org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=3, backoffTimeMS=5000)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:139)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getGlobalFailureHandlingResult(ExecutionFailureHandler.java:102)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleGlobalFailure(DefaultScheduler.java:301)
at org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder$LazyInitializedCoordinatorContext.lambda$failJob$0(OperatorCoordinatorHolder.java:618)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:453)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:453)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:218)
at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:84)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:168)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:127)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:126)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:175)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
at akka.actor.Actor.aroundReceive(Actor.scala:537)
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:579)
at akka.actor.ActorCell.invoke(ActorCell.scala:547)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
at akka.dispatch.Mailbox.run(Mailbox.scala:231)
at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
at java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290)
at java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020)
at java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656)
at java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594)
at java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:177)
Caused by: org.apache.flink.util.FlinkException: Global failure triggered by OperatorCoordinator for 'Source: T_ORG_ORG[2829] -> Calc[2830] -> Sink: Collect table sink' (operator cbc357ccb763df2852fee8c4fc7d55f2).
at org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder$LazyInitializedCoordinatorContext.failJob(OperatorCoordinatorHolder.java:600)
at org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator$QuiesceableContext.failJob(RecreateOnResetOperatorCoordinator.java:237)
at org.apache.flink.runtime.source.coordinator.SourceCoordinatorContext.failJob(SourceCoordinatorContext.java:374)
at org.apache.flink.runtime.source.coordinator.SourceCoordinator.start(SourceCoordinator.java:226)
at org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator$DeferrableCoordinator.resetAndStart(RecreateOnResetOperatorCoordinator.java:405)
at org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator.lambda$resetToCheckpoint$6(RecreateOnResetOperatorCoordinator.java:150)
at java.base/java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:859)
at java.base/java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:837)
at java.base/java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:506)
at java.base/java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:2073)
at org.apache.flink.runtime.operators.coordination.ComponentClosingUtils.lambda$closeAsyncWithTimeout$0(ComponentClosingUtils.java:77)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.flink.util.FlinkRuntimeException: Failed to discover captured tables for enumerator
at com.ververica.cdc.connectors.base.source.IncrementalSource.createEnumerator(IncrementalSource.java:151)
at org.apache.flink.runtime.source.coordinator.SourceCoordinator.start(SourceCoordinator.java:222)
... 8 more
Caused by: java.lang.RuntimeException: Failed to resolve Oracle database version
at io.debezium.connector.oracle.OracleConnection.resolveOracleDatabaseVersion(OracleConnection.java:159)
at io.debezium.connector.oracle.OracleConnection.(OracleConnection.java:71)
at com.ververica.cdc.connectors.oracle.source.utils.OracleConnectionUtils.createOracleConnection(OracleConnectionUtils.java:54)
at com.ververica.cdc.connectors.oracle.source.OracleDialect.openJdbcConnection(OracleDialect.java:90)
at com.ververica.cdc.connectors.oracle.source.OracleDialect.discoverDataCollections(OracleDialect.java:107)
at com.ververica.cdc.connectors.oracle.source.OracleDialect.discoverDataCollections(OracleDialect.java:51)
at com.ververica.cdc.connectors.base.source.IncrementalSource.createEnumerator(IncrementalSource.java:139)
... 9 more
Caused by: java.sql.SQLRecoverableException: Listener refused the connection with the following error:
ORA-12514, TNS:listener does not currently know of service requested in connect descriptor
at oracle.jdbc.driver.T4CConnection.logon(T4CConnection.java:854)
at oracle.jdbc.driver.PhysicalConnection.connect(PhysicalConnection.java:793)
at oracle.jdbc.driver.T4CDriverExtension.getConnection(T4CDriverExtension.java:57)
at oracle.jdbc.driver.OracleDriver.connect(OracleDriver.java:747)
at oracle.jdbc.driver.OracleDriver.connect(OracleDriver.java:562)
at java.sql/java.sql.DriverManager.getConnection(DriverManager.java:677)
at java.sql/java.sql.DriverManager.getConnection(DriverManager.java:189)
at io.debezium.jdbc.JdbcConnection.lambda$patternBasedFactory$0(JdbcConnection.java:184)
at io.debezium.jdbc.JdbcConnection$ConnectionFactoryDecorator.connect(JdbcConnection.java:121)
at io.debezium.jdbc.JdbcConnection.connection(JdbcConnection.java:890)
at io.debezium.jdbc.JdbcConnection.connection(JdbcConnection.java:885)
at io.debezium.jdbc.JdbcConnection.queryAndMap(JdbcConnection.java:643)
at io.debezium.jdbc.JdbcConnection.queryAndMap(JdbcConnection.java:517)
at io.debezium.connector.oracle.OracleConnection.resolveOracleDatabaseVersion(OracleConnection.java:129)
... 15 more
Caused by: oracle.net.ns.NetException: Listener refused the connection with the following error:
ORA-12514, TNS:listener does not currently know of service requested in connect descriptor
at oracle.net.ns.NSProtocolNIO.negotiateConnection(NSProtocolNIO.java:284)
at oracle.net.ns.NSProtocol.connect(NSProtocol.java:340)
at oracle.jdbc.driver.T4CConnection.connect(T4CConnection.java:1596)
at oracle.jdbc.driver.T4CConnection.logon(T4CConnection.java:588)
... 28 more
你的错误信息看起来像是Flink在执行作业失败后尝试恢复时出现了问题。这可能是因为Oracle数据库连接问题,或者是因为Flink无法正确处理Oracle数据库的异常。
首先,你需要检查Oracle数据库的日志,看看是否有任何相关的错误信息。同时,你也可以查看Flink的任务日志,看看是否有更多的错误信息。
其次,你可能需要调整Flink的恢复策略。在这个错误信息中,Flink使用了FixedDelayRestartBackoffTimeStrategy,这是一种基于时间延迟的重试策略。如果你发现任务一直在重试,但是无法成功,那么你可能需要调整这个策略,比如增加最大重试次数,或者减少重试间隔时间。
最后,你可能需要检查Flink的配置,特别是关于Oracle数据库的配置。例如,你可能需要检查数据库连接池的大小,或者检查是否正确设置了Oracle数据库的驱动和连接参数。
总的来说,解决这个问题需要结合数据库日志、Flink任务日志和Flink配置等多方面信息进行综合判断和处理。
版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。
实时计算Flink版是阿里云提供的全托管Serverless Flink云服务,基于 Apache Flink 构建的企业级、高性能实时大数据处理系统。提供全托管版 Flink 集群和引擎,提高作业开发运维效率。