sharenet/scripts/monitor.sh

#!/bin/bash

# Sharenet Monitoring Script
# This script monitors the application status and system resources

set -e

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

# Configuration
APP_NAME="${APP_NAME:-sharenet}"
MONITOR_TYPE="${MONITOR_TYPE:-production}"  # production or ci-cd

# Functions
log_info() {
    echo -e "${BLUE}[INFO]${NC} $1"
}

log_success() {
    echo -e "${GREEN}[SUCCESS]${NC} $1"
}

log_warning() {
    echo -e "${YELLOW}[WARNING]${NC} $1"
}

log_error() {
    echo -e "${RED}[ERROR]${NC} $1"
}

show_help() {
    cat << EOF
Sharenet Monitoring Script

Usage: $0 [OPTIONS]

Options:
    --type TYPE        Monitoring type: production or ci-cd (default: production)
    --app-name NAME    Application name (default: sharenet)
    --help             Show this help message

Environment Variables:
    MONITOR_TYPE       Set monitoring type (production/ci-cd)
    APP_NAME           Set application name

Examples:
    $0                                    # Monitor production environment
    $0 --type ci-cd                      # Monitor CI/CD environment
    $0 --app-name myapp                  # Monitor specific application
    MONITOR_TYPE=ci-cd $0                # Monitor CI/CD environment
EOF
}

monitor_production() {
    log_info "=== $APP_NAME Production Environment Status ==="
    echo "Date: $(date)"
    echo "Uptime: $(uptime)"
    echo

    # Check if we're in the application directory
    if [ -f "docker-compose.yml" ]; then
        log_info "Container Status:"
        if docker-compose ps; then
            log_success "Docker Compose is running"
        else
            log_error "Docker Compose is not running"
        fi
        echo

        log_info "Recent Application Logs:"
        docker-compose logs --tail=20
        echo
    else
        log_warning "Not in application directory (docker-compose.yml not found)"
    fi

    log_info "System Resources:"
    echo "CPU Usage:"
    top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1
    echo

    echo "Memory Usage:"
    free -h
    echo

    echo "Disk Usage:"
    df -h
    echo

    echo "Network Connections:"
    netstat -tuln | grep -E ':(80|443|3000|3001)' || log_warning "No application ports found"
    echo

    # Health check
    log_info "Health Check:"
    if curl -s -f http://localhost/health > /dev/null 2>&1; then
        log_success "Application health check passed"
    else
        log_error "Application health check failed"
    fi
}

monitor_ci_cd() {
    log_info "=== CI/CD Server Status ==="
    echo "Date: $(date)"
    echo "Uptime: $(uptime)"
    echo

    log_info "Docker Registry Status:"
    if docker ps --format "table {{.Names}}\t{{.Status}}" | grep -q registry; then
        log_success "Docker Registry containers are running"
        docker ps --format "table {{.Names}}\t{{.Status}}" | grep registry
    else
        log_error "Docker Registry containers are not running"
    fi
    echo

    log_info "Actions Runner Status:"
    if systemctl is-active --quiet forgejo-runner.service; then
        log_success "Forgejo runner is running"
        systemctl status forgejo-runner.service --no-pager
    else
        log_error "Forgejo runner is not running"
    fi
    echo

    log_info "System Resources:"
    echo "CPU Usage:"
    top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1
    echo

    echo "Memory Usage:"
    free -h | grep Mem
    echo

    echo "Disk Usage:"
    df -h /
    echo

    # Registry health check
    log_info "Registry Health Check:"
    if curl -s -f -k https://localhost/v2/_catalog > /dev/null 2>&1; then
        log_success "Docker Registry is accessible"
    else
        log_error "Docker Registry is not accessible"
    fi
}

# Parse command line arguments
while [[ $# -gt 0 ]]; do
    case $1 in
        --type)
            MONITOR_TYPE="$2"
            shift 2
            ;;
        --app-name)
            APP_NAME="$2"
            shift 2
            ;;
        --help|-h)
            show_help
            exit 0
            ;;
        *)
            log_error "Unknown option: $1"
            show_help
            exit 1
            ;;
    esac
done

# Main monitoring logic
case "$MONITOR_TYPE" in
    production)
        monitor_production
        ;;
    ci-cd)
        monitor_ci_cd
        ;;
    *)
        log_error "Invalid monitor type: $MONITOR_TYPE"
        log_error "Valid types: production, ci-cd"
        exit 1
        ;;
esac

log_success "Monitoring completed"