KI-Server-Wartung: Linux-Tipps für produktive LLM-Pipelines

# System-Updates prüfen (nicht installieren!)
sudo apt list --upgradable

# Logs durchsehen
sudo journalctl --since "7 days ago" | grep -i error

# Disk Usage prüfen
df -h

# GPU-Status
nvidia-smi

# Docker Containers
docker ps -a

# System-Updates installieren
sudo apt update && sudo apt upgrade -y

# Nützliche Tools
sudo apt install -y htop glances nvtop

# Prometheus + Grafana Update
cd /opt/monitoring && docker compose pull && docker compose up -d

# docker-compose.yml für Monitoring
services:
  prometheus:
    image: prom/prometheus:latest
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./prometheus_data:/prometheus
    ports:
      - "9090:9090"

  node-exporter:
    image: prom/node-exporter:latest
    pid: host
    restart: unless-stopped
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    volumes:
      - ./grafana_data:/var/lib/grafana