java - 为什么当 zookeeper 重新上线时 curator 没有恢复？

Question

我有一个针对 Zookeeper 服务器 (v3.7.0) 运行的 CuratorFramework 客户端 (v5.1.0)。如果Zookeeper 服务器在客户端连接到它时关闭我可以看到连接状态(使用 ConnectionStateListener)SUSPENDED，然后是 LOST，然后仅此而已当服务器重新联机时。

这感觉像是一个非常标准的用例，我一定错过了一些愚蠢的东西，但我永远不能一旦服务器在线，让客户端再次连接。

我进行了一些谷歌搜索，但没有发现关于如何处理丢失状态后的恢复的有用信息。

我有一个 self-contained example我在做什么中的示例代码 CuratorRecoveryTest类(class)(在 IDE 而不是 Maven 中运行)。它的主要内容是(从测试类中提取):

// setup the server and client
server = new TestingServer();

client = newClient(server.getConnectString(), 60000, 15000, new RetryNTimes(1, 250));
client.start();
client.blockUntilConnected();
            
// add the listener
final var stateListener = new StateListener();
stateListener.stateChanged(client, CONNECTED);

// register the listener
client.getConnectionStateListenable().addListener(stateListener);

// verify connection
assertTrue(client.getZookeeperClient().isConnected());

// let things settle
nap(3, "initial settling");

// stop zk
stopServer();
log.info(">>>>>>>>>> STOPPED ZK SERVER");

// let it bake
nap(3, "letting things bake");

// ensure disconnected
assertFalse(client.getZookeeperClient().isConnected());

nap(3, "disconnecting");

// start zk
server.start();
log.info(">>>>>>>>>> STARTED ZK SERVER");

await().atMost(5, MINUTES).until(() -> stateListener.getCurrentState() == CONNECTED || stateListener.getCurrentState() == RECONNECTED);

// NOTE: it never gets here - no state changes after LOST

assertTrue(client.getZookeeperClient().isConnected());

运行时我得到以下输出:

[Thread-0] INFO org.apache.curator.test.TestingZooKeeperMain - Starting server
[Thread-0] WARN org.apache.zookeeper.server.ServerCnxnFactory - maxCnxns is not configured, using default value 0.
[main] INFO org.apache.curator.framework.imps.CuratorFrameworkImpl - Starting
[main] INFO org.apache.curator.framework.imps.CuratorFrameworkImpl - Default schema
[main] WARN demo.CuratorRecoveryTest - CONNECTION-STATE-CHANGE: null --> CONNECTED
[main] DEBUG demo.CuratorRecoveryTest - Taking a 3s nap for initial settling...
[main] DEBUG demo.CuratorRecoveryTest - Done napping for initial settling...
[Curator-ConnectionStateManager-0] WARN demo.CuratorRecoveryTest - CONNECTION-STATE-CHANGE: CONNECTED --> SUSPENDED
[main] INFO demo.CuratorRecoveryTest - >>>>>>>>>> STOPPED ZK SERVER
[main] DEBUG demo.CuratorRecoveryTest - Taking a 3s nap for letting things bake...
[main] DEBUG demo.CuratorRecoveryTest - Done napping for letting things bake...
[main] DEBUG demo.CuratorRecoveryTest - Taking a 3s nap for disconnecting...
[main] DEBUG demo.CuratorRecoveryTest - Done napping for disconnecting...
[main] INFO demo.CuratorRecoveryTest - >>>>>>>>>> STARTED ZK SERVER
[Curator-ConnectionStateManager-0] WARN org.apache.curator.framework.state.ConnectionStateManager - Session timeout has elapsed while SUSPENDED. Injecting a session expiration. Elapsed ms: 20009. Adjusted session timeout ms: 20000
[main-EventThread] WARN org.apache.curator.ConnectionState - Session expired event received
[Curator-ConnectionStateManager-0] WARN demo.CuratorRecoveryTest - CONNECTION-STATE-CHANGE: SUSPENDED --> LOST

当等待条件从未发生时，它就会失败。

NOTE: This happens on an older version combination of Curator and Zookeeper as well, so this is not a "bleeding edge" issue.

我错过了什么？

Answer 1

我有一个类似的问题，并得出结论，当 zookeeper 服务器重新启动时，馆长似乎重用了过时的 IP。

this ticket 中概述的方法为我工作。特别是，this commit它添加了一个自定义的 ZookeeperFactory，它不会重用以前的过时 IP，而是使用原始的未解析的主机名。

简而言之，在创建策展人时，分配一个自定义的 ZookeeperFactory

CuratorFramework zkClient = CuratorFrameworkFactory
    .builder()
...
    .zookeeperFactory(new ZKClientFactory())

ZKClientFactory 从缓存的 connectString 创建一个新的 Zookeeper。