Files
michaelschiemer/deployment/applications/scripts/health-check.sh
Michael Schiemer 9b74ade5b0 feat: Fix discovery system critical issues
Resolved multiple critical discovery system issues:

## Discovery System Fixes
- Fixed console commands not being discovered on first run
- Implemented fallback discovery for empty caches
- Added context-aware caching with separate cache keys
- Fixed object serialization preventing __PHP_Incomplete_Class

## Cache System Improvements
- Smart caching that only caches meaningful results
- Separate caches for different execution contexts (console, web, test)
- Proper array serialization/deserialization for cache compatibility
- Cache hit logging for debugging and monitoring

## Object Serialization Fixes
- Fixed DiscoveredAttribute serialization with proper string conversion
- Sanitized additional data to prevent object reference issues
- Added fallback for corrupted cache entries

## Performance & Reliability
- All 69 console commands properly discovered and cached
- 534 total discovery items successfully cached and restored
- No more __PHP_Incomplete_Class cache corruption
- Improved error handling and graceful fallbacks

## Testing & Quality
- Fixed code style issues across discovery components
- Enhanced logging for better debugging capabilities
- Improved cache validation and error recovery

Ready for production deployment with stable discovery system.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-08-13 12:04:17 +02:00

463 lines
13 KiB
Bash
Executable File

#!/bin/bash
# Health Check Script for Custom PHP Framework
# Verifies application health after deployment
# Usage: ./health-check.sh [environment] [options]
set -euo pipefail
# Script configuration
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "${SCRIPT_DIR}/../../../" && pwd)"
DEPLOYMENT_DIR="${PROJECT_ROOT}/deployment"
APPLICATIONS_DIR="${DEPLOYMENT_DIR}/applications"
# Default settings
DEFAULT_ENV="staging"
VERBOSE=false
MAX_RETRIES=10
RETRY_INTERVAL=30
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# Logging functions
log() {
echo -e "${GREEN}[$(date +'%Y-%m-%d %H:%M:%S')] INFO: $1${NC}"
}
warn() {
echo -e "${YELLOW}[$(date +'%Y-%m-%d %H:%M:%S')] WARN: $1${NC}"
}
error() {
echo -e "${RED}[$(date +'%Y-%m-%d %H:%M:%S')] ERROR: $1${NC}"
}
debug() {
if [ "$VERBOSE" = true ]; then
echo -e "${BLUE}[$(date +'%Y-%m-%d %H:%M:%S')] DEBUG: $1${NC}"
fi
}
success() {
echo -e "${GREEN}[$(date +'%Y-%m-%d %H:%M:%S')] SUCCESS: $1${NC}"
}
# Usage information
show_usage() {
cat << EOF
Usage: $0 [environment] [options]
Environment:
staging Check staging environment (default)
production Check production environment
Options:
--verbose Enable verbose output
--max-retries N Maximum number of health check retries (default: 10)
--retry-interval N Seconds between retries (default: 30)
-h, --help Show this help message
Examples:
$0 staging # Check staging environment
$0 production --verbose # Check production with detailed output
$0 staging --max-retries 5 # Check with custom retry limit
EOF
}
# Parse command line arguments
parse_arguments() {
local environment=""
while [[ $# -gt 0 ]]; do
case $1 in
staging|production)
environment="$1"
shift
;;
--verbose)
VERBOSE=true
shift
;;
--max-retries)
MAX_RETRIES="$2"
shift 2
;;
--retry-interval)
RETRY_INTERVAL="$2"
shift 2
;;
-h|--help)
show_usage
exit 0
;;
*)
error "Unknown argument: $1"
show_usage
exit 1
;;
esac
done
# Set environment, defaulting to staging
CHECK_ENV="${environment:-$DEFAULT_ENV}"
}
# Load environment configuration
load_environment() {
local env_file="${APPLICATIONS_DIR}/environments/.env.${CHECK_ENV}"
if [[ ! -f "$env_file" ]]; then
error "Environment file not found: $env_file"
exit 1
fi
debug "Loading environment from: $env_file"
set -a
source "$env_file"
set +a
}
# Check Docker container health
check_container_health() {
log "Checking Docker container health"
local compose_files="-f ${PROJECT_ROOT}/docker-compose.yml -f ${APPLICATIONS_DIR}/docker-compose.${CHECK_ENV}.yml"
local env_file="--env-file ${APPLICATIONS_DIR}/environments/.env.${CHECK_ENV}"
cd "$PROJECT_ROOT"
# Get container status
local containers
containers=$(docker-compose $compose_files $env_file ps --services)
local all_healthy=true
while IFS= read -r service; do
if [[ -n "$service" ]]; then
local container_status
container_status=$(docker-compose $compose_files $env_file ps "$service" | tail -n +3 | awk '{print $4}')
case "$container_status" in
"Up"|"Up (healthy)")
success "Container $service: $container_status"
;;
*)
error "Container $service: $container_status"
all_healthy=false
;;
esac
fi
done <<< "$containers"
if [ "$all_healthy" = false ]; then
return 1
fi
debug "All containers are healthy"
return 0
}
# Check HTTP endpoints
check_http_endpoints() {
log "Checking HTTP endpoints"
# Determine base URL based on environment
local base_url
if [ "$CHECK_ENV" = "production" ]; then
base_url="https://michaelschiemer.de"
else
base_url="https://localhost:${APP_SSL_PORT:-443}"
fi
# Test endpoints
local endpoints=(
"/"
"/health"
"/api/health"
)
local all_ok=true
for endpoint in "${endpoints[@]}"; do
local url="${base_url}${endpoint}"
debug "Testing endpoint: $url"
local http_code
http_code=$(curl -s -o /dev/null -w "%{http_code}" -k \
-H "User-Agent: Mozilla/5.0 (HealthCheck)" \
--max-time 30 \
"$url" || echo "000")
case "$http_code" in
200|301|302)
success "Endpoint $endpoint: HTTP $http_code"
;;
000)
error "Endpoint $endpoint: Connection failed"
all_ok=false
;;
*)
error "Endpoint $endpoint: HTTP $http_code"
all_ok=false
;;
esac
done
if [ "$all_ok" = false ]; then
return 1
fi
debug "All HTTP endpoints are responding correctly"
return 0
}
# Check database connectivity
check_database() {
log "Checking database connectivity"
local compose_files="-f ${PROJECT_ROOT}/docker-compose.yml -f ${APPLICATIONS_DIR}/docker-compose.${CHECK_ENV}.yml"
local env_file="--env-file ${APPLICATIONS_DIR}/environments/.env.${CHECK_ENV}"
cd "$PROJECT_ROOT"
# Test database connection through application
local db_check
if db_check=$(docker-compose $compose_files $env_file exec -T php \
php console.php db:ping 2>&1); then
success "Database connection: OK"
debug "Database response: $db_check"
return 0
else
error "Database connection: FAILED"
error "Database error: $db_check"
return 1
fi
}
# Check Redis connectivity
check_redis() {
log "Checking Redis connectivity"
local compose_files="-f ${PROJECT_ROOT}/docker-compose.yml -f ${APPLICATIONS_DIR}/docker-compose.${CHECK_ENV}.yml"
local env_file="--env-file ${APPLICATIONS_DIR}/environments/.env.${CHECK_ENV}"
cd "$PROJECT_ROOT"
# Test Redis connection
local redis_check
if redis_check=$(docker-compose $compose_files $env_file exec -T redis \
redis-cli ping 2>&1); then
if [[ "$redis_check" == *"PONG"* ]]; then
success "Redis connection: OK"
debug "Redis response: $redis_check"
return 0
else
error "Redis connection: Unexpected response - $redis_check"
return 1
fi
else
error "Redis connection: FAILED"
error "Redis error: $redis_check"
return 1
fi
}
# Check queue worker status
check_queue_worker() {
log "Checking queue worker status"
local compose_files="-f ${PROJECT_ROOT}/docker-compose.yml -f ${APPLICATIONS_DIR}/docker-compose.${CHECK_ENV}.yml"
local env_file="--env-file ${APPLICATIONS_DIR}/environments/.env.${CHECK_ENV}"
cd "$PROJECT_ROOT"
# Check if worker container is running
local worker_status
worker_status=$(docker-compose $compose_files $env_file ps queue-worker | tail -n +3 | awk '{print $4}')
case "$worker_status" in
"Up")
success "Queue worker: Running"
# Check worker process inside container
local worker_process
if worker_process=$(docker-compose $compose_files $env_file exec -T queue-worker \
ps aux | grep -v grep | grep worker 2>&1); then
debug "Worker process found: $worker_process"
return 0
else
warn "Queue worker container running but no worker process found"
return 1
fi
;;
*)
error "Queue worker: $worker_status"
return 1
;;
esac
}
# Check application performance
check_performance() {
log "Checking application performance"
local base_url
if [ "$CHECK_ENV" = "production" ]; then
base_url="https://michaelschiemer.de"
else
base_url="https://localhost:${APP_SSL_PORT:-443}"
fi
# Test response times
local response_time
response_time=$(curl -s -o /dev/null -w "%{time_total}" -k \
-H "User-Agent: Mozilla/5.0 (HealthCheck)" \
--max-time 30 \
"${base_url}/" || echo "timeout")
if [[ "$response_time" == "timeout" ]]; then
error "Performance check: Request timed out"
return 1
fi
local response_ms
response_ms=$(echo "$response_time * 1000" | bc -l | cut -d. -f1)
# Performance thresholds (milliseconds)
local warning_threshold=2000
local error_threshold=5000
if [ "$response_ms" -lt "$warning_threshold" ]; then
success "Performance: ${response_ms}ms (Good)"
return 0
elif [ "$response_ms" -lt "$error_threshold" ]; then
warn "Performance: ${response_ms}ms (Slow)"
return 0
else
error "Performance: ${response_ms}ms (Too slow)"
return 1
fi
}
# Check SSL certificate
check_ssl() {
if [ "$CHECK_ENV" != "production" ]; then
debug "Skipping SSL check for non-production environment"
return 0
fi
log "Checking SSL certificate"
local domain="michaelschiemer.de"
local ssl_info
if ssl_info=$(echo | openssl s_client -connect "${domain}:443" -servername "$domain" 2>/dev/null | \
openssl x509 -noout -dates 2>/dev/null); then
local expiry_date
expiry_date=$(echo "$ssl_info" | grep "notAfter" | cut -d= -f2)
local expiry_timestamp
expiry_timestamp=$(date -d "$expiry_date" +%s 2>/dev/null || echo "0")
local current_timestamp
current_timestamp=$(date +%s)
local days_until_expiry
days_until_expiry=$(( (expiry_timestamp - current_timestamp) / 86400 ))
if [ "$days_until_expiry" -gt 30 ]; then
success "SSL certificate: Valid (expires in $days_until_expiry days)"
return 0
elif [ "$days_until_expiry" -gt 7 ]; then
warn "SSL certificate: Expires soon (in $days_until_expiry days)"
return 0
else
error "SSL certificate: Critical expiry (in $days_until_expiry days)"
return 1
fi
else
error "SSL certificate: Could not retrieve certificate information"
return 1
fi
}
# Comprehensive health check with retries
run_health_checks() {
log "Starting comprehensive health check for $CHECK_ENV environment"
local checks=(
"check_container_health"
"check_database"
"check_redis"
"check_queue_worker"
"check_http_endpoints"
"check_performance"
"check_ssl"
)
local attempt=1
local all_passed=false
while [ $attempt -le $MAX_RETRIES ] && [ "$all_passed" = false ]; do
log "Health check attempt $attempt of $MAX_RETRIES"
local failed_checks=()
for check in "${checks[@]}"; do
debug "Running check: $check"
if ! $check; then
failed_checks+=("$check")
fi
done
if [ ${#failed_checks[@]} -eq 0 ]; then
all_passed=true
success "All health checks passed!"
else
warn "Failed checks: ${failed_checks[*]}"
if [ $attempt -lt $MAX_RETRIES ]; then
log "Waiting $RETRY_INTERVAL seconds before retry..."
sleep $RETRY_INTERVAL
fi
fi
((attempt++))
done
if [ "$all_passed" = false ]; then
error "Health checks failed after $MAX_RETRIES attempts"
return 1
fi
return 0
}
# Main function
main() {
log "Starting health check for $CHECK_ENV environment"
load_environment
if run_health_checks; then
success "Health check completed successfully for $CHECK_ENV environment"
log "Application is healthy and ready to serve traffic"
return 0
else
error "Health check failed for $CHECK_ENV environment"
error "Please review the application status and fix any issues"
return 1
fi
}
# Parse arguments and run main function
parse_arguments "$@"
main