Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save nsivabalan/cafc53fc9a8681923e4e2fa4eb2133fe to your computer and use it in GitHub Desktop.
Save nsivabalan/cafc53fc9a8681923e4e2fa4eb2133fe to your computer and use it in GitHub Desktop.
scala> dfFromData8.write.format("hudi").
| options(getQuickstartWriteConfigs).
| option(PRECOMBINE_FIELD_OPT_KEY, "preComb").
| option(RECORDKEY_FIELD_OPT_KEY, "rowId").
| option(PARTITIONPATH_FIELD_OPT_KEY, "partitionId").
| option("hoodie.index.type","SIMPLE").
| option(TABLE_NAME, tableName).
| mode(Append).
| save(basePath)
21/02/27 16:09:10 ERROR BoundedInMemoryExecutor: error producing records
org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
21/02/27 16:09:11 ERROR BoundedInMemoryExecutor: error consuming records 1) / 1]
org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
21/02/27 16:09:11 ERROR BaseSparkCommitActionExecutor: Error upserting bucketType UPDATE for partition :0
org.apache.hudi.exception.HoodieException: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:102)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdateInternal(BaseSparkCommitActionExecutor.java:308)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdate(BaseSparkCommitActionExecutor.java:299)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:272)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:135)
at org.apache.spark.api.java.JavaRDDLike.$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$2(RDD.scala:889)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:889)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:362)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1388)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1298)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1362)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1186)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:360)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:311)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:143)
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:100)
... 31 more
Caused by: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:141)
... 32 more
Caused by: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
... 3 more
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
21/02/27 16:09:11 WARN BlockManager: Putting block rdd_373_0 failed due to exception org.apache.hudi.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :0.
21/02/27 16:09:11 WARN BlockManager: Block rdd_373_0 could not be removed as it was not found on disk or in memory
21/02/27 16:09:11 ERROR Executor: Exception in task 0.0 in stage 190.0 (TID 1742)
org.apache.hudi.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :0
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:279)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:135)
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:889)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:889)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:362)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1388)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1298)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1362)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1186)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:360)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:311)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.hudi.exception.HoodieException: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:102)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdateInternal(BaseSparkCommitActionExecutor.java:308)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdate(BaseSparkCommitActionExecutor.java:299)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:272)
... 28 more
Caused by: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:143)
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:100)
... 31 more
Caused by: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:141)
... 32 more
Caused by: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
... 3 more
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
21/02/27 16:09:11 WARN TaskSetManager: Lost task 0.0 in stage 190.0 (TID 1742, sivabala-c02xg219jgh6.attlocal.net, executor driver): org.apache.hudi.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :0
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:279)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:135)
at org.apache.spark.api.java.JavaRDDLike.$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$2(RDD.scala:889)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:889)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:362)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1388)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1298)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1362)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1186)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:360)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:311)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.hudi.exception.HoodieException: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:102)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdateInternal(BaseSparkCommitActionExecutor.java:308)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdate(BaseSparkCommitActionExecutor.java:299)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:272)
... 28 more
Caused by: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:143)
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:100)
... 31 more
Caused by: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:141)
... 32 more
Caused by: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
... 3 more
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
21/02/27 16:09:11 ERROR TaskSetManager: Task 0 in stage 190.0 failed 1 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 190.0 failed 1 times, most recent failure: Lost task 0.0 in stage 190.0 (TID 1742, sivabala-c02xg219jgh6.attlocal.net, executor driver): org.apache.hudi.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :0
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:279)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:135)
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:889)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:889)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:362)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1388)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1298)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1362)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1186)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:360)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:311)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.hudi.exception.HoodieException: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:102)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdateInternal(BaseSparkCommitActionExecutor.java:308)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdate(BaseSparkCommitActionExecutor.java:299)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:272)
... 28 more
Caused by: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:143)
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:100)
... 31 more
Caused by: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:141)
... 32 more
Caused by: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
... 3 more
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2008)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2007)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2007)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:973)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2239)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2188)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2177)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:775)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2099)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2120)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2139)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2164)
at org.apache.spark.rdd.RDD.count(RDD.scala:1227)
at org.apache.hudi.HoodieSparkSqlWriter$.commitAndPerformPostOperations(HoodieSparkSqlWriter.scala:433)
at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:218)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:134)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:90)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:175)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:122)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:121)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:963)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:415)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:399)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:288)
... 69 elided
Caused by: org.apache.hudi.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :0
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:279)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.lambda$execute$ecf5068c$1(BaseSparkCommitActionExecutor.java:135)
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:889)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:889)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:362)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1388)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1298)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1362)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1186)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:360)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:311)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.hudi.exception.HoodieException: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:102)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdateInternal(BaseSparkCommitActionExecutor.java:308)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpdate(BaseSparkCommitActionExecutor.java:299)
at org.apache.hudi.table.action.commit.BaseSparkCommitActionExecutor.handleUpsertPartition(BaseSparkCommitActionExecutor.java:272)
... 28 more
Caused by: org.apache.hudi.exception.HoodieException: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:143)
at org.apache.hudi.table.action.commit.SparkMergeHelper.runMerge(SparkMergeHelper.java:100)
... 31 more
Caused by: java.util.concurrent.ExecutionException: org.apache.hudi.exception.HoodieException: operation has failed
at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.execute(BoundedInMemoryExecutor.java:141)
... 32 more
Caused by: org.apache.hudi.exception.HoodieException: operation has failed
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.throwExceptionIfFailed(BoundedInMemoryQueue.java:247)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.readNextRecord(BoundedInMemoryQueue.java:226)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue.access$100(BoundedInMemoryQueue.java:52)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueue$QueueIterator.hasNext(BoundedInMemoryQueue.java:277)
at org.apache.hudi.common.util.queue.BoundedInMemoryQueueConsumer.consume(BoundedInMemoryQueueConsumer.java:36)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$2(BoundedInMemoryExecutor.java:121)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
... 3 more
Caused by: org.apache.parquet.io.InvalidRecordException: Parquet/Avro schema mismatch: Avro field 'toBeDeletedStr' not found
at org.apache.parquet.avro.AvroRecordConverter.getAvroField(AvroRecordConverter.java:225)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:130)
at org.apache.parquet.avro.AvroRecordConverter.<init>(AvroRecordConverter.java:95)
at org.apache.parquet.avro.AvroRecordMaterializer.<init>(AvroRecordMaterializer.java:33)
at org.apache.parquet.avro.AvroReadSupport.prepareForRead(AvroReadSupport.java:138)
at org.apache.parquet.hadoop.InternalParquetRecordReader.initialize(InternalParquetRecordReader.java:183)
at org.apache.parquet.hadoop.ParquetReader.initReader(ParquetReader.java:156)
at org.apache.parquet.hadoop.ParquetReader.read(ParquetReader.java:135)
at org.apache.hudi.common.util.ParquetReaderIterator.hasNext(ParquetReaderIterator.java:49)
at org.apache.hudi.common.util.queue.IteratorBasedQueueProducer.produce(IteratorBasedQueueProducer.java:45)
at org.apache.hudi.common.util.queue.BoundedInMemoryExecutor.lambda$null$0(BoundedInMemoryExecutor.java:92)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
... 4 more
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment