submission

Author: BulatGazizov-dev

app_python/app.py

@@ -1,5 +1,5 @@
 from fastapi import FastAPI, Request
-from fastapi.responses import JSONResponse
+from fastapi.responses import JSONResponse, Response
 import os
 import platform
 import socket
@@ -9,6 +9,9 @@
 import time
 import uuid
 from contextlib import asynccontextmanager
+from prometheus_client import Counter, Histogram, Gauge, generate_latest, CONTENT_TYPE_LATEST
+import asyncio
+
 
 HOST = os.getenv('HOST', '0.0.0.0')
 PORT = int(os.getenv('PORT', 5000))
@@ -39,6 +42,77 @@ def format(self, record):
 app = FastAPI()
 start_time = datetime.now()
 
+http_requests_total = Counter(
+    'http_requests_total',
+    'Total HTTP requests',
+    ['method', 'endpoint', 'status']
+)
+
+http_request_duration_seconds = Histogram(
+    'http_request_duration_seconds',
+    'HTTP request duration',
+    ['method', 'endpoint']
+)
+
+http_requests_in_progress = Gauge(
+    'http_requests_in_progress',
+    'HTTP requests currently being processed'
+)
+
+# Application-specific metrics
+
+uptime_seconds = Gauge(
+    'app_uptime_seconds',
+    'Application uptime in seconds'
+)
+
+endpoint_response_size_bytes = Histogram(
+    'endpoint_response_size_bytes',
+    'Response payload size in bytes',
+    ['endpoint']
+)
+
+
+@app.middleware("http")
+async def dispatch(request, call_next):
+    if request.url.path == "/metrics":
+        return await call_next(request)
+
+    http_requests_in_progress.inc()
+
+    start_time = time.time()
+    status_code = 500
+    response = None
+    try:
+        response = await call_next(request)
+        status_code = response.status_code
+    except Exception as e:
+        status_code = 500
+        http_requests_in_progress.dec()
+        raise
+    finally:
+        duration = time.time() - start_time
+
+        http_requests_total.labels(
+            method=request.method,
+            endpoint=request.url.path,
+            status=status_code
+        ).inc()
+
+        http_request_duration_seconds.labels(
+            method=request.method,
+            endpoint=request.url.path
+        ).observe(duration)
+
+        if response and hasattr(response, 'body'):
+            response_size = len(response.body)
+            endpoint_response_size_bytes.labels(
+                endpoint=request.url.path).observe(response_size)
+
+        http_requests_in_progress.dec()
+
+    return response
+
 
 @app.middleware("http")
 async def log_requests(request: Request, call_next):
@@ -88,9 +162,25 @@ async def lifespan(app: FastAPI):
     logger.info("Application starting up", extra={
                 "extra_info": {"config": startup_config}})
 
+    async def update_uptime():
+        while True:
+            uptime_seconds.set(get_uptime()['seconds'])
+            await asyncio.sleep(5)  # Update every 5 seconds
+
+    uptime_task = asyncio.create_task(update_uptime())
+
     yield
 
     logger.info("Application shutting down")
+    uptime_task.cancel()
+
+
+@app.get('/metrics')
+def metrics():
+    return Response(
+        generate_latest(),
+        media_type=CONTENT_TYPE_LATEST
+    )
 
 
 @app.get("/")

app_python/requirements.txt

@@ -47,4 +47,5 @@ jsonschema==4.23.0
 flake8==7.3.0
 mccabe==0.7.0
 pycodestyle==2.14.0
-pyflakes==3.4.0
+pyflakes==3.4.0
+prometheus-client==0.23.1

monitoring/docker-compose.yml

@@ -60,6 +60,32 @@ services:
           cpus: '0.5'
           memory: 256M
 
+  prometheus:
+    image: prom/prometheus:v3.9.0
+    container_name: prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.retention.time=15d'
+      - '--storage.tsdb.retention.size=10GB'
+    ports:
+      - 9090:9090
+    restart: unless-stopped
+    volumes:
+      - ./prometheus:/etc/prometheus
+      - prometheus-data:/prometheus
+    networks:
+      - logging
+    deploy:
+      resources:
+        limits:
+          cpus: '1.0'
+          memory: 1G
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9090/-/healthy || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
   grafana:
     image: grafana/grafana:12.3.1
     container_name: grafana
@@ -87,6 +113,7 @@ services:
 volumes:
   loki-data:
   grafana-data:
+  prometheus-data:
 
 networks:
   logging: