[HUDI-3237] ALTER TABLE column type change fails select query

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 0.10.1
• Fix Version/s: 0.11.0
• Component/s: spark-sql
• Labels: pull-request-available
• Story Points: 0.25
• Assignee: Yann Byron
• Reporter: Raymond Xu

Reviewers

Raymond Xu, sivabalan narayanan

• Created: 12/Jan/22 18:23
• Updated: 25/Jan/22 16:58
• Resolved: 25/Jan/22 00:34

Description

create table if not exists cow_nonpt_nonpcf_tbl (
  id int,
  name string,
  price double
) using hudi
options (
  type = 'cow',
  primaryKey = 'id'
);

insert into cow_nonpt_nonpcf_tbl select 1, 'a1', 20;

DESC cow_nonpt_nonpcf_tbl;

-- shows id int

ALTER TABLE cow_nonpt_nonpcf_tbl change column id id bigint;

DESC cow_nonpt_nonpcf_tbl;

-- shows id bigint
-- this works fine so far

select * from cow_nonpt_nonpcf_tbl;

-- throws exception

org.apache.spark.sql.execution.QueryExecutionException: Parquet column cannot be converted in file file:///opt/spark-warehouse/cow_nonpt_nonpcf_tbl/ff3c68e6-84d4-4a8a-8bc8-cc58736847aa-0_0-7-7_20220112182401452.parquet. Column: [id], Expected: bigint, Found: INT32
        at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:179)
        at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
        at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:503)
        at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)
        at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
        at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
        at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
        at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:345)
        at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
        at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
        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.scheduler.ResultTask.runTask(ResultTask.scala:90)
        at org.apache.spark.scheduler.Task.run(Task.scala:131)
        at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
        at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.sql.execution.datasources.SchemaColumnConvertNotSupportedException
        at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.constructConvertNotSupportedException(VectorizedColumnReader.java:339)
        at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readIntBatch(VectorizedColumnReader.java:571)
        at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBatch(VectorizedColumnReader.java:294)
        at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:283)
        at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:181)
        at org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:37)
        at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
        at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:173)
        ... 20 more

reported while testing on 0.10.1-rc1 (spark 3.0.3, 3.1.2)

Issue Links

• links to: GitHub Pull Request #4677