storm Async loop died! & reconnect

最新推荐文章于 2024-01-11 09:28:57 发布

原创最新推荐文章于 2024-01-11 09:28:57 发布 · 404 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#storm #报错

storm 专栏收录该内容

11 篇文章

订阅专栏

探讨了Apache Storm中Supervisor重启导致的Topology错误及spout消费停滞现象。分析了异常堆栈，发现由于客户端关闭不再接收请求引发的问题，并给出了通过检查重复worker端口并删除冗余worker的解决方案。

storm 在有supervisor重启的时候，topology报错，导致所有spout不消费：

2015-07-15T09:48:26.470+0800 b.s.util [ERROR] Async loop died!
java.lang.RuntimeException: java.lang.RuntimeException: Client is being closed, and does not take requests any more
        at backtype.storm.utils.DisruptorQueue.consumeBatchToCursor(DisruptorQueue.java:128) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.utils.DisruptorQueue.consumeBatchWhenAvailable(DisruptorQueue.java:99) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.disruptor$consume_batch_when_available.invoke(disruptor.clj:80) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.disruptor$consume_loop_STAR_$fn__1460.invoke(disruptor.clj:94) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.util$async_loop$fn__464.invoke(util.clj:463) ~[storm-core-0.9.3.jar:0.9.3]
        at clojure.lang.AFn.run(AFn.java:24) [clojure-1.5.1.jar:na]
        at java.lang.Thread.run(Thread.java:745) [na:1.7.0_75]
Caused by: java.lang.RuntimeException: Client is being closed, and does not take requests any more
        at backtype.storm.messaging.netty.Client.send(Client.java:185) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.utils.TransferDrainer.send(TransferDrainer.java:54) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.daemon.worker$mk_transfer_tuples_handler$fn__3730$fn__3731.invoke(worker.clj:330) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.daemon.worker$mk_transfer_tuples_handler$fn__3730.invoke(worker.clj:328) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.disruptor$clojure_handler$reify__1447.onEvent(disruptor.clj:58) ~[storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.utils.DisruptorQueue.consumeBatchToCursor(DisruptorQueue.java:125) ~[storm-core-0.9.3.jar:0.9.3]
        ... 6 common frames omitted
2015-07-15T09:48:26.507+0800 b.s.util [ERROR] Halting process: ("Async loop died!")
java.lang.RuntimeException: ("Async loop died!")
        at backtype.storm.util$exit_process_BANG_.doInvoke(util.clj:325) [storm-core-0.9.3.jar:0.9.3]
        at clojure.lang.RestFn.invoke(RestFn.java:423) [clojure-1.5.1.jar:na]
        at backtype.storm.disruptor$consume_loop_STAR_$fn__1458.invoke(disruptor.clj:92) [storm-core-0.9.3.jar:0.9.3]
        at backtype.storm.util$async_loop$fn__464.invoke(util.clj:473) [storm-core-0.9.3.jar:0.9.3]
        at clojure.lang.AFn.run(AFn.java:24) [clojure-1.5.1.jar:na]
        at java.lang.Thread.run(Thread.java:745) [na:1.7.0_75]

在日志上边，大量reconnection

 Reconnect started for Netty-Client-hostxx/ip:6703... [91]
 Reconnect started for Netty-Client-hostxx/ip:6703... [92]
 Reconnect started for Netty-Client-hostxx/ip:6703... [93]
 Reconnect started for Netty-Client-hostxx/ip:6703... [94]
 Reconnect started for Netty-Client-hostxx/ip:6703... [95]
 Reconnect started for Netty-Client-hostxx/ip:6703... [96]
 Reconnect started for Netty-Client-hostxx/ip:6703... [97]
 Reconnect started for Netty-Client-hostxx/ip:6703... [98]
 Reconnect started for Netty-Client-hostxx/ip:6703... [99]

登录到ip，发现6703端口有两个worker，导致一个work端口被占用（之前supervisor重启work没有关闭，bug，待解决）

解决：删除重复的端口的worker，让topology自动用其他work