adding task files

common-qabilah/qabilah-profile.txt

@@ -0,0 +1 @@
+https://qabilah.com/profile/moustafamedhet97/posts

q1-deploy-monitor/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8080
+
+CMD ["python", "app.py"]

q1-deploy-monitor/app.py

@@ -0,0 +1,70 @@
+from flask import Flask, jsonify, render_template, request
+import time
+
+app = Flask(__name__)
+
+# Application start time
+start_time = time.time()
+
+# Metrics
+request_count = 0
+last_response_time = 0
+
+
+@app.before_request
+def before_request():
+    request.start_time = time.perf_counter()
+
+
+@app.after_request
+def after_request(response):
+    global request_count
+    global last_response_time
+
+    request_count += 1
+    last_response_time = round(
+        (time.perf_counter() - request.start_time) * 1000, 2
+    )
+
+    return response
+
+
+@app.route("/")
+def home():
+    return render_template("dashboard.html")
+
+
+@app.route("/health")
+def health():
+    return jsonify({
+        "status": "UP",
+        "message": "Application is healthy",
+        "uptime_seconds": round(time.time() - start_time, 2),
+        "timestamp": time.strftime("%Y-%m-%d %H:%M:%S"),
+        "version": "1.0.0"
+    }), 200
+
+
+@app.route("/metrics")
+def metrics():
+    return jsonify({
+        "status": "UP",
+        "requests": request_count,
+        "response_time_ms": last_response_time,
+        "uptime_seconds": round(time.time() - start_time, 2)
+    })
+
+
+@app.route("/api/info")
+def api_info():
+    return jsonify({
+        "application": "Ghaymah SRE API",
+        "language": "Python",
+        "framework": "Flask",
+        "version": "1.0.0",
+        "author": "Moustafa Medhat"
+    })
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8080)

q1-deploy-monitor/health-check.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+URL="http://localhost:8080/health"
+LOG_FILE="/home/ec2-user/projects/ghaymah-exam-moustafa-medhat-sre/q1-deploy-monitor/health.log"
+
+touch "$LOG_FILE"
+
+echo "===== Health Monitor Started =====" >> "$LOG_FILE"
+
+while true
+do
+    START=$(date +%s%3N)
+
+    HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" "$URL")
+
+    END=$(date +%s%3N)
+    RESPONSE_TIME=$((END - START))
+
+    TIMESTAMP=$(date "+%Y-%m-%d %H:%M:%S")
+
+    if [ "$HTTP_CODE" -eq 200 ]; then
+        STATUS="UP"
+    else
+        STATUS="DOWN"
+    fi
+
+    echo "[$TIMESTAMP] Status=$STATUS | HTTP=$HTTP_CODE | Response=${RESPONSE_TIME}ms" >> "$LOG_FILE"
+
+    sleep 30
+done

q1-deploy-monitor/health.log

@@ -0,0 +1,29 @@
+[2026-07-29 20:25:07] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:25:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:26:07] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:26:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:27:07] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:27:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:28:07] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:28:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:29:07] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:29:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:30:07] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:30:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:31:07] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:31:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:32:07] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:32:37] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:33:07] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:33:37] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:34:07] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:34:38] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:35:08] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:35:38] Status=DOWN | HTTP=000 | Response=8ms
+[2026-07-29 20:36:08] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:36:38] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:37:08] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:37:38] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:38:08] Status=DOWN | HTTP=000 | Response=6ms
+[2026-07-29 20:38:38] Status=DOWN | HTTP=000 | Response=7ms
+[2026-07-29 20:39:08] Status=DOWN | HTTP=000 | Response=7ms

q1-deploy-monitor/requirements.txt

@@ -0,0 +1 @@
+Flask==3.1.0

q1-deploy-monitor/templates/dashboard.html

@@ -0,0 +1,151 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Ghaymah API Dashboard</title>
+
+    <style>
+        *{
+            margin:0;
+            padding:0;
+            box-sizing:border-box;
+            font-family:Arial, Helvetica, sans-serif;
+        }
+
+        body{
+            background:#f5f7fb;
+        }
+
+        .container{
+            width:900px;
+            margin:40px auto;
+        }
+
+        h1{
+            text-align:center;
+            margin-bottom:30px;
+            color:#2c3e50;
+        }
+
+        .cards{
+            display:flex;
+            justify-content:space-between;
+            gap:20px;
+        }
+
+        .card{
+            flex:1;
+            background:white;
+            border-radius:10px;
+            padding:25px;
+            text-align:center;
+            box-shadow:0 5px 15px rgba(0,0,0,.1);
+        }
+
+        .title{
+            color:#666;
+            font-size:18px;
+            margin-bottom:15px;
+        }
+
+        .value{
+            font-size:34px;
+            font-weight:bold;
+        }
+
+        .up{
+            color:green;
+        }
+
+        .down{
+            color:red;
+        }
+
+        .footer{
+            margin-top:35px;
+            text-align:center;
+            color:#777;
+        }
+    </style>
+</head>
+
+<body>
+
+<div class="container">
+
+    <h1>🚀 Ghaymah SRE Dashboard</h1>
+
+    <div class="cards">
+
+        <div class="card">
+            <div class="title">Status</div>
+            <div id="status" class="value">Loading...</div>
+        </div>
+
+        <div class="card">
+            <div class="title">Response Time</div>
+            <div id="response" class="value">0 ms</div>
+        </div>
+
+        <div class="card">
+            <div class="title">Requests</div>
+            <div id="requests" class="value">0</div>
+        </div>
+
+    </div>
+
+    <div class="footer">
+        Last Update:
+        <span id="time">--</span>
+    </div>
+
+</div>
+
+<script>
+
+async function loadMetrics(){
+
+    try{
+
+        const response = await fetch('/metrics');
+
+        const data = await response.json();
+
+        const status=document.getElementById("status");
+
+        status.innerHTML=data.status;
+
+        status.className="value";
+
+        if(data.status==="UP")
+            status.classList.add("up");
+        else
+            status.classList.add("down");
+
+        document.getElementById("response").innerHTML=data.response_time_ms+" ms";
+
+        document.getElementById("requests").innerHTML=data.requests;
+
+        document.getElementById("time").innerHTML=
+            new Date().toLocaleTimeString();
+
+    }
+
+    catch(error){
+
+        document.getElementById("status").innerHTML="DOWN";
+
+        document.getElementById("status").className="value down";
+
+    }
+
+}
+
+loadMetrics();
+
+setInterval(loadMetrics,30000);
+
+</script>
+
+</body>

q2-postmortem/postmortem-report.md

@@ -0,0 +1,120 @@
+# Postmortem Report
+
+## Incident Summary
+
+**Incident Title:** Repeated OOMKilled Causing Application Downtime
+
+**Date:** 2026-07-28
+
+**Duration:** 45 minutes
+
+**Severity:** High (SEV-1)
+
+**Impact:**
+The application became unavailable for 45 minutes because the container was repeatedly terminated with the `OOMKilled` status. During the outage, users were unable to access the application, resulting in service disruption.
+
+---
+
+# Timeline
+
+| Time | Event |
+|------|-------|
+| 14:00 | Increased traffic caused memory usage to rise. |
+| 14:05 | Container exceeded its memory limit and was terminated (OOMKilled). |
+| 14:06 | Kubernetes restarted the container automatically. |
+| 14:10 - 14:40 | Continuous restart loop occurred due to repeated OOMKilled events. |
+| 14:25 | Monitoring system generated high memory usage alerts. |
+| 14:35 | SRE team began investigating pod events and resource metrics. |
+| 14:45 | Memory limit was increased and the deployment was restarted. |
+| 14:45 | Application recovered successfully. |
+
+---
+
+# Root Cause Analysis
+
+### Primary Root Cause
+
+The application exceeded the configured memory limit. When the container reached the limit, the Linux Out Of Memory (OOM) Killer terminated the process.
+
+### Contributing Factors
+
+- Memory limits were configured too low.
+- No Horizontal Pod Autoscaler (HPA) was configured.
+- Monitoring alerts were triggered after the application became unstable.
+- No load testing had been performed before production deployment.
+
+---
+
+# Resolution
+
+The following actions restored the service:
+
+- Increased container memory limits.
+- Restarted the deployment.
+- Verified application health using `/health`.
+- Confirmed stable memory usage.
+
+---
+
+# Preventive Actions
+
+### Immediate
+
+- Increase memory requests and limits.
+- Add memory usage alerts.
+- Perform load testing before deployment.
+
+### Long-term
+
+- Configure Horizontal Pod Autoscaler (HPA).
+- Implement automatic scaling based on CPU and Memory.
+- Enable centralized logging.
+- Create SLOs and alerting rules.
+- Review resource requests for every deployment.
+
+---
+
+# Auto-Scaling Policy
+
+To prevent similar incidents:
+
+- Minimum Replicas: **2**
+- Maximum Replicas: **10**
+- Target CPU Utilization: **70%**
+- Target Memory Utilization: **75%**
+- Scale Up immediately when thresholds are exceeded.
+- Scale Down gradually after 5 minutes of stable utilization.
+- Configure PodDisruptionBudget to maintain availability.
+
+---
+
+# Early Detection Using Ghaymah Monitoring
+
+The issue can be detected early by monitoring:
+
+- Container Memory Usage
+- Pod Restart Count
+- OOMKilled Events
+- Container Health Checks
+- Response Time
+- Error Rate (5xx)
+- Request Rate
+- Application Availability
+
+Recommended alerts:
+
+- Memory Usage > 80%
+- Restart Count > 3 within 5 minutes
+- Health Check Failure
+- Response Time > 500 ms
+- Availability below 99%
+
+---
+
+# Lessons Learned
+
+- Configure appropriate resource limits.
+- Enable proactive monitoring and alerting.
+- Test the application under expected production load.
+- Implement autoscaling before deploying production workloads.
+- Continuously review resource utilization trends.

q3-cicd/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8080
+
+CMD ["python", "app.py"]

q3-cicd/README.md

@@ -0,0 +1,254 @@
+# Ghaymah SRE - CI/CD Pipeline Project
+
+## Overview
+
+This project demonstrates a complete CI/CD pipeline using **GitHub Actions**, **Docker**, **Docker Hub**, and **AWS EC2**.
+
+The pipeline automatically builds a Docker image, pushes it to Docker Hub, waits for manual approval before production deployment, and deploys the application to an EC2 instance.
+
+---
+
+# Project Architecture
+
+Developer
+   │
+   ▼
+GitHub Repository
+   │
+   ▼
+GitHub Actions
+   │
+   ▼
+Build Docker Image
+   │
+   ▼
+Push Image to Docker Hub
+   │
+   ▼
+Manual Approval
+   │
+   ▼
+Deploy to AWS EC2
+   │
+   ▼
+Docker Container
+   │
+   ▼
+Running Flask Application
+
+---
+
+# Technologies Used
+
+- Git
+- GitHub
+- GitHub Actions
+- Docker
+- Docker Hub
+- AWS EC2 (Amazon Linux 2023)
+- Python Flask
+
+---
+
+# Project Structure
+
+```
+.
+├── .github
+│   └── workflows
+│       └── docker-build-push.yml
+├── Dockerfile
+├── requirements.txt
+├── app.py
+├── templates/
+├── static/
+└── README.md
+```
+
+---
+
+# CI/CD Workflow
+
+The GitHub Actions workflow performs the following steps:
+
+1. Trigger on every push to the main branch.
+2. Checkout the repository.
+3. Log in to Docker Hub using GitHub Secrets.
+4. Build the Docker image.
+5. Push the image to Docker Hub.
+6. Wait for manual approval using the Production Environment.
+7. Deploy the latest image to the EC2 server.
+8. Verify that the application is running successfully.
+
+---
+
+# GitHub Secrets
+
+The following repository secrets were configured:
+
+| Secret | Description |
+|---------|-------------|
+| DOCKER_USERNAME | Docker Hub username |
+| DOCKER_TOKEN | Docker Hub Access Token |
+
+---
+
+# Manual Approval
+
+A GitHub Environment named **production** was created.
+
+Deployment to production requires manual approval before execution.
+
+This prevents accidental deployments and provides an additional safety layer.
+
+---
+
+# Docker Image
+
+The application image is stored in Docker Hub.
+
+Image name:
+
+```
+moustafamedhat97/ghaymah-api
+```
+
+Each build is tagged using the Git commit SHA.
+
+Example:
+
+```
+moustafamedhat97/ghaymah-api:0367751868ea7532b1b22f744baa5e49851158f6
+```
+
+---
+
+# Deployment
+
+The deployment process performs the following:
+
+- Pull latest Docker image
+- Stop old container (if exists)
+- Remove old container
+- Start new container
+- Expose port 8080
+- Restart application
+
+Deployment command:
+
+```bash
+docker pull moustafamedhat97/ghaymah-api:latest
+
+docker stop ghaymah-api || true
+
+docker rm ghaymah-api || true
+
+docker run -d \
+--name ghaymah-api \
+-p 8080:8080 \
+moustafamedhat97/ghaymah-api:latest
+```
+
+---
+
+# Application Health Check
+
+The application exposes a health endpoint:
+
+```
+GET /health
+```
+
+Example:
+
+```
+http://<EC2-Public-IP>:8080/health
+```
+
+Expected response:
+
+```json
+{
+  "status":"UP"
+}
+```
+
+---
+
+# Dashboard
+
+The deployed application provides a dashboard displaying:
+
+- Application Status
+- Response Time
+- Total Requests
+- Last Update Time
+
+Example:
+
+```
+http://<EC2-Public-IP>:8080
+```
+
+---
+
+# Difference Between Staging and Production
+
+## Staging
+
+- Used for testing before release.
+- Mirrors the production environment.
+- Safe for validation and QA.
+- Can contain test data.
+
+## Production
+
+- Live environment.
+- Used by end users.
+- Requires high availability.
+- Requires manual approval before deployment.
+
+---
+
+# Ghaymah CLI Integration
+
+The original requirement requested deployment using the Ghaymah CLI.
+
+Since the CLI was not available in the execution environment, deployment was simulated using Docker commands.
+
+The integration steps would normally be:
+
+1. Install Ghaymah CLI.
+2. Authenticate using:
+
+```bash
+ghaymah login
+```
+
+3. Configure the target project.
+
+4. Deploy the application:
+
+```bash
+ghaymah deploy
+```
+
+---
+
+# Result
+
+The CI/CD pipeline was successfully implemented.
+
+Achievements:
+
+- Docker image successfully built.
+- Image pushed to Docker Hub.
+- Manual approval configured.
+- Application deployed to AWS EC2.
+- Docker container started successfully.
+- Flask application became accessible.
+- Health checks passed.
+- Dashboard successfully displayed through the browser.
+
+---
+

q3-cicd/app.py

@@ -0,0 +1,70 @@
+from flask import Flask, jsonify, render_template, request
+import time
+
+app = Flask(__name__)
+
+# Application start time
+start_time = time.time()
+
+# Metrics
+request_count = 0
+last_response_time = 0
+
+
+@app.before_request
+def before_request():
+    request.start_time = time.perf_counter()
+
+
+@app.after_request
+def after_request(response):
+    global request_count
+    global last_response_time
+
+    request_count += 1
+    last_response_time = round(
+        (time.perf_counter() - request.start_time) * 1000, 2
+    )
+
+    return response
+
+
+@app.route("/")
+def home():
+    return render_template("dashboard.html")
+
+
+@app.route("/health")
+def health():
+    return jsonify({
+        "status": "UP",
+        "message": "Application is healthy",
+        "uptime_seconds": round(time.time() - start_time, 2),
+        "timestamp": time.strftime("%Y-%m-%d %H:%M:%S"),
+        "version": "1.0.0"
+    }), 200
+
+
+@app.route("/metrics")
+def metrics():
+    return jsonify({
+        "status": "UP",
+        "requests": request_count,
+        "response_time_ms": last_response_time,
+        "uptime_seconds": round(time.time() - start_time, 2)
+    })
+
+
+@app.route("/api/info")
+def api_info():
+    return jsonify({
+        "application": "Ghaymah SRE API",
+        "language": "Python",
+        "framework": "Flask",
+        "version": "1.0.0",
+        "author": "Moustafa Medhat"
+    })
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8080)

q3-cicd/requirements.txt

@@ -0,0 +1 @@
+Flask==3.1.0

q3-cicd/templates/dashboard.html

@@ -0,0 +1,151 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Ghaymah SRE Dashboard</title>
+
+    <style>
+        *{
+            margin:0;
+            padding:0;
+            box-sizing:border-box;
+            font-family:Arial, Helvetica, sans-serif;
+        }
+
+        body{
+            background:#f5f7fb;
+        }
+
+        .container{
+            width:900px;
+            margin:40px auto;
+        }
+
+        h1{
+            text-align:center;
+            margin-bottom:30px;
+            color:#2c3e50;
+        }
+
+        .cards{
+            display:flex;
+            justify-content:space-between;
+            gap:20px;
+        }
+
+        .card{
+            flex:1;
+            background:white;
+            border-radius:10px;
+            padding:25px;
+            text-align:center;
+            box-shadow:0 5px 15px rgba(0,0,0,.1);
+        }
+
+        .title{
+            color:#666;
+            font-size:18px;
+            margin-bottom:15px;
+        }
+
+        .value{
+            font-size:34px;
+            font-weight:bold;
+        }
+
+        .up{
+            color:green;
+        }
+
+        .down{
+            color:red;
+        }
+
+        .footer{
+            margin-top:35px;
+            text-align:center;
+            color:#777;
+        }
+    </style>
+</head>
+
+<body>
+
+<div class="container">
+
+    <h1>🚀 Ghaymah API Dashboard</h1>
+
+    <div class="cards">
+
+        <div class="card">
+            <div class="title">Status</div>
+            <div id="status" class="value">Loading...</div>
+        </div>
+
+        <div class="card">
+            <div class="title">Response Time</div>
+            <div id="response" class="value">0 ms</div>
+        </div>
+
+        <div class="card">
+            <div class="title">Requests</div>
+            <div id="requests" class="value">0</div>
+        </div>
+
+    </div>
+
+    <div class="footer">
+        Last Update:
+        <span id="time">--</span>
+    </div>
+
+</div>
+
+<script>
+
+async function loadMetrics(){
+
+    try{
+
+        const response = await fetch('/metrics');
+
+        const data = await response.json();
+
+        const status=document.getElementById("status");
+
+        status.innerHTML=data.status;
+
+        status.className="value";
+
+        if(data.status==="UP")
+            status.classList.add("up");
+        else
+            status.classList.add("down");
+
+        document.getElementById("response").innerHTML=data.response_time_ms+" ms";
+
+        document.getElementById("requests").innerHTML=data.requests;
+
+        document.getElementById("time").innerHTML=
+            new Date().toLocaleTimeString();
+
+    }
+
+    catch(error){
+
+        document.getElementById("status").innerHTML="DOWN";
+
+        document.getElementById("status").className="value down";
+
+    }
+
+}
+
+loadMetrics();
+
+setInterval(loadMetrics,30000);
+
+</script>
+
+</body>

q3-cicd/workflow.yml

@@ -0,0 +1,59 @@
+name: Build, Push and Deploy
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build and Push Docker Image
+    runs-on: self-hosted
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build Docker Image
+        run: |
+          docker build -t ${{ secrets.DOCKER_USERNAME }}/ghaymah-api:${{ github.sha }} .
+
+      - name: Push Docker Image
+        run: |
+          docker push ${{ secrets.DOCKER_USERNAME }}/ghaymah-api:${{ github.sha }}
+
+  deploy-production:
+    name: Deploy to Production
+    needs: build
+    runs-on: self-hosted
+
+    environment:
+      name: production
+
+    steps:
+      - name: Pull Latest Image
+        run: |
+          docker pull ${{ secrets.DOCKER_USERNAME }}/ghaymah-api:${{ github.sha }}
+
+      - name: Stop Existing Container
+        run: |
+          docker stop ghaymah-api || true
+          docker rm ghaymah-api || true
+
+      - name: Run New Container
+        run: |
+          docker run -d \
+            --name ghaymah-api \
+            --restart unless-stopped \
+            -p 8080:8080 \
+            ${{ secrets.DOCKER_USERNAME }}/ghaymah-api:${{ github.sha }}
+
+      - name: Verify Deployment
+        run: |
+          docker ps

q4-scalability/calculations.md

@@ -0,0 +1,74 @@
+# Scalability and Load Balancing
+
+## 1. Container Calculation
+
+### Given
+
+- Expected traffic: **15,000 requests/second**
+- One container capacity: **500 requests/second**
+- Safety margin: **30%**
+
+### Step 1: Base Number of Containers
+
+15000 / 500 = **30 containers**
+
+### Step 2: Add Safety Margin
+
+30 × 1.30 = **39 containers**
+
+### Final Result
+
+**39 containers** are required to safely handle 15,000 requests per second while maintaining a 30% capacity margin for traffic spikes and failover scenarios.
+
+---
+
+# 2. Cold Start Strategy
+
+To minimize startup latency for new containers:
+
+- Keep a small pool of warm containers ready to receive traffic.
+- Use Kubernetes Horizontal Pod Autoscaler (HPA).
+- Pre-pull container images on worker nodes.
+- Configure Readiness Probes before accepting requests.
+- Use Rolling Updates for zero-downtime deployments.
+- Scale based on CPU utilization and request rate.
+
+---
+
+# 3. Ghaymah Block Storage for Stateful Workloads
+
+Containers are ephemeral and lose local storage when restarted. Stateful workloads require persistent storage.
+
+Ghaymah Block Storage provides persistent volumes that remain attached to applications even after pod or container recreation.
+
+Typical stateful workloads include:
+
+- PostgreSQL
+- MySQL
+- MongoDB
+- Redis Persistence
+- Elasticsearch
+- Jenkins
+- Kafka
+- RabbitMQ
+
+Benefits:
+
+- Persistent storage
+- High performance
+- Volume reattachment after restart
+- Snapshot support
+- Backup and disaster recovery
+- Independent lifecycle from containers
+
+---
+
+# Summary
+
+| Requirement | Solution |
+|------------|----------|
+| Incoming Traffic | 15,000 req/s |
+| Container Capacity | 500 req/s |
+| Safety Margin | 30% |
+| Required Containers | **39 Containers** |
+| Cold Start | Warm Pool, HPA, Image Pre-Pulling, Readiness Probes |

q5-mithal-monitor/Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11-slim AS builder
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir \
+    --prefix=/install \
+    -r requirements.txt
+
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY --from=builder /install /usr/local
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["python3", "-m", "http.server", "8000", "--directory", "/app"]

q5-mithal-monitor/app.js

@@ -0,0 +1,230 @@
+let chart = null;
+
+async function loadData() {
+
+    try {
+
+        const response = await fetch("../metrics.csv?t=" + Date.now());
+
+        const text = await response.text();
+
+        let rows = text.trim().split("\n");
+
+        if (rows.length <= 1) return;
+
+        // Remove CSV header
+        rows.shift();
+
+        const data = rows
+            .map(row => row.split(","))
+            .filter(row => row.length >= 7);
+
+        const history = document.getElementById("history");
+        history.innerHTML = "";
+
+        const now = new Date();
+
+        // ==========================
+        // Uptime (24h)
+        // ==========================
+
+        const last24 = data.filter(row => {
+
+            const t = new Date(row[0].replace(" ", "T"));
+
+            return (now - t) <= (24 * 60 * 60 * 1000);
+
+        });
+
+        const up = last24.filter(row => row[2] === "200").length;
+
+        const uptime =
+            last24.length === 0
+                ? 0
+                : ((up / last24.length) * 100).toFixed(2);
+
+        document.getElementById("uptime").textContent = uptime + "%";
+
+        // ==========================
+        // SSL Status
+        // ==========================
+
+        const latest = data[data.length - 1];
+
+        document.getElementById("ssl").textContent =
+            latest[5] + " Days Remaining";
+
+        // ==========================
+        // Chart
+        // ==========================
+
+        let labels = [];
+        let values = [];
+
+        data.forEach(row => {
+
+            const latency = parseFloat(row[1]);
+
+            // Ignore abnormal values
+            if (latency <= 500) {
+
+                labels.push(row[0].split(" ")[1]);
+
+                values.push(latency);
+
+            }
+
+        });
+
+        drawChart(labels, values);
+
+        // ==========================
+        // Last 10 Checks
+        // ==========================
+
+        data.slice(-10).reverse().forEach(row => {
+
+            const status = row[2] === "200";
+
+            history.innerHTML += `
+
+            <tr>
+
+                <td>${row[0]}</td>
+
+                <td class="${status ? "up" : "down"}">
+
+                    ${status ? "UP" : "DOWN"}
+
+                </td>
+
+                <td>${row[1]} ms</td>
+
+                <td>${row[3]} ms</td>
+
+                <td>${row[6]} ms</td>
+
+                <td>${row[5]} Days</td>
+
+            </tr>
+
+            `;
+
+        });
+
+    }
+
+    catch (err) {
+
+        console.error("Dashboard Error:", err);
+
+    }
+
+}
+
+function drawChart(labels, values) {
+
+    const canvas = document.getElementById("latencyChart");
+
+    if (!canvas) return;
+
+    if (chart) {
+
+        chart.destroy();
+
+    }
+
+    chart = new Chart(canvas, {
+
+        type: "line",
+
+        data: {
+
+            labels: labels,
+
+            datasets: [
+
+                {
+
+                    label: "Latency (ms)",
+
+                    data: values,
+
+                    borderColor: "#3498db",
+
+                    backgroundColor: "rgba(52,152,219,0.15)",
+
+                    borderWidth: 2,
+
+                    fill: true,
+
+                    tension: 0.3,
+
+                    pointRadius: 3,
+
+                    pointHoverRadius: 5
+
+                }
+
+            ]
+
+        },
+
+        options: {
+
+            responsive: true,
+
+            maintainAspectRatio: false,
+
+            animation: false,
+
+            plugins: {
+
+                legend: {
+
+                    display: true
+
+                }
+
+            },
+
+            scales: {
+
+                y: {
+
+                    min: 0,
+
+                    max: 250,
+
+                    title: {
+
+                        display: true,
+
+                        text: "Milliseconds"
+
+                    }
+
+                },
+
+                x: {
+
+                    title: {
+
+                        display: true,
+
+                        text: "Time"
+
+                    }
+
+                }
+
+            }
+
+        }
+
+    });
+
+}
+
+loadData();
+

q5-mithal-monitor/index.html

@@ -0,0 +1,84 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+
+    <meta charset="UTF-8">
+
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+    <title>Mithal Monitoring Dashboard</title>
+
+    <link rel="stylesheet" href="style.css?v=3">
+
+    <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+
+</head>
+
+<body>
+
+<div class="container">
+
+    <h1>Mithal Monitoring Dashboard</h1>
+
+    <div class="cards">
+
+        <div class="card">
+
+            <h3>Uptime (24h)</h3>
+
+            <h2 id="uptime">0%</h2>
+
+        </div>
+
+        <div class="card">
+
+            <h3>SSL Status</h3>
+
+            <h2 id="ssl">Loading...</h2>
+
+        </div>
+
+    </div>
+
+    <div class="chart-container">
+
+        <canvas id="latencyChart"></canvas>
+
+    </div>
+
+    <div class="table-container">
+
+        <h2>Last 10 Checks</h2>
+
+        <table>
+
+            <thead>
+
+                <tr>
+
+                    <th>Time</th>
+                    <th>Status</th>
+                    <th>Latency</th>
+                    <th>DNS</th>
+                    <th>Search</th>
+                    <th>SSL Days</th>
+
+                </tr>
+
+            </thead>
+
+            <tbody id="history">
+
+            </tbody>
+
+        </table>
+
+    </div>
+
+</div>
+
+<script src="app.js?v=3"></script>
+
+</body>
+

q5-mithal-monitor/metrics.csv

@@ -0,0 +1,53 @@
+Timestamp,Latency(ms),Status,DNS(ms),SSL Expiry,Days Left,Search(ms)
+2026-07-29 12:29:42,86.56,200,1.24,2026-09-15,48,77.74
+2026-07-29 13:02:47,115.84,200,0.63,2026-09-15,48,76.28
+2026-07-29 13:03:48,77.67,200,0.35,2026-09-15,48,75.12
+2026-07-29 13:04:48,81.49,200,0.94,2026-09-15,48,83.27
+2026-07-29 13:05:48,76.87,200,0.88,2026-09-15,48,79.01
+2026-07-29 13:06:48,105.08,200,0.47,2026-09-15,48,75.93
+2026-07-29 13:07:49,91.23,200,0.39,2026-09-15,48,74.53
+2026-07-29 13:08:49,87.99,200,0.38,2026-09-15,48,86.44
+2026-07-29 13:09:49,78.44,200,0.6,2026-09-15,48,78.73
+2026-07-29 13:10:50,75.26,200,0.45,2026-09-15,47,75.22
+2026-07-29 13:11:50,78.65,200,0.4,2026-09-15,47,78.07
+2026-07-29 13:12:50,82.63,200,0.31,2026-09-15,47,98.73
+2026-07-29 13:13:50,76.69,200,0.38,2026-09-15,47,76.14
+2026-07-29 13:14:51,78.32,200,0.29,2026-09-15,47,79.26
+2026-07-29 13:15:51,78.01,200,0.34,2026-09-15,47,77.86
+2026-07-29 13:16:51,78.61,200,2.42,2026-09-15,47,75.91
+2026-07-29 13:17:51,112.39,200,0.39,2026-09-15,47,78.11
+2026-07-29 13:18:52,76.81,200,3.9,2026-09-15,47,79.26
+2026-07-29 13:19:52,76.79,200,0.29,2026-09-15,47,81.39
+2026-07-29 13:20:52,81.92,200,0.38,2026-09-15,47,81.31
+2026-07-29 13:21:52,79.67,200,0.39,2026-09-15,47,75.22
+2026-07-29 13:22:53,91.11,200,0.35,2026-09-15,47,77.56
+2026-07-29 13:23:53,85.6,200,4.12,2026-09-15,47,75.11
+2026-07-29 13:24:53,79.27,200,0.36,2026-09-15,47,80.63
+2026-07-29 13:25:53,77.88,200,0.32,2026-09-15,47,82.34
+2026-07-29 13:26:54,79.35,200,0.49,2026-09-15,47,74.78
+2026-07-29 13:27:54,96.65,200,0.37,2026-09-15,47,75.99
+2026-07-29 13:28:54,81.67,200,1.55,2026-09-15,47,72.96
+2026-07-29 13:29:54,96.08,200,4.82,2026-09-15,47,77.69
+2026-07-29 13:30:56,931.52,200,0.33,2026-09-15,47,83.28
+2026-07-29 13:31:56,80.81,200,1.11,2026-09-15,47,79.18
+2026-07-29 13:32:56,156.07,200,0.5,2026-09-15,47,77.07
+2026-07-29 13:35:19,84.33,200,1.81,2026-09-15,47,89.93
+2026-07-29 13:36:20,82.3,200,0.45,2026-09-15,47,76.14
+2026-07-29 13:37:20,81.27,200,0.38,2026-09-15,47,78.65
+2026-07-29 13:38:20,176.09,200,0.53,2026-09-15,47,102.99
+2026-07-29 13:46:29,92.47,200,0.31,2026-09-15,47,73.5
+2026-07-29 13:47:29,79.73,200,0.32,2026-09-15,47,79.24
+2026-07-29 13:48:29,76.52,200,0.64,2026-09-15,47,79.0
+2026-07-29 13:49:29,80.01,200,0.55,2026-09-15,47,78.53
+2026-07-29 13:50:30,78.15,200,1.62,2026-09-15,47,75.87
+2026-07-29 13:51:30,135.51,200,0.43,2026-09-15,47,79.1
+2026-07-29 13:52:30,75.61,200,0.36,2026-09-15,47,77.5
+2026-07-29 13:53:31,77.33,200,0.38,2026-09-15,47,120.55
+2026-07-29 13:54:31,77.05,200,0.57,2026-09-15,47,77.96
+2026-07-29 13:55:31,78.7,200,0.4,2026-09-15,47,72.49
+2026-07-29 13:56:31,100.53,200,0.36,2026-09-15,47,76.88
+2026-07-29 13:57:32,82.96,200,0.38,2026-09-15,47,86.56
+2026-07-29 13:58:32,96.16,200,0.45,2026-09-15,47,74.9
+2026-07-29 13:59:32,79.9,200,0.32,2026-09-15,47,74.98
+2026-07-29 14:00:32,80.24,200,1.81,2026-09-15,47,73.09
+2026-07-29 14:01:33,130.87,200,0.35,2026-09-15,47,76.39

q5-mithal-monitor/monitor.py

@@ -0,0 +1,142 @@
+import requests
+import socket
+import ssl
+import time
+import csv
+import os
+from datetime import datetime
+
+HOST = "mithal.space"
+URL = f"https://{HOST}"
+SEARCH_URL = f"{URL}/?q=test"
+
+CSV_FILE = "metrics.csv"
+
+
+def check_latency():
+    start = time.time()
+
+    response = requests.get(URL, timeout=10)
+
+    latency = round((time.time() - start) * 1000, 2)
+
+    return latency, response.status_code
+
+
+def check_dns():
+
+    start = time.time()
+
+    socket.gethostbyname(HOST)
+
+    dns_time = round((time.time() - start) * 1000, 2)
+
+    return dns_time
+
+
+def check_ssl():
+
+    context = ssl.create_default_context()
+
+    with context.wrap_socket(
+        socket.socket(),
+        server_hostname=HOST
+    ) as s:
+
+        s.settimeout(10)
+
+        s.connect((HOST, 443))
+
+        cert = s.getpeercert()
+
+    expire = cert["notAfter"]
+
+    expire_date = datetime.strptime(
+        expire,
+        "%b %d %H:%M:%S %Y %Z"
+    )
+
+    remaining = (expire_date - datetime.utcnow()).days
+
+    return expire_date.strftime("%Y-%m-%d"), remaining
+
+
+def check_search():
+
+    start = time.time()
+
+    requests.get(SEARCH_URL, timeout=10)
+
+    search_latency = round(
+        (time.time() - start) * 1000,
+        2
+    )
+
+    return search_latency
+
+
+def save_csv(data):
+
+    file_exists = os.path.isfile(CSV_FILE)
+
+    with open(CSV_FILE, "a", newline="") as file:
+
+        writer = csv.writer(file)
+
+        if not file_exists:
+
+            writer.writerow([
+                "Timestamp",
+                "Latency(ms)",
+                "Status",
+                "DNS(ms)",
+                "SSL Expiry",
+                "Days Left",
+                "Search(ms)"
+            ])
+
+        writer.writerow(data)
+
+
+def monitor():
+
+    while True:
+
+        try:
+
+            latency, status = check_latency()
+
+            dns = check_dns()
+
+            ssl_date, ssl_days = check_ssl()
+
+            search = check_search()
+
+            now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+            row = [
+                now,
+                latency,
+                status,
+                dns,
+                ssl_date,
+                ssl_days,
+                search
+            ]
+
+            save_csv(row)
+
+            print(row)
+
+        except Exception as e:
+
+            print("Monitoring Error:", e)
+
+        print("Waiting 60 seconds...\n")
+
+        time.sleep(60)
+
+
+if __name__ == "__main__":
+    monitor()
+

q5-mithal-monitor/monitoring-workflow.yml

@@ -0,0 +1,59 @@
+name: Build, Push and Deploy
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build and Push Docker Image
+    runs-on: self-hosted
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build Docker Image
+        run: |
+          docker build -t ${{ secrets.DOCKER_USERNAME }}/mithal-monitor:${{ github.sha }} .
+
+      - name: Push Docker Image
+        run: |
+          docker push ${{ secrets.DOCKER_USERNAME }}/mithal-monitor:${{ github.sha }}
+
+  deploy-production:
+    name: Deploy to Production
+    needs: build
+    runs-on: self-hosted
+
+    environment:
+      name: production
+
+    steps:
+      - name: Pull Latest Image
+        run: |
+          docker pull ${{ secrets.DOCKER_USERNAME }}/mithal-monitor:${{ github.sha }}
+
+      - name: Stop Existing Container
+        run: |
+          docker stop mithal-monitor || true
+          docker rm mithal-monitor || true
+
+      - name: Run New Container
+        run: |
+          docker run -d \
+            --name mithal-monitor \
+            --restart unless-stopped \
+            -p 8000:8000 \
+            ${{ secrets.DOCKER_USERNAME }}/mithal-monitor:${{ github.sha }}
+
+      - name: Verify Deployment
+        run: |
+          docker ps

q5-mithal-monitor/requirements.txt

@@ -0,0 +1,3 @@
+requests
+pandas
+dnspython

q5-mithal-monitor/style.css

@@ -0,0 +1,121 @@
+*{
+    margin:0;
+    padding:0;
+    box-sizing:border-box;
+    font-family:Arial, Helvetica, sans-serif;
+}
+
+body{
+    background:#f4f7fb;
+    color:#333;
+}
+
+.container{
+    width:95%;
+    max-width:1200px;
+    margin:30px auto;
+}
+
+h1{
+    text-align:center;
+    margin-bottom:30px;
+    color:#2c3e50;
+}
+
+.cards{
+    display:flex;
+    gap:20px;
+    justify-content:center;
+    margin-bottom:30px;
+    flex-wrap:wrap;
+}
+
+.card{
+    background:#fff;
+    width:280px;
+    padding:25px;
+    border-radius:12px;
+    text-align:center;
+    box-shadow:0 5px 15px rgba(0,0,0,.08);
+}
+
+.card h3{
+    color:#666;
+    margin-bottom:15px;
+}
+
+.card h2{
+    color:#2c3e50;
+    font-size:32px;
+}
+
+.chart-container{
+    background:#fff;
+    padding:20px;
+    border-radius:12px;
+    box-shadow:0 5px 15px rgba(0,0,0,.08);
+    margin-bottom:30px;
+    height:450px;
+}
+
+.table-container{
+    background:#fff;
+    padding:20px;
+    border-radius:12px;
+    box-shadow:0 5px 15px rgba(0,0,0,.08);
+}
+
+.table-container h2{
+    margin-bottom:20px;
+}
+
+table{
+    width:100%;
+    border-collapse:collapse;
+}
+
+th{
+    background:#3498db;
+    color:white;
+    padding:12px;
+}
+
+td{
+    padding:12px;
+    border-bottom:1px solid #ddd;
+    text-align:center;
+}
+
+tr:hover{
+    background:#f8f8f8;
+}
+
+.up{
+    color:green;
+    font-weight:bold;
+}
+
+.down{
+    color:red;
+    font-weight:bold;
+}
+
+canvas{
+    width:100% !important;
+    height:100% !important;
+}
+
+@media(max-width:768px){
+
+    .cards{
+        flex-direction:column;
+        align-items:center;
+    }
+
+    table{
+        font-size:14px;
+    }
+
+    .chart-container{
+        height:350px;
+    }