You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "xuzifu666 (via GitHub)" <gi...@apache.org> on 2023/07/29 00:55:19 UTC
[GitHub] [hudi] xuzifu666 commented on pull request #9001: [HUDI-6402] Hudi Spark3.3 and upper version need close JavaTimeModule For JsonUtils
xuzifu666 commented on PR #9001:
URL: https://github.com/apache/hudi/pull/9001#issuecomment-1656495304
> @xuzifu666 I am seeing `NoClassDefFoundError: org/apache/hudi/com/fasterxml/jackson/datatype/jsr310/JavaTimeModule` while running the following command shown below. Any suggestions on how to fix this?
>
> ```
> spark-3.3.2-bin-hadoop3 % ./bin/spark-submit \
> --packages org.apache.spark:spark-avro_2.12:3.3.2 \
> --conf spark.task.cpus=1 \
> --conf spark.executor.cores=1 \
> --conf spark.task.maxFailures=100 \
> --conf spark.memory.fraction=0.4 \
> --conf spark.rdd.compress=true \
> --conf spark.kryoserializer.buffer.max=2000m \
> --conf spark.serializer=org.apache.spark.serializer.KryoSerializer \
> --conf spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar \
> --conf spark.memory.storageFraction=0.1 \
> --conf spark.shuffle.service.enabled=true \
> --conf spark.sql.hive.convertMetastoreParquet=false \
> --conf spark.driver.maxResultSize=12g \
> --conf spark.executor.heartbeatInterval=120s \
> --conf spark.network.timeout=600s \
> --conf spark.yarn.max.executor.failures=10 \
> --conf spark.sql.catalogImplementation=hive \
> --class org.apache.hudi.integ.testsuite.HoodieTestSuiteJob /Users/amrish/code/amrish-hudi-3/packaging/hudi-integ-test-bundle/target/hudi-integ-test-bundle-0.14.0-SNAPSHOT.jar \
> --source-ordering-field test_suite_source_ordering_field \
> --use-deltastreamer \
> --target-base-path /tmp/hudi/output \
> --input-base-path /tmp/hudi/input \
> --target-table table1 \
> --props file:///Users/amrish/junk/test-aggressive-clean-archival.properties \
> --workload-yaml-path file:///Users/amrish/code/amrish-hudi-3/docker/demo/config/test-suite/simple-deltastreamer.yaml \
> --schemaprovider-class org.apache.hudi.integ.testsuite.schema.TestSuiteFileBasedSchemaProvider \
> --source-class org.apache.hudi.utilities.sources.AvroDFSSource \
> --input-file-size 125829120 \
> --workload-generator-classname org.apache.hudi.integ.testsuite.dag.WorkflowDagGenerator \
> --table-type COPY_ON_WRITE \
> --compact-scheduling-minshare 1 \
> --clean-input \
> --clean-output
> ```
>
> ```
> Exception in thread "main" org.apache.hudi.exception.HoodieException: Failed to run Test Suite
> at org.apache.hudi.integ.testsuite.HoodieTestSuiteJob.runTestSuite(HoodieTestSuiteJob.java:221)
> at org.apache.hudi.integ.testsuite.HoodieTestSuiteJob.main(HoodieTestSuiteJob.java:182)
> 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 org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:958)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1046)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1055)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.util.concurrent.ExecutionException: java.lang.NoClassDefFoundError: org/apache/hudi/com/fasterxml/jackson/datatype/jsr310/JavaTimeModule
> at java.util.concurrent.FutureTask.report(FutureTask.java:122)
> at java.util.concurrent.FutureTask.get(FutureTask.java:206)
> at org.apache.hudi.integ.testsuite.dag.scheduler.DagScheduler.execute(DagScheduler.java:112)
> at org.apache.hudi.integ.testsuite.dag.scheduler.DagScheduler.schedule(DagScheduler.java:67)
> at org.apache.hudi.integ.testsuite.HoodieTestSuiteJob.runTestSuite(HoodieTestSuiteJob.java:216)
> ... 13 more
> Caused by: java.lang.NoClassDefFoundError: org/apache/hudi/com/fasterxml/jackson/datatype/jsr310/JavaTimeModule
> at org.apache.hudi.common.util.JsonUtils.registerModules(JsonUtils.java:63)
> at org.apache.spark.sql.adapter.BaseSpark3Adapter.<init>(BaseSpark3Adapter.scala:51)
> at org.apache.spark.sql.adapter.Spark3_3Adapter.<init>(Spark3_3Adapter.scala:46)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
> at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
> at java.lang.Class.newInstance(Class.java:442)
> at org.apache.hudi.SparkAdapterSupport$.sparkAdapter$lzycompute(SparkAdapterSupport.scala:49)
> at org.apache.hudi.SparkAdapterSupport$.sparkAdapter(SparkAdapterSupport.scala:35)
> at org.apache.hudi.SparkAdapterSupport.sparkAdapter(SparkAdapterSupport.scala:29)
> at org.apache.hudi.SparkAdapterSupport.sparkAdapter$(SparkAdapterSupport.scala:29)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$.sparkAdapter$lzycompute(HoodieAnalysis.scala:39)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$.sparkAdapter(HoodieAnalysis.scala:39)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$MatchMergeIntoTable$.unapply(HoodieAnalysis.scala:334)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$AdaptIngestionTargetLogicalRelations$$anonfun$$nestedInanonfun$apply$1$1.applyOrElse(HoodieAnalysis.scala:208)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$AdaptIngestionTargetLogicalRelations$$anonfun$$nestedInanonfun$apply$1$1.applyOrElse(HoodieAnalysis.scala:205)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:584)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:176)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:584)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:560)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$AdaptIngestionTargetLogicalRelations.$anonfun$apply$1(HoodieAnalysis.scala:205)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:323)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$AdaptIngestionTargetLogicalRelations.apply(HoodieAnalysis.scala:205)
> at org.apache.spark.sql.hudi.analysis.HoodieAnalysis$AdaptIngestionTargetLogicalRelations.apply(HoodieAnalysis.scala:201)
> ```
what is your hudi version？
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@hudi.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org