[
https://issues.apache.org/jira/browse/SPARK-12340?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
QiangCai updated SPARK-12340:
-----------------------------
Description:
Reproduce
sql e.g. select * from talbe1 where c1 = 'abc' limit 2147483638
n will be Int.MaxValue(2147483647) in SparkPlan.executeTake(n: Int). If the
first partition just have one row ( buf.size will be one), the result of cod e
numPartsToTry = (1.5 * n * partsScanned / buf.size).toInt will be Int.MaxValue.
Then math.min(partsScanned + numPartsToTry, totalParts) will be Int.MinValue
(-2147483648) .
Exception
java.lang.IllegalArgumentException: Attempting to access a non-existent
partition: -2147483648. Total number of partitions: 200
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:531)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:530)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.submitJob(DAGScheduler.scala:530)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:558)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
at
org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at
org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1385)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1315)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1378)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.process(HBaseSQLCliDriver.scala:122)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.processLine(HBaseSQLCliDriver.scala:102)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.main(HBaseSQLCliDriver.scala:80)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver.main(HBaseSQLCliDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:601)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
was:
java.lang.IllegalArgumentException: Attempting to access a non-existent
partition: -2147483648. Total number of partitions: 200
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:531)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:530)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.submitJob(DAGScheduler.scala:530)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:558)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
at
org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at
org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1385)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1315)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1378)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.process(HBaseSQLCliDriver.scala:122)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.processLine(HBaseSQLCliDriver.scala:102)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver$.main(HBaseSQLCliDriver.scala:80)
at
org.apache.spark.sql.hbase.HBaseSQLCliDriver.main(HBaseSQLCliDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:601)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> overstep the bounds of Int in SparkPlan.executeTake
> ---------------------------------------------------
>
> Key: SPARK-12340
> URL: https://issues.apache.org/jira/browse/SPARK-12340
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Reporter: QiangCai
> Assignee: Apache Spark
>
> Reproduce
>
> sql e.g. select * from talbe1 where c1 = 'abc' limit 2147483638
>
> n will be Int.MaxValue(2147483647) in SparkPlan.executeTake(n: Int). If
> the first partition just have one row ( buf.size will be one), the result of
> cod e numPartsToTry = (1.5 * n * partsScanned / buf.size).toInt will be
> Int.MaxValue. Then math.min(partsScanned + numPartsToTry, totalParts) will be
> Int.MinValue (-2147483648) .
> Exception
> java.lang.IllegalArgumentException: Attempting to access a non-existent
> partition: -2147483648. Total number of partitions: 200
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:531)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$submitJob$2.apply(DAGScheduler.scala:530)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.submitJob(DAGScheduler.scala:530)
> at
> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:558)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
> at
> org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
> at
> org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
> at
> org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
> at
> org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
> at
> org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904)
> at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1385)
> at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1315)
> at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1378)
> at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
> at
> org.apache.spark.sql.hbase.HBaseSQLCliDriver$.process(HBaseSQLCliDriver.scala:122)
> at
> org.apache.spark.sql.hbase.HBaseSQLCliDriver$.processLine(HBaseSQLCliDriver.scala:102)
> at
> org.apache.spark.sql.hbase.HBaseSQLCliDriver$.main(HBaseSQLCliDriver.scala:80)
> at
> org.apache.spark.sql.hbase.HBaseSQLCliDriver.main(HBaseSQLCliDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:601)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
> at
> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
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
