jackwang2 opened a new issue #764: Hoodie 0.4.7: Error upserting bucketType UPDATE for partition, No value present URL: https://github.com/apache/incubator-hudi/issues/764 19/06/27 08:38:26 WARN TaskSetManager: Lost task 5.0 in stage 26.0 (TID 13747, ip-172-19-101-41, executor 0): com.uber.hoodie.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :5 at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:271) at com.uber.hoodie.HoodieWriteClient.lambda$upsertRecordsInternal$7ef77fd$1(HoodieWriteClient.java:442) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:337) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:335) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1109) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1018) at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:809) at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335) at org.apache.spark.rdd.RDD.iterator(RDD.scala:286) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:109) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:748) Caused by: java.util.NoSuchElementException: No value present at com.uber.hoodie.common.util.Option.get(Option.java:112) at com.uber.hoodie.io.HoodieMergeHandle.(HoodieMergeHandle.java:71) at com.uber.hoodie.table.HoodieCopyOnWriteTable.getUpdateHandle(HoodieCopyOnWriteTable.java:226) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpdate(HoodieCopyOnWriteTable.java:180) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:263) ... 28 more 19/06/27 08:38:26 INFO TaskSetManager: Starting task 5.1 in stage 26.0 (TID 13749, ip-172-19-102-145, executor 4, partition 5, PROCESS_LOCAL, 7653 bytes) 19/06/27 08:38:26 WARN TaskSetManager: Lost task 4.0 in stage 26.0 (TID 13746, ip-172-19-102-145, executor 4): com.uber.hoodie.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :4 at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:271) at com.uber.hoodie.HoodieWriteClient.lambda$upsertRecordsInternal$7ef77fd$1(HoodieWriteClient.java:442) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:337) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:335) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1109) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1018) at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:809) at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335) at org.apache.spark.rdd.RDD.iterator(RDD.scala:286) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:109) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:748) Caused by: java.util.NoSuchElementException: No value present at com.uber.hoodie.common.util.Option.get(Option.java:112) at com.uber.hoodie.io.HoodieMergeHandle.(HoodieMergeHandle.java:71) at com.uber.hoodie.table.HoodieCopyOnWriteTable.getUpdateHandle(HoodieCopyOnWriteTable.java:226) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpdate(HoodieCopyOnWriteTable.java:180) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:263) ... 28 more 19/06/27 08:38:26 INFO TaskSetManager: Starting task 4.1 in stage 26.0 (TID 13750, ip-172-19-103-242, executor 2, partition 4, PROCESS_LOCAL, 7653 bytes) 19/06/27 08:38:26 WARN TaskSetManager: Lost task 6.0 in stage 26.0 (TID 13748, ip-172-19-102-162, executor 3): com.uber.hoodie.exception.HoodieUpsertException: Error upserting bucketType UPDATE for partition :6 at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:271) at com.uber.hoodie.HoodieWriteClient.lambda$upsertRecordsInternal$7ef77fd$1(HoodieWriteClient.java:442) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.api.java.JavaRDDLike$$anonfun$mapPartitionsWithIndex$1.apply(JavaRDDLike.scala:102) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1$$anonfun$apply$26.apply(RDD.scala:847) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:337) at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:335) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1109) at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1018) at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:809) at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335) at org.apache.spark.rdd.RDD.iterator(RDD.scala:286) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324) at org.apache.spark.rdd.RDD.iterator(RDD.scala:288) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:109) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345) 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:748) Caused by: java.util.NoSuchElementException: No value present at com.uber.hoodie.common.util.Option.get(Option.java:112) at com.uber.hoodie.io.HoodieMergeHandle.(HoodieMergeHandle.java:71) at com.uber.hoodie.table.HoodieCopyOnWriteTable.getUpdateHandle(HoodieCopyOnWriteTable.java:226) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpdate(HoodieCopyOnWriteTable.java:180) at com.uber.hoodie.table.HoodieCopyOnWriteTable.handleUpsertPartition(HoodieCopyOnWriteTable.java:263) ... 28 more Any ideas?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
