[
https://issues.apache.org/jira/browse/FLINK-36517?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17897170#comment-17897170
]
Leonard Xu edited comment on FLINK-36517 at 11/18/24 7:32 AM:
--------------------------------------------------------------
master: ff77a490bd88d86952d47607f44a07163f5d8ced
3.2: 0b805a69ac49d032befad5d33586a47da3acb294
was (Author: leonard xu):
master: ff77a490bd88d86952d47607f44a07163f5d8ced
3.2: TODO
> Duplicate commit the same datafile in Paimon Sink
> -------------------------------------------------
>
> Key: FLINK-36517
> URL: https://issues.apache.org/jira/browse/FLINK-36517
> Project: Flink
> Issue Type: Bug
> Components: Flink CDC
> Affects Versions: cdc-3.2.0
> Environment: flink-1.18.0
> flink cdc 3.2.0
> Reporter: JunboWang
> Assignee: JunboWang
> Priority: Critical
> Labels: pull-request-available
> Fix For: cdc-3.3.0, cdc-3.2.1
>
>
> Same as https://issues.apache.org/jira/browse/FLINK-35938.
> When job restart from failure. This may cause the same datafile were added
> twice in PaimonCommitter.
>
> {code:java}
> // code placeholder
> 2024-09-26 19:50:04,623 INFO
> org.apache.flink.runtime.executiongraph.ExecutionGraph [] - Sink
> Writer: cupid_dev (1/1)
> (44d8fba307e7ff3403a94f71507d4523_26351f8267c5887c12c827914f3a91a9_0_1)
> switched from RUNNING to FAILED on
> container_e47_1710209318993_56454712_01_000002 @ xxxxxxxxxx
> (dataPort=41512).java.io.IOException: java.lang.IllegalStateException: Trying
> to add file {org.apache.paimon.data.BinaryRow@9c67b85d, 6, 0,
> data-f6d7562e-7995-464e-909d-aff0c19b244b-359.parquet} which is already
> added. at
> org.apache.flink.cdc.connectors.paimon.sink.v2.PaimonWriter.write(PaimonWriter.java:138)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.flink.streaming.runtime.operators.sink.SinkWriterOperator.processElement(SinkWriterOperator.java:161)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.cdc.runtime.operators.sink.DataSinkWriterOperator.processElement(DataSinkWriterOperator.java:177)
> ~[flink-cdc-dist.jar:3.2.0] at
> org.apache.flink.streaming.runtime.tasks.OneInputStreamTask$StreamTaskNetworkOutput.emitRecord(OneInputStreamTask.java:237)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.io.AbstractStreamTaskNetworkInput.processElement(AbstractStreamTaskNetworkInput.java:146)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.io.AbstractStreamTaskNetworkInput.emitNext(AbstractStreamTaskNetworkInput.java:110)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:65)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:562)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:231)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:858)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:807)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:971)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:950)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:764)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> org.apache.flink.runtime.taskmanager.Task.run(Task.java:566)
> ~[flink-dist-1.18.0.jar:1.18.0] at
> java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_202]Caused by:
> java.lang.IllegalStateException: Trying to add file
> {org.apache.paimon.data.BinaryRow@9c67b85d, 6, 0,
> data-f6d7562e-7995-464e-909d-aff0c19b244b-359.parquet} which is already
> added. at
> org.apache.paimon.utils.Preconditions.checkState(Preconditions.java:204)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.manifest.FileEntry.mergeEntries(FileEntry.java:130)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.manifest.FileEntry.mergeEntries(FileEntry.java:112)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreScan.readAndMergeFileEntries(AbstractFileStoreScan.java:391)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreScan.doPlan(AbstractFileStoreScan.java:295)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreScan.plan(AbstractFileStoreScan.java:219)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreWrite.scanExistingFileMetas(AbstractFileStoreWrite.java:425)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreWrite.createWriterContainer(AbstractFileStoreWrite.java:384)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreWrite.lambda$getWriterWrapper$2(AbstractFileStoreWrite.java:359)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> java.util.HashMap.computeIfAbsent(HashMap.java:1127) ~[?:1.8.0_202] at
> org.apache.paimon.operation.AbstractFileStoreWrite.getWriterWrapper(AbstractFileStoreWrite.java:358)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.operation.AbstractFileStoreWrite.write(AbstractFileStoreWrite.java:127)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.paimon.table.sink.TableWriteImpl.writeAndReturn(TableWriteImpl.java:151)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.flink.cdc.connectors.paimon.sink.v2.StoreSinkWriteImpl.write(StoreSinkWriteImpl.java:151)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] at
> org.apache.flink.cdc.connectors.paimon.sink.v2.PaimonWriter.write(PaimonWriter.java:136)
> ~[flink-cdc-pipeline-connector-paimon.jar:3.2.0] ... 15 more{code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)