Lab7

app_python/app.py

@@ -2,8 +2,10 @@
 DevOps Info Service - FastAPI implementation.
 
 Provides system, runtime, and request information plus a basic health check.
+Now emits structured JSON logs for easier aggregation.
 """
 
+import json
 import logging
 import os
 import platform
@@ -22,11 +24,39 @@
 DEBUG: bool = os.getenv("DEBUG", "False").lower() == "true"
 
 
-# Logging configuration
-logging.basicConfig(
-    level=logging.INFO,
-    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
-)
+class JSONFormatter(logging.Formatter):
+    """Format logs as JSON with common fields."""
+
+    def format(self, record: logging.LogRecord) -> str:  # type: ignore[override]
+        log_record: dict[str, Any] = {
+            "timestamp": datetime.now(UTC).isoformat(),
+            "level": record.levelname,
+            "message": record.getMessage(),
+            "logger": record.name,
+        }
+
+        for attr in (
+            "method",
+            "path",
+            "status_code",
+            "client_ip",
+            "duration",
+        ):
+            value = getattr(record, attr, None)
+            if value is not None:
+                log_record[attr] = value
+
+        if record.exc_info:
+            log_record["exc_info"] = self.formatException(record.exc_info)
+
+        return json.dumps(log_record)
+
+
+handler = logging.StreamHandler()
+handler.setFormatter(JSONFormatter())
+root_logger = logging.getLogger()
+root_logger.setLevel(logging.INFO)
+root_logger.handlers = [handler]
 logger = logging.getLogger(__name__)
 
 
@@ -37,6 +67,28 @@
 app = FastAPI(title="DevOps Info Service")
 
 
+@app.middleware("http")
+async def log_requests(request: Request, call_next):
+    """Log each HTTP request with structured JSON."""
+    start_time = datetime.now(UTC)
+    response = await call_next(request)
+
+    duration = (datetime.now(UTC) - start_time).total_seconds()
+
+    logger.info(
+        "HTTP request completed",
+        extra={
+            "method": request.method,
+            "path": request.url.path,
+            "status_code": response.status_code,
+            "client_ip": request.client.host if request.client else None,
+            "duration": duration,
+        },
+    )
+
+    return response
+
+
 def get_system_info() -> dict[str, Any]:
     """Collect system information."""
     return {
@@ -89,7 +141,14 @@ def get_endpoints() -> list[dict[str, str]]:
 @app.get("/")
 async def index(request: Request) -> dict[str, Any]:
     """Main endpoint - service and system information."""
-    logger.info("Handling request for %s %s", request.method, request.url.path)
+    logger.info(
+        "Handling request",
+        extra={
+            "method": request.method,
+            "path": request.url.path,
+            "client_ip": request.client.host if request.client else None,
+        },
+    )
 
     system_info = get_system_info()
     runtime_info = get_runtime_info()
@@ -157,5 +216,8 @@ async def unhandled_exception_handler(request: Request, exc: Exception) -> JSONR
 
 
 if __name__ == "__main__":
-    logger.info("Starting DevOps Info Service on %s:%s", HOST, PORT)
+    logger.info(
+        "Starting DevOps Info Service",
+        extra={"host": HOST, "port": PORT},
+    )
     uvicorn.run("app:app", host=HOST, port=PORT, reload=DEBUG)

monitoring/docker-compose.yml

@@ -0,0 +1,133 @@
+services:
+  loki:
+    image: grafana/loki:3.0.0
+    command: -config.file=/etc/loki/config.yml
+    ports:
+      - "3100:3100"
+    volumes:
+      - ./loki/config.yml:/etc/loki/config.yml:ro
+      - loki-data:/loki
+    networks:
+      - logging
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 1G
+        reservations:
+          cpus: "0.5"
+          memory: 512M
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 15s
+
+  promtail:
+    image: grafana/promtail:3.0.0
+    command: -config.file=/etc/promtail/config.yml
+    volumes:
+      - ./promtail/config.yml:/etc/promtail/config.yml:ro
+      - /var/log:/var/log:ro
+      - /var/snap/docker/common/var-lib-docker/containers:/var/lib/docker/containers:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+    networks:
+      - logging
+    depends_on:
+      loki:
+        condition: service_healthy
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 512M
+        reservations:
+          cpus: "0.25"
+          memory: 256M
+    healthcheck:
+      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/9080' || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 15s
+
+  grafana:
+    image: grafana/grafana:12.3.1
+    ports:
+      - "3000:3000"
+    environment:
+      GF_AUTH_ANONYMOUS_ENABLED: "true"
+      GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
+      GF_SECURITY_ALLOW_EMBEDDING: "true"
+    volumes:
+      - grafana-data:/var/lib/grafana
+    networks:
+      - logging
+    depends_on:
+      loki:
+        condition: service_healthy
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 1G
+        reservations:
+          cpus: "0.5"
+          memory: 512M
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:3000/api/health || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 15s
+
+  app-python:
+    build:
+      context: ../app_python
+    ports:
+      - "8000:5000"
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "devops-python"
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 512M
+        reservations:
+          cpus: "0.25"
+          memory: 256M
+
+  app-go:
+    build:
+      context: ../app_go
+    environment:
+      HOST: "0.0.0.0"
+      PORT: "8001"
+    ports:
+      - "8001:8001"
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "devops-go"
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 512M
+        reservations:
+          cpus: "0.25"
+          memory: 256M
+
+networks:
+  logging:
+    driver: bridge
+
+volumes:
+  loki-data:
+  grafana-data:
+