مراقبة بروميثيوس: الإعداد الكامل وممارسات الأفضل

sudo useradd --no-create-home --shell /bin/false prometheus

cd /tmp
wget https://github.com/prometheus/prometheus/releases/download/v2.48.0/prometheus-2.48.0.linux-amd64.tar.gz
tar xvf prometheus-2.48.0.linux-amd64.tar.gz
cd prometheus-2.48.0.linux-amd64

sudo cp prometheus /usr/local/bin/
sudo cp promtool /usr/local/bin/
sudo chown prometheus:prometheus /usr/local/bin/prometheus
sudo chown prometheus:prometheus /usr/local/bin/promtool

sudo mkdir /etc/prometheus
sudo mkdir /var/lib/prometheus
sudo chown prometheus:prometheus /etc/prometheus
sudo chown prometheus:prometheus /var/lib/prometheus

sudo cp -r consoles /etc/prometheus
sudo cp -r console_libraries /etc/prometheus
sudo cp prometheus.yml /etc/prometheus/prometheus.yml
sudo chown -R prometheus:prometheus /etc/prometheus

global:
  scrape_interval: 15s
  evaluation_interval: 15s

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

rule_files:
  - 'alert_rules.yml'

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

  - job_name: 'node_exporter'
    static_configs:
      - targets: ['localhost:9100']

[Unit]
Description=Prometheus
Wants=network-online.target
After=network-online.target

[Service]
User=prometheus
Group=prometheus
Type=simple
ExecStart=/usr/local/bin/prometheus \
  --config.file=/etc/prometheus/prometheus.yml \
  --storage.tsdb.path=/var/lib/prometheus/ \
  --web.console.templates=/etc/prometheus/consoles \
  --web.console.libraries=/etc/prometheus/console_libraries \
  --storage.tsdb.retention.time=30d

[Install]
WantedBy=multi-user.target

sudo systemctl daemon-reload
sudo systemctl start prometheus
sudo systemctl enable prometheus
sudo systemctl status prometheus

cd /tmp
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 cp node_exporter-1.7.0.linux-amd64/node_exporter /usr/local/bin/
sudo chown prometheus:prometheus /usr/local/bin/node_exporter

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

[Service]
User=prometheus
Group=prometheus
Type=simple
ExecStart=/usr/local/bin/node_exporter

[Install]
WantedBy=multi-user.target

sudo systemctl daemon-reload
sudo systemctl start node_exporter
sudo systemctl enable node_exporter

node_cpu_seconds_total

node_cpu_seconds_total{mode="idle"}

node_cpu_seconds_total{mode="idle",cpu="0"}

rate(node_cpu_seconds_total{mode="idle"}[5m])

sum(rate(node_cpu_seconds_total{mode="idle"}[5m]))

sum by (mode) (rate(node_cpu_seconds_total[5m]))

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

(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100

(node_filesystem_size_bytes - node_filesystem_avail_bytes) / node_filesystem_size_bytes * 100

rate(node_network_receive_bytes_total[5m])

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
    ports:
      - "9090:9090"
    restart: unless-stopped

  node_exporter:
    image: prom/node-exporter:latest
    container_name: node_exporter
    command:
      - '--path.rootfs=/host'
    volumes:
      - '/:/host:ro,rslave'
    ports:
      - "9100:9100"
    restart: unless-stopped

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager_data:/alertmanager
    ports:
      - "9093:9093"
    restart: unless-stopped

volumes:
  prometheus_data:
  alertmanager_data:

docker-compose up -d

helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update
helm install prometheus prometheus-community/kube-prometheus-stack

kubectl port-forward svc/prometheus-grafana 3000:80

groups:
  - name: system_alerts
    interval: 30s
    rules:
      - alert: HighCPUUsage
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "استخدام المعالج مرتفع على {{ $labels.instance }}"
          description: "استخدام المعالج أعلى من 80% (القيمة الحالية: {{ $value }}%)"

      - alert: HighMemoryUsage
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "استخدام الذاكرة مرتفع على {{ $labels.instance }}"
          description: "استخدام الذاكرة أعلى من 85% (القيمة الحالية: {{ $value }}%)"

      - alert: DiskSpaceLow
        expr: (node_filesystem_avail_bytes / node_filesystem_size_bytes) * 100 < 15
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: "مساحة القرص منخفضة على {{ $labels.instance }}"
          description: "مساحة القرص المتاحة أقل من 15% على {{ $labels.mountpoint }}"

      - alert: InstanceDown
        expr: up == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "الخادم {{ $labels.instance }} متوقف"
          description: "الخادم {{ $labels.job }} {{ $labels.instance }} متوقف منذ أكثر من 2 دقيقة"

global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.gmail.com:587'
  smtp_from: 'alerts@example.com'
  smtp_auth_username: 'alerts@example.com'
  smtp_auth_password: 'your-password'

route:
  group_by: ['alertname', 'cluster', 'service']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 12h
  receiver: 'team-email'
  routes:
    - match:
        severity: critical
      receiver: 'team-pagerduty'
    - match:
        severity: warning
      receiver: 'team-slack'

receivers:
  - name: 'team-email'
    email_configs:
      - to: 'team@example.com'
        headers:
          Subject: '{{ .GroupLabels.alertname }}: {{ .Status | toUpper }}'

  - name: 'team-slack'
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK'
        channel: '#alerts'
        title: 'تنبيه: {{ .GroupLabels.alertname }}'
        text: '{{ range .Alerts }}{{ .Annotations.description }}{{ end }}'

  - name: 'team-pagerduty'
    pagerduty_configs:
      - service_key: 'your-pagerduty-key'

{
  "title": "استخدام المعالج",
  "targets": [{
    "expr": "100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)"
  }]
}

scrape_configs:
  - job_name: 'blackbox'
    metrics_path: /probe
    params:
      module: [http_2xx]
    static_configs:
      - targets:
          - https://example.com
          - https://api.example.com
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: localhost:9115

--storage.tsdb.retention.time=30d
--storage.tsdb.retention.size=50GB

groups:
  - name: example_rules
    interval: 30s
    rules:
      - record: job:node_cpu_utilization:avg
        expr: 100 - (avg by (job) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)

# سيء: كثافة عالية
sum(rate(http_requests_total[5m]))

# جيد: تجميع حسب العلامات ذات الصلة
sum by (status, method) (rate(http_requests_total[5m]))

resources:
  requests:
    memory: "2Gi"
    cpu: "1000m"
  limits:
    memory: "4Gi"
    cpu: "2000m"