Davies Liu created SPARK-9529:
---------------------------------
Summary: Improve sort on Decimal
Key: SPARK-9529
URL: https://issues.apache.org/jira/browse/SPARK-9529
Project: Spark
Issue Type: Sub-task
Components: SQL
Reporter: Davies Liu
Assignee: Davies Liu
Priority: Critical
Right now, it's really slow, just hang there in random tests
{code}
pool-1-thread-1-ScalaTest-running-TungstenSortSuite" prio=5
tid=0x00007f822bc82800 nid=0x5103 runnable [0x000000011d1be000]
java.lang.Thread.State: RUNNABLE
at java.math.BigInteger.<init>(BigInteger.java:405)
at java.math.BigDecimal.bigTenToThe(BigDecimal.java:3380)
at java.math.BigDecimal.bigMultiplyPowerTen(BigDecimal.java:3508)
at java.math.BigDecimal.setScale(BigDecimal.java:2394)
at java.math.BigDecimal.divide(BigDecimal.java:1691)
at java.math.BigDecimal.divideToIntegralValue(BigDecimal.java:1734)
at java.math.BigDecimal.divideAndRemainder(BigDecimal.java:1891)
at java.math.BigDecimal.remainder(BigDecimal.java:1833)
at scala.math.BigDecimal.remainder(BigDecimal.scala:281)
at scala.math.BigDecimal.isWhole(BigDecimal.scala:215)
at scala.math.BigDecimal.hashCode(BigDecimal.scala:180)
at org.apache.spark.sql.types.Decimal.hashCode(Decimal.scala:260)
at
org.apache.spark.sql.catalyst.InternalRow.hashCode(InternalRow.scala:121)
at org.apache.spark.RangePartitioner.hashCode(Partitioner.scala:201)
at java.lang.Object.toString(Object.java:237)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1418)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:84)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:301)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:294)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:122)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2003)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1.apply(RDD.scala:683)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1.apply(RDD.scala:682)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:286)
at org.apache.spark.rdd.RDD.mapPartitions(RDD.scala:682)
at
org.apache.spark.sql.execution.Exchange$$anonfun$doExecute$1.apply(Exchange.scala:181)
at
org.apache.spark.sql.execution.Exchange$$anonfun$doExecute$1.apply(Exchange.scala:148)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
at org.apache.spark.sql.execution.Exchange.doExecute(Exchange.scala:148)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:113)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:112)
at
org.apache.spark.sql.execution.Sort$$anonfun$doExecute$1.apply(sort.scala:48)
at
org.apache.spark.sql.execution.Sort$$anonfun$doExecute$1.apply(sort.scala:48)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
at org.apache.spark.sql.execution.Sort.doExecute(sort.scala:47)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:113)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:112)
at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.SparkPlanTest$.executePlan(SparkPlanTest.scala:297)
at
org.apache.spark.sql.execution.SparkPlanTest$.checkAnswer(SparkPlanTest.scala:160)
at
org.apache.spark.sql.execution.SparkPlanTest.checkThatPlansAgree(SparkPlanTest.scala:126)
at
org.apache.spark.sql.execution.TungstenSortSuite$$anonfun$3$$anonfun$apply$2$$anonfun$apply$3$$anonfun$apply$4$$anonfun$apply$1.apply$mcV$sp(TungstenSortSuite.scala:76)
at
org.apache.spark.sql.execution.TungstenSortSuite$$anonfun$3$$anonfun$apply$2$$anonfun$apply$3$$anonfun$apply$4$$anonfun$apply$1.apply(TungstenSortSuite.scala:69)
at
org.apache.spark.sql.execution.TungstenSortSuite$$anonfun$3$$anonfun$apply$2$$anonfun$apply$3$$anonfun$apply$4$$anonfun$apply$1.apply(TungstenSortSuite.scala:69)
at
org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:42)
at
org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
at org.scalatest.FunSuite.runTest(FunSuite.scala:1555)
at
org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
at
org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
at
org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413)
at
org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
at
org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483)
at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208)
at org.scalatest.FunSuite.runTests(FunSuite.scala:1555)
at org.scalatest.Suite$class.run(Suite.scala:1424)
at
org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555)
at
org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
at
org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
at
org.apache.spark.sql.execution.TungstenSortSuite.org$scalatest$BeforeAndAfterAll$$super$run(TungstenSortSuite.scala:32)
at
org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at
org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at
org.apache.spark.sql.execution.TungstenSortSuite.run(TungstenSortSuite.scala:32)
at
org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:462)
at
org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:671)
at sbt.ForkMain$Run$2.call(ForkMain.java:294)
at sbt.ForkMain$Run$2.call(ForkMain.java:284)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
{code}
--
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
