fanyang

Memo

共 4 条

通过 SSH 迁移 docker images

需要安装好：

  • pv
  • zstd

把命令中的 ssh <user>@<host> 替换成目标端：

docker images --format "{{.Repository}}:{{.Tag}}" | grep -v 'none' \
| xargs -I{} bash -c \
"docker save {} | zstd -T0 --fast | pv | ssh <user>@<host> 'zstd -d | docker load'"

ArchLinux NVIDIA GPU 容器启动失败

ArchLinux （2025-09-06）启动 GPU 容器失败：

-> % docker run --rm --gpus=all nvidia/cuda:12.1.1-base-ubuntu22.04 nvidia-smi
Unable to find image 'nvidia/cuda:12.1.1-base-ubuntu22.04' locally
12.1.1-base-ubuntu22.04: Pulling from nvidia/cuda
aece8493d397: Already exists
dd4939a04761: Pull complete
b0d7cc89b769: Pull complete
1532d9024b9c: Pull complete
04fc8a31fa53: Pull complete
Digest: sha256:457a4076c56025f51217bff647ca631c7880ad3dbf546b03728ba98297ebbc22
Status: Downloaded newer image for nvidia/cuda:12.1.1-base-ubuntu22.04
docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: ldcache error: process /sbin/ldconfig terminated with signal 9

解决办法：

System Update in Arch Linux, broked NVIDIA container. Open Source drivers

sudo nvidia-ctk cdi generate --output=/etc/cdi/nvidia.yaml
sudo nvidia-ctk config --in-place --set nvidia-container-runtime.mode=cdi
systemctl restart docker

# /etc/docker/daemon.json
  "default-runtime": "nvidia",
  "runtimes": {
    "nvidia": {
      "path": "/usr/bin/nvidia-container-runtime",
      "runtimeArgs": []
    }
  }

docker-compose.yml 合集

本篇文章收录了鄙人使用的各种服务的 docker-compose.yml

Milvus

services:
  etcd:
    container_name: milvus-etcd
    image: registry.example.com/quay.io/coreos/etcd:v3.5.18
    environment:
      - ETCD_AUTO_COMPACTION_MODE=revision
      - ETCD_AUTO_COMPACTION_RETENTION=1000
      - ETCD_QUOTA_BACKEND_BYTES=4294967296
      - ETCD_SNAPSHOT_COUNT=50000
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/etcd:/etcd
    command: etcd -advertise-client-urls=http://etcd:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
    healthcheck:
      test: ["CMD", "etcdctl", "endpoint", "health"]
      interval: 30s
      timeout: 20s
      retries: 3

  minio:
    container_name: milvus-minio
    image: registry.example.com/minio/minio:RELEASE.2023-03-20T20-16-18Z
    environment:
      MINIO_ACCESS_KEY: minioadmin
      MINIO_SECRET_KEY: minioadmin
    ports:
      - "9001:9001"
      - "9000:9000"
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/minio:/minio_data
    command: minio server /minio_data --console-address ":9001"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 20s
      retries: 3

  standalone:
    container_name: milvus-standalone
    image: registry.example.com/milvusdb/milvus:v2.5.12
    command: ["milvus", "run", "standalone"]
    security_opt:
    - seccomp:unconfined
    environment:
      ETCD_ENDPOINTS: etcd:2379
      MINIO_ADDRESS: minio:9000
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/milvus:/var/lib/milvus
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
      interval: 30s
      start_period: 90s
      timeout: 20s
      retries: 3
    ports:
      - "19530:19530"
      - "9091:9091"
    depends_on:
      - "etcd"
      - "minio"

networks:
  default:
    name: milvus

使用 Docker Compose 运行 node-exporter

services:
  node_exporter:
    image: quay.io/prometheus/node-exporter:latest
    container_name: node-exporter
    command:
      - '--path.rootfs=/host'
    network_mode: host
    pid: host
    restart: unless-stopped
    volumes:
      - '/:/host:ro,rslave'
Memo