[
https://issues.apache.org/jira/browse/SPARK-8333?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14650555#comment-14650555
]
Sudhakar Thota commented on SPARK-8333:
---------------------------------------
Thanks for the clarification. I have used the same statement you suggested to
create HiveContext and was able to stop the sc without issues. After stopping
without issues, I have validated by trying to use sqlContext as well as
SparkContext. Please let me know if this is happening if you run it using a
script and not from REPL.
Please take a look.
-----------------
1. Creating HiveContext using hive, creating table, calling “sc.stop()” ,
verifying by trying to create a table again.
Sudhakars-MacBook-Pro-2:spark-1.4.0 sudhakarthota$ bin/spark-shell
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 1.4.0
/_/
Using Scala version 2.10.4 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_45)
Type in expressions to have them evaluated.
Type :help for more information.
Spark context available as sc.
SQL context available as sqlContext.
scala> val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc)
sqlContext: org.apache.spark.sql.hive.HiveContext =
org.apache.spark.sql.hive.HiveContext@5ac35b17
scala> sqlContext.sql("CREATE TABLE IF NOT EXISTS test1 (name STRING, rank INT)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n'")
res0: org.apache.spark.sql.DataFrame = [result: string]
scala> sc.stop()
scala> sqlContext.sql("CREATE TABLE IF NOT EXISTS test2 (name STRING, rank INT)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n'")
java.lang.IllegalStateException: Cannot call methods on a stopped SparkContext
at
org.apache.spark.SparkContext.org$apache$spark$SparkContext$$assertNotStopped(SparkContext.scala:103)
at
org.apache.spark.SparkContext$$anonfun$parallelize$1.apply(SparkContext.scala:696)
at
org.apache.spark.SparkContext$$anonfun$parallelize$1.apply(SparkContext.scala:695)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109)
at org.apache.spark.SparkContext.withScope(SparkContext.scala:681)
at org.apache.spark.SparkContext.parallelize(SparkContext.scala:695)
at
org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
at
org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:939)
at
org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:939)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:128)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:744)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:24)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:29)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:31)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:33)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
at $iwC$$iwC$$iwC.<init>(<console>:37)
at $iwC$$iwC.<init>(<console>:39)
at $iwC.<init>(<console>:41)
at <init>(<console>:43)
at .<init>(<console>:47)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
at
org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at
org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
scala> val fl1 = sc.textFile("/Users/sudhakarthota/spark/README.md")
java.lang.IllegalStateException: Cannot call methods on a stopped SparkContext
at
org.apache.spark.SparkContext.org$apache$spark$SparkContext$$assertNotStopped(SparkContext.scala:103)
at
org.apache.spark.SparkContext.defaultParallelism(SparkContext.scala:1912)
at
org.apache.spark.SparkContext.defaultMinPartitions(SparkContext.scala:1925)
at
org.apache.spark.SparkContext.textFile$default$2(SparkContext.scala:797)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:21)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:26)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
at $iwC$$iwC$$iwC.<init>(<console>:34)
at $iwC$$iwC.<init>(<console>:36)
at $iwC.<init>(<console>:38)
at <init>(<console>:40)
at .<init>(<console>:44)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
at
org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at
org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
scala>
----------------------
> Spark failed to delete temp directory created by HiveContext
> ------------------------------------------------------------
>
> Key: SPARK-8333
> URL: https://issues.apache.org/jira/browse/SPARK-8333
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.4.0
> Environment: Windows7 64bit
> Reporter: sheng
> Priority: Minor
> Labels: Hive, metastore, sparksql
>
> Spark 1.4.0 failed to stop SparkContext.
> {code:title=LocalHiveTest.scala|borderStyle=solid}
> val sc = new SparkContext("local", "local-hive-test", new SparkConf())
> val hc = Utils.createHiveContext(sc)
> ... // execute some HiveQL statements
> sc.stop()
> {code}
> sc.stop() failed to execute, it threw the following exception:
> {quote}
> 15/06/13 03:19:06 INFO Utils: Shutdown hook called
> 15/06/13 03:19:06 INFO Utils: Deleting directory
> C:\Users\moshangcheng\AppData\Local\Temp\spark-d6d3c30e-512e-4693-a436-485e2af4baea
> 15/06/13 03:19:06 ERROR Utils: Exception while deleting Spark temp dir:
> C:\Users\moshangcheng\AppData\Local\Temp\spark-d6d3c30e-512e-4693-a436-485e2af4baea
> java.io.IOException: Failed to delete:
> C:\Users\moshangcheng\AppData\Local\Temp\spark-d6d3c30e-512e-4693-a436-485e2af4baea
> at org.apache.spark.util.Utils$.deleteRecursively(Utils.scala:963)
> at
> org.apache.spark.util.Utils$$anonfun$1$$anonfun$apply$mcV$sp$5.apply(Utils.scala:204)
> at
> org.apache.spark.util.Utils$$anonfun$1$$anonfun$apply$mcV$sp$5.apply(Utils.scala:201)
> at scala.collection.mutable.HashSet.foreach(HashSet.scala:79)
> at org.apache.spark.util.Utils$$anonfun$1.apply$mcV$sp(Utils.scala:201)
> at org.apache.spark.util.SparkShutdownHook.run(Utils.scala:2292)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(Utils.scala:2262)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(Utils.scala:2262)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(Utils.scala:2262)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply$mcV$sp(Utils.scala:2262)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(Utils.scala:2262)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(Utils.scala:2262)
> at scala.util.Try$.apply(Try.scala:161)
> at
> org.apache.spark.util.SparkShutdownHookManager.runAll(Utils.scala:2262)
> at
> org.apache.spark.util.SparkShutdownHookManager$$anon$6.run(Utils.scala:2244)
> at
> org.apache.hadoop.util.ShutdownHookManager$1.run(ShutdownHookManager.java:54)
> {quote}
> It seems this bug is introduced by this SPARK-6907. In SPARK-6907, a local
> hive metastore is created in a temp directory. The problem is the local hive
> metastore is not shut down correctly. At the end of application, if
> SparkContext.stop() is called, it tries to delete the temp directory which is
> still used by the local hive metastore, and throws an exception.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
