Vrushali C created MAPREDUCE-5309: ------------------------------------- Summary: 2.0.4 JobHistoryParser can't parse certain failed job history files generated by 2.0.3 history server Key: MAPREDUCE-5309 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5309 Project: Hadoop Map/Reduce Issue Type: Bug Components: jobhistoryserver Affects Versions: 2.0.4-alpha Reporter: Vrushali C
When the 2.0.4 JobHistoryParser tries to parse a job history file generated by hadoop 2.0.3, the jobhistoryparser throws as an error as java.lang.ClassCastException: org.apache.avro.generic.GenericData$Array cannot be cast to org.apache.hadoop.mapreduce.jobhistory.JhCounters at org.apache.hadoop.mapreduce.jobhistory.TaskAttemptUnsuccessfulCompletion.put(TaskAttemptUnsuccessfulCompletion.java:58) at org.apache.avro.generic.GenericData.setField(GenericData.java:463) at org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:166) at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:138) at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:142) at org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:166) at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:138) at org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:129) at org.apache.hadoop.mapreduce.jobhistory.EventReader.getNextEvent(EventReader.java:93) at org.apache.hadoop.mapreduce.jobhistory.JobHistoryParser.parse(JobHistoryParser.java:111) at org.apache.hadoop.mapreduce.jobhistory.JobHistoryParser.parse(JobHistoryParser.java:156) at org.apache.hadoop.mapreduce.jobhistory.JobHistoryParser.parse(JobHistoryParser.java:142) at com.twitter.somepackage.Test20JobHistoryParsing.testFileAvro(Test20JobHistoryParsing.java:23) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25) at java.lang.reflect.Method.invoke(Method.java:597) at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:44) at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15) at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:41) at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:76) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50) at org.junit.runners.ParentRunner$3.run(ParentRunner.java:193) at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:52) at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:191) at org.junit.runners.ParentRunner.access$000(ParentRunner.java:42) at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:184) at org.junit.runners.ParentRunner.run(ParentRunner.java:236) at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50) at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:467) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:683) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:390) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:197) Test code and the job history file are attached. Test code: package com.twitter.somepackagel; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.mapreduce.jobhistory.JobHistoryParser; import org.apache.hadoop.mapreduce.jobhistory.JobHistoryParser.JobInfo; import org.junit.Test; import org.apache.hadoop.yarn.YarnException; public class Test20JobHistoryParsing { @Test public void testFileAvro() throws IOException { Path local_path2 = new Path("/tmp/job_2_0_3-KILLED.jhist"); JobHistoryParser parser2 = new JobHistoryParser(FileSystem.getLocal(new Configuration()), local_path2); try { JobInfo ji2 = parser2.parse(); System.out.println(" job info: " + ji2.getJobname() + " " + ji2.getFinishedMaps() + " " + ji2.getTotalMaps() + " " + ji2.getJobId() ) ; } catch (IOException e) { throw new YarnException("Could not load history file " + local_path2.getName(), e); } } } This seems to stem from the fix in https://issues.apache.org/jira/browse/MAPREDUCE-4693 that added counters to the historyserver for failed tasks. This breaks backward compatibility with JobHistoryServer. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira