lab done

Author: Gpshfrd

ansible/inventory/hosts.ini

@@ -1,2 +1,2 @@
 [webservers]
-lab04-vm ansible_host=62.84.113.180 ansible_user=ubuntu
+lab04-vm ansible_host=158.160.111.187 ansible_user=ubuntu

app_python/app.py

@@ -3,10 +3,12 @@
 import socket
 import logging
 import sys
+import time
 from datetime import datetime, timezone
 from pythonjsonlogger import jsonlogger
 
 from flask import Flask, jsonify, request
+from prometheus_client import Counter, Histogram, Gauge, generate_latest
 
 ### Configuration
 
@@ -36,6 +38,25 @@
 
 START_TIME = datetime.now(timezone.utc)
 
+### Prometeus metrics
+
+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 in seconds",
+    ["method", "endpoint"]
+)
+
+http_requests_in_progress = Gauge(
+    "http_requests_in_progress",
+    "Number of HTTP requests in progress"
+)
+
 ### Helper functions
 
 def get_uptime():
@@ -101,6 +122,10 @@ def health():
         "uptime_seconds": uptime_seconds,
     })
 
+@app.route("/metrics", methods=["GET"])
+def metrics():
+    return generate_latest(), 200, {"Content-Type": "text/plain"}
+
 ### Error Handlers
 @app.errorhandler(404)
 def not_found(error):
@@ -128,6 +153,10 @@ def handle_error(e):
 
 @app.before_request
 def log_request():
+    request.start_time = time.time()
+
+    http_requests_in_progress.inc()
+
     logger.info(
         "Request received",
         extra={
@@ -139,6 +168,21 @@ def log_request():
 
 @app.after_request
 def log_response(response):
+    duration = time.time() - request.start_time
+
+    http_requests_total.labels(
+        method=request.method,
+        endpoint=request.path,
+        status=response.status_code
+    ).inc()
+
+    http_request_duration_seconds.labels(
+        method=request.method,
+        endpoint=request.path
+    ).observe(duration)
+
+    http_requests_in_progress.dec()
+
     logger.info(
         "Response sent",
         extra={

app_python/requirements.txt

@@ -1,3 +1,4 @@
 Flask==3.1.0
 pytest
-python-json-logger
+python-json-logger
+prometheus-client==0.23.1

monitoring/docker-compose.yml

@@ -55,7 +55,7 @@ services:
     volumes:
       - grafana-data:/var/lib/grafana
     environment:
-      - GF_AUTH_ANONYMOUS_ENABLED=false
+      - GF_AUTH_ANONYMOUS_ENABLED=true
       # - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
     networks:
       - logging
@@ -76,6 +76,34 @@ services:
       retries: 5
       start_period: 10s
 
+  prometheus:
+    image: prom/prometheus:v3.9.0
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus-data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.retention.time=15d'
+      - '--storage.tsdb.retention.size=10GB'
+    networks:
+      - logging
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9090/-/healthy || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+    deploy:
+      resources:
+        limits:
+          cpus: '1.0'
+          memory: 1G
+        reservations:
+          cpus: '0.5'
+          memory: 512M
+
   app-python:
     build: ../app_python
     ports:
@@ -94,17 +122,16 @@ services:
         reservations:
           cpus: '0.25'
           memory: 128M
-
     healthcheck:
-      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/health')"]
+      test: ["CMD-SHELL", "curl -f http://localhost:8000/health || exit 1"]
       interval: 10s
       timeout: 5s
       retries: 5
-      start_period: 10s
 
 volumes:
   loki-data:
   grafana-data:
+  prometheus-data:
 
 networks:
   logging: