13 Commits

20 changed files with 197 additions and 132 deletions

View File

@ -11,6 +11,9 @@ metrics or alerting.
alertmanager for receiving alerts from prometheus and routing them
to the correct configured receivers.
- [`cadvisor`](roles/cadvisor/README.md): Run and configure cAdvisor, googles'
container performance and resource usage collection and aggregation daemon.
- [`grafana`](roles/grafana/README.md): a popular visualization and
dashboard creation tool able to use various datasources.

View File

@ -1,6 +1,6 @@
namespace: finallycoffee
name: observability
version: 0.1.1
version: 0.1.3
readme: README.md
authors:
- transcaffeine <transcaffeine@finally.coffee>

View File

@ -0,0 +1,8 @@
---
alertmanager_config_global: {}
alertmanager_config_route: {}
alertmanager_config_receivers: []
alertmanager_config:
global: "{{ alertmanager_config_global }}"
route: "{{ alertmanager_config_route }}"
receivers: "{{ alertmanager_config_receivers }}"

View File

@ -8,8 +8,3 @@ alertmanager_config_path: "{{ alertmanager_base_path }}/config"
alertmanager_config_file: "{{ alertmanager_config_path }}/alertmanager.yml"
alertmanager_data_path: "{{ alertmanager_base_path }}/data"
alertmanager_config:
global: {}
route: {}
receivers: []

View File

@ -1,52 +0,0 @@
---
cadvisor_version: 0.49.1
cadvisor_container_name: cadvisor
cadvisor_container_image_name: gcr.io/cadvisor/cadvisor
cadvisor_container_image_tag: ~
cadvisor_container_image_ref: >-
{{ cadvisor_container_image_name }}:{{ cadvisor_container_image_tag | default('v' + cadvisor_version, True) }}
cadvisor_container_volumes: >-
{{ cadvisor_container_base_volumes + cadvisor_container_extra_volumes | default([], True) }}
cadvisor_container_extra_volumes: ~
cadvisor_container_env: ~
cadvisor_container_labels: "{{ cadvisor_container_base_labels | combine(cadvisor_container_extra_labels) }}"
cadvisor_container_extra_labels: {}
cadvisor_container_ports: ~
cadvisor_container_networks: ~
cadvisor_container_etc_hosts: ~
cadvisor_container_devices: [ "/dev/kmsg:/dev/kmsg:rwm" ]
cadvisor_container_privileged: yes
cadvisor_container_pid_mode: "host"
cadvisor_container_userns_mode: "host"
cadvisor_container_capabilities: ~
cadvisor_container_restart_policy: unless-stopped
cadvisor_container_command: >-2
{{ ["--docker_only=false"]
+ (["--disable_metrics=" + cadvisor_disabled_metrics | join( ',' )]
if cadvisor_disabled_metrics | default(false, True) else [])
+ (["--enable_metrics=" + cadvisor_force_enable_metrics | join( ',' )]
if cadvisor_force_enable_metrics | default(false, True) else [])
}}
cadvisor_container_base_labels:
version: "{{ cadvisor_version }}"
cadvisor_container_base_volumes:
- "/:/rootfs:ro"
- "/var/run:/var/run:ro"
- "/sys:/sys:ro"
- "/var/lib/docker/:/var/lib/docker:ro"
- "/dev/disk/:/dev/disk:ro"
cadvisor_disabled_metrics:
- advtcp
- cpu_topology
- cpuset
- hugetlb
- memory_numa
- process
- referenced_memory
- resctrl
- sched
- tcp
- udp
cadvisor_force_enable_metrics: []

View File

@ -0,0 +1,56 @@
---
cadvisor_container_image_registry: gcr.io
cadvisor_container_image_namespace: cadvisor
cadvisor_container_image_name: cadvisor
cadvisor_container_image: >-2
{{
[
cadvisor_container_image_registry,
cadvisor_container_image_namespace,
cadvisor_container_image_name,
] | flatten | join('/')
}}
cadvisor_container_image_tag: ~
cadvisor_container_image_ref: >-2
{{ cadvisor_container_image }}:{{ cadvisor_container_image_tag | default('v' + cadvisor_version, true) }}
cadvisor_container_image_source: pull
cadvisor_container_image_force_source: >-2
{{ cadvisor_container_image_tag | default(false, true) | bool }}
cadvisor_container_state: >-2
{{ (cadvisor_state == 'present') | ternary('started', 'absent') }}
cadvisor_container_name: cadvisor
cadvisor_container_volumes: >-2
{{ cadvisor_container_base_volumes + cadvisor_container_extra_volumes | default([], true) }}
cadvisor_container_extra_volumes: ~
cadvisor_container_env: ~
cadvisor_container_labels: >-2
{{ cadvisor_container_base_labels | combine(cadvisor_container_extra_labels) }}
cadvisor_container_extra_labels: {}
cadvisor_container_ports: ~
cadvisor_container_networks: ~
cadvisor_container_etc_hosts: ~
cadvisor_container_devices:
- "/dev/kmsg:/dev/kmsg:rwm"
cadvisor_container_privileged: true
cadvisor_container_pid_mode: "host"
cadvisor_container_userns_mode: "host"
cadvisor_container_capabilities: ~
cadvisor_container_restart_policy: "unless-stopped"
cadvisor_container_command: >-2
{{ ["--docker_only=false"]
+ (["--disable_metrics=" + cadvisor_disabled_metrics | join( ',' )]
if cadvisor_disabled_metrics | default(false, true) else [])
+ (["--enable_metrics=" + cadvisor_force_enable_metrics | join( ',' )]
if cadvisor_force_enable_metrics | default(false, true) else [])
}}
cadvisor_container_base_labels:
version: "{{ cadvisor_version }}"
cadvisor_container_base_volumes:
- "/:/rootfs:ro"
- "/var/run:/var/run:ro"
- "/sys:/sys:ro"
- "/var/lib/docker/:/var/lib/docker:ro"
- "/dev/disk/:/dev/disk:ro"

View File

@ -0,0 +1,18 @@
---
cadvisor_version: "0.51.0"
cadvisor_state: present
cadvisor_deployment_method: docker
cadvisor_disabled_metrics:
- advtcp
- cpu_topology
- cpuset
- hugetlb
- memory_numa
- process
- referenced_memory
- resctrl
- sched
- tcp
- udp
cadvisor_force_enable_metrics: []

View File

@ -0,0 +1,11 @@
---
allow_duplicates: true
dependencies: []
galaxy_info:
role_name: cadvisor
description: Deploy cadvisor (Container Advisor), a container performance and resource usage aggregation daemon
galaxy_tags:
- cadvisor
- observability
- container
- docker

View File

@ -0,0 +1,25 @@
---
- name: Ensure cadvisor container image '{{ cadvisor_container_image_ref }}' is {{ cadvisor_state }}
community.docker.docker_image:
name: "{{ cadvisor_container_image_ref }}"
state: "{{ cadvisor_state }}"
source: "{{ cadvisor_container_image_source }}"
force_source: "{{ cadvisor_container_image_force_source }}"
- name: Ensure cadvisor container '{{ cadvisor_container_name }}' is {{ cadvisor_container_state }}
community.docker.docker_container:
name: "{{ cadvisor_container_name }}"
image: "{{ cadvisor_container_image_ref }}"
env: "{{ cadvisor_container_env | default(omit, true) }}"
ports: "{{ cadvisor_container_ports | default(omit, true) }}"
labels: "{{ cadvisor_container_labels }}"
devices: "{{ cadvisor_container_devices }}"
volumes: "{{ cadvisor_container_volumes }}"
networks: "{{ cadvisor_container_networks | default(omit, true) }}"
etc_hosts: "{{ cadvisor_container_etc_hosts | default(omit, true) }}"
privileged: "{{ cadvisor_container_privileged }}"
command: "{{ cadvisor_container_command }}"
pid_mode: "{{ cadvisor_container_pid_mode | default(omit, true) }}"
userns_mode: "{{ cadvisor_container_userns_mode | default(omit, true) }}"
restart_policy: "{{ cadvisor_container_restart_policy }}"
state: "{{ cadvisor_container_state }}"

View File

@ -1,26 +1,18 @@
---
- name: Ensure state is valid
ansible.builtin.fail:
msg: >-2
Unknown state '{{ cadvisor_state }}'! Supported
states are: {{ cadvisor_states | join(', ') }}.
when: cadvisor_state not in cadvisor_states
- name: Ensure container image is present
docker_image:
name: "{{ cadvisor_container_image_ref }}"
state: present
source: pull
force_source: "{{ cadvisor_container_image_tag|default(False, True) | bool }}"
- name: Ensure deployment method is valid
ansible.builtin.fail:
msg: >-2
Unknown deployment method '{{ cadvisor_deployment_method }}'! Supported
deployment methods are: {{ cadvisor_deployment_methods | join(', ') }}.
when: cadvisor_deployment_method not in cadvisor_deployment_methods
- name: Ensure cadvisor container is running
docker_container:
name: "{{ cadvisor_container_name }}"
image: "{{ cadvisor_container_image_ref }}"
env: "{{ cadvisor_container_env | default(omit, True) }}"
ports: "{{ cadvisor_container_ports | default(omit, True) }}"
labels: "{{ cadvisor_container_labels }}"
devices: "{{ cadvisor_container_devices }}"
volumes: "{{ cadvisor_container_volumes }}"
networks: "{{ cadvisor_container_networks | default(omit, True) }}"
etc_hosts: "{{ cadvisor_container_etc_hosts | default(omit, True) }}"
privileged: "{{ cadvisor_container_privileged }}"
command: "{{ cadvisor_container_command }}"
pid_mode: "{{ cadvisor_container_pid_mode | default(omit, True) }}"
userns_mode: "{{ cadvisor_container_userns_mode | default(omit, True) }}"
restart_policy: "{{ cadvisor_container_restart_policy }}"
state: started
- name: Deploy using {{ cadvisor_deployment_method }}
ansible.builtin.include_tasks:
file: "deploy-{{ cadvisor_deployment_method }}.yml"

View File

@ -0,0 +1,6 @@
---
cadvisor_states:
- present
- absent
cadvisor_deployment_methods:
- docker

View File

@ -1,50 +1,4 @@
---
grafana_user: grafana
grafana_version: "10.1.1"
grafana_base_path: "/opt/grafana"
grafana_config_path: "{{ grafana_base_path }}/config"
grafana_config_file: "{{ grafana_config_path }}/grafana.ini"
grafana_ldap_config_file: "{{ grafana_config_path }}/ldap.toml"
grafana_provisioning_path: "{{ grafana_config_path }}/provisioning"
grafana_notifier_provisioning_path: "{{ grafana_provisioning_path }}/notifiers"
grafana_dashboard_provisioning_path: "{{ grafana_provisioning_path }}/dashboards"
grafana_datasource_provisioning_path: "{{ grafana_provisioning_path }}/datasources"
grafana_plugin_provisioning_path: "{{ grafana_provisioning_path }}/plugins"
grafana_data_path: "{{ grafana_base_path }}/data"
grafana_logs_path: "{{ grafana_base_path }}/logs"
grafana_state: present
grafana_run_user: >-
{{ ('uid' in (grafana_user_info | default([]))) | ternary(grafana_user_info.uid, grafana_user) }}
grafana_run_group: >-
{{ ('group' in (grafana_user_info | default([]))) | ternary(grafana_user_info.group, grafana_user) }}
grafana_container_image_server: "docker.io"
grafana_container_image_namespace: "grafana"
grafana_container_image_container: "grafana"
grafana_container_image_name: >-
{{
[
((grafana_container_image_server is defined)
| ternary([ grafana_container_image_server ], [])),
((grafana_container_image_namespace is defined)
| ternary([ grafana_container_image_namespace], [])),
grafana_container_image_container,
] | ansible.builtin.flatten | join('/')
}}
grafana_container_image: >-
{{ grafana_container_image_name }}:{{ grafana_container_image_tag | default(grafana_version, true) }}
grafana_container_name: grafana
grafana_container_base_volumes:
- "{{ grafana_config_path }}:{{ grafana_container_config_path }}:ro"
- "{{ grafana_data_path }}:{{ grafana_container_data_path }}:rw"
- "{{ grafana_logs_path }}:{{ grafana_container_logs_path }}:rw"
grafana_container_volumes: []
grafana_container_collected_volumes: >-
{{ grafana_container_base_volumes + grafana_container_volumes }}
grafana_container_restart_policy: "unless-stopped"
grafana_config_log_mode:
- console
- file

View File

@ -0,0 +1,26 @@
---
grafana_container_image_server: "docker.io"
grafana_container_image_namespace: "grafana"
grafana_container_image_container: "grafana"
grafana_container_image_name: >-2
{{
[
((grafana_container_image_server is defined)
| ternary([ grafana_container_image_server ], [])),
((grafana_container_image_namespace is defined)
| ternary([ grafana_container_image_namespace], [])),
grafana_container_image_container,
] | ansible.builtin.flatten | join('/')
}}
grafana_container_image: >-2
{{ grafana_container_image_name }}:{{ grafana_container_image_tag | default(grafana_version, true) }}
grafana_container_name: grafana
grafana_container_base_volumes:
- "{{ grafana_config_path }}:{{ grafana_container_config_path }}:ro"
- "{{ grafana_data_path }}:{{ grafana_container_data_path }}:rw"
- "{{ grafana_logs_path }}:{{ grafana_container_logs_path }}:rw"
grafana_container_volumes: []
grafana_container_collected_volumes: >-2
{{ grafana_container_base_volumes + grafana_container_volumes }}
grafana_container_restart_policy: "unless-stopped"

View File

@ -0,0 +1,20 @@
---
grafana_user: grafana
grafana_version: "11.3.0"
grafana_base_path: "/opt/grafana"
grafana_config_path: "{{ grafana_base_path }}/config"
grafana_config_file: "{{ grafana_config_path }}/grafana.ini"
grafana_ldap_config_file: "{{ grafana_config_path }}/ldap.toml"
grafana_provisioning_path: "{{ grafana_config_path }}/provisioning"
grafana_notifier_provisioning_path: "{{ grafana_provisioning_path }}/notifiers"
grafana_dashboard_provisioning_path: "{{ grafana_provisioning_path }}/dashboards"
grafana_datasource_provisioning_path: "{{ grafana_provisioning_path }}/datasources"
grafana_plugin_provisioning_path: "{{ grafana_provisioning_path }}/plugins"
grafana_data_path: "{{ grafana_base_path }}/data"
grafana_logs_path: "{{ grafana_base_path }}/logs"
grafana_state: present
grafana_run_user: >-
{{ ('uid' in (grafana_user_info | default([]))) | ternary(grafana_user_info.uid, grafana_user) }}
grafana_run_group: >-
{{ ('group' in (grafana_user_info | default([]))) | ternary(grafana_user_info.group, grafana_user) }}

View File

@ -2,7 +2,7 @@
- name: Ensure grafana_state is valid
ansible.builtin.assert:
that:
- "grafana_state in ['present', 'absent']"
- "grafana_state in grafana_states"
fail_msg: >-
Only 'present' and 'absent' are allowed as values for grafana_state

View File

@ -1,4 +1,7 @@
---
grafana_states:
- present
- absent
grafana_container_config_path: "/etc/grafana"
grafana_container_data_path: "/var/lib/grafana"
grafana_container_logs_path: "/var/log/grafana"

View File

@ -1,6 +1,6 @@
---
postgres_exporter_version: "0.10.1"
postgres_exporter_version: "0.15.0"
postgres_exporter_user: root
postgres_exporter_create_user: false

View File

@ -1,6 +1,6 @@
---
vmagent_user: vmagent
vmagent_version: "1.104.0"
vmagent_version: "1.106.0"
vmagent_state: present
vmagent_deployment_method: "docker"

View File

@ -1,7 +1,7 @@
---
vmalert_state: present
vmalert_user: vmalert
vmalert_version: "1.104.0"
vmalert_version: "1.106.0"
vmalert_base_path: "/opt/vmalert"
vmalert_config_path: "{{ vmalert_base_path }}/config"
vmalert_alert_config: "{{ vmalert_config_path }}/alerts.yml"

View File

@ -1,7 +1,7 @@
---
vmtsdb_state: present
vmtsdb_user: vmtsdb
vmtsdb_version: "1.104.0"
vmtsdb_version: "1.106.0"
vmtsdb_base_path: "/opt/vmtsdb"
vmtsdb_data_path: "{{ vmtsdb_base_path }}/data"