MAPREDUCE-5379. Include token tracking ids in jobconf. (kkambatl via tucu)

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2.1-beta@1523608 13f79535-47bb-0310-9956-ffa450edef68

Author: Alejandro Abdelnur

hadoop-mapreduce-project/CHANGES.txt

@@ -15,6 +15,8 @@ Release 2.1.1-beta - UNRELEASED
     but just before ClientService to avoid race conditions during RM restart.
     (Jian He via vinodkv)
 
+    MAPREDUCE-5379. Include token tracking ids in jobconf. (kkambatl via tucu)
+
   OPTIMIZATIONS
 
     MAPREDUCE-5446. TestJobHistoryEvents and TestJobHistoryParsing have race

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmitter.java

@@ -24,6 +24,7 @@
 import java.net.URISyntaxException;
 import java.net.UnknownHostException;
 import java.security.NoSuchAlgorithmException;
+import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Comparator;
 import java.util.List;
@@ -56,6 +57,7 @@
 import org.apache.hadoop.security.UserGroupInformation;
 import org.apache.hadoop.security.authorize.AccessControlList;
 import org.apache.hadoop.security.token.Token;
+import org.apache.hadoop.security.token.TokenIdentifier;
 import org.apache.hadoop.util.ReflectionUtils;
 import org.codehaus.jackson.JsonParseException;
 import org.codehaus.jackson.map.JsonMappingException;
@@ -405,6 +407,19 @@ JobStatus submitJobInternal(Job job, Cluster cluster)
       // different job.
       TokenCache.cleanUpTokenReferral(conf);
 
+      if (conf.getBoolean(
+          MRJobConfig.JOB_TOKEN_TRACKING_IDS_ENABLED,
+          MRJobConfig.DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED)) {
+        // Add HDFS tracking ids
+        ArrayList<String> trackingIds = new ArrayList<String>();
+        for (Token<? extends TokenIdentifier> t :
+            job.getCredentials().getAllTokens()) {
+          trackingIds.add(t.decodeIdentifier().getTrackingId());
+        }
+        conf.setStrings(MRJobConfig.JOB_TOKEN_TRACKING_IDS,
+            trackingIds.toArray(new String[trackingIds.size()]));
+      }
+
       // Write job file to submit dir
       writeConf(conf, submitJobFile);
 

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java

@@ -308,6 +308,13 @@ public interface MRJobConfig {
   public static final String MAPREDUCE_JOB_CREDENTIALS_BINARY = 
       "mapreduce.job.credentials.binary";
 
+  /* Configs for tracking ids of tokens used by a job */
+  public static final String JOB_TOKEN_TRACKING_IDS_ENABLED =
+      "mapreduce.job.token.tracking.ids.enabled";
+  public static final boolean DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED = false;
+  public static final String JOB_TOKEN_TRACKING_IDS =
+      "mapreduce.job.token.tracking.ids";
+
   public static final String JOB_SUBMITHOST =
     "mapreduce.job.submithostname";
   public static final String JOB_SUBMITHOSTADDR =

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml

@@ -1130,6 +1130,23 @@
   </description>
 </property>
 
+<property>
+  <name>mapreduce.job.token.tracking.ids.enabled</name>
+  <value>false</value>
+  <description>Whether to write tracking ids of tokens to
+    job-conf. When true, the configuration property
+    "mapreduce.job.token.tracking.ids" is set to the token-tracking-ids of
+    the job</description>
+</property>
+
+<property>
+  <name>mapreduce.job.token.tracking.ids</name>
+  <value></value>
+  <description>When mapreduce.job.token.tracking.ids.enabled is
+    set to true, this is set by the framework to the
+    token-tracking-ids used by the job.</description>
+</property>
+
 <property>
   <name>mapreduce.task.merge.progress.records</name>
   <value>10000</value>