[
https://issues.apache.org/jira/browse/SPARK-10030?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
wangwei updated SPARK-10030:
----------------------------
Description:
I test the lastest spark-1.5.0 in local, standalone, yarn mode and follow the
steps bellow, then errors occured.
1. create table cache_test(id int, name string) stored as textfile ;
2. load data local inpath
'SparkSource/sql/hive/src/test/resources/data/files/kv1.txt' into table
cache_test;
3. cache table test as select * from cache_test distribute by id;
configuration:
spark.driver.memory 5g
spark.executor.memory 28g
spark.cores.max 21
15/08/16 17:14:47 ERROR Executor: Managed memory leak detected; size = 67108864
bytes, TID = 434
15/08/16 17:14:47 ERROR Executor: Exception in task 23.0 in stage 9.0 (TID 434)
java.util.NoSuchElementException: key not found: val_54
at scala.collection.MapLike$class.default(MapLike.scala:228)
at scala.collection.AbstractMap.default(Map.scala:58)
at scala.collection.mutable.HashMap.apply(HashMap.scala:64)
at
org.apache.spark.sql.columnar.compression.DictionaryEncoding$Encoder.compress(compressionSchemes.scala:258)
at
org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.build(CompressibleColumnBuilder.scala:110)
at
org.apache.spark.sql.columnar.NativeColumnBuilder.build(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:153)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120)
at
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278)
at
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:262)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:46)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603)
at java.lang.Thread.run(Thread.java:722)
was:
I test lastest spark-1.5.0 in local, standalone, yarn mode and follow the steps
bellow, then errors occured.
1. create table cache_test(id int, name string) stored as textfile ;
2. load data local inpath
'SparkSource/sql/hive/src/test/resources/data/files/kv1.txt' into table
cache_test;
3. cache table test as select * from cache_test distribute by id;
configuration:
spark.driver.memory 5g
spark.executor.memory 28g
spark.cores.max 21
15/08/16 17:14:47 ERROR Executor: Managed memory leak detected; size = 67108864
bytes, TID = 434
15/08/16 17:14:47 ERROR Executor: Exception in task 23.0 in stage 9.0 (TID 434)
java.util.NoSuchElementException: key not found: val_54
at scala.collection.MapLike$class.default(MapLike.scala:228)
at scala.collection.AbstractMap.default(Map.scala:58)
at scala.collection.mutable.HashMap.apply(HashMap.scala:64)
at
org.apache.spark.sql.columnar.compression.DictionaryEncoding$Encoder.compress(compressionSchemes.scala:258)
at
org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.build(CompressibleColumnBuilder.scala:110)
at
org.apache.spark.sql.columnar.NativeColumnBuilder.build(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:153)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120)
at
org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278)
at
org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:262)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:46)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603)
at java.lang.Thread.run(Thread.java:722)
> Managed memory leak detected when cache table
> ---------------------------------------------
>
> Key: SPARK-10030
> URL: https://issues.apache.org/jira/browse/SPARK-10030
> Project: Spark
> Issue Type: Bug
> Affects Versions: 1.5.0
> Reporter: wangwei
>
> I test the lastest spark-1.5.0 in local, standalone, yarn mode and follow the
> steps bellow, then errors occured.
> 1. create table cache_test(id int, name string) stored as textfile ;
> 2. load data local inpath
> 'SparkSource/sql/hive/src/test/resources/data/files/kv1.txt' into table
> cache_test;
> 3. cache table test as select * from cache_test distribute by id;
> configuration:
> spark.driver.memory 5g
> spark.executor.memory 28g
> spark.cores.max 21
> 15/08/16 17:14:47 ERROR Executor: Managed memory leak detected; size =
> 67108864 bytes, TID = 434
> 15/08/16 17:14:47 ERROR Executor: Exception in task 23.0 in stage 9.0 (TID
> 434)
> java.util.NoSuchElementException: key not found: val_54
> at scala.collection.MapLike$class.default(MapLike.scala:228)
> at scala.collection.AbstractMap.default(Map.scala:58)
> at scala.collection.mutable.HashMap.apply(HashMap.scala:64)
> at
> org.apache.spark.sql.columnar.compression.DictionaryEncoding$Encoder.compress(compressionSchemes.scala:258)
> at
> org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.build(CompressibleColumnBuilder.scala:110)
> at
> org.apache.spark.sql.columnar.NativeColumnBuilder.build(ColumnBuilder.scala:87)
> at
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
> at
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:153)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
> at
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:153)
> at
> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120)
> at
> org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278)
> at
> org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
> at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:262)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:46)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603)
> at java.lang.Thread.run(Thread.java:722)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
