📊 Monitorizare servere cu Prometheus și Grafana

# Descarcă și instalează Prometheus
cd /tmp
wget https://github.com/prometheus/prometheus/releases/download/v2.53.0/prometheus-2.53.0.linux-amd64.tar.gz
tar xvf prometheus-2.53.0.linux-amd64.tar.gz
sudo mv prometheus-2.53.0.linux-amd64 /opt/prometheus

# Creează utilizator dedicat
sudo useradd --no-create-home --shell /bin/false prometheus
sudo chown -R prometheus:prometheus /opt/prometheus

# Creează fișierul de service systemd
sudo nano /etc/systemd/system/prometheus.service

[Unit]
Description=Prometheus
After=network.target

[Service]
User=prometheus
Group=prometheus
Type=simple
ExecStart=/opt/prometheus/prometheus --config.file=/opt/prometheus/prometheus.yml --storage.tsdb.path=/opt/prometheus/data
Restart=always

[Install]
WantedBy=multi-user.target

# Pornește Prometheus
sudo systemctl daemon-reload
sudo systemctl enable prometheus
sudo systemctl start prometheus

# Verifică statusul
sudo systemctl status prometheus
# Accesează http://IP_SERVER:9090

# Instalează Node Exporter pe fiecare server monitorizat
wget https://github.com/prometheus/node_exporter/releases/download/v1.7.0/node_exporter-1.7.0.linux-amd64.tar.gz
tar xvf node_exporter-1.7.0.linux-amd64.tar.gz
sudo mv node_exporter-1.7.0.linux-amd64/node_exporter /usr/local/bin/

# Creează service
sudo nano /etc/systemd/system/node_exporter.service

[Unit]
Description=Node Exporter
After=network.target

[Service]
User=nobody
Group=nogroup
Type=simple
ExecStart=/usr/local/bin/node_exporter

[Install]
WantedBy=multi-user.target

sudo systemctl daemon-reload
sudo systemctl enable node_exporter
sudo systemctl start node_exporter
# Verifică: http://IP_SERVER:9100/metrics

# /opt/prometheus/prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['localhost:9093']

rule_files:
  - "alerts.yml"

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  - job_name: 'node_exporter'
    static_configs:
      - targets:
        - 'server1:9100'
        - 'server2:9100'
        - 'server3:9100'

  - job_name: 'blackbox'
    metrics_path: /probe
    params:
      module: [http_2xx]
    static_configs:
      - targets:
        - https://exemplu.ro
        - https://serviciilinux.bluemails.eu
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: localhost:9115

# Instalează Alertmanager
wget https://github.com/prometheus/alertmanager/releases/download/v0.27.0/alertmanager-0.27.0.linux-amd64.tar.gz
tar xvf alertmanager-0.27.0.linux-amd64.tar.gz
sudo mv alertmanager-0.27.0.linux-amd64 /opt/alertmanager

# Configurare alertmanager.yml
route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'email'

receivers:
- name: 'email'
  email_configs:
  - to: 'admin@exemplu.ro'
    from: 'alerts@exemplu.ro'
    smarthost: 'smtp.gmail.com:587'
    auth_username: 'alerts@exemplu.ro'
    auth_password: 'parola'
    require_tls: true

- name: 'slack'
  slack_configs:
  - api_url: 'https://hooks.slack.com/services/...'
    channel: '#alerts'

# Fișier alerts.yml pentru reguli de alertare
groups:
- name: instance_down
  rules:
  - alert: InstanceDown
    expr: up == 0
    for: 5m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."

- name: high_cpu
  rules:
  - alert: HighCPUUsage
    expr: (100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)) > 80
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: "High CPU usage on {{ $labels.instance }}"
      description: "CPU usage is above 80% for more than 10 minutes."

- name: high_memory
  rules:
  - alert: HighMemoryUsage
    expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 90
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "High memory usage on {{ $labels.instance }}"

- name: disk_space
  rules:
  - alert: DiskSpaceLow
    expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 10
    for: 5m
    labels:
      severity: critical
    annotations:
      summary: "Low disk space on {{ $labels.instance }}"

# Adaugă repository Grafana
sudo apt-get install -y software-properties-common wget
sudo wget -q -O /usr/share/keyrings/grafana.key https://apt.grafana.com/gpg.key
echo "deb [signed-by=/usr/share/keyrings/grafana.key] https://apt.grafana.com stable main" | sudo tee /etc/apt/sources.list.d/grafana.list

# Instalează Grafana
sudo apt-get update
sudo apt-get install -y grafana

# Pornește serviciul
sudo systemctl daemon-reload
sudo systemctl enable grafana-server
sudo systemctl start grafana-server

# Accesează http://IP_SERVER:3000 (user: admin, pass: admin)

# Importă dashboard-uri gata făcute
# Node Exporter Full: 1860
# Prometheus 2.0 Stats: 3662
# Kubernetes Cluster: 6417
# PostgreSQL: 9628
# Nginx: 12708

# docker-compose.yml
version: '3.8'

services:
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana_data:/var/lib/grafana
    depends_on:
      - prometheus

  node_exporter:
    image: prom/node-exporter:latest
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'

volumes:
  prometheus_data:
  grafana_data:

# CPU
(100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100))

# RAM
(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100

# Disk
(node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100

# Network Traffic
rate(node_network_receive_bytes_total[5m])
rate(node_network_transmit_bytes_total[5m])

# Load Average
node_load1, node_load5, node_load15

# System Uptime
time() - node_boot_time_seconds