问题
I trying to deploy docker stack, that includes my development environment. But in random cases I have next error:
> failed to create service < service_name >: Cannot connect to the
> Docker daemon at unix:///var/run/docker.sock. Is the docker daemon
> running?
Next I restart docker daemon. Sometimes it requires to kill docker processes and shims. I deleting old stack and build again. Some times docker successfully finishes build, but socket crashes on the starting stage.
Also all containers work properly when I starting it in regular mode, without swarm or stack. It is not work exactly inside swarm.
I have used next command to build:
> $ docker stack deploy dev-env-stc -c docker-compose.yml
Environment run in Antergos Linux(Arch).
Layout is like at the diagram
Nginx container and docker networks created using commands:
>$ 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
My docker-compose.yml file:
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
回答1:
Problem with socket was from wrong Python installation from sources and manual installation of libs. Looks like I have installed incompatible versions. When I have reinstalled Python from repository this problem wasn't appear again.
But I has concluded that using Docker Stack in development environment is not good decision, better to use Docker Compose for this reasons. So Docker Stack should be used for deployment configurations(like deploy of Docker Swarm or to the Kubernetes or to another cloud environments).
来源：https://stackoverflow.com/questions/51126509/docker-socket-crash-after-stack-up