docker - Kubernetes 中的 Rabbitmq 集群设置

Question

我使用 docker compose 成功设置了 rabbitmq 集群以了解集群概念。下面是 docker compose 文件，它运行良好:

rabbit1:
  image: ipf-queue-node
  hostname: rabbit1
  cap_add:
    - ALL
    - NET_ADMIN
    - SYS_ADMIN
  ports:
    - "5671:5671"
    - "5672:5672"
    - "15672:15672"

rabbit2:
  image: ipf-queue-node
  hostname: rabbit2
  cap_add:
    - ALL
    - NET_ADMIN
    - SYS_ADMIN
  links:
    - rabbit1
  environment: 
   - CLUSTERED=true
   - CLUSTER_WITH=rabbit1
   - RAM_NODE=true
  ports:
      - "5675:5671"
      - "5673:5672"
      - "15673:15672"

Docker 文件内容:

FROM queue-base

# Create directories
RUN mkdir /opt/rabbit
RUN mkdir /opt/simulator
RUN mkdir /opt/simulator/tools

# Add the files from the local repository into the container
ADD rabbitmq.config     /etc/rabbitmq/
ADD rabbitmq-env.conf   /etc/rabbitmq/
ADD erlang.cookie       /var/lib/rabbitmq/.erlang.cookie
ADD startclusternode.sh /opt/rabbit/
ADD debugnodes.sh       /opt/rabbit/
ADD tl                  /bin/tl
ADD rl                  /bin/rl
ADD rst                 /bin/rst

# Add the simulator tooling
ADD simulator_tools/   /opt/simulator/tools/
ADD ./testca /tmp/ssl
ADD ./server /tmp/ssl

# Set the file permissions in the container
RUN chmod 644 /etc/rabbitmq/rabbitmq.config
RUN chmod 644 /etc/rabbitmq/rabbitmq-env.conf
RUN chmod 400 /var/lib/rabbitmq/.erlang.cookie
RUN chmod 777 /opt/rabbit/startclusternode.sh
RUN chmod 777 /opt/rabbit/debugnodes.sh
RUN chmod 777 /bin/tl
RUN chmod 777 /bin/rl
RUN chmod 777 /bin/rst
RUN chmod -R 777 /opt/simulator

# Set ownership permissions on files in the container
RUN chown rabbitmq:rabbitmq /var/lib/rabbitmq/.erlang.cookie

# Expose ports inside the container to the host
EXPOSE 5672
EXPOSE 5671
EXPOSE 15672
EXPOSE 25672

# Run this to debug the cluster nodes by allowing ssh login
#CMD /opt/rabbit/debugnodes.sh

# Run this to autostart the cluster nodes
CMD /opt/rabbit/startclusternode.sh

startclusternode.sh 是设置集群的脚本:

#!/bin/bash

logfile="/tmp/rabbitnode.log"
firsttimefile="/tmp/firsttimerunning"

curhostname=`hostname`
username="<<username>>"
password="<<password>>"
echo "" > $logfile
echo "New Start Date:" >> $logfile
date >> $logfile
echo "" >> $logfile

( sleep 40 ; \
rabbitmqctl add_user $username $password ; \
rabbitmqctl set_user_tags $username administrator ; \
rabbitmqctl add_vhost $curhostname ; \
rabbitmqctl add_vhost localhost; \
rabbitmqctl set_permissions -p $curhostname $username ".*" ".*" ".*" ; \
rabbitmqctl set_permissions -p localhost $username ".*" ".*" ".*" ; \
rabbitmqctl set_policy ha-all "" '{"ha-mode":"all","ha-sync-mode":"automatic"}'
) & 

sleep 5

# For version 3.5.6 the first time running the cluster needs to enable the plugins
if [ -f $firsttimefile ]; then
  echo "First Time Running Enabling Plugins" >> $logfile
  /usr/sbin/rabbitmq-server -d &
  echo "Waiting for RabbitMQ Server to start" >> $logfile
  sleep 3
  echo "Enabling Plugins" >> $logfile
  /usr/sbin/rabbitmq-plugins enable rabbitmq_stomp rabbitmq_management  rabbitmq_management_agent rabbitmq_management_visualiser rabbitmq_federation rabbitmq_federation_management sockjs >> $logfile
  echo "Waiting for Plugins to finish" >> $logfile
  sleep 1
  echo "Stopping the RabbitMQ using stop_app" >> $logfile
  /usr/sbin/rabbitmqctl stop_app
  echo "Stopping the RabbitMQ using stop" >> $logfile
  /usr/sbin/rabbitmqctl stop

  echo "Stopping the RabbitMQ Server" >> $logfile
  kill -9 `ps auwwx | grep rabbitmq-server | awk '{print $2}'`
  sleep 1

  echo "Done First Time Running Enabling Plugins" >> $logfile
  rm -f $firsttimefile >> $logfile
  echo "Done Cleanup First Time File" >> $logfile


  # Allow the cluster nodes to wait for the master to start the first time
  if [ -z "$CLUSTERED" ]; then
    echo "Ignoring as this is the server node" >> $logfile
  else
    if [ -z "$CLUSTER_WITH" ]; then
      echo "Ignoring as this is the cluster master node" >> $logfile
    else
      echo "Waiting for the master node to start up" >> $logfile
      sleep 5
      echo "Done waiting for the master node to start up" >> $logfile
    fi
  fi
fi


if [ -z "$CLUSTERED" ]; then

  echo "Starting non-Clustered Server Instance" >> $logfile
  # if not clustered then start it normally as if it is a single server
  /usr/sbin/rabbitmq-server  >> $logfile
  echo "Done Starting non-Clustered Server Instance" >> $logfile

  # Tail to keep the foreground process active.
  tail -f /var/log/rabbitmq/*

else
  if [ -z "$CLUSTER_WITH" ]; then
    # If clustered, but cluster is not specified then start normally as this could be the first server in the cluster
    echo "Starting Single Server Instance" >> $logfile
    /usr/sbin/rabbitmq-server >> $logfile

    echo "Done Starting Single Server Instance" >> $logfile
  else
    echo "Starting Clustered Server Instance as a DETACHED single instance" >> $logfile
    /usr/sbin/rabbitmq-server -detached >> $logfile

    echo "Stopping App with /usr/sbin/rabbitmqctl stop_app" >> $logfile
    /usr/sbin/rabbitmqctl stop_app >> $logfile

    # This should attempt to join a cluster master node from the yaml file
    if [ -z "$RAM_NODE" ]; then
      echo "Attempting to join as DISC node: /usr/sbin/rabbitmqctl join_cluster rabbit@$CLUSTER_WITH" >> $logfile
      /usr/sbin/rabbitmqctl join_cluster rabbit@$CLUSTER_WITH >> $logfile
    else
      echo "Attempting to join as RAM node: /usr/sbin/rabbitmqctl join_cluster --ram rabbit@$CLUSTER_WITH" >> $logfile
      /usr/sbin/rabbitmqctl join_cluster --ram rabbit@$CLUSTER_WITH >> $logfile
    fi
    echo "Starting App" >> $logfile
    /usr/sbin/rabbitmqctl start_app >> $logfile

    echo "Done Starting Cluster Node" >> $logfile
  fi

  # Tail to keep the foreground process active.
  tail -f /var/log/rabbitmq/*

fi

问题是当我尝试使用 kubernetes 进行相同的设置时，我无法从从节点连接到主节点。我采取的方法是，我为主节点创建了一个 pod，为从节点创建了另一个 pod，通过环境变量传递了主节点的主机名(当前是硬编码的)。我还检查了/tmp/rabbitmq.log 中的日志文件，它正确地获取了所有环境变量。但是，它无法向 master 注册。我也尝试使用 rabbitmqctl 命令手动执行此操作。但它没有工作说主机无法访问。也尝试更改/etc/hosts 文件。

根据我对 kubernetes 中的 pod 通过服务进行通信的理解，我猜正因为如此，直接传递容器主机名是行不通的，rabbitmq 基于主机名的 clusiering 工作。

有没有人尝试过任何解决方法？我想在不同的节点上运行主站和从站。下面是主从 Pod 的内容:

apiVersion: v1
kind: Service
metadata:
  name: rabbitmqsvc
  labels:
    app: queue-master
spec:
  ports:
    - port: 5672
      name: queue-rw-port
    - port: 15672
      name: queue-mgt-port
      nodePort: 31606
    - port: 5671
      name: queue-ssl
      nodePort: 32718
  selector:
    app: queue-master
  type: NodePort
  clusterIP: 10.16.0.121
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: rabbitmq-controller
  labels:
    app: queue-master
spec:
  replicas: 1
  selector:
    app: queue-master
  template:
    metadata:
      name: rabbitmq-pod
      labels:
        app: queue-master
    spec:
      nodeSelector:
        nodesize: small1
      containers:
      - name: rabbitmq-master
        image: 172.17.0.1:5000/queue-node
        ports:
        - containerPort: 5672
          name: queue-rw-port
        - containerPort: 15672
          name: queue-mgt-port
        - containerPort: 5671
          name: queue-ssl

奴隶:

apiVersion: v1
kind: Service
metadata:
  name: rabbitmqsvc-slave
  labels:
    app: queue-slave
spec:
  ports:
    - port: 5672
      name: queue-rw-port
    - port: 15672
      name: queue-mgt-port
      nodePort: 31607
    - port: 5671
      name: queue-ssl
      nodePort: 32719
  selector:
    app: queue-slave
  type: NodePort
  clusterIP: 10.16.0.122
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: rabbitmq-controller-slave
  labels:
    app: queue-slave
spec:
  replicas: 1
  selector:
    app: queue-slave
  template:
    metadata:
      name: rabbitmq-pod
      labels:
        app: queue-slave
    spec:
      nodeSelector:
        nodesize: small2
      containers:
      - name: rabbitmq-slave
        image: 172.17.0.1:5000/queue-node
        env:
        - name: CLUSTERED
          value: "true"
        - name: CLUSTER_WITH
          value: "rabbitmq-controller-2ll1s"
        - name: RAM_NODE
          value: "true"
        - name: HOST_NAME
          value: "rabbit2"
        ports:
        - containerPort: 5672
          name: queue-rw-port
        - containerPort: 15672
          name: queue-mgt-port
        - containerPort: 5671
          name: queue-ssl

Answer 1

您不能将 Docker 主机名和链接与 Kubernetes 一起使用。它只有在你有一台机器时才有效，但 Kubernetes 被指定为集群解决方案。

启用 DNS在您的集群中。创建 Master service (rabbitmqsvc - 已经完成)然后使用您的 DNS 名称 Master service在您的从属配置中:

    - name: CLUSTER_WITH
      value: "rabbitmqsvc.svc.cluster.local"

您也可以使用 environment variables ，但恕我直言 DNS 是更好的选择。