Rajat Khandelwal created HIVE-13500:
---------------------------------------
Summary: Launching big queries fails with Out of Memory Exception
Key: HIVE-13500
URL: https://issues.apache.org/jira/browse/HIVE-13500
Project: Hive
Issue Type: Bug
Reporter: Rajat Khandelwal
Assignee: Rajat Khandelwal
There is a code snipped in Driver class in compile method:
{noformat}
if (conf.getBoolVar(ConfVars.HIVE_LOG_EXPLAIN_OUTPUT) ||
conf.isWebUiQueryInfoCacheEnabled()) {
String explainOutput = getExplainOutput(sem, plan, tree);
if (explainOutput != null) {
if (conf.getBoolVar(ConfVars.HIVE_LOG_EXPLAIN_OUTPUT)) {
LOG.info("EXPLAIN output for queryid " + queryId + " : "
+ explainOutput);
}
if (conf.isWebUiQueryInfoCacheEnabled()) {
queryDisplay.setExplainPlan(explainOutput);
}
}
}
{noformat}
This is the stack trace
{noformat}
org.apache.hive.service.cli.HiveSQLException: Error running query:
java.lang.OutOfMemoryError
at
org.apache.hive.service.cli.operation.SQLOperation.prepare(SQLOperation.java:178)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.operation.SQLOperation.runInternal(SQLOperation.java:216)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.operation.Operation.run(Operation.java:325)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.session.HiveSessionImpl.executeStatementInternal(HiveSessionImpl.java:456)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.session.HiveSessionImpl.executeStatementAsync(HiveSessionImpl.java:433)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
~[?:1.8.0_72]
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
~[?:1.8.0_72]
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
~[?:1.8.0_72]
at java.lang.reflect.Method.invoke(Method.java:498) ~[?:1.8.0_72]
at
org.apache.hive.service.cli.session.HiveSessionProxy.invoke(HiveSessionProxy.java:78)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.session.HiveSessionProxy.access$000(HiveSessionProxy.java:36)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.session.HiveSessionProxy$1.run(HiveSessionProxy.java:63)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at java.security.AccessController.doPrivileged(Native Method)
~[?:1.8.0_72]
at javax.security.auth.Subject.doAs(Subject.java:422) ~[?:1.8.0_72]
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628)
~[hadoop-common-2.6.0.2.2.4.2-2.jar:?]
at
org.apache.hive.service.cli.session.HiveSessionProxy.invoke(HiveSessionProxy.java:59)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at com.sun.proxy.$Proxy33.executeStatementAsync(Unknown Source) ~[?:?]
at
org.apache.hive.service.cli.CLIService.executeStatementAsync(CLIService.java:272)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.thrift.ThriftCLIService.ExecuteStatement(ThriftCLIService.java:554)
[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.rpc.thrift.TCLIService$Processor$ExecuteStatement.getResult(TCLIService.java:1317)
[hive-service-rpc-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.rpc.thrift.TCLIService$Processor$ExecuteStatement.getResult(TCLIService.java:1302)
[hive-service-rpc-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.thrift.ProcessFunction.process(ProcessFunction.java:39)
[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.thrift.TBaseProcessor.process(TBaseProcessor.java:39)
[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.auth.TSetIpAddressProcessor.process(TSetIpAddressProcessor.java:56)
[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.thrift.server.TThreadPoolServer$WorkerProcess.run(TThreadPoolServer.java:286)
[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
[?:1.8.0_72]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
[?:1.8.0_72]
at java.lang.Thread.run(Thread.java:745) [?:1.8.0_72]
Caused by: java.lang.OutOfMemoryError
at
java.io.ByteArrayOutputStream.hugeCapacity(ByteArrayOutputStream.java:123)
~[?:1.8.0_72]
at java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:117)
~[?:1.8.0_72]
at
java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93)
~[?:1.8.0_72]
at java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:153)
~[?:1.8.0_72]
at java.io.PrintStream.write(PrintStream.java:480) ~[?:1.8.0_72]
at sun.nio.cs.StreamEncoder.writeBytes(StreamEncoder.java:221)
~[?:1.8.0_72]
at sun.nio.cs.StreamEncoder.implFlushBuffer(StreamEncoder.java:291)
~[?:1.8.0_72]
at sun.nio.cs.StreamEncoder.flushBuffer(StreamEncoder.java:104)
~[?:1.8.0_72]
at java.io.OutputStreamWriter.flushBuffer(OutputStreamWriter.java:185)
~[?:1.8.0_72]
at java.io.PrintStream.write(PrintStream.java:527) ~[?:1.8.0_72]
at java.io.PrintStream.print(PrintStream.java:683) ~[?:1.8.0_72]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputMap(ExplainTask.java:420)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:737)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:581)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:765)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:581)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputMap(ExplainTask.java:508)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:737)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:581)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:765)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:581)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputPlan(ExplainTask.java:826)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.outputStagePlans(ExplainTask.java:970)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.ExplainTask.getJSONPlan(ExplainTask.java:223)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.getExplainOutput(Driver.java:597)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:525)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:318)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1192)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1179)
~[hive-exec-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
at
org.apache.hive.service.cli.operation.SQLOperation.prepare(SQLOperation.java:144)
~[hive-service-2.1.0-SNAPSHOT.jar:2.1.0-SNAPSHOT]
... 27 more
{noformat}
Now, in plain English, in the compile phase, hive is trying to generate explain
output and set that output in the query display. Generating the explain output
fails with OOM.
I propose that setting of the explain output in query display be made optional,
so that queries can still launch.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
