24f2cd64e9
🎬 ARR Suite Template Bootstrap - Complete Media Automation Stack Features: - 16 production services (Prowlarr, Sonarr, Radarr, Plex, etc.) - One-command Ansible deployment - VPN-protected downloads via Gluetun - Tailscale secure access - Production-ready security (UFW, Fail2Ban) - Automated backups and monitoring - Comprehensive documentation Ready for customization and deployment to any VPS. Co-authored-by: openhands <openhands@all-hands.dev>
104 lines
4.0 KiB
Django/Jinja
104 lines
4.0 KiB
Django/Jinja
#!/bin/bash
|
|
# Docker monitoring script for Arrs Media Stack
|
|
# Generated by Ansible
|
|
|
|
LOG_DIR="{{ docker_root }}/logs/arrs"
|
|
TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
|
|
LOG_FILE="$LOG_DIR/docker-monitor-$(date '+%Y%m%d').log"
|
|
|
|
# Ensure log directory exists
|
|
mkdir -p "$LOG_DIR"
|
|
|
|
# Function to log with timestamp
|
|
log_with_timestamp() {
|
|
echo "[$TIMESTAMP] $1" >> "$LOG_FILE"
|
|
}
|
|
|
|
# Change to compose directory
|
|
cd {{ docker_compose_dir }}
|
|
|
|
# Check Docker daemon
|
|
if ! docker info >/dev/null 2>&1; then
|
|
log_with_timestamp "DOCKER_DAEMON FAILED - Docker daemon not responding"
|
|
exit 1
|
|
fi
|
|
|
|
log_with_timestamp "DOCKER_DAEMON OK"
|
|
|
|
# Get container stats
|
|
CONTAINER_STATS=$(docker stats --no-stream --format "table {{ '{{.Container}}' }}\t{{ '{{.CPUPerc}}' }}\t{{ '{{.MemUsage}}' }}\t{{ '{{.MemPerc}}' }}\t{{ '{{.NetIO}}' }}\t{{ '{{.BlockIO}}' }}")
|
|
|
|
# Log container resource usage
|
|
while IFS=$'\t' read -r container cpu mem_usage mem_perc net_io block_io; do
|
|
if [[ "$container" != "CONTAINER" ]]; then
|
|
log_with_timestamp "CONTAINER_STATS $container CPU:$cpu MEM:$mem_usage($mem_perc) NET:$net_io DISK:$block_io"
|
|
fi
|
|
done <<< "$CONTAINER_STATS"
|
|
|
|
# Check individual service health
|
|
SERVICES=("sonarr" "radarr" "lidarr" "bazarr" "prowlarr" "watchtower")
|
|
PORTS=({{ ports.sonarr }} {{ ports.radarr }} {{ ports.lidarr }} {{ ports.bazarr }} {{ ports.prowlarr }})
|
|
|
|
for i in "${!SERVICES[@]}"; do
|
|
service="${SERVICES[$i]}"
|
|
|
|
# Get container status
|
|
STATUS=$(docker-compose ps -q "$service" | xargs docker inspect --format='{{ "{{.State.Status}}" }}' 2>/dev/null)
|
|
|
|
if [[ "$STATUS" == "running" ]]; then
|
|
# Check container health
|
|
HEALTH=$(docker-compose ps -q "$service" | xargs docker inspect --format='{{ "{{.State.Health.Status}}" }}' 2>/dev/null)
|
|
|
|
if [[ "$HEALTH" == "healthy" ]] || [[ "$HEALTH" == "" ]]; then
|
|
log_with_timestamp "SERVICE_$service OK"
|
|
else
|
|
log_with_timestamp "SERVICE_$service UNHEALTHY - Health status: $HEALTH"
|
|
fi
|
|
|
|
# Check restart count
|
|
RESTART_COUNT=$(docker-compose ps -q "$service" | xargs docker inspect --format='{{ "{{.RestartCount}}" }}' 2>/dev/null)
|
|
if [[ "$RESTART_COUNT" -gt 5 ]]; then
|
|
log_with_timestamp "SERVICE_$service WARNING - High restart count: $RESTART_COUNT"
|
|
fi
|
|
|
|
else
|
|
log_with_timestamp "SERVICE_$service FAILED - Status: $STATUS"
|
|
|
|
# Try to restart the service
|
|
log_with_timestamp "SERVICE_$service RESTART_ATTEMPT"
|
|
docker-compose restart "$service" 2>/dev/null
|
|
fi
|
|
done
|
|
|
|
# Check Docker system resources
|
|
DOCKER_SYSTEM_DF=$(docker system df --format "table {{ '{{.Type}}' }}\t{{ '{{.Total}}' }}\t{{ '{{.Active}}' }}\t{{ '{{.Size}}' }}\t{{ '{{.Reclaimable}}' }}")
|
|
log_with_timestamp "DOCKER_SYSTEM_DF $DOCKER_SYSTEM_DF"
|
|
|
|
# Check for stopped containers
|
|
STOPPED_CONTAINERS=$(docker ps -a --filter "status=exited" --format "{{ '{{.Names}}' }}" | grep -E "(sonarr|radarr|lidarr|bazarr|prowlarr|watchtower)" || true)
|
|
if [[ -n "$STOPPED_CONTAINERS" ]]; then
|
|
log_with_timestamp "STOPPED_CONTAINERS $STOPPED_CONTAINERS"
|
|
fi
|
|
|
|
# Check Docker logs for errors (last 5 minutes)
|
|
FIVE_MIN_AGO=$(date -d '5 minutes ago' '+%Y-%m-%dT%H:%M:%S')
|
|
for service in "${SERVICES[@]}"; do
|
|
ERROR_COUNT=$(docker-compose logs --since="$FIVE_MIN_AGO" "$service" 2>/dev/null | grep -i error | wc -l)
|
|
if [[ "$ERROR_COUNT" -gt 0 ]]; then
|
|
log_with_timestamp "SERVICE_$service ERRORS - $ERROR_COUNT errors in last 5 minutes"
|
|
fi
|
|
done
|
|
|
|
# Cleanup old log files (keep 7 days)
|
|
find "$LOG_DIR" -name "docker-monitor-*.log" -mtime +7 -delete 2>/dev/null
|
|
|
|
# Cleanup Docker system if disk usage is high
|
|
DISK_USAGE=$(df {{ docker_root }} | tail -1 | awk '{print $5}' | cut -d'%' -f1)
|
|
if [[ $DISK_USAGE -gt 85 ]]; then
|
|
log_with_timestamp "CLEANUP_ATTEMPT Disk usage ${DISK_USAGE}% - Running Docker cleanup"
|
|
docker system prune -f >/dev/null 2>&1
|
|
docker image prune -f >/dev/null 2>&1
|
|
log_with_timestamp "CLEANUP_COMPLETED Docker cleanup finished"
|
|
fi
|
|
|
|
exit 0 |