}'
+

files/hypervisors-stats.sh

@@ -0,0 +1,7 @@
+#! /usr/bin/env bash
+
+source /root/openrc
+
+# Usage of the whole compute nodes
+openstack hypervisor stats show -f shell --prefix openstack.hypervisors.usage.total.|gawk '{gsub("\"","") ; gsub("="," ") ; print $0,systime()}'
+

files/instances-stats.sh

@@ -0,0 +1,13 @@
+#! /usr/bin/env bash
+
+source /root/openrc
+
+# Number of instances per tenant
+for tenant in $(openstack project list --format=value|tr ' ' ':') ; do
+	tenant_id=$(echo $tenant|awk -F: '{print $1}')
+	tenant_name=$(echo $tenant|awk -F: '{print $2}')
+
+	instances=$(openstack server list --project $tenant_id --format value -c ID|wc -l)
+	echo "openstack.tenants.$tenant_name.instances $instances" | gawk '{print $0" "systime()}'
+done
+

files/neutron-stats.sh

@@ -0,0 +1,32 @@
+#! /usr/bin/env bash
+
+source /root/openrc
+
+# TODO: Public IPs usage
+# openstack floating ip list
+
+# TODO: Public IPs usage per tenant
+# openstack.tenants.ID.floating_ips.available
+# openstack.tenants.ID.floating_ips.used
+
+for tenant in $(openstack project list --format=value|tr ' ' ':') ; do
+        tenant_id=$(echo $tenant|awk -F: '{print $1}')
+        tenant_name=$(echo $tenant|awk -F: '{print $2}')
+
+	# Network usage rate per tenant
+	for net in $(openstack network list --column ID --format value --project $tenant_id) ; do
+		openstack ip availability show $net --format=yaml -c network_name -c total_ips -c used_ips | \
+			awk '{gsub(": ", "=") ; print}'| \
+			tr '\n' ' '| \
+			gawk '{print $0,systime()}' | \
+			perl -ne '/network_name=(\w+) total_ips=(\d+) used_ips=(\d+)  (\d+)/ ; print("$1.total_ips $2 $4\n$1.used_ips $3 $4\n")' | \
+			perl -pe "s/^/openstack.tenants.$tenant_name.networks./"
+	done
+
+	# Number of security groups per tenant
+	echo -n openstack.tenants.$tenant_name.
+	openstack security group list -c Project --format value --project $tenant_id| wc -l | gawk '{print "security-groups.number "$1" "systime()}'
+done
+
+
+

files/usage-stats.sh

@@ -0,0 +1,8 @@
+#! /usr/bin/env bash
+
+source /root/openrc
+
+# Get general usage stats (4 weeks by default)
+openstack usage list --format csv | \
+	fgrep -v Project | \
+	gawk -F, '{gsub("\"","") ; print "openstack.tenants."$1".usage.instances "$2,systime()"\nopenstack.tenants."$1".usage.ram-mb-hours "$3,systime()"\nopenstack.tenants."$1".usage.cpu-hours "$4,systime()"\nopenstack.tenants."$1".usage.disks-gb-hours "$5,systime()}'

files/user.conf

@@ -0,0 +1,3 @@
+# Ansible managed
+[Service]
+User=root

handlers/main.yml

@@ -0,0 +1,11 @@
+---
+
+- name: restart telegraf
+  service:
+    name: telegraf
+    state: restarted
+
+- name: reload systemd
+  shell: systemctl daemon-reload
+  notify: restart telegraf
+

meta/main.yml

@@ -0,0 +1,64 @@
+galaxy_info:
+  author: Mathieu GRZYBEK
+  description: Telegraf client installation
+  company: Gendarmerie Nationale
+
+  # If the issue tracker for your role is not on github, uncomment the
+  # next line and provide a value
+  # issue_tracker_url: http://example.com/issue/tracker
+
+  # Some suggested licenses:
+  # - BSD (default)
+  # - MIT
+  # - GPLv2
+  # - GPLv3
+  # - Apache
+  # - CC-BY
+  license: GPLv3
+
+  min_ansible_version: 2.3
+
+  # If this a Container Enabled role, provide the minimum Ansible Container version.
+  # min_ansible_container_version:
+
+  # Optionally specify the branch Galaxy will use when accessing the GitHub
+  # repo for this role. During role install, if no tags are available,
+  # Galaxy will use this branch. During import Galaxy will access files on
+  # this branch. If Travis integration is configured, only notifications for this
+  # branch will be accepted. Otherwise, in all cases, the repo's default branch
+  # (usually master) will be used.
+  #github_branch:
+
+  #
+  # platforms is a list of platforms, and each platform has a name and a list of versions.
+  #
+  # platforms:
+  # - name: Fedora
+  #   versions:
+  #   - all
+  #   - 25
+  # - name: SomePlatform
+  #   versions:
+  #   - all
+  #   - 1.0
+  #   - 7
+  #   - 99.99
+
+  galaxy_tags: []
+    # List tags for your role here, one per line. A tag is a keyword that describes
+    # and categorizes the role. Users find roles by searching for tags. Be sure to
+    # remove the '[]' above, if you add tags to this list.
+    #
+    # NOTE: A tag is limited to a single word comprised of alphanumeric characters.
+    #       Maximum 20 tags per role.
+
+  categories:
+    - client
+    - telegraf
+    - monitoring
+    - metrics
+    - openstack
+
+dependencies: []
+  # List your role dependencies here, one per line. Be sure to remove the '[]' above,
+  # if you add dependencies to this list.

tasks/main.yml

@@ -0,0 +1,25 @@
+---
+# tasks file for metrics
+
+- name: Gather variables for each operating system
+  include_vars: "{{ item }}"
+  with_first_found:
+    - "{{ ansible_distribution | lower }}-{{ ansible_distribution_version | lower }}.yml"
+    - "{{ ansible_distribution | lower }}-{{ ansible_distribution_major_version | lower }}.yml"
+    - "{{ ansible_os_family | lower }}-{{ ansible_distribution_major_version | lower }}.yml"
+    - "{{ ansible_distribution | lower }}.yml"
+    - "{{ ansible_os_family | lower }}.yml"
+  tags:
+    - always
+
+- include: telegraf_pre_install.yml
+  tags:
+    - telegraf-install
+
+- include: telegraf_install.yml
+  tags:
+    - telegraf-install
+
+- include: telegraf_post_install.yml
+  tags:
+    - telegraf-install

tasks/telegraf_install.yml

@@ -0,0 +1,15 @@
+- name: Install telegraf packages
+  package:
+    name: "{{ telegraf_distro_packages }}"
+    state: "{{ telegraf_package_state }}"
+    update_cache: "{{ (ansible_pkg_mgr == 'apt') | ternary('yes', omit) }}"
+    cache_valid_time: "{{ (ansible_pkg_mgr == 'apt') | ternary(cache_timeout, omit) }}"
+  register: install_packages
+  until: install_packages | success
+  retries: 5
+  delay: 2
+  tags:
+    - install-apt
+    - install-yum
+    - install-zypper
+

tasks/telegraf_post_install.yml

@@ -0,0 +1,71 @@
+- name: Telegraf basic setup
+  template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: "root"
+    group: "root"
+  with_items:
+    - { src: "telegraf.conf.j2", dest: "/etc/telegraf/telegraf.conf" }
+    - { src: "system.conf.j2", dest: "/etc/telegraf/telegraf.d/system.conf" }
+    - { src: "processes.conf.j2", dest: "/etc/telegraf/telegraf.d/processes.conf" }
+    - { src: "cgroup.conf.j2", dest: "/etc/telegraf/telegraf.d/cgroup.conf" }
+    - { src: "output.conf.j2", dest: "/etc/telegraf/telegraf.d/output.conf" }
+  tags:
+    - client-config
+  notify:
+    - restart telegraf
+
+- include: telegraf_post_install_net.yml
+
+- name: Telegraf setup for physical hosts
+  template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: "root"
+    group: "root"
+  with_items:
+    - { src: "ipmi.conf.j2", dest: "/etc/telegraf/telegraf.d/ipmi.conf" }
+  when: ansible_virtualization_role == 'host'
+  tags:
+    - client-config
+  notify:
+    - restart telegraf
+
+- name: Telegraf privileges on physical or haproxy hosts (systemd custom directory)
+  file:
+    path: /etc/systemd/system/telegraf.service.d
+    state: directory
+  when: ansible_virtualization_role == 'host' or inventory_hostname in groups['haproxy']
+  tags:
+    - client-config
+  notify:
+    - restart telegraf
+
+- name: Telegraf privileges on physical or haproxy hosts (systemd custom file)
+  copy:
+    src: user.conf
+    dest: /etc/systemd/system/telegraf.service.d/user.conf
+  when: ansible_virtualization_role == 'host' or inventory_hostname in groups['haproxy']
+  tags:
+    - client-config
+  notify:
+    - reload systemd
+    - restart telegraf
+
+- include: telegraf_post_install_rabbitmq.yml
+  when: inventory_hostname in groups['rabbitmq']
+
+- include: telegraf_post_install_galera.yml
+  when: inventory_hostname in groups['galera']
+
+- include: telegraf_post_install_haproxy.yml
+  when: inventory_hostname in groups['haproxy'] or inventory_hostname in groups['network_all']
+
+- include: telegraf_post_install_utility.yml
+  when: inventory_hostname in groups['utility']
+
+- include: telegraf_post_install_swift.yml
+  when: inventory_hostname in groups['swift-proxy_containers']
+
+- name: Enable Telegraf at boot time
+  service: name=telegraf enabled=true

tasks/telegraf_post_install_galera.yml

@@ -0,0 +1,13 @@
+- name: Telegraf configuration for Galera
+  template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: "root"
+    group: "root"
+  with_items:
+    - { src: "mariadb.conf.j2", dest: "/etc/telegraf/telegraf.d/mariadb.conf" }
+  tags:
+    - telegraf_client-config
+  notify:
+    - restart telegraf
+