Author: sseth Date: Sun Oct 13 20:20:11 2013 New Revision: 1531743 URL: http://svn.apache.org/r1531743 Log: MAPREDUCE-5329. Allow MR applications to use additional AuxServices, which are compatible with the default MapReduce shuffle. Contributed by Avner BenHanoch.
Added: hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TestShuffleProvider.java - copied unchanged from r1531742, hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TestShuffleProvider.java Modified: hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/CHANGES.txt hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java Modified: hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/CHANGES.txt URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/CHANGES.txt?rev=1531743&r1=1531742&r2=1531743&view=diff ============================================================================== --- hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/CHANGES.txt (original) +++ hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/CHANGES.txt Sun Oct 13 20:20:11 2013 @@ -7,6 +7,10 @@ Release 2.2.1 - UNRELEASED NEW FEATURES IMPROVEMENTS + + MAPREDUCE-5329. Allow MR applications to use additional AuxServices, + which are compatible with the default MapReduce shuffle. + (Avner BenHanoch via sseth) OPTIMIZATIONS Modified: hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java?rev=1531743&r1=1531742&r2=1531743&view=diff ============================================================================== --- hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java (original) +++ hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java Sun Oct 13 20:20:11 2013 @@ -31,6 +31,7 @@ import java.util.List; import java.util.Map; import java.util.Map.Entry; import java.util.Set; +import java.util.Collection; import java.util.concurrent.atomic.AtomicBoolean; import java.util.concurrent.locks.Lock; import java.util.concurrent.locks.ReadWriteLock; @@ -722,6 +723,32 @@ public abstract class TaskAttemptImpl im serviceData.put(ShuffleHandler.MAPREDUCE_SHUFFLE_SERVICEID, ShuffleHandler.serializeServiceData(shuffleToken)); + // add external shuffle-providers - if any + Collection<String> shuffleProviders = conf.getStringCollection( + MRJobConfig.MAPREDUCE_JOB_SHUFFLE_PROVIDER_SERVICES); + if (! shuffleProviders.isEmpty()) { + Collection<String> auxNames = conf.getStringCollection( + YarnConfiguration.NM_AUX_SERVICES); + + for (final String shuffleProvider : shuffleProviders) { + if (shuffleProvider.equals(ShuffleHandler.MAPREDUCE_SHUFFLE_SERVICEID)) { + continue; // skip built-in shuffle-provider that was already inserted with shuffle secret key + } + if (auxNames.contains(shuffleProvider)) { + LOG.info("Adding ShuffleProvider Service: " + shuffleProvider + " to serviceData"); + // This only serves for INIT_APP notifications + // The shuffle service needs to be able to work with the host:port information provided by the AM + // (i.e. shuffle services which require custom location / other configuration are not supported) + serviceData.put(shuffleProvider, ByteBuffer.allocate(0)); + } + else { + throw new YarnRuntimeException("ShuffleProvider Service: " + shuffleProvider + + " was NOT found in the list of aux-services that are available in this NM." + + " You may need to specify this ShuffleProvider as an aux-service in your yarn-site.xml"); + } + } + } + Apps.addToEnvironment( environment, Environment.CLASSPATH.name(), Modified: hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java?rev=1531743&r1=1531742&r2=1531743&view=diff ============================================================================== --- hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java (original) +++ hadoop/common/branches/branch-2.2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java Sun Oct 13 20:20:11 2013 @@ -133,6 +133,13 @@ public interface MRJobConfig { public static final String MAPREDUCE_JOB_CLASSLOADER = "mapreduce.job.classloader"; + /** + * A comma-separated list of services that function as ShuffleProvider aux-services + * (in addition to the built-in ShuffleHandler). + * These services can serve shuffle requests from reducetasks. + */ + public static final String MAPREDUCE_JOB_SHUFFLE_PROVIDER_SERVICES = "mapreduce.job.shuffle.provider.services"; + public static final String MAPREDUCE_JOB_CLASSLOADER_SYSTEM_CLASSES = "mapreduce.job.classloader.system.classes"; public static final String IO_SORT_FACTOR = "mapreduce.task.io.sort.factor";