Flink Cdc EOFException 的问题

今日公司有一个Flink Cdc的任务将mysql的binlog数据同步到kudu中，但是有一天凌晨开始间歇性的报异常，任务间歇性的重启。如下：

java.lang.RuntimeException: One or more fetchers have encountered exception
	at org.apache.flink.connector.base.source.reader.fetcher.SplitFetcherManager.checkErrors(SplitFetcherManager.java:223) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.connector.base.source.reader.SourceReaderBase.getNextFetch(SourceReaderBase.java:154) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.connector.base.source.reader.SourceReaderBase.pollNext(SourceReaderBase.java:116) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.connector.base.source.reader.SourceReaderBase.pollNext(SourceReaderBase.java:141) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.api.operators.SourceOperator.emitNext(SourceOperator.java:305) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.io.StreamTaskSourceInput.emitNext(StreamTaskSourceInput.java:69) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:66) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:423) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:204) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:684) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.StreamTask.executeInvoke(StreamTask.java:639) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.StreamTask.runWithCleanUpOnFail(StreamTask.java:650) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:623) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:779) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:566) ~[flink-dist_2.11-1.13.6.jar:1.13.6]
	at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_232]
Caused by: java.lang.RuntimeException: SplitFetcher thread 0 received unexpected exception while polling the records
	at org.apache.flink.connector.base.source.reader.fetcher.SplitFetcher.runOnce(SplitFetcher.java:148) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at org.apache.flink.connector.base.source.reader.fetcher.SplitFetcher.run(SplitFetcher.java:103) ~[flink-table-blink_2.11-1.13.6.jar:1.13.6]
	at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) ~[?:1.8.0_232]
	at java.util.concurrent.FutureTask.run(FutureTask.java:266) ~[?:1.8.0_232]
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) ~[?:1.8.0_232]
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ~[?:1.8.0_232]
	... 1 more
Caused by: org.apache.kafka.connect.errors.ConnectException: An exception occurred in the change event producer. This connector will be stopped.
	at io.debezium.pipeline.ErrorHandler.setProducerThrowable(ErrorHandler.java:42) ~[?:?]
	at com.ververica.cdc.connectors.mysql.debezium.task.context.MySqlErrorHandler.setProducerThrowable(MySqlErrorHandler.java:72) ~[?:?]
	at io.debezium.connector.mysql.MySqlStreamingChangeEventSource$ReaderThreadLifecycleListener.onCommunicationFailure(MySqlStreamingChangeEventSource.java:1185) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.listenForEventPackets(BinaryLogClient.java:973) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.connect(BinaryLogClient.java:606) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient$7.run(BinaryLogClient.java:850) ~[?:?]
	... 1 more
Caused by: io.debezium.DebeziumException: Failed to deserialize data of EventHeaderV4{timestamp=1656995117000, eventType=EXT_UPDATE_ROWS, serverId=443165, headerLength=19, dataLength=6275, nextPosition=121667864, flags=0}
	at io.debezium.connector.mysql.MySqlStreamingChangeEventSource.wrap(MySqlStreamingChangeEventSource.java:1146) ~[?:?]
	at io.debezium.connector.mysql.MySqlStreamingChangeEventSource$ReaderThreadLifecycleListener.onCommunicationFailure(MySqlStreamingChangeEventSource.java:1185) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.listenForEventPackets(BinaryLogClient.java:973) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.connect(BinaryLogClient.java:606) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient$7.run(BinaryLogClient.java:850) ~[?:?]
	... 1 more
Caused by: com.github.shyiko.mysql.binlog.event.deserialization.EventDataDeserializationException: Failed to deserialize data of EventHeaderV4{timestamp=1656995117000, eventType=EXT_UPDATE_ROWS, serverId=443165, headerLength=19, dataLength=6275, nextPosition=121667864, flags=0}
	at com.github.shyiko.mysql.binlog.event.deserialization.EventDeserializer.deserializeEventData(EventDeserializer.java:309) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.EventDeserializer.nextEvent(EventDeserializer.java:232) ~[?:?]
	at io.debezium.connector.mysql.MySqlStreamingChangeEventSource$1.nextEvent(MySqlStreamingChangeEventSource.java:233) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.listenForEventPackets(BinaryLogClient.java:945) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.connect(BinaryLogClient.java:606) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient$7.run(BinaryLogClient.java:850) ~[?:?]
	... 1 more
Caused by: java.io.EOFException
	at com.github.shyiko.mysql.binlog.io.ByteArrayInputStream.read(ByteArrayInputStream.java:209) ~[?:?]
	at com.github.shyiko.mysql.binlog.io.ByteArrayInputStream.readInteger(ByteArrayInputStream.java:51) ~[?:?]
	at io.debezium.connector.mysql.RowDeserializers.deserializeVarString(RowDeserializers.java:263) ~[?:?]
	at io.debezium.connector.mysql.RowDeserializers$UpdateRowsDeserializer.deserializeVarString(RowDeserializers.java:130) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.AbstractRowsEventDataDeserializer.deserializeCell(AbstractRowsEventDataDeserializer.java:189) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.AbstractRowsEventDataDeserializer.deserializeRow(AbstractRowsEventDataDeserializer.java:143) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.UpdateRowsEventDataDeserializer.deserializeRows(UpdateRowsEventDataDeserializer.java:72) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.UpdateRowsEventDataDeserializer.deserialize(UpdateRowsEventDataDeserializer.java:58) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.UpdateRowsEventDataDeserializer.deserialize(UpdateRowsEventDataDeserializer.java:33) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.EventDeserializer.deserializeEventData(EventDeserializer.java:303) ~[?:?]
	at com.github.shyiko.mysql.binlog.event.deserialization.EventDeserializer.nextEvent(EventDeserializer.java:232) ~[?:?]
	at io.debezium.connector.mysql.MySqlStreamingChangeEventSource$1.nextEvent(MySqlStreamingChangeEventSource.java:233) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.listenForEventPackets(BinaryLogClient.java:945) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient.connect(BinaryLogClient.java:606) ~[?:?]
	at com.github.shyiko.mysql.binlog.BinaryLogClient$7.run(BinaryLogClient.java:850) ~[?:?]
	... 1 more

翻遍了github issue：

Debezium Connectors Throwing EOF / Connection reset while reading bin-logs · Issue #15 · osheroff/mysql-binlog-connector-java · GitHub

最后在Debezuim的FAQ上找到了对此的解决方法：

https://debezium.io/documentation/faq/#what_is_causing_intermittent_eventdatadeserializationexceptions_with_the_mysql_connector

 先改了试试，观察下还会不会出现该问题。

20220718更新

出现以上原因是因为，任务的算子链中有一个算子去查询kudu表延时很高导致，出现了反压到了mysql-cdc的地方，而mysql-cdc实现其实是socket连接到了mysql-server，server端推送日志数据，由于客户端背压之后，很长事件没有读取数据，导致出现了超时的情况，所以才报以上的错误。