Manoj Govindassamy created HUDI-2905:
----------------------------------------
Summary: Insert crashes in MOR table with NullPointerException
from HoodieMergeHandle
Key: HUDI-2905
URL: https://issues.apache.org/jira/browse/HUDI-2905
Project: Apache Hudi
Issue Type: Task
Reporter: Manoj Govindassamy
Fix For: 0.10.0
Running Hoodie integration test suite with a MOR table type sometimes crashes
with the following stack trace
{noformat}
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
at
org.apache.spark.rdd.DoubleRDDFunctions.sum(DoubleRDDFunctions.scala:35)
at org.apache.spark.api.java.JavaDoubleRDD.sum(JavaDoubleRDD.scala:165)
at
org.apache.hudi.utilities.deltastreamer.DeltaSync.writeToSink(DeltaSync.java:519)
at
org.apache.hudi.utilities.deltastreamer.DeltaSync.syncOnce(DeltaSync.java:306)
at
org.apache.hudi.integ.testsuite.HoodieDeltaStreamerWrapper.upsert(HoodieDeltaStreamerWrapper.java:44)
at
org.apache.hudi.integ.testsuite.HoodieDeltaStreamerWrapper.insert(HoodieDeltaStreamerWrapper.java:48)
at
org.apache.hudi.integ.testsuite.HoodieTestSuiteWriter.insert(HoodieTestSuiteWriter.java:166)
at
org.apache.hudi.integ.testsuite.dag.nodes.InsertNode.ingest(InsertNode.java:70)
at
org.apache.hudi.integ.testsuite.dag.nodes.InsertNode.execute(InsertNode.java:53)
at
org.apache.hudi.integ.testsuite.dag.scheduler.DagScheduler.executeNode(DagScheduler.java:139)
... 6 more
Caused by: org.apache.hudi.exception.HoodieUpsertException: Error upserting
bucketType UPDATE for partition :33
at
org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:320)
at
org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleInsertPartition(BaseSparkCommitActionExecutor.java:326)
at
org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:174)
at
org.apache.spark.api.java.JavaRDDLike.$anonfun$mapPartitionsWithIndex$1(JavaRDDLike.scala:102)
at
org.apache.spark.api.java.JavaRDDLike.$anonfun$mapPartitionsWithIndex$1$adapted(JavaRDDLike.scala:102)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2(RDD.scala:915)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:915)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at
org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:386){noformat}
Test properties
{noformat}
hoodie.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100hoodie.deltastreamer.source.test.num_partitions=100
hoodie.deltastreamer.source.test.datagen.use_rocksdb_for_storing_existing_keys=false
hoodie.deltastreamer.source.test.max_unique_records=100000000
hoodie.embed.timeline.server=false
hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelectorhoodie.datasource.hive_sync.skip_ro_suffix=truehoodie.datasource.write.recordkey.field=_row_key
hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
hoodie.datasource.write.partitionpath.field=timestamphoodie.clustering.plan.strategy.sort.columns=_row_key
hoodie.clustering.plan.strategy.daybased.lookback.partitions=0
hoodie.clustering.inline.max.commits=1hoodie.deltastreamer.source.dfs.root=s3a://dl-scale-test/manoj/010RC2/integration-test-large-scale/slong/mor/input
hoodie.deltastreamer.schemaprovider.target.schema.file=file:/home/hadoop/staging/source.avsc
hoodie.deltastreamer.schemaprovider.source.schema.file=file:/home/hadoop/staging/source.avsc
hoodie.deltastreamer.keygen.timebased.timestamp.type=UNIX_TIMESTAMP
hoodie.deltastreamer.keygen.timebased.output.dateformat=yyyy/MM/ddhoodie.datasource.hive_sync.database=testdb{noformat}
{noformat}
/home/hadoop/spark-3.2.0-bin-hadoop3.2/bin/spark-submit \
--packages org.apache.spark:spark-avro_2.12:3.2.0 \
--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.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 \
--conf
spark.hadoop.fs.s3a.aws.credentials.provider=com.amazonaws.auth.DefaultAWSCredentialsProviderChain
\
--conf spark.hadoop.fs.s3a.connection.maximum=500 \
--class org.apache.hudi.integ.testsuite.HoodieTestSuiteJob \
/home/hadoop/staging/hudi-integ-test-bundle-0.10.0-rc2.jar \
--source-ordering-field test_suite_source_ordering_field \
--use-deltastreamer \
--target-base-path
s3a://dl-scale-test/manoj/010RC2/integration-test-large-scale/slong/mor/output \
--input-base-path
s3a://dl-scale-test/manoj/010RC2/integration-test-large-scale/slong/mor/input \
--target-table table1 \
--props file:/home/hadoop/staging/MERGE_ON_READ-true-test-slong.properties \
--schemaprovider-class
org.apache.hudi.integ.testsuite.schema.TestSuiteFileBasedSchemaProvider \
--source-class org.apache.hudi.utilities.sources.AvroDFSSource \
--input-file-size 125829120 \
--workload-yaml-path file:/home/hadoop/staging/MERGE_ON_READ-true-slong.yaml \
--workload-generator-classname
org.apache.hudi.integ.testsuite.dag.WorkflowDagGenerator \
--table-type MERGE_ON_READ \
--compact-scheduling-minshare 1 \
--clean-input \
--clean-output{noformat}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
