MAPREDUCE-3815. Fixed MR AM to always use hostnames and never IPs when requesting containers so that scheduler can give off data local containers correctly. Contributed by Siddarth Seth.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1241654 13f79535-47bb-0310-9956-ffa450edef68

hadoop-mapreduce-project/CHANGES.txt

@@ -750,6 +750,10 @@ Release 0.23.1 - Unreleased
 
     MAPREDUCE-3436. JobHistory webapp address should use the host configured
     in the jobhistory address. (Ahmed Radwan via sseth)
+
+    MAPREDUCE-3815. Fixed MR AM to always use hostnames and never IPs when
+    requesting containers so that scheduler can give off data local containers
+    correctly. (Siddarth Seth via vinodkv)
  
 Release 0.23.0 - 2011-11-01 
 

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java

@@ -19,7 +19,9 @@
 package org.apache.hadoop.mapreduce.v2.app.job.impl;
 
 import java.io.IOException;
+import java.net.InetAddress;
 import java.net.InetSocketAddress;
+import java.net.UnknownHostException;
 import java.nio.ByteBuffer;
 import java.util.ArrayList;
 import java.util.Collection;
@@ -32,6 +34,7 @@ import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.concurrent.locks.Lock;
 import java.util.concurrent.locks.ReadWriteLock;
 import java.util.concurrent.locks.ReentrantReadWriteLock;
+import java.util.regex.Pattern;
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
@@ -142,7 +145,7 @@ public abstract class TaskAttemptImpl implements
   protected final JobConf conf;
   protected final Path jobFile;
   protected final int partition;
-  protected final EventHandler eventHandler;
+  protected EventHandler eventHandler;
   private final TaskAttemptId attemptId;
   private final Clock clock;
   private final org.apache.hadoop.mapred.JobID oldJobId;
@@ -1056,7 +1059,7 @@ public abstract class TaskAttemptImpl implements
     }
   }
 
-  private static class RequestContainerTransition implements
+  static class RequestContainerTransition implements
       SingleArcTransition<TaskAttemptImpl, TaskAttemptEvent> {
     private final boolean rescheduled;
     public RequestContainerTransition(boolean rescheduled) {
@@ -1081,14 +1084,44 @@ public abstract class TaskAttemptImpl implements
         for (String host : taskAttempt.dataLocalHosts) {
           racks[i++] = RackResolver.resolve(host).getNetworkLocation();
         }
-        taskAttempt.eventHandler.handle(
-            new ContainerRequestEvent(taskAttempt.attemptId, 
-                taskAttempt.resourceCapability, 
-                taskAttempt.dataLocalHosts, racks));
+        taskAttempt.eventHandler.handle(new ContainerRequestEvent(
+            taskAttempt.attemptId, taskAttempt.resourceCapability, taskAttempt
+                .resolveHosts(taskAttempt.dataLocalHosts), racks));
       }
     }
   }
 
+  protected String[] resolveHosts(String[] src) {
+    String[] result = new String[src.length];
+    for (int i = 0; i < src.length; i++) {
+      if (isIP(src[i])) {
+        result[i] = resolveHost(src[i]);
+      } else {
+        result[i] = src[i];
+      }
+    }
+    return result;
+  }
+
+  protected String resolveHost(String src) {
+    String result = src; // Fallback in case of failure.
+    try {
+      InetAddress addr = InetAddress.getByName(src);
+      result = addr.getHostName();
+    } catch (UnknownHostException e) {
+      LOG.warn("Failed to resolve address: " + src
+          + ". Continuing to use the same.");
+    }
+    return result;
+  }
+
+  private static final Pattern ipPattern = // Pattern for matching ip
+    Pattern.compile("\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}");
+  
+  protected boolean isIP(String src) {
+    return ipPattern.matcher(src).matches();
+  }
+
   private static class ContainerAssignedTransition implements
       SingleArcTransition<TaskAttemptImpl, TaskAttemptEvent> {
     @SuppressWarnings({ "unchecked" })

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TestTaskAttempt.java

@@ -18,30 +18,54 @@
 
 package org.apache.hadoop.mapreduce.v2.app.job.impl;
 
+import static org.junit.Assert.assertEquals;
+import static org.mockito.Mockito.mock;
+import static org.mockito.Mockito.spy;
+import static org.mockito.Mockito.times;
+import static org.mockito.Mockito.verify;
+import static org.mockito.Mockito.when;
+
+import java.util.HashMap;
 import java.util.Iterator;
 import java.util.Map;
 
 import junit.framework.Assert;
 
 import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapTaskAttemptImpl;
+import org.apache.hadoop.mapreduce.OutputCommitter;
 import org.apache.hadoop.mapreduce.jobhistory.JobHistoryEvent;
 import org.apache.hadoop.mapreduce.jobhistory.TaskAttemptUnsuccessfulCompletion;
+import org.apache.hadoop.mapreduce.split.JobSplit.TaskSplitMetaInfo;
+import org.apache.hadoop.mapreduce.v2.api.records.JobId;
 import org.apache.hadoop.mapreduce.v2.api.records.JobState;
 import org.apache.hadoop.mapreduce.v2.api.records.TaskAttemptId;
 import org.apache.hadoop.mapreduce.v2.api.records.TaskAttemptReport;
 import org.apache.hadoop.mapreduce.v2.api.records.TaskAttemptState;
 import org.apache.hadoop.mapreduce.v2.api.records.TaskId;
 import org.apache.hadoop.mapreduce.v2.api.records.TaskState;
+import org.apache.hadoop.mapreduce.v2.api.records.TaskType;
 import org.apache.hadoop.mapreduce.v2.app.AppContext;
 import org.apache.hadoop.mapreduce.v2.app.MRApp;
+import org.apache.hadoop.mapreduce.v2.app.TaskAttemptListener;
 import org.apache.hadoop.mapreduce.v2.app.job.Job;
 import org.apache.hadoop.mapreduce.v2.app.job.Task;
 import org.apache.hadoop.mapreduce.v2.app.job.TaskAttempt;
 import org.apache.hadoop.mapreduce.v2.app.job.event.TaskAttemptDiagnosticsUpdateEvent;
 import org.apache.hadoop.mapreduce.v2.app.job.event.TaskAttemptEvent;
 import org.apache.hadoop.mapreduce.v2.app.job.event.TaskAttemptEventType;
+import org.apache.hadoop.mapreduce.v2.app.rm.ContainerRequestEvent;
+import org.apache.hadoop.mapreduce.v2.util.MRBuilderUtils;
+import org.apache.hadoop.yarn.Clock;
+import org.apache.hadoop.yarn.SystemClock;
+import org.apache.hadoop.yarn.api.records.ApplicationId;
+import org.apache.hadoop.yarn.event.Event;
 import org.apache.hadoop.yarn.event.EventHandler;
+import org.apache.hadoop.yarn.util.BuilderUtils;
 import org.junit.Test;
+import org.mockito.ArgumentCaptor;
 
 @SuppressWarnings("unchecked")
 public class TestTaskAttempt{
@@ -57,6 +81,64 @@ public class TestTaskAttempt{
     MRApp app = new FailingAttemptsMRApp(0, 1);
     testMRAppHistory(app);
   }
+  
+  @SuppressWarnings("rawtypes")
+  @Test
+  public void testHostResolveAttempt() throws Exception {
+    TaskAttemptImpl.RequestContainerTransition rct =
+        new TaskAttemptImpl.RequestContainerTransition(false);
+
+    EventHandler eventHandler = mock(EventHandler.class);
+    String[] hosts = new String[3];
+    hosts[0] = "192.168.1.1";
+    hosts[1] = "host2";
+    hosts[2] = "host3";
+    TaskSplitMetaInfo splitInfo =
+        new TaskSplitMetaInfo(hosts, 0, 128 * 1024 * 1024l);
+
+    TaskAttemptImpl mockTaskAttempt =
+        createMapTaskAttemptImplForTest(eventHandler, splitInfo);
+    TaskAttemptImpl spyTa = spy(mockTaskAttempt);
+    when(spyTa.resolveHost(hosts[0])).thenReturn("host1");
+
+    TaskAttemptEvent mockTAEvent = mock(TaskAttemptEvent.class);
+    rct.transition(spyTa, mockTAEvent);
+    verify(spyTa).resolveHost(hosts[0]);
+    ArgumentCaptor<Event> arg = ArgumentCaptor.forClass(Event.class);
+    verify(eventHandler, times(2)).handle(arg.capture());
+    if (!(arg.getAllValues().get(1) instanceof ContainerRequestEvent)) {
+      Assert.fail("Second Event not of type ContainerRequestEvent");
+    }
+    Map<String, Boolean> expected = new HashMap<String, Boolean>();
+    expected.put("host1", true);
+    expected.put("host2", true);
+    expected.put("host3", true);
+    ContainerRequestEvent cre =
+        (ContainerRequestEvent) arg.getAllValues().get(1);
+    String[] requestedHosts = cre.getHosts();
+    for (String h : requestedHosts) {
+      expected.remove(h);
+    }
+    assertEquals(0, expected.size());
+  }
+
+  @SuppressWarnings("rawtypes")
+  private TaskAttemptImpl createMapTaskAttemptImplForTest(
+      EventHandler eventHandler, TaskSplitMetaInfo taskSplitMetaInfo) {
+    ApplicationId appId = BuilderUtils.newApplicationId(1, 1);
+    JobId jobId = MRBuilderUtils.newJobId(appId, 1);
+    TaskId taskId = MRBuilderUtils.newTaskId(jobId, 1, TaskType.MAP);
+    TaskAttemptListener taListener = mock(TaskAttemptListener.class);
+    Path jobFile = mock(Path.class);
+    JobConf jobConf = new JobConf();
+    OutputCommitter outputCommitter = mock(OutputCommitter.class);
+    Clock clock = new SystemClock();
+    TaskAttemptImpl taImpl =
+        new MapTaskAttemptImpl(taskId, 1, eventHandler, jobFile, 1,
+            taskSplitMetaInfo, jobConf, taListener, outputCommitter, null,
+            null, clock);
+    return taImpl;
+  }
 
   private void testMRAppHistory(MRApp app) throws Exception {
     Configuration conf = new Configuration();

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TestTaskImpl.java

@@ -59,7 +59,7 @@ import org.junit.After;
 import org.junit.Before;
 import org.junit.Test;
 
-@SuppressWarnings({ "rawtypes", "deprecation" })
+@SuppressWarnings("rawtypes")
 public class TestTaskImpl {
 
   private static final Log LOG = LogFactory.getLog(TestTaskImpl.class);