Junior Site Reliability Engineer Interview Questions: Complete Guide

# Example SLI/SLO calculation
def calculate_error_budget(total_requests, failed_requests, slo_target=0.999):
    """
    Calculate error budget consumption
    
    SLO: 99.9% success rate
    Error Budget: 0.1% allowed failures
    """
    success_rate = (total_requests - failed_requests) / total_requests
    error_rate = failed_requests / total_requests
    
    # Error budget: how much of allowed 0.1% we've used
    allowed_errors = total_requests * (1 - slo_target)
    budget_consumed = (failed_requests / allowed_errors) * 100
    
    return {
        'success_rate': success_rate,
        'error_rate': error_rate,
        'slo_target': slo_target,
        'slo_met': success_rate >= slo_target,
        'error_budget_consumed': budget_consumed,
        'remaining_budget': max(0, 100 - budget_consumed)
    }

# Example
result = calculate_error_budget(
    total_requests=1000000,
    failed_requests=500,  # 0.05% error rate
    slo_target=0.999
)

print(f"Success Rate: {result['success_rate']:.4%}")
print(f"SLO Met: {result['slo_met']}")
print(f"Error Budget Consumed: {result['error_budget_consumed']:.1f}%")

# Example: Automate service restart
#!/bin/bash
# auto-restart-service.sh

SERVICE_NAME="myapp"
MAX_RETRIES=3
RETRY_DELAY=5

check_service() {
    systemctl is-active --quiet $SERVICE_NAME
    return $?
}

restart_service() {
    echo "$(date): Restarting $SERVICE_NAME"
    systemctl restart $SERVICE_NAME
    
    # Wait for service to stabilize
    sleep $RETRY_DELAY
    
    if check_service; then
        echo "$(date): $SERVICE_NAME restarted successfully"
        # Send notification
        curl -X POST https://alerts.company.com/webhook \
          -d "{\"message\": \"$SERVICE_NAME auto-restarted\"}"
        return 0
    else
        return 1
    fi
}

# Main logic
if ! check_service; then
    echo "$(date): $SERVICE_NAME is down"
    
    for i in $(seq 1 $MAX_RETRIES); do
        echo "Attempt $i of $MAX_RETRIES"
        if restart_service; then
            exit 0
        fi
        sleep $RETRY_DELAY
    done
    
    # All retries failed - escalate
    echo "$(date): Failed to restart $SERVICE_NAME after $MAX_RETRIES attempts"
    curl -X POST https://pagerduty.com/api/incidents \
      -d "{\"service\": \"$SERVICE_NAME\", \"severity\": \"critical\"}"
    exit 1
fi

# Prometheus scrape config
scrape_configs:
  - job_name: 'api-server'
    static_configs:
      - targets: ['localhost:8080']
    metrics_path: '/metrics'
    scrape_interval: 15s

# Bad: Alert on high CPU
- alert: HighCPU
  expr: cpu_usage > 80
  
# Good: Alert on user impact
- alert: HighLatency
  expr: http_request_duration_seconds{quantile="0.95"} > 1
  for: 5m
  annotations:
    summary: "API latency is high"
    description: "95th percentile latency is {{ $value }}s"

- alert: DatabaseConnectionPoolExhausted
  expr: db_connection_pool_active / db_connection_pool_max > 0.9
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: "Database connection pool nearly exhausted"
    runbook: "https://wiki.company.com/runbooks/db-connections"

# Page-worthy (wakes someone up)
- alert: ServiceDown
  expr: up{job="api"} == 0
  for: 1m
  labels:
    severity: critical
    
# Ticket-worthy (handle during business hours)
- alert: DiskSpaceWarning
  expr: disk_free_percent < 20
  for: 30m
  labels:
    severity: warning

# Quick assessment checklist
- What's the user impact?
- How many users affected?
- What services are impacted?
- Is it getting worse?

# Common mitigation strategies
- Rollback recent deployment
- Scale up resources
- Disable problematic feature
- Failover to backup system
- Rate limit traffic

# Incident Postmortem Template

## Summary
Brief description of what happened

## Impact
- Duration: 2024-11-25 10:00 - 10:45 UTC (45 minutes)
- Users affected: ~10,000 (5% of total)
- Services impacted: API, Web Frontend

## Root Cause
Database connection pool exhausted due to slow queries

## Timeline
- 10:00: Alert fired for high API latency
- 10:05: On-call engineer acknowledged
- 10:10: Identified database as bottleneck
- 10:15: Increased connection pool size (mitigation)
- 10:30: Identified and killed slow queries
- 10:45: Service fully recovered

## Resolution
- Immediate: Increased connection pool from 100 to 200
- Short-term: Added query timeout (30s)
- Long-term: Optimize slow queries, add query monitoring

## Action Items
- [ ] Add alert for slow queries (Owner: Alice, Due: 2024-12-01)
- [ ] Implement query timeout in application (Owner: Bob, Due: 2024-12-05)
- [ ] Review and optimize top 10 slowest queries (Owner: Charlie, Due: 2024-12-10)

## Lessons Learned
- Connection pool monitoring was insufficient
- Query performance degradation went unnoticed

# 1. Verify the problem
curl -w "@curl-format.txt" -o /dev/null -s https://api.example.com/health

# curl-format.txt:
#     time_namelookup:  %{time_namelookup}s\n
#        time_connect:  %{time_connect}s\n
#     time_appconnect:  %{time_appconnect}s\n
#    time_pretransfer:  %{time_pretransfer}s\n
#       time_redirect:  %{time_redirect}s\n
#  time_starttransfer:  %{time_starttransfer}s\n
#                     ----------\n
#          time_total:  %{time_total}s\n

# 2. Check application metrics
# - Request rate (sudden spike?)
# - Error rate (errors causing retries?)
# - Resource usage (CPU, memory)

# 3. Check dependencies
# - Database query time
# - External API calls
# - Cache hit rate

# 4. Check infrastructure
top  # CPU usage
free -h  # Memory
iostat  # Disk I/O
netstat -s  # Network stats

# 5. Check logs for errors
tail -f /var/log/app/error.log | grep -i "timeout\|slow\|error"

# 6. Profile the application
# Python example
import cProfile
cProfile.run('my_function()')

# 7. Check database
# Slow query log
SELECT * FROM mysql.slow_log ORDER BY query_time DESC LIMIT 10;

# Active queries
SELECT pid, query, state, query_start 
FROM pg_stat_activity 
WHERE state = 'active';

#!/usr/bin/env python3
"""
Service health checker with auto-restart capability
"""
import requests
import subprocess
import time
import sys
from datetime import datetime

class ServiceMonitor:
    def __init__(self, service_name, health_url, max_retries=3):
        self.service_name = service_name
        self.health_url = health_url
        self.max_retries = max_retries
    
    def check_health(self):
        """Check if service is healthy"""
        try:
            response = requests.get(
                self.health_url,
                timeout=5
            )
            return response.status_code == 200
        except requests.exceptions.RequestException as e:
            print(f"{datetime.now()}: Health check failed: {e}")
            return False
    
    def restart_service(self):
        """Restart the service using systemctl"""
        try:
            print(f"{datetime.now()}: Restarting {self.service_name}")
            subprocess.run(
                ['systemctl', 'restart', self.service_name],
                check=True,
                capture_output=True
            )
            time.sleep(10)  # Wait for service to start
            return True
        except subprocess.CalledProcessError as e:
            print(f"{datetime.now()}: Restart failed: {e.stderr}")
            return False
    
    def send_alert(self, message, severity='warning'):
        """Send alert to monitoring system"""
        try:
            requests.post(
                'https://alerts.company.com/webhook',
                json={
                    'service': self.service_name,
                    'message': message,
                    'severity': severity,
                    'timestamp': datetime.now().isoformat()
                },
                timeout=5
            )
        except Exception as e:
            print(f"Failed to send alert: {e}")
    
    def monitor(self):
        """Main monitoring loop"""
        if self.check_health():
            print(f"{datetime.now()}: {self.service_name} is healthy")
            return 0
        
        print(f"{datetime.now()}: {self.service_name} is unhealthy")
        self.send_alert(f"{self.service_name} is down", severity='warning')
        
        # Attempt restart
        for attempt in range(1, self.max_retries + 1):
            print(f"Restart attempt {attempt}/{self.max_retries}")
            
            if self.restart_service() and self.check_health():
                print(f"{datetime.now()}: Service recovered")
                self.send_alert(
                    f"{self.service_name} auto-recovered after restart",
                    severity='info'
                )
                return 0
            
            time.sleep(5)
        
        # All retries failed
        print(f"{datetime.now()}: Failed to recover service")
        self.send_alert(
            f"{self.service_name} failed to recover after {self.max_retries} attempts",
            severity='critical'
        )
        return 1

if __name__ == '__main__':
    monitor = ServiceMonitor(
        service_name='myapp',
        health_url='http://localhost:8080/health'
    )
    sys.exit(monitor.monitor())

# Runbook: High API Latency

## Symptoms
- API 95th percentile latency > 1 second
- User complaints about slow page loads
- Alert: "HighAPILatency" firing

## Severity
**Warning** - Degrades user experience but service is functional

## Investigation Steps

### 1. Check current metrics
```bash
# Check latency distribution
curl -s http://prometheus:9090/api/v1/query?query='histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))'

# Check request rate
curl -s http://prometheus:9090/api/v1/query?query='rate(http_requests_total[5m])'

# Database connections
mysql -e "SHOW PROCESSLIST;"

# Redis latency
redis-cli --latency

# External APIs
curl -w "%{time_total}\n" -o /dev/null -s https://external-api.com/health

kubectl scale deployment api --replicas=10

redis-cli CONFIG SET maxmemory-policy allkeys-lru

kubectl rollout undo deployment/api

kubectl apply -f rate-limit-config.yaml

from enum import Enum
import time

class CircuitState(Enum):
    CLOSED = "closed"  # Normal operation
    OPEN = "open"      # Failing, reject requests
    HALF_OPEN = "half_open"  # Testing recovery

class CircuitBreaker:
    def __init__(self, failure_threshold=5, timeout=60):
        self.failure_threshold = failure_threshold
        self.timeout = timeout
        self.failures = 0
        self.last_failure_time = None
        self.state = CircuitState.CLOSED
    
    def call(self, func, *args, **kwargs):
        if self.state == CircuitState.OPEN:
            if time.time() - self.last_failure_time > self.timeout:
                self.state = CircuitState.HALF_OPEN
            else:
                # Return fallback instead of calling failing service
                return self.fallback()
        
        try:
            result = func(*args, **kwargs)
            self.on_success()
            return result
        except Exception as e:
            self.on_failure()
            return self.fallback()
    
    def on_success(self):
        self.failures = 0
        self.state = CircuitState.CLOSED
    
    def on_failure(self):
        self.failures += 1
        self.last_failure_time = time.time()
        if self.failures >= self.failure_threshold:
            self.state = CircuitState.OPEN
    
    def fallback(self):
        # Return cached data or default response
        return {"status": "degraded", "data": []}

# Usage
breaker = CircuitBreaker()
result = breaker.call(external_api_call, user_id=123)

import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

def create_resilient_session():
    session = requests.Session()
    
    # Retry strategy
    retry = Retry(
        total=3,
        backoff_factor=0.3,
        status_forcelist=[500, 502, 503, 504]
    )
    
    adapter = HTTPAdapter(max_retries=retry)
    session.mount('http://', adapter)
    session.mount('https://', adapter)
    
    return session

# Usage with timeout
session = create_resilient_session()
try:
    response = session.get('https://api.example.com/data', timeout=5)
except requests.exceptions.Timeout:
    # Gracefully degrade - use cached data
    response = get_cached_data()

# Pull an image
docker pull nginx:latest

# Run a container
docker run -d \
  --name my-nginx \
  -p 8080:80 \
  nginx:latest

# List running containers
docker ps

# View logs
docker logs my-nginx

# Execute command in container
docker exec -it my-nginx bash

# Stop container
docker stop my-nginx

# Remove container
docker rm my-nginx

# Base image
FROM python:3.9-slim

# Set working directory
WORKDIR /app

# Copy requirements
COPY requirements.txt .

# Install dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=3s \
  CMD curl -f http://localhost:8000/health || exit 1

# Run application
CMD ["python", "app.py"]

# Build image
docker build -t myapp:1.0 .

# Run with environment variables
docker run -d \
  --name myapp \
  -p 8000:8000 \
  -e DATABASE_URL=postgres://db:5432/mydb \
  -e LOG_LEVEL=info \
  myapp:1.0

# View resource usage
docker stats myapp

version: '3.8'

services:
  web:
    build: .
    ports:
      - "8000:8000"
    environment:
      - DATABASE_URL=postgresql://db:5432/mydb
    depends_on:
      - db
      - redis
    restart: unless-stopped
  
  db:
    image: postgres:14
    environment:
      - POSTGRES_DB=mydb
      - POSTGRES_PASSWORD=secret
    volumes:
      - postgres_data:/var/lib/postgresql/data
  
  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"

volumes:
  postgres_data:

# Start all services
docker-compose up -d

# View logs
docker-compose logs -f web

# Scale service
docker-compose up -d --scale web=3

# Stop all services
docker-compose down

# Clone repository
git clone https://github.com/company/repo.git
cd repo

# Create feature branch
git checkout -b feature/add-monitoring

# Make changes and commit
git add .
git commit -m "Add Prometheus monitoring"

# Push to remote
git push origin feature/add-monitoring

# Update from main
git checkout main
git pull origin main
git checkout feature/add-monitoring
git rebase main

# Merge feature (after PR approval)
git checkout main
git merge feature/add-monitoring
git push origin main

# Short-lived feature branches
git checkout -b feature/quick-fix
# Work for < 1 day
git push origin feature/quick-fix
# Merge to main immediately after review

name: Deploy to Production

on:
  push:
    branches: [main]

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      
      - name: Run tests
        run: |
          npm install
          npm test
      
      - name: Run linting
        run: npm run lint
  
  build:
    needs: test
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      
      - name: Build Docker image
        run: |
          docker build -t myapp:${{ github.sha }} .
          docker tag myapp:${{ github.sha }} myapp:latest
      
      - name: Push to registry
        run: |
          echo ${{ secrets.DOCKER_PASSWORD }} | docker login -u ${{ secrets.DOCKER_USERNAME }} --password-stdin
          docker push myapp:${{ github.sha }}
          docker push myapp:latest
  
  deploy:
    needs: build
    runs-on: ubuntu-latest
    steps:
      - name: Deploy to production
        run: |
          kubectl set image deployment/myapp \
            myapp=myapp:${{ github.sha }}
          kubectl rollout status deployment/myapp

#!/bin/bash
# deploy.sh - Simple deployment script

set -e  # Exit on error

# Configuration
APP_NAME="myapp"
VERSION=$(git rev-parse --short HEAD)
ENVIRONMENT=${1:-staging}

echo "Deploying $APP_NAME version $VERSION to $ENVIRONMENT"

# Run tests
echo "Running tests..."
npm test

# Build application
echo "Building application..."
npm run build

# Build Docker image
echo "Building Docker image..."
docker build -t $APP_NAME:$VERSION .

# Push to registry
echo "Pushing to registry..."
docker tag $APP_NAME:$VERSION registry.company.com/$APP_NAME:$VERSION
docker push registry.company.com/$APP_NAME:$VERSION

# Deploy to Kubernetes
echo "Deploying to Kubernetes..."
kubectl set image deployment/$APP_NAME \
  $APP_NAME=registry.company.com/$APP_NAME:$VERSION \
  --namespace=$ENVIRONMENT

# Wait for rollout
kubectl rollout status deployment/$APP_NAME \
  --namespace=$ENVIRONMENT \
  --timeout=5m

echo "Deployment complete!"

# Run smoke tests
echo "Running smoke tests..."
curl -f https://$ENVIRONMENT.company.com/health || {
  echo "Health check failed! Rolling back..."
  kubectl rollout undo deployment/$APP_NAME --namespace=$ENVIRONMENT
  exit 1
}

echo "Deployment successful!"

# View deployment history
kubectl rollout history deployment/myapp

# Rollback to previous version
kubectl rollout undo deployment/myapp

# Rollback to specific revision
kubectl rollout undo deployment/myapp --to-revision=3

# Check rollback status
kubectl rollout status deployment/myapp

# View current load average
uptime
# Output: 15:30:45 up 10 days, 3:25, 2 users, load average: 2.5, 2.0, 1.8
# Load average: 1min, 5min, 15min

# View detailed system stats
top
# Press '1' to see per-CPU stats
# Press 'M' to sort by memory
# Press 'P' to sort by CPU

# Better alternative to top
htop

# CPU usage per process
ps aux --sort=-%cpu | head -10

# Real-time CPU monitoring
mpstat 1 5  # 5 samples, 1 second apart

# CPU usage by core
lscpu

# Memory usage
free -h
#               total        used        free      shared  buff/cache   available
# Mem:           15Gi       8.2Gi       2.1Gi       324Mi       5.0Gi       6.5Gi
# Swap:         2.0Gi       512Mi       1.5Gi

# Memory usage per process
ps aux --sort=-%mem | head -10

# Detailed memory info
cat /proc/meminfo

# Check for OOM (Out of Memory) kills
dmesg | grep -i "out of memory"
journalctl -k | grep -i "killed process"

# Disk usage
df -h

# Inode usage (can run out even with disk space)
df -i

# Disk I/O statistics
iostat -x 1 5

# Find large files
du -sh /* | sort -rh | head -10

# Find files using most disk I/O
iotop

# Network connections
netstat -tuln  # Listening ports
netstat -tun   # Established connections

# Network statistics
netstat -s

# Network interface stats
ifconfig
ip addr show

# Bandwidth usage
iftop

# Check DNS resolution
nslookup google.com
dig google.com

# All processes
ps aux

# Process tree
pstree

# Find process by name
pgrep -a nginx

# Kill process
kill -9 <PID>
pkill -9 nginx

# Check zombie processes
ps aux | grep 'Z'

# System logs
tail -f /var/log/syslog
journalctl -f  # Follow systemd logs

# Application logs
tail -f /var/log/nginx/error.log

# Search for errors
grep -i error /var/log/syslog | tail -20

# Check auth logs
tail -f /var/log/auth.log

# Find CPU-intensive process
top -o %CPU

# If it's a runaway process
kill -15 <PID>  # Graceful
kill -9 <PID>   # Force kill

# If it's legitimate high load
# - Scale horizontally (add servers)
# - Optimize application code
# - Add caching

# Clear cache (safe, kernel will rebuild)
sync
echo 3 > /proc/sys/vm/drop_caches

# Find memory leaks
valgrind --leak-check=full ./myapp

# Restart memory-hungry service
systemctl restart myapp

# Find large files
find / -type f -size +100M -exec ls -lh {} \;

# Clean up logs
journalctl --vacuum-time=7d  # Keep last 7 days
find /var/log -name "*.log" -mtime +30 -delete

# Clean package cache (Ubuntu/Debian)
apt-get clean
apt-get autoclean

# Test connectivity
ping -c 5 google.com

# Test bandwidth
iperf3 -c server.example.com

# Trace route
traceroute google.com

# Check firewall
iptables -L -n

#!/bin/bash
# quick-diag.sh - Quick system diagnostics

echo "=== System Load ==="
uptime

echo -e "\n=== CPU Usage ==="
top -bn1 | head -20

echo -e "\n=== Memory Usage ==="
free -h

echo -e "\n=== Disk Usage ==="
df -h

echo -e "\n=== Top CPU Processes ==="
ps aux --sort=-%cpu | head -6

echo -e "\n=== Top Memory Processes ==="
ps aux --sort=-%mem | head -6

echo -e "\n=== Network Connections ==="
netstat -tuln | wc -l
echo "connections"

echo -e "\n=== Recent Errors ==="
journalctl -p err -n 10 --no-pager