[
https://issues.apache.org/jira/browse/HUDI-4541?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ethan Guo updated HUDI-4541:
----------------------------
Description:
Environment: EMR 6.7.0 Flink 1.14.2
Reproducible steps: Build Hudi Flink bundle from master
{code:java}
mvn clean package -DskipTests -pl :hudi-flink1.14-bundle -am {code}
Copy to EMR master node /lib/flink/lib
Launch Flink SQL client:
{code:java}
cd /lib/flink && ./bin/yarn-session.sh --detached
./bin/sql-client.sh {code}
Run the following from the Flink quick start guide with metadata table, column
stats, and data skipping enabled
{code:java}
CREATE TABLE t1(
uuid VARCHAR(20) PRIMARY KEY NOT ENFORCED,
name VARCHAR(10),
age INT,
ts TIMESTAMP(3),
`partition` VARCHAR(20)
)
PARTITIONED BY (`partition`)
WITH (
'connector' = 'hudi',
'path' = 's3a://<table_path>',
'table.type' = 'MERGE_ON_READ', -- this creates a MERGE_ON_READ table, by
default is COPY_ON_WRITE
'metadata.enabled' = 'true', -- enables multi-modal index and metadata table
'hoodie.metadata.index.column.stats.enable' = 'true', -- enables column stats
in metadata table
'read.data.skipping.enabled' = 'true' -- enables data skipping
);
INSERT INTO t1 VALUES
('id1','Danny',23,TIMESTAMP '1970-01-01 00:00:01','par1'),
('id2','Stephen',33,TIMESTAMP '1970-01-01 00:00:02','par1'),
('id3','Julian',53,TIMESTAMP '1970-01-01 00:00:03','par2'),
('id4','Fabian',31,TIMESTAMP '1970-01-01 00:00:04','par2'),
('id5','Sophia',18,TIMESTAMP '1970-01-01 00:00:05','par3'),
('id6','Emma',20,TIMESTAMP '1970-01-01 00:00:06','par3'),
('id7','Bob',44,TIMESTAMP '1970-01-01 00:00:07','par4'),
('id8','Han',56,TIMESTAMP '1970-01-01 00:00:08','par4'); {code}
!Screen Shot 2022-08-04 at 17.10.05.png|width=1130,height=463!
Exception:
{code:java}
2022-08-04 17:04:41
org.apache.flink.runtime.JobException: Recovery is suppressed by
NoRestartBackoffTimeStrategy
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:228)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:218)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:209)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:679)
at
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:79)
at
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:444)
at sun.reflect.GeneratedMethodAccessor35.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:316)
at
org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:314)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:217)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at akka.actor.Actor.aroundReceive(Actor.scala:537)
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
at akka.actor.ActorCell.invoke(ActorCell.scala:548)
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.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.util.FlinkRuntimeException: Cannot serialize
operator event
at
org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:111)
at
org.apache.hudi.sink.StreamWriteFunction.flushRemaining(StreamWriteFunction.java:479)
at
org.apache.hudi.sink.StreamWriteFunction.endInput(StreamWriteFunction.java:152)
at
org.apache.hudi.sink.common.AbstractWriteOperator.endInput(AbstractWriteOperator.java:48)
at
org.apache.flink.streaming.runtime.tasks.StreamOperatorWrapper.endOperatorInput(StreamOperatorWrapper.java:91)
at
org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.endInput(RegularOperatorChain.java:100)
at
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:68)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:496)
at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:203)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:809)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:761)
at
org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958)
at org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:937)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:766)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:575)
at java.lang.Thread.run(Thread.java:750)
Caused by: java.io.NotSerializableException:
org.apache.hudi.org.apache.avro.util.Utf8
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1184)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at java.util.HashMap.internalWriteEntries(HashMap.java:1817)
at java.util.HashMap.writeObject(HashMap.java:1364)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at java.util.ArrayList.writeObject(ArrayList.java:768)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.flink.util.InstantiationUtil.serializeObject(InstantiationUtil.java:632)
at org.apache.flink.util.SerializedValue.<init>(SerializedValue.java:62)
at
org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:107)
... 15 more {code}
was:
Environment: EMR 6.7.0 Flink 1.14.2
Reproducible steps: Build Hudi Flink bundle from master
{code:java}
mvn clean package -DskipTests -pl :hudi-flink1.14-bundle -am {code}
Copy to EMR master node /lib/flink/lib
Launch Flink SQL client:
{code:java}
cd /lib/flink && ./bin/yarn-session.sh --detached
./bin/sql-client.sh {code}
Run the following from the Flink quick start guide with metadata table, column
stats, and data skipping enabled
{code:java}
CREATE TABLE t1(
uuid VARCHAR(20) PRIMARY KEY NOT ENFORCED,
name VARCHAR(10),
age INT,
ts TIMESTAMP(3),
`partition` VARCHAR(20)
)
PARTITIONED BY (`partition`)
WITH (
'connector' = 'hudi',
'path' = 's3a://<table_path>',
'table.type' = 'MERGE_ON_READ', -- this creates a MERGE_ON_READ table, by
default is COPY_ON_WRITE
'metadata.enabled' = 'true', -- enables multi-modal index and metadata table
'hoodie.metadata.index.column.stats.enable' = 'true', -- enables column stats
in metadata table
'read.data.skipping.enabled' = 'true' -- enables data skipping
);
INSERT INTO t1 VALUES
('id1','Danny',23,TIMESTAMP '1970-01-01 00:00:01','par1'),
('id2','Stephen',33,TIMESTAMP '1970-01-01 00:00:02','par1'),
('id3','Julian',53,TIMESTAMP '1970-01-01 00:00:03','par2'),
('id4','Fabian',31,TIMESTAMP '1970-01-01 00:00:04','par2'),
('id5','Sophia',18,TIMESTAMP '1970-01-01 00:00:05','par3'),
('id6','Emma',20,TIMESTAMP '1970-01-01 00:00:06','par3'),
('id7','Bob',44,TIMESTAMP '1970-01-01 00:00:07','par4'),
('id8','Han',56,TIMESTAMP '1970-01-01 00:00:08','par4'); {code}
!Screen Shot 2022-08-04 at 17.10.05.png|width=1130,height=463!
Exception:
{code:java}
2022-08-04 17:04:41org.apache.flink.runtime.JobException: Recovery is
suppressed by NoRestartBackoffTimeStrategy at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:228)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:218)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:209)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:679)
at
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:79)
at
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:444)
at sun.reflect.GeneratedMethodAccessor35.invoke(Unknown Source) at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:316)
at
org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:314)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:217)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24) at
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20) at
scala.PartialFunction.applyOrElse(PartialFunction.scala:123) at
scala.PartialFunction.applyOrElse$(PartialFunction.scala:122) at
akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) at
akka.actor.Actor.aroundReceive(Actor.scala:537) at
akka.actor.Actor.aroundReceive$(Actor.scala:535) at
akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220) at
akka.actor.ActorCell.receiveMessage(ActorCell.scala:580) at
akka.actor.ActorCell.invoke(ActorCell.scala:548) 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.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)Caused
by: org.apache.flink.util.FlinkRuntimeException: Cannot serialize operator
event at
org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:111)
at
org.apache.hudi.sink.StreamWriteFunction.flushRemaining(StreamWriteFunction.java:479)
at
org.apache.hudi.sink.StreamWriteFunction.endInput(StreamWriteFunction.java:152)
at
org.apache.hudi.sink.common.AbstractWriteOperator.endInput(AbstractWriteOperator.java:48)
at
org.apache.flink.streaming.runtime.tasks.StreamOperatorWrapper.endOperatorInput(StreamOperatorWrapper.java:91)
at
org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.endInput(RegularOperatorChain.java:100)
at
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:68)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:496)
at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:203)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:809)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:761)
at
org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958)
at
org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:937) at
org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:766) at
org.apache.flink.runtime.taskmanager.Task.run(Task.java:575) at
java.lang.Thread.run(Thread.java:750)Caused by:
java.io.NotSerializableException: org.apache.hudi.org.apache.avro.util.Utf8
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1184) at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at
java.util.HashMap.internalWriteEntries(HashMap.java:1817) at
java.util.HashMap.writeObject(HashMap.java:1364) at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154) at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496) at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at
java.util.ArrayList.writeObject(ArrayList.java:768) at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154) at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496) at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at
org.apache.flink.util.InstantiationUtil.serializeObject(InstantiationUtil.java:632)
at org.apache.flink.util.SerializedValue.<init>(SerializedValue.java:62)
at
org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:107)
... 15 more
{code}
> Flink job fails with column stats enabled in metadata table due to
> NotSerializableException
> --------------------------------------------------------------------------------------------
>
> Key: HUDI-4541
> URL: https://issues.apache.org/jira/browse/HUDI-4541
> Project: Apache Hudi
> Issue Type: Bug
> Components: flink-sql
> Reporter: Ethan Guo
> Priority: Blocker
> Fix For: 0.12.0
>
> Attachments: Screen Shot 2022-08-04 at 17.10.05.png
>
>
> Environment: EMR 6.7.0 Flink 1.14.2
> Reproducible steps: Build Hudi Flink bundle from master
> {code:java}
> mvn clean package -DskipTests -pl :hudi-flink1.14-bundle -am {code}
> Copy to EMR master node /lib/flink/lib
> Launch Flink SQL client:
> {code:java}
> cd /lib/flink && ./bin/yarn-session.sh --detached
> ./bin/sql-client.sh {code}
> Run the following from the Flink quick start guide with metadata table,
> column stats, and data skipping enabled
> {code:java}
> CREATE TABLE t1(
> uuid VARCHAR(20) PRIMARY KEY NOT ENFORCED,
> name VARCHAR(10),
> age INT,
> ts TIMESTAMP(3),
> `partition` VARCHAR(20)
> )
> PARTITIONED BY (`partition`)
> WITH (
> 'connector' = 'hudi',
> 'path' = 's3a://<table_path>',
> 'table.type' = 'MERGE_ON_READ', -- this creates a MERGE_ON_READ table, by
> default is COPY_ON_WRITE
> 'metadata.enabled' = 'true', -- enables multi-modal index and metadata table
> 'hoodie.metadata.index.column.stats.enable' = 'true', -- enables column
> stats in metadata table
> 'read.data.skipping.enabled' = 'true' -- enables data skipping
> );
> INSERT INTO t1 VALUES
> ('id1','Danny',23,TIMESTAMP '1970-01-01 00:00:01','par1'),
> ('id2','Stephen',33,TIMESTAMP '1970-01-01 00:00:02','par1'),
> ('id3','Julian',53,TIMESTAMP '1970-01-01 00:00:03','par2'),
> ('id4','Fabian',31,TIMESTAMP '1970-01-01 00:00:04','par2'),
> ('id5','Sophia',18,TIMESTAMP '1970-01-01 00:00:05','par3'),
> ('id6','Emma',20,TIMESTAMP '1970-01-01 00:00:06','par3'),
> ('id7','Bob',44,TIMESTAMP '1970-01-01 00:00:07','par4'),
> ('id8','Han',56,TIMESTAMP '1970-01-01 00:00:08','par4'); {code}
> !Screen Shot 2022-08-04 at 17.10.05.png|width=1130,height=463!
> Exception:
> {code:java}
> 2022-08-04 17:04:41
> org.apache.flink.runtime.JobException: Recovery is suppressed by
> NoRestartBackoffTimeStrategy
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:228)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:218)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:209)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:679)
> at
> org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:79)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:444)
> at sun.reflect.GeneratedMethodAccessor35.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:316)
> at
> org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:314)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:217)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at akka.actor.Actor.aroundReceive(Actor.scala:537)
> at akka.actor.Actor.aroundReceive$(Actor.scala:535)
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
> at akka.actor.ActorCell.invoke(ActorCell.scala:548)
> 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.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
> Caused by: org.apache.flink.util.FlinkRuntimeException: Cannot serialize
> operator event
> at
> org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:111)
> at
> org.apache.hudi.sink.StreamWriteFunction.flushRemaining(StreamWriteFunction.java:479)
> at
> org.apache.hudi.sink.StreamWriteFunction.endInput(StreamWriteFunction.java:152)
> at
> org.apache.hudi.sink.common.AbstractWriteOperator.endInput(AbstractWriteOperator.java:48)
> at
> org.apache.flink.streaming.runtime.tasks.StreamOperatorWrapper.endOperatorInput(StreamOperatorWrapper.java:91)
> at
> org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.endInput(RegularOperatorChain.java:100)
> at
> org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:68)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:496)
> at
> org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:203)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:809)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:761)
> at
> org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958)
> at
> org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:937)
> at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:766)
> at org.apache.flink.runtime.taskmanager.Task.run(Task.java:575)
> at java.lang.Thread.run(Thread.java:750)
> Caused by: java.io.NotSerializableException:
> org.apache.hudi.org.apache.avro.util.Utf8
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1184)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
> at java.util.HashMap.internalWriteEntries(HashMap.java:1817)
> at java.util.HashMap.writeObject(HashMap.java:1364)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
> at java.util.ArrayList.writeObject(ArrayList.java:768)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at
> java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
> at
> org.apache.flink.util.InstantiationUtil.serializeObject(InstantiationUtil.java:632)
> at org.apache.flink.util.SerializedValue.<init>(SerializedValue.java:62)
> at
> org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:107)
> ... 15 more {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)