我尝试部署 Docker 堆栈，其中包括我的开发环境。但在随机情况下，我会遇到下一个错误:
> failed to create service < service_name >: Cannot connect to the
> Docker daemon at unix:///var/run/docker.sock. Is the docker daemon
> running?
接下来我重新启动 docker 守护进程。有时需要终止 docker 进程和 shim。我删除旧堆栈并重新构建。有时 docker 成功完成构建，但套接字在启动阶段崩溃。
当我以常规模式启动它时，所有容器都可以正常工作，没有集群或堆栈。它并不完全在群体内部工作。
我使用下一个命令来构建:
> $ docker stack deploy dev-env-stc -c docker-compose.yml
环境在Antergos Linux(Arch)中运行。
布局如图所示
使用命令创建的 Nginx 容器和 docker 网络:
>$ docker run --detach --name nginx-main --net dev-env-ext --ip 10.20.20.10 --publish 80:80 --publish 443:443 --volume /env-vol/nginx/conf:/etc/nginx:ro --volume /env-vol/nginx/www:/usr/var/www --volume /env-vol/nginx/logs:/usr/var/logs --volume /env-vol/nginx/run:/usr/var/run --volume /env-vol/ssl:/usr/var/ssl:ro nginx-webserver
>
> $ docker network create --driver=bridge --attachable --ipv6 --subnet fd19:eb5a:3d2f:f15d::/48 --subnet 10.20.20.0/24 --gateway 10.20.20.1 dev-env-ext
>
> $ docker network create --driver=bridge --attachable --ipv6 --subnet fd19:eb5a:3e30:f15d::/48 --subnet 10.20.30.0/24 --gateway 10.20.30.1 dev-env-int
>
> $ docker network create --driver=overlay --attachable --ipv6 --subnet fd19:eb5a:3c1e:f15d::/48 --subnet 10.20.40.0/24 --gateway 10.20.40.1 dev-env-swarm
>
> $ docker network connect dev-env-swarm --ip=10.20.40.10 nginx-main
>
> $ docker network connect dev-env-int --ip=10.20.30.10 nginx-main
我的 docker-compose.yml 文件:
version: '3.6'
volumes:
postgres-data:
driver: local
redis-data:
driver: local
networks:
dev-env-swarm:
external: true
services:
gitlab:
image: gitlab/gitlab-ce:latest
hostname: gitlab.testenv.top
external_links:
- nginx-main
ports:
- 22:22
healthcheck:
test: ["CMD", "curl", "-f", "https://localhost:443"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: vip
resources:
limits:
cpus: "0.50"
memory: 4096M
reservations:
cpus: "0.10"
memory: 512M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 300s
networks:
dev-env-swarm:
aliases:
- gitlab.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
volumes:
- /env-vol/gitlab/config:/etc/gitlab
- /env-vol/gitlab/logs:/var/log/gitlab
- /env-vol/gitlab/data:/var/opt/gitlab
external_links:
- nginx-main
redis:
env_file: .env
image: redis:3.2.6-alpine
hostname: redis.testenv.top
external_links:
- nginx-main
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:6379"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 1024M
reservations:
cpus: "0.05"
memory: 128M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
volumes:
- redis-data:/var/lib/redis
command: redis-server --appendonly yes
networks:
dev-env-swarm:
aliases:
- redis.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
redisco:
image: rediscommander/redis-commander:latest
hostname: redisco.testenv.top
external_links:
- nginx-main
depends_on:
- redis
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8081"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 512M
reservations:
cpus: "0.05"
memory: 256M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
networks:
dev-env-swarm:
aliases:
- redisco.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
environment:
REDIS_PORT: 6379
REDIS_HOST: redis.testenv.top
plantuml:
image: plantuml/plantuml-server:tomcat
hostname: plantuml.testenv.top
external_links:
- nginx-main
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 1024M
reservations:
cpus: "0.05"
memory: 256M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
networks:
dev-env-swarm:
aliases:
- plantuml.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
portainer-agent:
image: portainer/agent
external_links:
- nginx-main
expose:
- 9001
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 1024M
reservations:
cpus: "0.05"
memory: 256M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
environment:
AGENT_CLUSTER_ADDR: tasks.portainer-agent
AGENT_PORT: 9001
LOG_LEVEL: debug
volumes:
- /var/run/docker.sock:/var/run/docker.sock
networks:
dev-env-swarm:
aliases:
- portainer-agent.testenv.top
deploy:
mode: global
portainer:
image: portainer/portainer
command: -H tcp://tasks.portainer-agent:9001 --tlsskipverify
depends_on:
- portainer-agent
external_links:
- nginx-main
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9000"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 2024M
reservations:
cpus: "0.05"
memory: 512M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
volumes:
- /env-vol/portainer/data:/data
hostname: portainer.testenv.top
networks:
dev-env-swarm:
aliases:
- portainer.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
pgadmin4:
image: dpage/pgadmin4:latest
hostname: pgadmin.testenv.top
external_links:
- nginx-main
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost"]
interval: 1m30s
timeout: 10s
retries: 3
start_period: 60s
deploy:
mode: global
endpoint_mode: dnsrr
resources:
limits:
cpus: "0.20"
memory: 1024M
reservations:
cpus: "0.05"
memory: 256M
restart_policy:
condition: on-failure
delay: 20s
max_attempts: 3
window: 60s
environment:
PGADMIN_DEFAULT_EMAIL: email@example.com
PGADMIN_DEFAULT_PASSWORD: PASWORD
networks:
dev-env-swarm:
aliases:
- pgadmin.testenv.top
dns:
- 10.10.10.10
- 8.8.8.8
volumes:
- /env-vol/pgadmin:/var/lib/pgadmin
最佳答案
套接字问题是由于源代码安装错误的 Python 以及手动安装库造成的。看起来我安装了不兼容的版本。当我从存储库重新安装 Python 时，这个问题不再出现。
关于Docker 套接字在堆栈后崩溃，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/51126509/