[
https://issues.apache.org/jira/browse/SPARK-25727?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xiao Li updated SPARK-25727:
----------------------------
Description:
{code}
val data = Seq(100).toDF("count").cache()
data.queryExecution.optimizedPlan.toJSON
{code}
The above code can generate the following error:
{code}
assertion failed: InMemoryRelation fields: output, cacheBuilder,
statsOfPlanToCache, outputOrdering, values: List(count#178),
CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1
replicas),*(1) Project [value#176 AS count#178]
+- LocalTableScan [value#176]
,None), Statistics(sizeInBytes=12.0 B, hints=none)
java.lang.AssertionError: assertion failed: InMemoryRelation fields: output,
cacheBuilder, statsOfPlanToCache, outputOrdering, values: List(count#178),
CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1
replicas),*(1) Project [value#176 AS count#178]
+- LocalTableScan [value#176]
,None), Statistics(sizeInBytes=12.0 B, hints=none)
at scala.Predef$.assert(Predef.scala:170)
at
org.apache.spark.sql.catalyst.trees.TreeNode.jsonFields(TreeNode.scala:611)
at
org.apache.spark.sql.catalyst.trees.TreeNode.org$apache$spark$sql$catalyst$trees$TreeNode$$collectJsonValue$1(TreeNode.scala:599)
at
org.apache.spark.sql.catalyst.trees.TreeNode.jsonValue(TreeNode.scala:604)
at
org.apache.spark.sql.catalyst.trees.TreeNode.toJSON(TreeNode.scala:590)
{code}
was:
When make a copy of a tree, it caused the following error:
{code}
makeCopy, tree:
InMemoryRelation [count#181], StorageLevel(disk, memory, deserialized, 1
replicas)
+- *(2) Sort [count#181 ASC NULLS FIRST], true, 0
+- Exchange rangepartitioning(count#181 ASC NULLS FIRST, 5)
+- *(1) FileScan parquet [count#181] Batched: true, DataFilters: [],
Format: Parquet, Location:
InMemoryFileIndex[file:/private/var/folders/vx/j0ydl5rn0gd9mgrh1pljnw900000gn/T/spark-ecec0785-8b...,
PartitionFilters: [], PushedFilters: [], ReadSchema: struct<count:int>
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: makeCopy, tree:
InMemoryRelation [count#181], StorageLevel(disk, memory, deserialized, 1
replicas)
+- *(2) Sort [count#181 ASC NULLS FIRST], true, 0
+- Exchange rangepartitioning(count#181 ASC NULLS FIRST, 5)
+- *(1) FileScan parquet [count#181] Batched: true, DataFilters: [],
Format: Parquet, Location:
InMemoryFileIndex[file:/private/var/folders/vx/j0ydl5rn0gd9mgrh1pljnw900000gn/T/spark-ecec0785-8b...,
PartitionFilters: [], PushedFilters: [], ReadSchema: struct<count:int>
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
at
org.apache.spark.sql.catalyst.trees.TreeNode.makeCopy(TreeNode.scala:377)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite$$anonfun$21$$anonfun$apply$mcV$sp$34.apply(InMemoryColumnarQuerySuite.scala:498)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite$$anonfun$21$$anonfun$apply$mcV$sp$34.apply(InMemoryColumnarQuerySuite.scala:492)
at
org.apache.spark.sql.catalyst.plans.SQLHelper$class.withTempPath(SQLHelper.scala:62)
at org.apache.spark.sql.QueryTest.withTempPath(QueryTest.scala:29)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite$$anonfun$21.apply$mcV$sp(InMemoryColumnarQuerySuite.scala:492)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite$$anonfun$21.apply(InMemoryColumnarQuerySuite.scala:492)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite$$anonfun$21.apply(InMemoryColumnarQuerySuite.scala:492)
at org.scalatest.OutcomeOf$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$$anon$1.apply(FunSuiteLike.scala:186)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:103)
at
org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:183)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
at
org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:196)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite.org$scalatest$BeforeAndAfterEach$$super$runTest(InMemoryColumnarQuerySuite.scala:36)
at
org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:221)
at
org.apache.spark.sql.execution.columnar.InMemoryColumnarQuerySuite.runTest(InMemoryColumnarQuerySuite.scala:36)
at
org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
at
org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
at
org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396)
at
org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384)
at scala.collection.immutable.List.foreach(List.scala:381)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
at
org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:229)
at org.scalatest.FunSuite.runTests(FunSuite.scala:1560)
at org.scalatest.Suite$class.run(Suite.scala:1147)
at
org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560)
at
org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
at
org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:233)
at
org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:52)
at
org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:213)
at
org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:210)
at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:52)
at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45)
at
org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340)
at
org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1334)
at scala.collection.immutable.List.foreach(List.scala:381)
at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334)
at
org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011)
at
org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010)
at
org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500)
at
org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010)
at org.scalatest.tools.Runner$.run(Runner.scala:850)
at org.scalatest.tools.Runner.run(Runner.scala)
at
org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2(ScalaTestRunner.java:131)
at
org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:28)
Caused by: org.apache.spark.sql.catalyst.errors.package$TreeNodeException:
Failed to copy node.
Is otherCopyArgs specified correctly for InMemoryRelation.
Exception message: wrong number of arguments
ctor: public
org.apache.spark.sql.execution.columnar.InMemoryRelation(scala.collection.Seq,org.apache.spark.sql.execution.columnar.CachedRDDBuilder,org.apache.spark.sql.catalyst.plans.logical.Statistics,scala.collection.Seq)?
types:
args:
, tree:
InMemoryRelation [count#181], StorageLevel(disk, memory, deserialized, 1
replicas)
+- *(2) Sort [count#181 ASC NULLS FIRST], true, 0
+- Exchange rangepartitioning(count#181 ASC NULLS FIRST, 5)
+- *(1) FileScan parquet [count#181] Batched: true, DataFilters: [],
Format: Parquet, Location:
InMemoryFileIndex[file:/private/var/folders/vx/j0ydl5rn0gd9mgrh1pljnw900000gn/T/spark-ecec0785-8b...,
PartitionFilters: [], PushedFilters: [], ReadSchema: struct<count:int>
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1.apply(TreeNode.scala:407)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$makeCopy$1.apply(TreeNode.scala:377)
at
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
... 55 more
{code}
> makeCopy failed in InMemoryRelation
> -----------------------------------
>
> Key: SPARK-25727
> URL: https://issues.apache.org/jira/browse/SPARK-25727
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.4.0
> Reporter: Xiao Li
> Assignee: Xiao Li
> Priority: Major
>
> {code}
> val data = Seq(100).toDF("count").cache()
> data.queryExecution.optimizedPlan.toJSON
> {code}
> The above code can generate the following error:
> {code}
> assertion failed: InMemoryRelation fields: output, cacheBuilder,
> statsOfPlanToCache, outputOrdering, values: List(count#178),
> CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1
> replicas),*(1) Project [value#176 AS count#178]
> +- LocalTableScan [value#176]
> ,None), Statistics(sizeInBytes=12.0 B, hints=none)
> java.lang.AssertionError: assertion failed: InMemoryRelation fields: output,
> cacheBuilder, statsOfPlanToCache, outputOrdering, values: List(count#178),
> CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1
> replicas),*(1) Project [value#176 AS count#178]
> +- LocalTableScan [value#176]
> ,None), Statistics(sizeInBytes=12.0 B, hints=none)
> at scala.Predef$.assert(Predef.scala:170)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.jsonFields(TreeNode.scala:611)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.org$apache$spark$sql$catalyst$trees$TreeNode$$collectJsonValue$1(TreeNode.scala:599)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.jsonValue(TreeNode.scala:604)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.toJSON(TreeNode.scala:590)
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
