当使用副本参数部署到Docker上时，RabbitMQ集群的非resovalbe主机名

Question

我使用Docker部署了3个RabbitMQ和领事实例，以便进行对等发现。

version: '3.7'

services:
  rabbitmq-1:
    image: rabbitmq:3.8.9-alpine
    hostname: "rabbitmq-1"
    environment:
      - RABBITMQ_ERLANG_COOKIE="SECRET_COOKIE"
    networks:
      - prod-net
    configs:
      - source: rabbitmq-config
        target: /etc/rabbitmq/rabbitmq.conf
      - source: rabbitmq-plugins-config
        target: /etc/rabbitmq/enabled_plugins
    volumes:
      - /shared/rabbitmq/1/config:/etc/rabbitmq
      - /shared/rabbitmq/1/data:/var/lib/rabbitmq
    deploy:      
      replicas: 1

  rabbitmq-2:
    image: rabbitmq:3.8.9-alpine
    hostname: "rabbitmq-2"
    environment:
      - RABBITMQ_ERLANG_COOKIE="SECRET_COOKIE"
    networks:
      - prod-net
    configs:
      - source: rabbitmq-config
        target: /etc/rabbitmq/rabbitmq.conf
      - source: rabbitmq-plugins-config
        target: /etc/rabbitmq/enabled_plugins
    volumes:
      - /shared/rabbitmq/2/config:/etc/rabbitmq
      - /shared/rabbitmq/2/data:/var/lib/rabbitmq
    deploy:      
      replicas: 1

  rabbitmq-3:
    image: rabbitmq:3.8.9-alpine
    hostname: "rabbitmq-3"
    environment:
      - RABBITMQ_ERLANG_COOKIE="SECRET_COOKIE"
    networks:
      - prod-net
    configs:
      - source: rabbitmq-config
        target: /etc/rabbitmq/rabbitmq.conf
      - source: rabbitmq-plugins-config
        target: /etc/rabbitmq/enabled_plugins
    volumes:
      - /shared/rabbitmq/3/config:/etc/rabbitmq
      - /shared/rabbitmq/3/data:/var/lib/rabbitmq
    deploy:      
      replicas: 1

networks:
  consul-net:
    external: true
    name: prod-net

configs:
  rabbitmq-config:
    external: true
  rabbitmq-plugins-config:
    external: true

RabbitMQ通过主机名向领事注册自己，这样节点就可以彼此发现。因此，所有主机名都必须在所有节点上解析。在上面的示例中，我对主机名和服务名都使用了相同的值来实现这一点。但是，我想使用一种更紧凑的方式来使用replicas: 3参数来表示集群。

version: '3.7'

services:
  rabbitmq:
    image: rabbitmq:3.8.9-alpine
    hostname: "rabbitmq-{{.Task.Slot}}"
    networks:
      - prod-net
    configs:
      - source: rabbitmq-config
        target: /etc/rabbitmq/rabbitmq.conf
      - source: rabbitmq-plugins-config
        target: /etc/rabbitmq/enabled_plugins
    deploy:      
      replicas: 3
      restart_policy:
        condition: any

networks:
  prod-net:
    external: true

configs:
  rabbitmq-config:
    external: true
  rabbitmq-plugins-config:
    external: true

可悲的是，在这种情况下，主机名不再可以由码头DNS解析，并且节点之间无法看到对方。有办法做到这一点吗？

编辑1：

在rabbitmq-config中使用这些方法会出现以下错误：

cluster_formation.peer_discovery_backend = rabbit_peer_discovery_dns
cluster_formation.dns.hostname = tasks.rabbitmq

2020-10-15 22:06:01.573 [error] <0.272.0> attempted to contact: ['rabbit@rabbitmq-3','rabbit@rabbitmq-2']
2020-10-15 22:06:01.574 [error] <0.272.0> rabbit@rabbitmq-3:
2020-10-15 22:06:01.574 [error] <0.272.0>   * unable to connect to epmd (port 4369) on rabbitmq-3: couldn't resolve hostname
2020-10-15 22:06:01.574 [error] <0.272.0> rabbit@rabbitmq-2:
2020-10-15 22:06:01.575 [error] <0.272.0>   * unable to connect to epmd (port 4369) on rabbitmq-2: couldn't resolve hostname

编辑2:使用领事对等发现的 rabbitmq.conf

# Credentials
default_user = admin
default_pass = Pa$$w0rd1

loopback_users.admin = false
vm_memory_high_watermark.absolute = 1024MiB
disk_free_limit.absolute = 5GB
loopback_users.guest = false

# TLS Support in RabbitMQ
listeners.ssl.default = 5671

# Disables non-TLS listeners, only TLS-enabled clients will be able to connect
listeners.tcp = none

ssl_options.cacertfile = /etc/rabbitmq/ca_certificate.pem
ssl_options.certfile   = /etc/rabbitmq/server_certificate.pem
ssl_options.keyfile    = /etc/rabbitmq/server_key.pem
ssl_options.password   = Pa$$phr@se
ssl_options.verify     = verify_peer
ssl_options.fail_if_no_peer_cert = true

# TLS Support in RabbitMQ UI
management.ssl.port       = 15671
management.ssl.cacertfile = /etc/rabbitmq/ca_certificate.pem
management.ssl.certfile   = /etc/rabbitmq/server_certificate.pem
management.ssl.keyfile    = /etc/rabbitmq/server_key.pem
management.ssl.password   = Pa$$phr@se
management.ssl.verify     = verify_none
management.ssl.fail_if_no_peer_cert = false

management.ssl.honor_cipher_order   = true
management.ssl.honor_ecc_order      = true
management.ssl.client_renegotiation = false
management.ssl.secure_renegotiate   = true

cluster_partition_handling = autoheal

# Consul peer discovery
cluster_formation.peer_discovery_backend = rabbit_peer_discovery_consul

# Consul host (hostname or IP address)
cluster_formation.consul.host = consul_client

# Service name (as registered in Consul) defaults to "rabbitmq"
cluster_formation.consul.svc = rabbitmq

# Compute service address (if not specify it below) 
cluster_formation.consul.svc_addr_auto = true
cluster_formation.consul.use_longname = true
cluster_formation.consul.svc_ttl = 50
cluster_formation.consul.deregister_after = 100
cluster_formation.node_cleanup.only_log_warning = true

或者使用DNS对等发现：

#DNS Peer Discovery
cluster_formation.peer_discovery_backend = rabbit_peer_discovery_dns
cluster_formation.dns.hostname = tasks.rabbitmq

Answer 1

为了实现RabbitMQ副本之间的DNS解析，需要修改每个RabbitMQ容器的/etc/hosts。

这将允许通过rabbtimq配置文件形成RabbitMQ集群。

参见如何使用单码头群服务创建RabbitMQ集群上的演示。为了简单起见，我从rabbitmq.conf中删除了对领事和TLS的引用。