一文秒懂 kafka HA（高可用）

# cd /usr/local/zookeeper-cluster/zk1/bin
# ./zkCli.sh

[zk: localhost:2181(CONNECTED) 0] ls /
[cluster, controller_epoch, controller, brokers, zookeeper, admin, isr_change_notification, consumers, log_dir_event_notification, latest_producer_id_block, config]

[zk: localhost:2181(CONNECTED) 1] ls /brokers
[ids, topics, seqid]
[zk: localhost:2181(CONNECTED) 2] ls /brokers/ids
[0]
[zk: localhost:2181(CONNECTED) 3] get /brokers/ids/0
{"listener_security_protocol_map":{"PLAINTEXT":"PLAINTEXT"},"endpoints":["PLAINTEXT://172.17.80.219:9092"],"jmx_port":-1,"host":"172.17.80.219","timestamp":"1584267365984","port":9092,"version":4}
cZxid = 0x300000535
ctime = Sun Mar 15 18:16:06 CST 2020
mZxid = 0x300000535
mtime = Sun Mar 15 18:16:06 CST 2020
pZxid = 0x300000535
cversion = 0
dataVersion = 1
aclVersion = 0
ephemeralOwner = 0x20191d7053f0009
dataLength = 196
numChildren = 0
[zk: localhost:2181(CONNECTED) 4] 
[zk: localhost:2181(CONNECTED) 4]
[zk: localhost:2181(CONNECTED) 4]
[zk: localhost:2181(CONNECTED) 4] ls /brokers/topics
[__consumer_offsets, first]
[zk: localhost:2181(CONNECTED) 5] ls /brokers/topics/first
[partitions]
[zk: localhost:2181(CONNECTED) 6] ls /brokers/topics/first/partitions
[0, 1]
[zk: localhost:2181(CONNECTED) 7] ls /brokers/topics/first/partitions/0
[state]
[zk: localhost:2181(CONNECTED) 8] get /brokers/topics/first/partitions/0/state
{"controller_epoch":21,"leader":0,"version":1,"leader_epoch":8,"isr":[0]}
cZxid = 0x3000003e9
ctime = Sun Mar 08 16:24:37 CST 2020
mZxid = 0x3000005cb
mtime = Sun Mar 15 18:54:09 CST 2020
pZxid = 0x3000003e9
cversion = 0
dataVersion = 10
aclVersion = 0
ephemeralOwner = 0x0
dataLength = 73
numChildren = 0
[zk: localhost:2181(CONNECTED) 9]

def onControllerFailover() {
    if (isRunning) {
        info("Broker %d starting become controller state transition".format(config.brokerId))
        //read controller epoch from zk
        readControllerEpochFromZookeeper()
        // increment the controller epoch
        incrementControllerEpoch(zkUtils.zkClient)
        // before reading source of truth from zookeeper, register the listeners to get broker/topic callbacks
        registerReassignedPartitionsListener()
        registerIsrChangeNotificationListener()
        registerPreferredReplicaElectionListener()
        partitionStateMachine.registerListeners()
        replicaStateMachine.registerListeners()
        initializeControllerContext()
        replicaStateMachine.startup()
        partitionStateMachine.startup()
        // register the partition change listeners for all existing topics on failover
        controllerContext.allTopics.foreach(topic => partitionStateMachine.registerPartitionChangeListener(topic))
        info("Broker %d is ready to serve as the new controller with epoch %d".format(config.brokerId, epoch))
        brokerState.newState(RunningAsController)
        maybeTriggerPartitionReassignment()
        maybeTriggerPreferredReplicaElection()
        /* send partition leadership info to all live brokers */
        sendUpdateMetadataRequest(controllerContext.liveOrShuttingDownBrokerIds.toSeq)
        if (config.autoLeaderRebalanceEnable) {
            info("starting the partition rebalance scheduler")
            autoRebalanceScheduler.startup()
            autoRebalanceScheduler.schedule("partition-rebalance-thread", checkAndTriggerPartitionRebalance,
                5, config.leaderImbalanceCheckIntervalSeconds.toLong, TimeUnit.SECONDS)
        }
        deleteTopicManager.start()
    }
    else
        info("Controller has been shut down, aborting startup/failover")
}