[
https://issues.apache.org/jira/browse/HUDI-8825?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Y Ethan Guo updated HUDI-8825:
------------------------------
Parent: HUDI-9109 (was: HUDI-8722)
> MIT in partitioned MOR table with global index hit type mismatch error
> ----------------------------------------------------------------------
>
> Key: HUDI-8825
> URL: https://issues.apache.org/jira/browse/HUDI-8825
> Project: Apache Hudi
> Issue Type: Sub-task
> Components: spark-sql
> Reporter: Davis Zhang
> Priority: Major
> Fix For: 1.0.2
>
> Attachments: itFailure.zip
>
>
> the attached is the table folder ^ after merge into of the below query suite
> vv
> spark 3.4. hudi internal & OSS all have such issue.
> Impact: MIT does not work when column type is double in some cases. No data
> corruption.
> I don't think there is an easy alternative except deleting records and
> re-insert new ones, especially for cross partition updates.
>
> CREATE TABLE hudi_global_index_mor ( record_key STRING, name STRING, age INT,
> department STRING, salary DOUBLE, ts BIGINT ) USING hudi PARTITIONED BY
> (department) LOCATION
> 's3a://onehouse-customer-bucket-fb543790/lakes/observed-default/sql_global_bloom_filter_db_3c97332a_1732579795651/hudi_global_index_mor/'
> TBLPROPERTIES ( type = 'mor', 'hoodie.index.type' = 'GLOBAL_SIMPLE',
> 'hoodie.index.global.index.enable' = 'true',
> 'hoodie.bloom.index.use.metadata' = 'true', primaryKey = 'record_key',
> preCombineField = 'ts' ) ; INSERT INTO hudi_global_index_mor SELECT * FROM (
> SELECT 'emp_001' as record_key, 'John Doe' as name, 30 as age, 'Sales' as
> department, 80000.0 as salary, 1598886000 as ts UNION ALL SELECT 'emp_002',
> 'Jane Smith', 28, 'Sales', 75000.0, 1598886001 UNION ALL SELECT 'emp_003',
> 'Bob Wilson', 35, 'Marketing', 85000.0, 1598886002 ) ; UPDATE
> hudi_global_index_mor SET department = 'Sales', salary = 90000.0, ts =
> 1598886100 WHERE record_key = 'emp_001' ; SELECT record_key, name, age,
> department, salary, ts FROM hudi_global_index_mor ORDER BY record_key ;
> CREATE OR REPLACE TEMPORARY VIEW source_updates AS SELECT * FROM ( SELECT
> 'emp_001' as record_key, 'John Doe' as name, 30 as age, 'Engineering' as
> department, 95000.0 as salary, cast(1598886200 as BIGINT) as ts UNION ALL
> SELECT 'emp_004', 'Alice Brown', 29, 'Engineering', 82000.0, cast(1598886201
> as BIGINT) ) ; MERGE INTO hudi_global_index_mor t USING source_updates s ON
> t.record_key = s.record_key WHEN MATCHED THEN UPDATE SET department =
> s.department, salary = s.salary, ts = s.ts WHEN NOT MATCHED THEN INSERT * ;
>
>
>
> Error
> Caused by: org.apache.avro.AvroTypeException: Found double, expecting
> hoodie.hudi_global_index_mor.hudi_global_index_mor_record.salary.fixed at
> org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:308) at
> org.apache.avro.io.parsing.Parser.advance(Parser.java:86) at
> org.apache.avro.io.ValidatingDecoder.checkFixed(ValidatingDecoder.java:134)
> at org.apache.avro.io.ValidatingDecoder.readFixed(ValidatingDecoder.java:144)
> at
> org.apache.avro.generic.GenericDatumReader.readFixed(GenericDatumReader.java:387)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:190)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:260)
> at
> org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:248)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:180)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:154)
> at
> From the timeline we clearly see the column salary is "double"
> { "name": "salary", "type": [ "null", "double" ], "default": null },
> Also checked the parquet file, I didn't see anything abnormal.
> parquet.avro.schema:
> \{"type":"record","name":"hudi_global_index_mor_record","namespace":"hoodie.hudi_global_index_mor","fields":[{"name":"_hoodie_commit_time","type":["null","string"],"doc":"","default":null},\{"name":"_hoodie_commit_seqno","type":["null","string"],"doc":"","default":null},\{"name":"_hoodie_record_key","type":["null","string"],"doc":"","default":null},\{"name":"_hoodie_partition_path","type":["null","string"],"doc":"","default":null},\{"name":"_hoodie_file_name","type":["null","string"],"doc":"","default":null},\{"name":"record_key","type":["null","string"],"default":null},\{"name":"name","type":["null","string"],"default":null},\{"name":"age","type":["null","int"],"default":null},\{"name":"salary","type":["null","double"],"default":null},\{"name":"ts","type":["null","long"],"default":null},\{"name":"department","type":["null","string"],"default":null}]}
> writer.model.name: avro hoodie_max_record_key: emp_003 Schema: message
> hoodie.hudi_global_index_mor.hudi_global_index_mor_record \{ optional binary
> _hoodie_commit_time (STRING); optional binary _hoodie_commit_seqno (STRING);
> optional binary _hoodie_record_key (STRING); optional binary
> _hoodie_partition_path (STRING); optional binary _hoodie_file_name (STRING);
> optional binary record_key (STRING); optional binary name (STRING); optional
> int32 age; optional double salary; optional int64 ts; optional binary
> department (STRING); } Row group 0: count: 1 728.00 B records start: 4
> total(compressed): 728 B total(uncompressed):540 B
> --------------------------------------------------------------------------------
> type encodings count avg size nulls min / max _hoodie_commit_time BINARY G _
> 1 68.00 B 0 "20241126001135153" / "20241126001135153" _hoodie_commit_seqno
> BINARY G _ 1 72.00 B 0 "20241126001135153_1_0" / "20241126001135153_1_0"
> _hoodie_record_key BINARY G _ 1 58.00 B 0 "emp_003" / "emp_003"
> _hoodie_partition_path BINARY G _ 1 71.00 B 0 "department=Marketing" /
> "department=Marketing" _hoodie_file_name BINARY G _ 1 118.00 B 0
> "31aa5fb4-9732-4376-bf6c-3..." / "31aa5fb4-9732-4376-bf6c-3..." record_key
> BINARY G _ 1 58.00 B 0 "emp_003" / "emp_003" name BINARY G _ 1 61.00 B 0 "Bob
> Wilson" / "Bob Wilson" age INT32 G _ 1 51.00 B 0 "35" / "35" salary DOUBLE G
> _ 1 56.00 B 0 "85000.0" / "85000.0" ts INT64 G _ 1 55.00 B 0 "1598886002" /
> "1598886002" department BINARY G _ 1 60.00 B 0 "Marketing" / "Marketing"
>
> *One theory is the code path trying to parse the double value in DECIMAL,
> whose underlying avro type is either bytes or fixed.*
> h3. *Decimal*
> The decimal logical type represents an arbitrary-precision signed decimal
> number of the form {_}unscaled × 10{_}{^}_-scale_{^}.
> A decimal logical type annotates Avro *bytes* or *fixed* types. The byte
> array must contain the two's-complement representation of the unscaled
> integer value in big-endian byte order. The scale is fixed, and is specified
> using an attribute.
>
>
> full stack trace
> Caused by: org.apache.hudi.exception.HoodieUpsertException: Failed to upsert
> for commit time 20241126001204349 at
> org.apache.hudi.table.action.commit.BaseWriteHelper.write(BaseWriteHelper.java:80)
> at
> org.apache.hudi.table.action.deltacommit.SparkUpsertDeltaCommitActionExecutor.execute(SparkUpsertDeltaCommitActionExecutor.java:47)
> at
> org.apache.hudi.table.HoodieSparkMergeOnReadTable.upsert(HoodieSparkMergeOnReadTable.java:98)
> at
> org.apache.hudi.table.HoodieSparkMergeOnReadTable.upsert(HoodieSparkMergeOnReadTable.java:88)
> at
> org.apache.hudi.client.SparkRDDWriteClient.upsert(SparkRDDWriteClient.java:162)
> at
> org.apache.hudi.DataSourceUtils.doWriteOperation(DataSourceUtils.java:221) at
> org.apache.hudi.HoodieSparkSqlWriterInternal.liftedTree1$1(HoodieSparkSqlWriter.scala:484)
> at
> org.apache.hudi.HoodieSparkSqlWriterInternal.writeInternal(HoodieSparkSqlWriter.scala:482)
> at
> org.apache.hudi.HoodieSparkSqlWriterInternal.write(HoodieSparkSqlWriter.scala:180)
> at
> org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:118)
> at
> org.apache.spark.sql.hudi.command.MergeIntoHoodieTableCommand.executeUpsert(MergeIntoHoodieTableCommand.scala:421)
> at
> org.apache.spark.sql.hudi.command.MergeIntoHoodieTableCommand.run(MergeIntoHoodieTableCommand.scala:264)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
> at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:98)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:118)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:195)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:103)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:827) at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
> at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
> at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:94)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:512)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:104)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:512)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:31)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:31)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:31)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:488)
> at
> org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:94)
> at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:81)
> at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:79)
> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:218) at
> org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:98) at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:827) at
> org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:95) at
> org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:640) at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:827) at
> org.apache.spark.sql.SparkSession.sql(SparkSession.scala:630) at
> org.apache.spark.sql.SparkSession.sql(SparkSession.scala:671) at
> org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651) at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:226)
> ... 16 more Caused by: org.apache.spark.SparkException: Job aborted due to
> stage failure: Task 1 in stage 4579.0 failed 4 times, most recent failure:
> Lost task 1.3 in stage 4579.0 (TID 9325) (10.0.91.170 executor 1):
> org.apache.hudi.exception.HoodieException: Exception when reading log file at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternalV1(AbstractHoodieLogRecordReader.java:359)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternal(AbstractHoodieLogRecordReader.java:218)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.performScan(HoodieMergedLogRecordScanner.java:203)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.<init>(HoodieMergedLogRecordScanner.java:119)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.<init>(HoodieMergedLogRecordScanner.java:77)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner$Builder.build(HoodieMergedLogRecordScanner.java:465)
> at
> org.apache.hudi.io.HoodieMergedReadHandle.getLogRecordScanner(HoodieMergedReadHandle.java:148)
> at
> org.apache.hudi.io.HoodieMergedReadHandle.getMergedRecords(HoodieMergedReadHandle.java:89)
> at
> org.apache.hudi.index.HoodieIndexUtils.lambda$getExistingRecords$c7e45d15$1(HoodieIndexUtils.java:246)
> at
> org.apache.hudi.data.HoodieJavaRDD.lambda$flatMap$a6598fcb$1(HoodieJavaRDD.java:137)
> at
> org.apache.spark.api.java.JavaRDDLike.$anonfun$flatMap$1(JavaRDDLike.scala:125)
> at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486) at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492) at
> scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460) at
> org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)
> at
> org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:101)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
> at org.apache.spark.scheduler.Task.run(Task.scala:139) at
> org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529) at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557) at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
> at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown
> Source) at java.base/java.lang.Thread.run(Unknown Source) Caused by:
> org.apache.avro.AvroTypeException: Found double, expecting
> hoodie.hudi_global_index_mor.hudi_global_index_mor_record.salary.fixed at
> org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:308) at
> org.apache.avro.io.parsing.Parser.advance(Parser.java:86) at
> org.apache.avro.io.ValidatingDecoder.checkFixed(ValidatingDecoder.java:134)
> at org.apache.avro.io.ValidatingDecoder.readFixed(ValidatingDecoder.java:144)
> at
> org.apache.avro.generic.GenericDatumReader.readFixed(GenericDatumReader.java:387)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:190)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:260)
> at
> org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:248)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:180)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:154)
> at
> org.apache.hudi.common.table.log.block.HoodieAvroDataBlock$RecordIterator.next(HoodieAvroDataBlock.java:223)
> at
> org.apache.hudi.common.table.log.block.HoodieAvroDataBlock$RecordIterator.next(HoodieAvroDataBlock.java:168)
> at
> org.apache.hudi.common.util.collection.MappingIterator.next(MappingIterator.java:44)
> at
> org.apache.hudi.common.util.collection.MappingIterator.next(MappingIterator.java:44)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.processDataBlock(AbstractHoodieLogRecordReader.java:613)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.processQueuedBlocksForInstant(AbstractHoodieLogRecordReader.java:654)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternalV1(AbstractHoodieLogRecordReader.java:349)
> ... 25 more Driver stacktrace: at
> org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2790)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2726)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2725)
> at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49) at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2725)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1211)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1211)
> at scala.Option.foreach(Option.scala:407) at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1211)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2989)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2928)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2917)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at
> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:976) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2263) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2284) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2303) at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2328) at
> org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1022) at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:408) at
> org.apache.spark.rdd.RDD.collect(RDD.scala:1021) at
> org.apache.spark.rdd.PairRDDFunctions.$anonfun$countByKey$1(PairRDDFunctions.scala:367)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:408) at
> org.apache.spark.rdd.PairRDDFunctions.countByKey(PairRDDFunctions.scala:367)
> at org.apache.spark.api.java.JavaPairRDD.countByKey(JavaPairRDD.scala:314) at
> org.apache.hudi.data.HoodieJavaPairRDD.countByKey(HoodieJavaPairRDD.java:105)
> at
> org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.buildProfile(BaseSparkCommitActionExecutor.java:220)
> at
> org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.execute(BaseSparkCommitActionExecutor.java:186)
> at
> org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.execute(BaseSparkCommitActionExecutor.java:90)
> at
> org.apache.hudi.table.action.commit.BaseWriteHelper.write(BaseWriteHelper.java:74)
> ... 60 more Caused by: org.apache.hudi.exception.HoodieException: Exception
> when reading log file at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternalV1(AbstractHoodieLogRecordReader.java:359)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternal(AbstractHoodieLogRecordReader.java:218)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.performScan(HoodieMergedLogRecordScanner.java:203)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.<init>(HoodieMergedLogRecordScanner.java:119)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner.<init>(HoodieMergedLogRecordScanner.java:77)
> at
> org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner$Builder.build(HoodieMergedLogRecordScanner.java:465)
> at
> org.apache.hudi.io.HoodieMergedReadHandle.getLogRecordScanner(HoodieMergedReadHandle.java:148)
> at
> org.apache.hudi.io.HoodieMergedReadHandle.getMergedRecords(HoodieMergedReadHandle.java:89)
> at
> org.apache.hudi.index.HoodieIndexUtils.lambda$getExistingRecords$c7e45d15$1(HoodieIndexUtils.java:246)
> at
> org.apache.hudi.data.HoodieJavaRDD.lambda$flatMap$a6598fcb$1(HoodieJavaRDD.java:137)
> at
> org.apache.spark.api.java.JavaRDDLike.$anonfun$flatMap$1(JavaRDDLike.scala:125)
> at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:486) at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:492) at
> scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460) at
> org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)
> at
> org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:101)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
> at org.apache.spark.scheduler.Task.run(Task.scala:139) at
> org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529) at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557) ... 3
> more Caused by: org.apache.avro.AvroTypeException: Found double, expecting
> hoodie.hudi_global_index_mor.hudi_global_index_mor_record.salary.fixed at
> org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:308) at
> org.apache.avro.io.parsing.Parser.advance(Parser.java:86) at
> org.apache.avro.io.ValidatingDecoder.checkFixed(ValidatingDecoder.java:134)
> at org.apache.avro.io.ValidatingDecoder.readFixed(ValidatingDecoder.java:144)
> at
> org.apache.avro.generic.GenericDatumReader.readFixed(GenericDatumReader.java:387)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:190)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:260)
> at
> org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:248)
> at
> org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:180)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:161)
> at
> org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:154)
> at
> org.apache.hudi.common.table.log.block.HoodieAvroDataBlock$RecordIterator.next(HoodieAvroDataBlock.java:223)
> at
> org.apache.hudi.common.table.log.block.HoodieAvroDataBlock$RecordIterator.next(HoodieAvroDataBlock.java:168)
> at
> org.apache.hudi.common.util.collection.MappingIterator.next(MappingIterator.java:44)
> at
> org.apache.hudi.common.util.collection.MappingIterator.next(MappingIterator.java:44)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.processDataBlock(AbstractHoodieLogRecordReader.java:613)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.processQueuedBlocksForInstant(AbstractHoodieLogRecordReader.java:654)
> at
> org.apache.hudi.common.table.log.AbstractHoodieLogRecordReader.scanInternalV1(AbstractHoodieLogRecordReader.java:349)
> ... 25 more at
> org.apache.hive.jdbc.HiveStatement.waitForOperationToComplete(HiveStatement.java:385)
> at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:254) at
> com.zaxxer.hikari.pool.ProxyStatement.execute(ProxyStatement.java:94) at
> com.zaxxer.hikari.pool.HikariProxyStatement.execute(HikariProxyStatement.java)
> at
> integrationTests.sql.HiveConnection.runQueryAndFetchResultsInCsv(HiveConnection.java:102)
> ... 154 more
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
