[HIVE-22595] Dynamic partition inserts fail on Avro table table with external schema

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 4.0.0-alpha-1
• Component/s: Avro, Serializers/Deserializers
• Assignee: Jason Dere
• Reporter: Jason Dere
• Created: 07/Dec/19 02:27
• Updated: 27/Feb/24 22:23
• Resolved: 10/Jan/20 16:43

Description

Example qfile test:

create external table avro_extschema_insert1 (name string) partitioned by (p1 string)
  stored as avro tblproperties ('avro.schema.url'='${system:test.tmp.dir}/table1.avsc');

create external table avro_extschema_insert2 like avro_extschema_insert1;

insert overwrite table avro_extschema_insert1 partition (p1='part1') values ('col1_value', 1, 'col3_value');

insert overwrite table avro_extschema_insert2 partition (p1) select * from avro_extschema_insert1;

The last statement fails with the following error:

], TaskAttempt 3 failed, info=[Error: Error while running task ( failure ) : attempt_1575484789169_0003_4_00_000000_3:java.lang.RuntimeException: java.lang.RuntimeException: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
	at org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:296)
	at org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:250)
	at org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:374)
	at org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:73)
	at org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:61)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
	at org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:61)
	at org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:37)
	at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36)
	at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:125)
	at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:69)
	at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:78)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
	at org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:101)
	at org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.pushRecord(MapRecordSource.java:76)
	at org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.run(MapRecordProcessor.java:426)
	at org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:267)
	... 16 more
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
	at org.apache.hadoop.hive.ql.exec.MapOperator.process(MapOperator.java:576)
	at org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:92)
	... 19 more
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: org.apache.hadoop.hive.serde2.avro.AvroSerdeException: Number of input columns was different than output columns (in = 2 vs out = 1
	at org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:1047)
	at org.apache.hadoop.hive.ql.exec.Operator.baseForward(Operator.java:994)
	at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:940)
	at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:927)
	at org.apache.hadoop.hive.ql.exec.SelectOperator.process(SelectOperator.java:95)
	at org.apache.hadoop.hive.ql.exec.Operator.baseForward(Operator.java:994)
	at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:940)
	at org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:125)
	at org.apache.hadoop.hive.ql.exec.MapOperator$MapOpCtx.forward(MapOperator.java:153)
	at org.apache.hadoop.hive.ql.exec.MapOperator.process(MapOperator.java:555)
	... 20 more
Caused by: org.apache.hadoop.hive.serde2.avro.AvroSerdeException: Number of input columns was different than output columns (in = 2 vs out = 1
	at org.apache.hadoop.hive.serde2.avro.AvroSerializer.serialize(AvroSerializer.java:77)
	at org.apache.hadoop.hive.serde2.avro.AvroSerDe.serialize(AvroSerDe.java:223)
	at org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:951)
	... 29 more

Issue Links

• is caused by: HIVE-11972 [Refactor] Improve determination of dynamic partitioning columns in FileSink Operator