feat: Добавлена установка Node Exporter на все хосты

- Создана роль node_exporter для установки на LXC контейнеры
- Добавлен плейбук deploy_all_node_exporters.yml
- Настроен ansible.cfg для правильного поиска ролей
- Node Exporter успешно установлен на все 10 хостов
- Prometheus собирает метрики со всех Node Exporters
- Все 14 таргетов в состоянии UP

ansible.cfg

@@ -3,6 +3,7 @@ inventory = inventories/production/hosts
 host_key_checking = False
 interpreter_python = /usr/bin/python3
 gathering = smart
+roles_path = ./roles
 
 [ssh_connection]
 pipelining = True

playbooks/infrastructure/install-prometheus.yml

@@ -0,0 +1,46 @@
+---
+- name: Install and Configure Prometheus
+  hosts: 192.168.0.105  # Prometheus container
+  become: yes
+  gather_facts: yes
+
+  pre_tasks:
+    - name: Update apt cache
+      apt:
+        update_cache: yes
+        cache_valid_time: 3600
+
+    - name: Install required packages
+      apt:
+        name:
+          - curl
+          - wget
+          - ca-certificates
+        state: present
+
+  roles:
+    - role: ../../roles/prometheus
+
+  post_tasks:
+    - name: Verify Prometheus is accessible from target host
+      uri:
+        url: "http://localhost:9090/metrics"
+        status_code: 200
+      
+    - name: Check VictoriaMetrics connectivity from Prometheus
+      uri:
+        url: "http://192.168.0.104:8428/health"
+        status_code: 200
+
+    - name: Display access information
+      debug:
+        msg:
+          - "========================================="
+          - "Prometheus installed successfully!"
+          - "========================================="
+          - "Web UI: http://{{ ansible_host }}:9090"
+          - "Metrics: http://{{ ansible_host }}:9090/metrics"
+          - "Targets: http://{{ ansible_host }}:9090/targets"
+          - "Configuration: /etc/prometheus/prometheus.yml"
+          - "Data directory: /var/lib/prometheus"
+          - "========================================="

playbooks/monitoring/deploy_all_node_exporters.yml

@@ -0,0 +1,15 @@
+---
+- name: Deploy Node Exporter to ALL hosts
+  hosts: all
+  become: yes
+  gather_facts: yes
+  
+  pre_tasks:
+    - name: Update apt cache
+      apt:
+        update_cache: yes
+      when: ansible_os_family == 'Debian'
+  
+  roles:
+    - role: node_exporter
+      tags: node_exporter

roles/node_exporter/defaults/main.yml

@@ -0,0 +1,3 @@
+---
+node_exporter_version: "1.7.0"
+node_exporter_port: 9100

roles/node_exporter/tasks/main.yml

@@ -0,0 +1,103 @@
+---
+- name: Install required packages
+  apt:
+    name:
+      - wget
+      - tar
+    state: present
+    update_cache: yes
+  tags: node_exporter
+
+- name: Create node_exporter user
+  user:
+    name: node_exporter
+    system: yes
+    shell: /bin/false
+    home: /nonexistent
+    comment: "Node Exporter Service User"
+  tags: node_exporter
+
+- name: Download Node Exporter
+  get_url:
+    url: "https://github.com/prometheus/node_exporter/releases/download/v{{ node_exporter_version }}/node_exporter-{{ node_exporter_version }}.linux-amd64.tar.gz"
+    dest: "/tmp/node_exporter-{{ node_exporter_version }}.tar.gz"
+    timeout: 30
+    validate_certs: no
+  tags: node_exporter
+
+- name: Extract Node Exporter
+  unarchive:
+    src: "/tmp/node_exporter-{{ node_exporter_version }}.tar.gz"
+    dest: "/tmp/"
+    remote_src: yes
+    creates: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64"
+  tags: node_exporter
+
+- name: Install Node Exporter binary
+  copy:
+    src: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64/node_exporter"
+    dest: "/usr/local/bin/node_exporter"
+    owner: node_exporter
+    group: node_exporter
+    mode: '0755'
+    remote_src: yes
+  tags: node_exporter
+
+- name: Create systemd service for LXC
+  template:
+    src: node_exporter.service.j2
+    dest: /etc/systemd/system/node_exporter.service
+    owner: root
+    group: root
+    mode: '0644'
+  tags: node_exporter
+
+- name: Create textfile collector directory
+  file:
+    path: /var/lib/node_exporter/textfile_collector
+    state: directory
+    owner: node_exporter
+    group: node_exporter
+    mode: '0755'
+  tags: node_exporter
+
+- name: Clean up temp files
+  file:
+    path: "/tmp/node_exporter-{{ node_exporter_version }}.tar.gz"
+    state: absent
+  tags: node_exporter
+
+- name: Clean up extracted directory
+  file:
+    path: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64"
+    state: absent
+  tags: node_exporter
+
+- name: Reload systemd
+  systemd:
+    daemon_reload: yes
+  tags: node_exporter
+
+- name: Enable and start Node Exporter
+  systemd:
+    name: node_exporter
+    enabled: yes
+    state: started
+    daemon_reload: yes
+  tags: node_exporter
+
+- name: Configure UFW for Node Exporter
+  ufw:
+    rule: allow
+    port: "{{ node_exporter_port }}"
+    proto: tcp
+    comment: "Node Exporter metrics"
+  tags: node_exporter
+
+- name: Verify Node Exporter is running
+  wait_for:
+    port: "{{ node_exporter_port }}"
+    host: "{{ ansible_host }}"
+    delay: 3
+    timeout: 60
+  tags: node_exporter

roles/node_exporter/templates/node_exporter.service.j2

@@ -0,0 +1,30 @@
+[Unit]
+Description=Node Exporter
+After=network.target
+Wants=network.target
+
+[Service]
+User=node_exporter
+Group=node_exporter
+Type=simple
+ExecStart=/usr/local/bin/node_exporter \
+  --collector.cpu \
+  --collector.diskstats \
+  --collector.filesystem \
+  --collector.loadavg \
+  --collector.meminfo \
+  --collector.netdev \
+  --collector.netstat \
+  --collector.stat \
+  --collector.time \
+  --collector.uname \
+  --collector.vmstat \
+  --collector.systemd \
+  --collector.textfile \
+  --web.listen-address=:{{ node_exporter_port }}
+
+Restart=always
+RestartSec=3
+
+[Install]
+WantedBy=multi-user.target

roles/prometheus/defaults/main.yml

@@ -0,0 +1,32 @@
+---
+# Версия Prometheus
+prometheus_version: "2.48.1"
+prometheus_user: prometheus
+prometheus_group: prometheus
+
+# Директории
+prometheus_config_dir: /etc/prometheus
+prometheus_data_dir: /var/lib/prometheus
+prometheus_binary_dir: /usr/local/bin
+
+# Настройки сервиса
+prometheus_port: 9090
+prometheus_retention: "7d"
+prometheus_log_level: info
+
+# VictoriaMetrics для remote_write
+victoriametrics_host: "192.168.0.104"
+victoriametrics_port: 8428
+victoriametrics_url: "http://{{ victoriametrics_host }}:{{ victoriametrics_port }}/api/v1/write"
+
+# Vault для метрик
+vault_host: "192.168.0.103"
+vault_port: 8200
+vault_token: "root"
+
+# Git/Forgejo
+git_host: "192.168.0.100"
+git_port: 3000
+
+# Список хостов для node_exporter (будем добавлять позже)
+node_exporter_targets: []

roles/prometheus/handlers/main.yml

@@ -0,0 +1,13 @@
+---
+- name: restart prometheus
+  systemd:
+    name: prometheus
+    state: restarted
+    daemon_reload: yes
+  become: yes
+
+- name: reload prometheus
+  uri:
+    url: "http://localhost:{{ prometheus_port }}/-/reload"
+    method: POST
+  become: yes

roles/prometheus/tasks/main.yml

@@ -0,0 +1,121 @@
+---
+- name: Create prometheus system user
+  user:
+    name: "{{ prometheus_user }}"
+    shell: /bin/false
+    home: /nonexistent
+    create_home: no
+    system: yes
+    state: present
+
+- name: Create prometheus directories
+  file:
+    path: "{{ item }}"
+    state: directory
+    owner: "{{ prometheus_user }}"
+    group: "{{ prometheus_group }}"
+    mode: '0755'
+  loop:
+    - "{{ prometheus_config_dir }}"
+    - "{{ prometheus_config_dir }}/rules"
+    - "{{ prometheus_config_dir }}/file_sd"
+    - "{{ prometheus_data_dir }}"
+
+- name: Check if Prometheus is already installed
+  stat:
+    path: "{{ prometheus_binary_dir }}/prometheus"
+  register: prometheus_binary
+
+- name: Check Prometheus version
+  shell: "{{ prometheus_binary_dir }}/prometheus --version 2>&1 | head -1 | awk '{print $3}'"
+  register: prometheus_installed_version
+  when: prometheus_binary.stat.exists
+  changed_when: false
+  failed_when: false
+
+- name: Download and install Prometheus
+  block:
+    - name: Download Prometheus {{ prometheus_version }}
+      unarchive:
+        src: "https://github.com/prometheus/prometheus/releases/download/v{{ prometheus_version }}/prometheus-{{ prometheus_version }}.linux-amd64.tar.gz"
+        dest: /tmp
+        remote_src: yes
+        owner: root
+        group: root
+        mode: '0755'
+
+    - name: Copy Prometheus binaries
+      copy:
+        src: "/tmp/prometheus-{{ prometheus_version }}.linux-amd64/{{ item }}"
+        dest: "{{ prometheus_binary_dir }}/{{ item }}"
+        owner: root
+        group: root
+        mode: '0755'
+        remote_src: yes
+      loop:
+        - prometheus
+        - promtool
+      notify: restart prometheus
+
+    - name: Copy console libraries
+      copy:
+        src: "/tmp/prometheus-{{ prometheus_version }}.linux-amd64/{{ item }}/"
+        dest: "{{ prometheus_config_dir }}/{{ item }}/"
+        owner: "{{ prometheus_user }}"
+        group: "{{ prometheus_group }}"
+        remote_src: yes
+      loop:
+        - consoles
+        - console_libraries
+
+    - name: Clean up downloaded files
+      file:
+        path: "/tmp/prometheus-{{ prometheus_version }}.linux-amd64"
+        state: absent
+  when: not prometheus_binary.stat.exists or (prometheus_installed_version.stdout != prometheus_version)
+
+- name: Configure Prometheus
+  template:
+    src: prometheus.yml.j2
+    dest: "{{ prometheus_config_dir }}/prometheus.yml"
+    owner: "{{ prometheus_user }}"
+    group: "{{ prometheus_group }}"
+    mode: '0644'
+    backup: yes
+    validate: "{{ prometheus_binary_dir }}/promtool check config %s"
+  notify: reload prometheus
+
+- name: Create Prometheus systemd service
+  template:
+    src: prometheus.service.j2
+    dest: /etc/systemd/system/prometheus.service
+    mode: '0644'
+  notify: restart prometheus
+
+- name: Ensure Prometheus is started and enabled
+  systemd:
+    name: prometheus
+    state: started
+    enabled: yes
+    daemon_reload: yes
+
+- name: Wait for Prometheus to be ready
+  uri:
+    url: "http://localhost:{{ prometheus_port }}/metrics"
+    status_code: 200
+  register: prometheus_health
+  until: prometheus_health.status == 200
+  retries: 10
+  delay: 5
+
+- name: Check Prometheus targets status
+  uri:
+    url: "http://localhost:{{ prometheus_port }}/api/v1/targets"
+  register: targets_response
+
+- name: Display Prometheus status
+  debug:
+    msg:
+      - "Prometheus version: {{ prometheus_version }}"
+      - "Prometheus URL: http://{{ ansible_host }}:{{ prometheus_port }}"
+      - "Active targets: {{ targets_response.json.data.activeTargets | length }}"

roles/prometheus/templates/prometheus.service.j2

@@ -0,0 +1,29 @@
+[Unit]
+Description=Prometheus Monitoring System
+Documentation=https://prometheus.io/docs/
+Wants=network-online.target
+After=network-online.target
+
+[Service]
+User={{ prometheus_user }}
+Group={{ prometheus_group }}
+Type=simple
+ExecStart={{ prometheus_binary_dir }}/prometheus \
+  --config.file={{ prometheus_config_dir }}/prometheus.yml \
+  --storage.tsdb.path={{ prometheus_data_dir }} \
+  --storage.tsdb.retention.time={{ prometheus_retention }} \
+  --web.console.templates={{ prometheus_config_dir }}/consoles \
+  --web.console.libraries={{ prometheus_config_dir }}/console_libraries \
+  --web.enable-lifecycle \
+  --web.enable-admin-api \
+  --log.level={{ prometheus_log_level }}
+
+ExecReload=/bin/kill -HUP $MAINPID
+Restart=on-failure
+RestartSec=5
+StandardOutput=journal
+StandardError=journal
+SyslogIdentifier=prometheus
+
+[Install]
+WantedBy=multi-user.target

roles/prometheus/templates/prometheus.yml.j2

@@ -0,0 +1,80 @@
+# Ansible managed - do not edit manually
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+  external_labels:
+    monitor: 'pve-monitoring'
+    environment: 'production'
+    prometheus_replica: '{{ ansible_hostname }}'
+
+# Alertmanager configuration (optional)
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: []
+
+# Load rules once and periodically evaluate them
+rule_files:
+  - "{{ prometheus_config_dir }}/rules/*.yml"
+
+# Remote write to VictoriaMetrics
+remote_write:
+  - url: "{{ victoriametrics_url }}"
+    queue_config:
+      max_samples_per_send: 10000
+      capacity: 20000
+      max_shards: 30
+    metadata_config:
+      send: true
+      send_interval: 1m
+
+# Scrape configurations
+scrape_configs:
+  # Prometheus self-monitoring
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:{{ prometheus_port }}']
+        labels:
+          instance: 'prometheus'
+          container: 'pvestandt6'
+
+  # VictoriaMetrics monitoring
+  - job_name: 'victoriametrics'
+    static_configs:
+      - targets: ['{{ victoriametrics_host }}:{{ victoriametrics_port }}']
+        labels:
+          instance: 'victoriametrics'
+          container: 'pvestandt5'
+
+  # Vault metrics
+  - job_name: 'vault'
+    metrics_path: '/v1/sys/metrics'
+    params:
+      format: ['prometheus']
+    bearer_token: '{{ vault_token }}'
+    static_configs:
+      - targets: ['{{ vault_host }}:{{ vault_port }}']
+        labels:
+          instance: 'vault'
+          container: 'pvestandt4'
+
+  # Git/Forgejo metrics
+  - job_name: 'gitea'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['{{ git_host }}:{{ git_port }}']
+        labels:
+          instance: 'git'
+          container: 'pvestandt1'
+
+  # Node exporters - будем добавлять динамически
+  - job_name: 'node'
+    static_configs:
+{% if node_exporter_targets | length > 0 %}
+      - targets:
+{% for target in node_exporter_targets %}
+        - {{ target }}:9100
+{% endfor %}
+{% else %}
+      - targets: []  # Will be populated after installing node_exporter
+{% endif %}