MAPREDUCE-6057. Remove obsolete entries from mapred-default.xml (Ray Chiang via aw)

hadoop-mapreduce-project/CHANGES.txt

@@ -105,6 +105,9 @@ Trunk (Unreleased)
     MAPREDUCE-6260. Convert site documentation to markdown (Masatake Iwasaki
     via aw)
 
+    MAPREDUCE-6057. Remove obsolete entries from mapred-default.xml
+    (Ray Chiang via aw)
+
   BUG FIXES
 
     MAPREDUCE-6191. Improve clearing stale state of Java serialization

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

@@ -978,8 +978,9 @@ public class MapTask extends Task {
         throw new IOException(
             "Invalid \"" + JobContext.IO_SORT_MB + "\": " + sortmb);
       }
-      sorter = ReflectionUtils.newInstance(job.getClass("map.sort.class",
-            QuickSort.class, IndexedSorter.class), job);
+      sorter = ReflectionUtils.newInstance(job.getClass(
+                   MRJobConfig.MAP_SORT_CLASS, QuickSort.class,
+                   IndexedSorter.class), job);
       // buffers and accounting
       int maxMemUsage = sortmb << 20;
       maxMemUsage -= maxMemUsage % METASIZE;

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

@@ -28,6 +28,9 @@ import org.apache.hadoop.yarn.util.Apps;
 @InterfaceStability.Evolving
 public interface MRJobConfig {
 
+  // Used by MapTask
+  public static final String MAP_SORT_CLASS = "map.sort.class";
+
   // Put all of the attribute names in here so that Job and JobContext are
   // consistent.
   public static final String INPUT_FORMAT_CLASS_ATTR = "mapreduce.job.inputformat.class";

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

@@ -57,13 +57,6 @@
   set to less than .5</description>
 </property>
 
-<property>
-  <name>mapreduce.local.clientfactory.class.name</name>
-  <value>org.apache.hadoop.mapred.LocalClientFactory</value>
-  <description>This the client factory that is responsible for 
-  creating local job runner client</description>
-</property>
-
 <property>
   <name>mapreduce.job.maps</name>
   <value>2</value>
@@ -883,30 +876,6 @@
     </description>
   </property>
   
-  <property>
-    <name>mapreduce.map.skip.proc.count.autoincr</name>
-    <value>true</value>
-    <description> The flag which if set to true, 
-    SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS is incremented 
-    by MapRunner after invoking the map function. This value must be set to 
-    false for applications which process the records asynchronously 
-    or buffer the input records. For example streaming. 
-    In such cases applications should increment this counter on their own.
-    </description>
-  </property>
-  
-  <property>
-    <name>mapreduce.reduce.skip.proc.count.autoincr</name>
-    <value>true</value>
-    <description> The flag which if set to true, 
-    SkipBadRecords.COUNTER_REDUCE_PROCESSED_GROUPS is incremented 
-    by framework after invoking the reduce function. This value must be set to 
-    false for applications which process the records asynchronously 
-    or buffer the input records. For example streaming. 
-    In such cases applications should increment this counter on their own.
-    </description>
-  </property>
-  
   <property>
     <name>mapreduce.job.skip.outdir</name>
     <value></value>

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/resources/job_1329348432655_0001_conf.xml

@@ -93,7 +93,6 @@
 <property><!--Loaded from job.xml--><name>mapreduce.reduce.input.buffer.percent</name><value>0.0</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.map.output.compress.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
 <property><!--Loaded from job.xml--><name>yarn.resourcemanager.delegation-token.keepalive-time-ms</name><value>300000</value></property>
-<property><!--Loaded from job.xml--><name>mapreduce.map.skip.proc.count.autoincr</name><value>true</value></property>
 <property><!--Loaded from job.xml--><name>dfs.datanode.directoryscan.threads</name><value>1</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.jobtracker.address</name><value>local</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.cluster.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
@@ -197,7 +196,6 @@
 <property><!--Loaded from job.xml--><name>dfs.block.access.key.update.interval</name><value>600</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.jobhistory.move.interval-ms</name><value>30000</value></property>
 <property><!--Loaded from job.xml--><name>dfs.datanode.dns.interface</name><value>default</value></property>
-<property><!--Loaded from job.xml--><name>mapreduce.reduce.skip.proc.count.autoincr</name><value>true</value></property>
 <property><!--Loaded from job.xml--><name>dfs.namenode.backup.http-address</name><value>0.0.0.0:50105</value></property>
 <property><!--Loaded from job.xml--><name>yarn.nodemanager.container-monitor.interval-ms</name><value>3000</value></property>
 <property><!--Loaded from job.xml--><name>mapred.reducer.new-api</name><value>true</value></property>
@@ -290,7 +288,6 @@
 <property><!--Loaded from job.xml--><name>yarn.app.mapreduce.am.command-opts</name><value>-Xmx500m</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.admin.user.env</name><value>LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native</value></property>
 <property><!--Loaded from job.xml--><name>dfs.namenode.checkpoint.edits.dir</name><value>${dfs.namenode.checkpoint.dir}</value></property>
-<property><!--Loaded from job.xml--><name>mapreduce.local.clientfactory.class.name</name><value>org.apache.hadoop.mapred.LocalClientFactory</value></property>
 <property><!--Loaded from job.xml--><name>hadoop.common.configuration.version</name><value>0.23.0</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.tasktracker.dns.interface</name><value>default</value></property>
 <property><!--Loaded from job.xml--><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization,org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization,org.apache.hadoop.io.serializer.avro.AvroReflectSerialization</value></property>
@@ -380,7 +377,6 @@
 <property><!--Loaded from job.xml--><name>fs.AbstractFileSystem.viewfs.impl</name><value>org.apache.hadoop.fs.viewfs.ViewFs</value></property>
 <property><!--Loaded from job.xml--><name>yarn.resourcemanager.resource-tracker.client.thread-count</name><value>50</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><!--Loaded from job.xml--><name>mapreduce.clientfactory.class.name</name><value>org.apache.hadoop.mapred.YarnClientFactory</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.map.output.compress</name><value>false</value></property>
 <property><!--Loaded from job.xml--><name>mapreduce.job.counters.limit</name><value>120</value></property>
 <property><!--Loaded from job.xml--><name>dfs.datanode.ipc.address</name><value>0.0.0.0:50020</value></property>

hadoop-tools/hadoop-sls/src/main/data/2jobs2min-rumen-jh.json

@@ -4645,7 +4645,6 @@
     "dfs.ha.log-roll.period" : "120",
     "mapreduce.reduce.input.buffer.percent" : "0.0",
     "mapreduce.map.output.compress.codec" : "org.apache.hadoop.io.compress.SnappyCodec",
-    "mapreduce.map.skip.proc.count.autoincr" : "true",
     "dfs.client.failover.sleep.base.millis" : "500",
     "dfs.datanode.directoryscan.threads" : "1",
     "mapreduce.jobtracker.address" : "neededForHive:999999",
@@ -4765,7 +4764,6 @@
     "dfs.namenode.backup.address" : "0.0.0.0:50100",
     "hadoop.util.hash.type" : "murmur",
     "dfs.block.access.key.update.interval" : "600",
-    "mapreduce.reduce.skip.proc.count.autoincr" : "true",
     "dfs.datanode.dns.interface" : "default",
     "dfs.datanode.use.datanode.hostname" : "false",
     "mapreduce.job.output.key.class" : "org.apache.hadoop.io.Text",
@@ -4875,7 +4873,6 @@
     "mapreduce.reduce.shuffle.read.timeout" : "180000",
     "mapreduce.admin.user.env" : "LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native",
     "yarn.app.mapreduce.am.command-opts" : " -Xmx1238932873",
-    "mapreduce.local.clientfactory.class.name" : "org.apache.hadoop.mapred.LocalClientFactory",
     "dfs.namenode.checkpoint.edits.dir" : "${dfs.namenode.checkpoint.dir}",
     "fs.permissions.umask-mode" : "022",
     "dfs.client.domain.socket.data.traffic" : "false",
@@ -9754,7 +9751,6 @@
     "dfs.ha.log-roll.period" : "120",
     "mapreduce.reduce.input.buffer.percent" : "0.0",
     "mapreduce.map.output.compress.codec" : "org.apache.hadoop.io.compress.SnappyCodec",
-    "mapreduce.map.skip.proc.count.autoincr" : "true",
     "dfs.client.failover.sleep.base.millis" : "500",
     "dfs.datanode.directoryscan.threads" : "1",
     "mapreduce.jobtracker.address" : "neededForHive:999999",
@@ -9874,7 +9870,6 @@
     "dfs.namenode.backup.address" : "0.0.0.0:50100",
     "hadoop.util.hash.type" : "murmur",
     "dfs.block.access.key.update.interval" : "600",
-    "mapreduce.reduce.skip.proc.count.autoincr" : "true",
     "dfs.datanode.dns.interface" : "default",
     "dfs.datanode.use.datanode.hostname" : "false",
     "mapreduce.job.output.key.class" : "org.apache.hadoop.io.Text",
@@ -9984,7 +9979,6 @@
     "mapreduce.reduce.shuffle.read.timeout" : "180000",
     "mapreduce.admin.user.env" : "LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native",
     "yarn.app.mapreduce.am.command-opts" : " -Xmx1238932873",
-    "mapreduce.local.clientfactory.class.name" : "org.apache.hadoop.mapred.LocalClientFactory",
     "dfs.namenode.checkpoint.edits.dir" : "${dfs.namenode.checkpoint.dir}",
     "fs.permissions.umask-mode" : "022",
     "dfs.client.domain.socket.data.traffic" : "false",