[ https://issues.apache.org/jira/browse/TEZ-1807?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tsuyoshi OZAWA updated TEZ-1807: -------------------------------- Description: I ran Hive 0.14 on Tez 0.5.2. Data size is 100GB texts generated by RandomTextWriter. {code} create external table randomText100GB( text string ) location 'hdfs:///user/ozawa/randomText100GB'; CREATE TABLE wordcount AS SELECT word, count(1) AS count FROM (SELECT EXPLODE(SPLIT(LCASE(REGEXP_REPLACE(text,'[\\p{Punct},\\p{Cntrl}]','')),' ')) AS word FROM randomText100GB) words GROUP BY word; {code} As a result, an exception is thrown: {quote} -------------------------------------------------------------------------------- VERTICES STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED -------------------------------------------------------------------------------- Map 1 ......... KILLED 115 104 0 11 0 11 Reducer 2 FAILED 3 0 0 3 1 2 -------------------------------------------------------------------------------- VERTICES: 00/02 [======================>>----] 88% ELAPSED TIME: 108.81 s -------------------------------------------------------------------------------- Status: Failed Vertex failed, vertexName=Reducer 2, vertexId=vertex_1417036912823_0071_1_01, diagnostics=[Task failed, taskId=task_1417036912823_0071_1_01_000000, diagnostics=[TaskAttempt 0 failed, info=[Error: exceptionThrown=org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: error in shuffle in MemToMemMerger [Map_1] at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Caused by: java.io.EOFException: Reach the limit of the buffer at org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) at org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) at java.io.DataOutputStream.write(DataOutputStream.java:107) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) at org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) , errorMessage=Shuffle Runner Failed:org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: error in shuffle in MemToMemMerger [Map_1] at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Caused by: java.io.EOFException: Reach the limit of the buffer at org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) at org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) at java.io.DataOutputStream.write(DataOutputStream.java:107) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) at org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) ]], Vertex failed as one or more tasks failed. failedTasks:1, Vertex vertex_1417036912823_0071_1_01 [Reducer 2] killed/failed due to:null] Vertex killed, vertexName=Map 1, vertexId=vertex_1417036912823_0071_1_00, diagnostics=[Vertex received Kill while in RUNNING state., Vertex killed as other vertex failed. failedTasks:0, Vertex vertex_1417036912823_0071_1_00 [Map 1] killed/failed due to:null] DAG failed due to vertex failure. failedVertices:1 killedVertices:1 {quote} was: I ran Hive 0.14 on Tez 0.5.2 and master. Data size is 100GB texts generated by RandomTextWriter. {code} create external table randomText100GB( text string ) location 'hdfs:///user/ozawa/randomText100GB'; CREATE TABLE wordcount AS SELECT word, count(1) AS count FROM (SELECT EXPLODE(SPLIT(LCASE(REGEXP_REPLACE(text,'[\\p{Punct},\\p{Cntrl}]','')),' ')) AS word FROM randomText100GB) words GROUP BY word; {code} As a result, an exception is thrown: {quote} -------------------------------------------------------------------------------- VERTICES STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED -------------------------------------------------------------------------------- Map 1 ......... KILLED 115 104 0 11 0 11 Reducer 2 FAILED 3 0 0 3 1 2 -------------------------------------------------------------------------------- VERTICES: 00/02 [======================>>----] 88% ELAPSED TIME: 108.81 s -------------------------------------------------------------------------------- Status: Failed Vertex failed, vertexName=Reducer 2, vertexId=vertex_1417036912823_0071_1_01, diagnostics=[Task failed, taskId=task_1417036912823_0071_1_01_000000, diagnostics=[TaskAttempt 0 failed, info=[Error: exceptionThrown=org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: error in shuffle in MemToMemMerger [Map_1] at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Caused by: java.io.EOFException: Reach the limit of the buffer at org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) at org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) at java.io.DataOutputStream.write(DataOutputStream.java:107) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) at org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) , errorMessage=Shuffle Runner Failed:org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: error in shuffle in MemToMemMerger [Map_1] at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Caused by: java.io.EOFException: Reach the limit of the buffer at org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) at org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) at java.io.DataOutputStream.write(DataOutputStream.java:107) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) at org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) at org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) at org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) ]], Vertex failed as one or more tasks failed. failedTasks:1, Vertex vertex_1417036912823_0071_1_01 [Reducer 2] killed/failed due to:null] Vertex killed, vertexName=Map 1, vertexId=vertex_1417036912823_0071_1_00, diagnostics=[Vertex received Kill while in RUNNING state., Vertex killed as other vertex failed. failedTasks:0, Vertex vertex_1417036912823_0071_1_00 [Map 1] killed/failed due to:null] DAG failed due to vertex failure. failedVertices:1 killedVertices:1 {quote} > BoundedByteArrayOutputStream throw EOFException because of "Reach the limit > of the buffer" > ------------------------------------------------------------------------------------------ > > Key: TEZ-1807 > URL: https://issues.apache.org/jira/browse/TEZ-1807 > Project: Apache Tez > Issue Type: Improvement > Affects Versions: 0.6.0, 0.5.2 > Reporter: Tsuyoshi OZAWA > > I ran Hive 0.14 on Tez 0.5.2. Data size is 100GB texts generated by > RandomTextWriter. > {code} > create external table randomText100GB( > text string > ) location 'hdfs:///user/ozawa/randomText100GB'; > CREATE TABLE wordcount AS > SELECT word, count(1) AS count > FROM (SELECT > EXPLODE(SPLIT(LCASE(REGEXP_REPLACE(text,'[\\p{Punct},\\p{Cntrl}]','')),' ')) > AS word FROM randomText100GB) words > GROUP BY word; > {code} > As a result, an exception is thrown: > {quote} > -------------------------------------------------------------------------------- > VERTICES STATUS TOTAL COMPLETED RUNNING PENDING FAILED > KILLED > -------------------------------------------------------------------------------- > Map 1 ......... KILLED 115 104 0 11 0 > 11 > Reducer 2 FAILED 3 0 0 3 1 > 2 > -------------------------------------------------------------------------------- > VERTICES: 00/02 [======================>>----] 88% ELAPSED TIME: 108.81 s > > -------------------------------------------------------------------------------- > Status: Failed > Vertex failed, vertexName=Reducer 2, vertexId=vertex_1417036912823_0071_1_01, > diagnostics=[Task failed, taskId=task_1417036912823_0071_1_01_000000, > diagnostics=[TaskAttempt 0 failed, info=[Error: > exceptionThrown=org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: > error in shuffle in MemToMemMerger [Map_1] > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.io.EOFException: Reach the limit of the buffer > at > org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) > at > org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) > at java.io.DataOutputStream.write(DataOutputStream.java:107) > at > org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) > at > org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) > at > org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) > , errorMessage=Shuffle Runner > Failed:org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$ShuffleError: > error in shuffle in MemToMemMerger [Map_1] > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:338) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.Shuffle$RunShuffleCallable.call(Shuffle.java:319) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: java.io.EOFException: Reach the limit of the buffer > at > org.apache.hadoop.io.BoundedByteArrayOutputStream.write(BoundedByteArrayOutputStream.java:92) > at > org.apache.tez.runtime.library.common.sort.impl.IFileOutputStream.write(IFileOutputStream.java:120) > at java.io.DataOutputStream.write(DataOutputStream.java:107) > at > org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.writeKVPair(IFile.java:420) > at > org.apache.tez.runtime.library.common.sort.impl.IFile$Writer.append(IFile.java:390) > at > org.apache.tez.runtime.library.common.sort.impl.TezMerger.writeFile(TezMerger.java:203) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeManager$IntermediateMemoryToMemoryMerger.merge(MergeManager.java:527) > at > org.apache.tez.runtime.library.common.shuffle.orderedgrouped.MergeThread.run(MergeThread.java:89) > ]], Vertex failed as one or more tasks failed. failedTasks:1, Vertex > vertex_1417036912823_0071_1_01 [Reducer 2] killed/failed due to:null] > Vertex killed, vertexName=Map 1, vertexId=vertex_1417036912823_0071_1_00, > diagnostics=[Vertex received Kill while in RUNNING state., Vertex killed as > other vertex failed. failedTasks:0, Vertex vertex_1417036912823_0071_1_00 > [Map 1] killed/failed due to:null] > DAG failed due to vertex failure. failedVertices:1 killedVertices:1 > {quote} -- This message was sent by Atlassian JIRA (v6.3.4#6332)