প্রমিথিউস এবং গ্রাফানা গাইড 2026: মেট্রিক্স, সতর্কতা এবং ড্যাশবোর্ড

Monitoring Stack:

Application
  ↓ exposes /metrics endpoint
Prometheus (collector + time-series DB)
  ↓ scrapes every 15s
  ↓ evaluates alert rules
Alertmanager (routes alerts)
  ↓ PagerDuty / Slack / Email

Grafana (visualization)
  ← queries Prometheus (PromQL)
  ← queries Loki (logs)
  ← queries Tempo (traces)

# compose.yml — complete monitoring stack
services:
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./alert.rules.yml:/etc/prometheus/alert.rules.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=secret
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./grafana/datasources:/etc/grafana/provisioning/datasources

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

  alertmanager:
    image: prom/alertmanager:latest
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml

volumes:
  prometheus_data:
  grafana_data:

# prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
    cluster: production
    env: prod

rule_files:
  - /etc/prometheus/alert.rules.yml

alerting:
  alertmanagers:
    - static_configs:
        - targets: [alertmanager:9093]

scrape_configs:
  # Prometheus itself
  - job_name: prometheus
    static_configs:
      - targets: [localhost:9090]

  # Application metrics
  - job_name: myapp
    scrape_interval: 10s
    static_configs:
      - targets: [myapp:8000]
    metrics_path: /metrics

  # Node (server) metrics
  - job_name: node
    static_configs:
      - targets: [node-exporter:9100]

  # Kubernetes pod discovery
  - job_name: kubernetes-pods
    kubernetes_sd_configs:
      - role: pod
    relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: "true" 

# FastAPI + Prometheus metrics
from prometheus_client import Counter, Histogram, Gauge, generate_latest
from fastapi import FastAPI, Request, Response
import time

app = FastAPI()

# Define metrics
REQUEST_COUNT = Counter(
    "http_requests_total",
    "Total HTTP requests",
    ["method", "endpoint", "status_code"]
)

REQUEST_DURATION = Histogram(
    "http_request_duration_seconds",
    "HTTP request duration",
    ["method", "endpoint"],
    buckets=[0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 1.0, 2.5, 5.0]
)

ACTIVE_USERS = Gauge("active_users_total", "Currently active users")

DB_QUERY_DURATION = Histogram(
    "db_query_duration_seconds",
    "Database query duration",
    ["query_type", "table"]
)

@app.middleware("http")
async def metrics_middleware(request: Request, call_next):
    start = time.time()
    response = await call_next(request)
    duration = time.time() - start

    REQUEST_COUNT.labels(
        method=request.method,
        endpoint=request.url.path,
        status_code=response.status_code
    ).inc()

    REQUEST_DURATION.labels(
        method=request.method,
        endpoint=request.url.path
    ).observe(duration)

    return response

@app.get("/metrics")
async def metrics():
    return Response(generate_latest(), media_type="text/plain")

# Usage in code
ACTIVE_USERS.inc()    # user logged in
ACTIVE_USERS.dec()    # user logged out

with DB_QUERY_DURATION.labels(query_type="SELECT", table="users").time():
    users = await db.users.find_all()

# Request rate (per second, 5-min window)
rate(http_requests_total[5m])

# Error rate
rate(http_requests_total{status_code=~"5.."}[5m])

# 95th percentile response time
histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))

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

# Memory usage percentage
(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100

# Available disk space
(node_filesystem_avail_bytes / node_filesystem_size_bytes) * 100

# Requests per second by endpoint
topk(5, rate(http_requests_total[5m])) by (endpoint)

# Alert: error rate > 5%
(
  rate(http_requests_total{status_code=~"5.."}[5m]) /
  rate(http_requests_total[5m])
) > 0.05

# alert.rules.yml
groups:
  - name: application
    rules:
      - alert: HighErrorRate
        expr: |
          (
            rate(http_requests_total{status_code=~"5.."}[5m]) /
            rate(http_requests_total[5m])
          ) > 0.05
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "High error rate on {{ $labels.instance }}"
          description: "Error rate is {{ $value | humanizePercentage }}"

      - alert: HighLatency
        expr: |
          histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1.0
        for: 5m
        labels:
          severity: warning

      - alert: LowDiskSpace
        expr: |
          (node_filesystem_avail_bytes / node_filesystem_size_bytes) < 0.10
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Low disk space on {{ $labels.instance }}"

      - alert: HighMemoryUsage
        expr: |
          (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) > 0.90
        for: 5m
        labels:
          severity: warning

# grafana/datasources/prometheus.yml
apiVersion: 1
datasources:
  - name: Prometheus
    type: prometheus
    url: http://prometheus:9090
    isDefault: true
    jsonData:
      timeInterval: 15s

# Import community dashboards from grafana.com:
# Node Exporter Full: dashboard ID 1860
# FastAPI: dashboard ID 16110
# PostgreSQL: dashboard ID 9628