[
https://issues.apache.org/jira/browse/SPARK-1436?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Reynold Xin updated SPARK-1436:
-------------------------------
Description:
Try run the following code:
{code}
package org.apache.spark.sql
import org.apache.spark.sql.test.TestSQLContext._
import org.apache.spark.sql.catalyst.util._
case class Data(a: Int, b: Long)
object AggregationBenchmark {
def main(args: Array[String]): Unit = {
val rdd =
sparkContext.parallelize(1 to 20).flatMap(_ => (1 to 500000).map(i =>
Data(i % 100, i)))
rdd.registerAsTable("data")
cacheTable("data")
(1 to 10).foreach { i =>
println(s"=== ITERATION $i ===")
benchmark { println("SELECT COUNT() FROM data:" + sql("SELECT COUNT(*)
FROM data").collect().head) }
println("SELECT a, SUM(b) FROM data GROUP BY a")
benchmark { sql("SELECT a, SUM(b) FROM data GROUP BY a").count() }
println("SELECT SUM(b) FROM data")
benchmark { sql("SELECT SUM(b) FROM data").count() }
}
}
}
{code}
The following exception is thrown:
{code}
java.nio.BufferUnderflowException
at java.nio.Buffer.nextGetIndex(Buffer.java:498)
at java.nio.HeapByteBuffer.getInt(HeapByteBuffer.java:355)
at
org.apache.spark.sql.columnar.ColumnAccessor$.apply(ColumnAccessor.scala:103)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
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.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1.<init>(InMemoryColumnarTableScan.scala:61)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:60)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:56)
at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:161)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:102)
at org.apache.spark.scheduler.Task.run(Task.scala:52)
at
org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:211)
at
org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:46)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:176)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/04/07 12:07:38 WARN TaskSetManager: Lost TID 3 (task 4.0:0)
14/04/07 12:07:38 WARN TaskSetManager: Loss was due to
java.nio.BufferUnderflowException
java.nio.BufferUnderflowException
at java.nio.Buffer.nextGetIndex(Buffer.java:498)
at java.nio.HeapByteBuffer.getInt(HeapByteBuffer.java:355)
at
org.apache.spark.sql.columnar.ColumnAccessor$.apply(ColumnAccessor.scala:103)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1.<init>(InMemoryColumnarTableScan.scala:61)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:60)
at
org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:56)
at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:161)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:102)
at org.apache.spark.scheduler.Task.run(Task.scala:52)
at
org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:211)
at
org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:46)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:176)
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:744)
{code}
was:See my following comment...
> Compression code broke in-memory store
> --------------------------------------
>
> Key: SPARK-1436
> URL: https://issues.apache.org/jira/browse/SPARK-1436
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.0.0
> Reporter: Reynold Xin
> Assignee: Cheng Lian
> Priority: Blocker
> Fix For: 1.0.0
>
>
> Try run the following code:
> {code}
> package org.apache.spark.sql
> import org.apache.spark.sql.test.TestSQLContext._
> import org.apache.spark.sql.catalyst.util._
> case class Data(a: Int, b: Long)
> object AggregationBenchmark {
> def main(args: Array[String]): Unit = {
> val rdd =
> sparkContext.parallelize(1 to 20).flatMap(_ => (1 to 500000).map(i =>
> Data(i % 100, i)))
> rdd.registerAsTable("data")
> cacheTable("data")
> (1 to 10).foreach { i =>
> println(s"=== ITERATION $i ===")
> benchmark { println("SELECT COUNT() FROM data:" + sql("SELECT COUNT(*)
> FROM data").collect().head) }
> println("SELECT a, SUM(b) FROM data GROUP BY a")
> benchmark { sql("SELECT a, SUM(b) FROM data GROUP BY a").count() }
> println("SELECT SUM(b) FROM data")
> benchmark { sql("SELECT SUM(b) FROM data").count() }
> }
> }
> }
> {code}
> The following exception is thrown:
> {code}
> java.nio.BufferUnderflowException
> at java.nio.Buffer.nextGetIndex(Buffer.java:498)
> at java.nio.HeapByteBuffer.getInt(HeapByteBuffer.java:355)
> at
> org.apache.spark.sql.columnar.ColumnAccessor$.apply(ColumnAccessor.scala:103)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
> 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.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1.<init>(InMemoryColumnarTableScan.scala:61)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:60)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:56)
> at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
> at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:161)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:102)
> at org.apache.spark.scheduler.Task.run(Task.scala:52)
> at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:211)
> at
> org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:46)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:176)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/04/07 12:07:38 WARN TaskSetManager: Lost TID 3 (task 4.0:0)
> 14/04/07 12:07:38 WARN TaskSetManager: Loss was due to
> java.nio.BufferUnderflowException
> java.nio.BufferUnderflowException
> at java.nio.Buffer.nextGetIndex(Buffer.java:498)
> at java.nio.HeapByteBuffer.getInt(HeapByteBuffer.java:355)
> at
> org.apache.spark.sql.columnar.ColumnAccessor$.apply(ColumnAccessor.scala:103)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1$$anonfun$3.apply(InMemoryColumnarTableScan.scala:61)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1$$anon$1.<init>(InMemoryColumnarTableScan.scala:61)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:60)
> at
> org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$execute$1.apply(InMemoryColumnarTableScan.scala:56)
> at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
> at org.apache.spark.rdd.RDD$$anonfun$3.apply(RDD.scala:504)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:229)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:220)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:161)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:102)
> at org.apache.spark.scheduler.Task.run(Task.scala:52)
> at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:211)
> at
> org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:46)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:176)
> 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:744)
> {code}
--
This message was sent by Atlassian JIRA
(v6.2#6252)
