Merge pull request #246 from stfc/change_alertmanager

ENH: Change alertmanager to install by apt

Author: khalford

chatops_deployment/ansible/roles/alertmanager/files/alertmanager.filebeat.yml

@@ -1,9 +1,9 @@
 ---
-- type: filestream
-  id: alertmanager
-  enabled: true
-  paths:
-    - /opt/alertmanager/alertmanager.log
-  fields:
-    service.name: alertmanager
-  fields_under_root: true
+filebeat.inputs:
+  - type: journald
+    id: alertmanager
+    include_matches.match:
+      - _SYSTEMD_UNIT=prometheus-alertmanager.service
+    fields:
+      service.name: alertmanager
+    fields_under_root: true

chatops_deployment/ansible/roles/alertmanager/files/alertmanager.service

@@ -0,0 +1 @@
+ARGS="--web.config.file=/etc/prometheus/alertmanager-web.yml"

chatops_deployment/ansible/roles/alertmanager/files/prometheus-alertmanager

@@ -1,77 +1,55 @@
 ---
-- name: Create alertmanager group
+- name: Install Alertmanager
   become: true
-  ansible.builtin.group:
-    name: alertmanager
-    state: present
-
-- name: Add ubuntu to alertmanager group
-  become: true
-  ansible.builtin.user:
-    name: ubuntu
-    group: alertmanager
-
-- name: Reset connection for group changes
-  ansible.builtin.meta: reset_connection
-
-- name: Create a alertmanager user
-  become: true
-  ansible.builtin.user:
-    name: alertmanager
-    create_home: false
-    group: alertmanager
-    system: true
-
-- name: Download and extract Alertmanager
-  become: true
-  ansible.builtin.unarchive:
-    src: " https://github.com/prometheus/alertmanager/releases/download/v{{ alertmanager_version }}/alertmanager-{{ alertmanager_version }}.linux-amd64.tar.gz "
-    dest: /tmp
-    remote_src: true
-    creates: "/opt/alertmanager"
-    mode: "0774"
-    notify:
-      - Move Alertmanager binaries
-      - Start Alertmanager
-
-- name: Copy alertmanager service file
-  become: true
-  ansible.builtin.copy:
-    src: alertmanager.service
-    dest: /etc/systemd/system/alertmanager.service
-    owner: alertmanager
-    group: alertmanager
-    mode: "0774"
-    notify:
-      - Restart Alertmanager
+  ansible.builtin.apt:
+    name: prometheus-alertmanager
+    state: latest # noqa: package-latest
 
 - name: Template alertmanager config
   become: true
   ansible.builtin.template:
     src: "{{ item }}"
-    dest: "/opt/alertmanager/{{ item[:-3] }}"
-    owner: alertmanager
-    group: alertmanager
+    dest: "/etc/prometheus/{{ item[:-3] }}"
+    owner: prometheus
+    group: prometheus
     mode: "0770"
-    notify:
-      - Restart Alertmanager
   loop:
     - alertmanager.yml.j2
-    - web.yml.j2
+    - alertmanager-web.yml.j2
 
-- name: Create Alertmanager log directory
-  ansible.builtin.file:
-    path: /var/log/alertmanager
-    state: directory
-    owner: alertmanager
-    group: alertmanager
-    mode: "0770"
+- name: Copy systemd arguments
+  become: true
+  ansible.builtin.copy:
+    src: prometheus-alertmanager
+    dest: "/etc/default/prometheus-alertmanager"
+    owner: prometheus
+    group: prometheus
+    mode: "0644"
+
+- name: Copy certificate and key
+  become: true
+  ansible.builtin.copy:
+    src: "./{{ env }}_ssl/alertmanager.{{ item }}"
+    dest: "/etc/prometheus/alertmanager.{{ item }}"
+    owner: prometheus
+    group: prometheus
+    mode: "0440"
+  loop:
+    - crt
+    - key
+
+- name: Restart Alertmanager
+  become: true
+  ansible.builtin.systemd_service:
+    name: prometheus-alertmanager.service
+    state: restarted
+    daemon_reload: true
 
 - name: Copy filebeat external config
   become: true
   ansible.builtin.copy:
     src: alertmanager.filebeat.yml
     dest: /var/filebeat/alertmanager.filebeat.yml
-    owner: root
-    group: root
+    owner: prometheus
+    group: prometheus
     mode: "0640"

chatops_deployment/ansible/roles/alertmanager/handlers/main.yml

@@ -0,0 +1,6 @@
+basic_auth_users:
+    {{ alertmanager_username }}: {{ alertmanager_password | ansible.builtin.password_hash(hashtype="bcrypt") }}
+
+tls_server_config:
+  cert_file: /etc/prometheus/alertmanager.crt
+  key_file: /etc/prometheus/alertmanager.key

chatops_deployment/ansible/roles/alertmanager/tasks/main.yml

@@ -1,19 +1,18 @@
 global:
   resolve_timeout: 5m
+  smtp_smarthost: ${{ alertmanager_smtp_mail_server }}
+  smtp_from: [email protected]
+  smtp_require_tls: false
 
 route:
-  receiver: 'webhook-receiver'
+  receiver: 'email-receiver'
   group_wait: 10s
-  group_interval: 30s
+  group_interval: 5m
   repeat_interval: 3h
   group_by: ['...']
 
 receivers:
-  - name: "webhook-receiver"
-    webhook_configs:
-      - url: "https://chatops.dev-cloud-chatops.nubes.rl.ac.uk/alerts"  # Replace with your actual webhook URL
-        send_resolved: true  # Sends a notification when an alert is resolved
-        http_config:
-          authorization:
-            type: "token"
-            credentials: "{{ chatops_custom_api_token }}"
+  - name: "email-receiver"
+    email_configs:
+      - send_resolved: false
+        to: "[email protected]"