Merge -r 735776:735777 from trunk onto 0.20 branch. Fixes HADOOP-4828.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/core/branches/branch-0.20@735779 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -307,6 +307,9 @@ Release 0.20.0 - Unreleased
 
     HADOOP-5030. Build Chukwa RPM to install into configured directory. (Eric
     Yang via cdouglas)
+    
+    HADOOP-4828. Updates documents to do with configuration (HADOOP-4631).
+    (Sharad Agarwal via ddas)
 
   OPTIMIZATIONS
 

src/c++/libhdfs/hdfs.h

@@ -98,7 +98,7 @@ extern  "C" {
      * of the namenode of a hdfs cluster. 'host' should be passed as NULL if
      * you want to connect to local filesystem. 'host' should be passed as
      * 'default' (and port as 0) to used the 'configured' filesystem
-     * (hadoop-site/hadoop-default.xml).
+     * (core-site/core-default.xml).
      * @param port The port on which the server is listening.
      * @param user the user name (this is hadoop domain user). Or NULL is equivelant to hhdfsConnect(host, port)
      * @param groups the groups (these are hadoop domain groups)
@@ -114,7 +114,7 @@ extern  "C" {
      * of the namenode of a hdfs cluster. 'host' should be passed as NULL if
      * you want to connect to local filesystem. 'host' should be passed as
      * 'default' (and port as 0) to used the 'configured' filesystem
-     * (hadoop-site/hadoop-default.xml).
+     * (core-site/core-default.xml).
      * @param port The port on which the server is listening.
      * @return Returns a handle to the filesystem or NULL on error.
      */

src/c++/libhdfs/tests/conf/hadoop-site.xml

@@ -1,9 +1,11 @@
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="nutch-conf.xsl"?>
 
-<!-- Values used when running libhdfs unit tests. -->
-<!-- This is mostly empty, to use the default values, overriding the -->
-<!-- potentially user-editted hadoop-site.xml in the conf/ directory.  -->
+<!-- DO NOT PUT ANY PROPERTY IN THIS FILE. INSTEAD USE -->
+<!-- core-site.xml, mapred-site.xml OR hdfs-site.xml -->
+<!-- This empty script is to avoid picking properties from  -->
+<!-- conf/hadoop-site.xml This would be removed once support  -->
+<!-- for hadoop-site.xml is removed.  -->
 
 <configuration>
 

src/c++/libhdfs/tests/test-libhdfs.sh

@@ -30,8 +30,7 @@ HDFS_TEST=hdfs_test
 HADOOP_LIB_DIR=$HADOOP_HOME/lib
 HADOOP_BIN_DIR=$HADOOP_HOME/bin
 
-# Manipulate HADOOP_CONF_DIR so as to include 
-# HADOOP_HOME/conf/hadoop-default.xml too
+# Manipulate HADOOP_CONF_DIR too
 # which is necessary to circumvent bin/hadoop
 HADOOP_CONF_DIR=$HADOOP_CONF_DIR:$HADOOP_HOME/conf
 

src/contrib/chukwa/src/java/org/apache/hadoop/chukwa/datacollection/writer/SeqFileWriter.java

@@ -105,7 +105,7 @@ public class SeqFileWriter implements ChukwaWriter
 		log.info("rotateInterval is " + rotateInterval);
 		log.info("outputDir is " + outputDir);
 		log.info("fsname is " + fsname);
-		log.info("filesystem type from hadoop-default.xml is "
+		log.info("filesystem type from core-default.xml is "
 				+ conf.get("fs.hdfs.impl"));
 
 		if (fsname == null) {

src/contrib/fairscheduler/README

@@ -70,7 +70,7 @@ from HADOOP_HOME/build/contrib/fairscheduler to HADOOP_HOME/lib. Alternatively
 you can modify HADOOP_CLASSPATH to include this jar, in conf/hadoop-env.sh.
 
 You will also need to set the following property in the Hadoop config file
-(conf/hadoop-site.xml) to have Hadoop use the fair scheduler:
+(conf/mapred-site.xml) to have Hadoop use the fair scheduler:
 
 <property>
   <name>mapred.jobtracker.taskScheduler</name>
@@ -86,7 +86,7 @@ described in the Administration section.
 
 CONFIGURING:
 
-The following properties can be set in hadoop-site.xml to configure the
+The following properties can be set in mapred-site.xml to configure the
 scheduler:
 
 mapred.fairscheduler.allocation.file:

src/contrib/hdfsproxy/README

@@ -13,7 +13,7 @@ respectively. The location of these files can be specified in
 hdfsproxy-default.xml. Environmental variable HDFSPROXY_CONF_DIR can be used to
 point to the directory where these configuration files are located. The 
 configuration files of the proxied HDFS cluster should also be available on the
-classpath (hadoop-default.xml and hadoop-site.xml).
+classpath (hdfs-default.xml and hdfs-site.xml).
 
 Mirroring those used in HDFS, a few shell scripts are provided to start and 
 stop a group of proxy servers. The hosts to run hdfsproxy on are specified in 

src/contrib/test/hadoop-site.xml

@@ -1,9 +1,11 @@
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="nutch-conf.xsl"?>
 
-<!-- Values used when running unit tests.  This is mostly empty, to -->
-<!-- use of the default values, overriding the potentially -->
-<!-- user-editted hadoop-site.xml in the conf/ directory.  -->
+<!-- DO NOT PUT ANY PROPERTY IN THIS FILE. INSTEAD USE -->
+<!-- core-site.xml, mapred-site.xml OR hdfs-site.xml -->
+<!-- This empty script is to avoid picking properties from  -->
+<!-- conf/hadoop-site.xml This would be removed once support  -->
+<!-- for hadoop-site.xml is removed.  -->
 
 <configuration>
 

src/core/org/apache/hadoop/fs/kfs/package.html

@@ -32,7 +32,7 @@ documentation.
 <h3>Steps</h3>
 
         <ul>
-          <li>In the Hadoop conf directory edit hadoop-default.xml,
+          <li>In the Hadoop conf directory edit core-site.xml,
           add the following:
             <pre>
 &lt;property&gt;
@@ -42,7 +42,7 @@ documentation.
 &lt;/property&gt;
             </pre>
 
-          <li>In the Hadoop conf directory edit hadoop-site.xml,
+          <li>In the Hadoop conf directory edit core-site.xml,
           adding the following (with appropriate values for
           &lt;server&gt; and &lt;port&gt;):
             <pre>

src/core/overview.html

@@ -134,13 +134,13 @@ following:
 
 <li>The NameNode (Distributed Filesystem master) host.  This is
 specified with the configuration property <tt><a
- href="../hadoop-default.html#fs.default.name">fs.default.name</a></tt>.
+ href="../core-default.html#fs.default.name">fs.default.name</a></tt>.
 </li>
 
 <li>The {@link org.apache.hadoop.mapred.JobTracker} (MapReduce master)
 host and port.  This is specified with the configuration property
 <tt><a
-href="../hadoop-default.html#mapred.job.tracker">mapred.job.tracker</a></tt>.
+href="../mapred-default.html#mapred.job.tracker">mapred.job.tracker</a></tt>.
 </li>
 
 <li>A <em>slaves</em> file that lists the names of all the hosts in
@@ -151,8 +151,10 @@ the cluster.  The default slaves file is <tt>conf/slaves</tt>.
 <h3>Pseudo-distributed configuration</h3>
 
 You can in fact run everything on a single host.  To run things this
-way, put the following in conf/hadoop-site.xml:
-
+way, put the following in:
+<br/>
+<br/>
+conf/core-site.xml:
 <xmp><configuration>
 
   <property>
@@ -160,10 +162,10 @@ way, put the following in conf/hadoop-site.xml:
     <value>hdfs://localhost/</value>
   </property>
 
-  <property>
-    <name>mapred.job.tracker</name>
-    <value>localhost:9001</value>
-  </property>
+</configuration></xmp>
+
+conf/hdfs-site.xml:
+<xmp><configuration>
 
   <property>
     <name>dfs.replication</name>
@@ -172,6 +174,16 @@ way, put the following in conf/hadoop-site.xml:
 
 </configuration></xmp>
 
+conf/mapred-site.xml:
+<xmp><configuration>
+
+  <property>
+    <name>mapred.job.tracker</name>
+    <value>localhost:9001</value>
+  </property>
+
+</configuration></xmp>
+
 <p>(We also set the HDFS replication level to 1 in order to
 reduce warnings when running on a single node.)</p>
 
@@ -217,36 +229,38 @@ cat output/*
 <h3>Fully-distributed operation</h3>
 
 <p>Fully distributed operation is just like the pseudo-distributed operation
-described above, except, in <tt>conf/hadoop-site.xml</tt>, specify:</p>
+described above, except, specify:</p>
 
 <ol>
 
 <li>The hostname or IP address of your master server in the value
 for <tt><a
-href="../hadoop-default.html#fs.default.name">fs.default.name</a></tt>,
-  as <tt><em>hdfs://master.example.com/</em></tt>.</li>
+href="../core-default.html#fs.default.name">fs.default.name</a></tt>,
+  as <tt><em>hdfs://master.example.com/</em></tt> in <tt>conf/core-site.xml</tt>.</li>
 
 <li>The host and port of the your master server in the value
-of <tt><a href="../hadoop-default.html#mapred.job.tracker">mapred.job.tracker</a></tt>
-as <tt><em>master.example.com</em>:<em>port</em></tt>.</li>
+of <tt><a href="../mapred-default.html#mapred.job.tracker">mapred.job.tracker</a></tt>
+as <tt><em>master.example.com</em>:<em>port</em></tt> in <tt>conf/mapred-site.xml</tt>.</li>
 
 <li>Directories for <tt><a
-href="../hadoop-default.html#dfs.name.dir">dfs.name.dir</a></tt> and
-<tt><a href="../hadoop-default.html#dfs.data.dir">dfs.data.dir</a>.
+href="../hdfs-default.html#dfs.name.dir">dfs.name.dir</a></tt> and
+<tt><a href="../hdfs-default.html#dfs.data.dir">dfs.data.dir</a> 
+in <tt>conf/hdfs-site.xml</tt>.
 </tt>These are local directories used to hold distributed filesystem
 data on the master node and slave nodes respectively.  Note
 that <tt>dfs.data.dir</tt> may contain a space- or comma-separated
 list of directory names, so that data may be stored on multiple local
 devices.</li>
 
-<li><tt><a href="../hadoop-default.html#mapred.local.dir">mapred.local.dir</a></tt>,
-  the local directory where temporary MapReduce data is stored.  It
-  also may be a list of directories.</li>
+<li><tt><a href="../mapred-default.html#mapred.local.dir">mapred.local.dir</a></tt>
+  in <tt>conf/mapred-site.xml</tt>, the local directory where temporary 
+  MapReduce data is stored.  It also may be a list of directories.</li>
 
 <li><tt><a
-href="../hadoop-default.html#mapred.map.tasks">mapred.map.tasks</a></tt>
+href="../mapred-default.html#mapred.map.tasks">mapred.map.tasks</a></tt>
 and <tt><a
-href="../hadoop-default.html#mapred.reduce.tasks">mapred.reduce.tasks</a></tt>.
+href="../mapred-default.html#mapred.reduce.tasks">mapred.reduce.tasks</a></tt> 
+in <tt>conf/mapred-site.xml</tt>.
 As a rule of thumb, use 10x the
 number of slave processors for <tt>mapred.map.tasks</tt>, and 2x the
 number of slave processors for <tt>mapred.reduce.tasks</tt>.</li>

src/docs/src/documentation/content/xdocs/cluster_setup.xml

@@ -75,15 +75,20 @@
       <section>
         <title>Configuration Files</title>
         
-        <p>Hadoop configuration is driven by two important configuration files
-        found in the <code>conf/</code> directory of the distribution:</p>
+        <p>Hadoop configuration is driven by two types of important 
+        configuration files:</p>
         <ol>
           <li>
-            <a href="ext:hadoop-default">hadoop-default.xml</a> - Read-only 
-            default configuration.
+            Read-only default configuration - 
+            <a href="ext:core-default">src/core/core-default.xml</a>, 
+            <a href="ext:hdfs-default">src/hdfs/hdfs-default.xml</a> and 
+            <a href="ext:mapred-default">src/mapred/mapred-default.xml</a>.
           </li>
           <li>
-            <em>hadoop-site.xml</em> - Site-specific configuration.
+            Site-specific configuration - 
+            <em>conf/core-site.xml</em>, 
+            <em>conf/hdfs-site.xml</em> and 
+            <em>conf/mapred-site.xml</em>.
           </li>
         </ol>
       
@@ -157,7 +162,9 @@
           <title>Configuring the Hadoop Daemons</title>
           
           <p>This section deals with important parameters to be specified in the
-          <code>conf/hadoop-site.xml</code> for the Hadoop cluster.</p>
+          following:
+          <br/>
+          <code>conf/core-site.xml</code>:</p>
 
 		  <table>
   		    <tr>
@@ -165,16 +172,21 @@
 		      <th>Value</th> 
 		      <th>Notes</th>
 		    </tr>
-  		    <tr>
-		      <td>fs.default.name</td>
-  		      <td>URI of <code>NameNode</code>.</td>
-		      <td><em>hdfs://hostname/</em></td>
-		    </tr>
 		    <tr>
-		      <td>mapred.job.tracker</td>
-		      <td>Host or IP and port of <code>JobTracker</code>.</td>
-		      <td><em>host:port</em> pair.</td>
-		    </tr>
+              <td>fs.default.name</td>
+              <td>URI of <code>NameNode</code>.</td>
+              <td><em>hdfs://hostname/</em></td>
+            </tr>
+          </table>
+
+      <p><br/><code>conf/hdfs-site.xml</code>:</p>
+          
+      <table>   
+        <tr>
+          <th>Parameter</th>
+          <th>Value</th> 
+          <th>Notes</th>
+        </tr>
 		    <tr>
 		      <td>dfs.name.dir</td>
 		      <td>
@@ -197,6 +209,21 @@
 		        devices.
 		      </td>
 		    </tr>
+      </table>
+
+      <p><br/><code>conf/mapred-site.xml</code>:</p>
+
+      <table>
+          <tr>
+          <th>Parameter</th>
+          <th>Value</th> 
+          <th>Notes</th>
+        </tr>
+        <tr>
+          <td>mapred.job.tracker</td>
+          <td>Host or IP and port of <code>JobTracker</code>.</td>
+          <td><em>host:port</em> pair.</td>
+        </tr>
 		    <tr>
 		      <td>mapred.system.dir</td>
 		      <td>
@@ -322,16 +349,19 @@
                 that is 9TB of data sorted on a cluster with 900 nodes:</p>
                 <table>
   		          <tr>
+                <th>Configuration File</th>
 		            <th>Parameter</th>
 		            <th>Value</th> 
 		            <th>Notes</th>
 		          </tr>
                   <tr>
+                    <td>conf/hdfs-site.xml</td>
                     <td>dfs.block.size</td>
                     <td>134217728</td>
                     <td>HDFS blocksize of 128MB for large file-systems.</td>
                   </tr>
                   <tr>
+                    <td>conf/hdfs-site.xml</td>
                     <td>dfs.namenode.handler.count</td>
                     <td>40</td>
                     <td>
@@ -340,6 +370,7 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>mapred.reduce.parallel.copies</td>
                     <td>20</td>
                     <td>
@@ -348,6 +379,7 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>mapred.child.java.opts</td>
                     <td>-Xmx512M</td>
                     <td>
@@ -355,6 +387,7 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/core-site.xml</td>
                     <td>fs.inmemory.size.mb</td>
                     <td>200</td>
                     <td>
@@ -363,16 +396,19 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/core-site.xml</td>
                     <td>io.sort.factor</td>
                     <td>100</td>
                     <td>More streams merged at once while sorting files.</td>
                   </tr>
                   <tr>
+                    <td>conf/core-site.xml</td>
                     <td>io.sort.mb</td>
                     <td>200</td>
                     <td>Higher memory-limit while sorting data.</td>
                   </tr>
                   <tr>
+                    <td>conf/core-site.xml</td>
                     <td>io.file.buffer.size</td>
                     <td>131072</td>
                     <td>Size of read/write buffer used in SequenceFiles.</td>
@@ -385,11 +421,13 @@
                 data sorted on 2000 nodes:</p>
                 <table>
   		          <tr>
+                <th>Configuration File</th>
 		            <th>Parameter</th>
 		            <th>Value</th> 
 		            <th>Notes</th>
 		          </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>mapred.job.tracker.handler.count</td>
                     <td>60</td>
                     <td>
@@ -398,11 +436,13 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>mapred.reduce.parallel.copies</td>
                     <td>50</td>
                     <td></td>
                   </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>tasktracker.http.threads</td>
                     <td>50</td>
                     <td>
@@ -412,6 +452,7 @@
                     </td>
                   </tr>
                   <tr>
+                    <td>conf/mapred-site.xml</td>
                     <td>mapred.child.java.opts</td>
                     <td>-Xmx1024M</td>
                     <td>Larger heap-size for child jvms of maps/reduces.</td>

src/docs/src/documentation/content/xdocs/hdfs_user_guide.xml

@@ -474,7 +474,7 @@
         <a href="mailto:core-user@hadoop.apache.org">core-user[at]hadoop.apache.org</a>.
       </li>
       <li>
-         Explore <code>conf/hadoop-default.xml</code>. 
+         Explore <code>src/hdfs/hdfs-default.xml</code>. 
          It includes brief 
          description of most of the configuration variables available.
       </li>

src/docs/src/documentation/content/xdocs/libhdfs.xml

@@ -82,7 +82,7 @@ gcc above_sample.c -I${HADOOP_HOME}/src/c++/libhdfs -L${HADOOP_HOME}/libhdfs -lh
 <section>
 <title>Common problems</title>
 <p>
-The most common problem is the CLASSPATH is not set properly when calling a program that uses libhdfs. Make sure you set it to all the hadoop jars needed to run Hadoop itself. Currently, there is no way to programmatically generate the classpath, but a good bet is to include all the jar files in ${HADOOP_HOME} and ${HADOOP_HOME}/lib as well as the right configuration directory containing hadoop-site.xml
+The most common problem is the CLASSPATH is not set properly when calling a program that uses libhdfs. Make sure you set it to all the hadoop jars needed to run Hadoop itself. Currently, there is no way to programmatically generate the classpath, but a good bet is to include all the jar files in ${HADOOP_HOME} and ${HADOOP_HOME}/lib as well as the right configuration directory containing hdfs-site.xml
 </p>
 </section>
 <section>

src/docs/src/documentation/content/xdocs/quickstart.xml

@@ -161,7 +161,9 @@
 	  
       <section>
         <title>Configuration</title>
-        <p>Use the following <code>conf/hadoop-site.xml</code>:</p>
+        <p>Use the following:
+        <br/>
+        <code>conf/core-site.xml</code>:</p>
         <table>
         <tr><td>&lt;configuration&gt;</td></tr>
 
@@ -170,10 +172,12 @@
             <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;value&gt;hdfs://localhost:9000&lt;/value&gt;</td></tr>
           <tr><td>&nbsp;&nbsp;&lt;/property&gt;</td></tr>
 
-          <tr><td>&nbsp;&nbsp;&lt;property&gt;</td></tr>
-            <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;name&gt;mapred.job.tracker&lt;/name&gt;</td></tr>
-            <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;value&gt;localhost:9001&lt;/value&gt;</td></tr>
-          <tr><td>&nbsp;&nbsp;&lt;/property&gt;</td></tr>
+        <tr><td>&lt;/configuration&gt;</td></tr>
+        </table>
+      
+        <p><br/><code>conf/hdfs-site.xml</code>:</p>
+        <table>
+        <tr><td>&lt;configuration&gt;</td></tr>
 
           <tr><td>&nbsp;&nbsp;&lt;property&gt;</td></tr>
             <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;name&gt;dfs.replication&lt;/name&gt;</td></tr>
@@ -182,6 +186,18 @@
 
         <tr><td>&lt;/configuration&gt;</td></tr>
         </table>
+      
+        <p><br/><code>conf/mapred-site.xml</code>:</p>
+        <table>
+        <tr><td>&lt;configuration&gt;</td></tr>
+
+          <tr><td>&nbsp;&nbsp;&lt;property&gt;</td></tr>
+            <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;name&gt;mapred.job.tracker&lt;/name&gt;</td></tr>
+            <tr><td>&nbsp;&nbsp;&nbsp;&nbsp;&lt;value&gt;localhost:9001&lt;/value&gt;</td></tr>
+          <tr><td>&nbsp;&nbsp;&lt;/property&gt;</td></tr>
+
+        <tr><td>&lt;/configuration&gt;</td></tr>
+        </table>
       </section>
 
       <section>

src/docs/src/documentation/content/xdocs/site.xml

@@ -73,6 +73,9 @@ See http://forrest.apache.org/docs/linking.html for more info.
     <wiki      href="http://wiki.apache.org/hadoop/" />
     <faq       href="http://wiki.apache.org/hadoop/FAQ" />
     <hadoop-default href="http://hadoop.apache.org/core/docs/current/hadoop-default.html" />
+    <core-default href="http://hadoop.apache.org/core/docs/current/core-default.html" />
+    <hdfs-default href="http://hadoop.apache.org/core/docs/current/hdfs-default.html" />
+    <mapred-default href="http://hadoop.apache.org/core/docs/current/mapred-default.html" />
     <zlib      href="http://www.zlib.net/" />
     <gzip      href="http://www.gzip.org/" />
     <bzip      href="http://www.bzip.org/" />

src/docs/src/documentation/content/xdocs/streaming.xml

@@ -223,7 +223,7 @@ The -D mapred.reduce.tasks=2 in the above example specifies to use two reducers
 </p>
 <p>
 For more details on the jobconf parameters see:
-<a href="ext:hadoop-default">hadoop-default.html</a></p>
+<a href="ext:mapred-default">mapred-default.html</a></p>
 </section>
 
 <section>
@@ -276,7 +276,7 @@ To specify additional local temp directories use:
 </source>
 <p>
 For more details on jobconf parameters see:
-<a href="ext:hadoop-default">hadoop-default.html</a></p>
+<a href="ext:mapred-default">mapred-default.html</a></p>
 <p>
 To set an environment variable in a streaming command use:
 </p>

src/mapred/org/apache/hadoop/mapred/InputFormat.java

@@ -48,7 +48,7 @@ import org.apache.hadoop.fs.FileSystem;
  * bytes, of the input files. However, the {@link FileSystem} blocksize of  
  * the input files is treated as an upper bound for input splits. A lower bound 
  * on the split size can be set via 
- * <a href="{@docRoot}/../hadoop-default.html#mapred.min.split.size">
+ * <a href="{@docRoot}/../mapred-default.html#mapred.min.split.size">
  * mapred.min.split.size</a>.</p>
  * 
  * <p>Clearly, logical splits based on input-size is insufficient for many 

src/mapred/org/apache/hadoop/mapred/JobConf.java

@@ -1047,7 +1047,7 @@ public class JobConf extends Configuration {
    * bytes, of input files. However, the {@link FileSystem} blocksize of the 
    * input files is treated as an upper bound for input splits. A lower bound 
    * on the split size can be set via 
-   * <a href="{@docRoot}/../hadoop-default.html#mapred.min.split.size">
+   * <a href="{@docRoot}/../mapred-default.html#mapred.min.split.size">
    * mapred.min.split.size</a>.</p>
    *  
    * <p>Thus, if you expect 10TB of input data and have a blocksize of 128MB, 
@@ -1077,7 +1077,7 @@ public class JobConf extends Configuration {
    * 
    * <p>The right number of reduces seems to be <code>0.95</code> or 
    * <code>1.75</code> multiplied by (&lt;<i>no. of nodes</i>&gt; * 
-   * <a href="{@docRoot}/../hadoop-default.html#mapred.tasktracker.reduce.tasks.maximum">
+   * <a href="{@docRoot}/../mapred-default.html#mapred.tasktracker.reduce.tasks.maximum">
    * mapred.tasktracker.reduce.tasks.maximum</a>).
    * </p>
    * 
@@ -1173,7 +1173,7 @@ public class JobConf extends Configuration {
    * performance metrics system via the org.apache.hadoop.metrics API.  The 
    * session identifier is intended, in particular, for use by Hadoop-On-Demand 
    * (HOD) which allocates a virtual Hadoop cluster dynamically and transiently. 
-   * HOD will set the session identifier by modifying the hadoop-site.xml file 
+   * HOD will set the session identifier by modifying the mapred-site.xml file 
    * before starting the cluster.
    *
    * When not running under HOD, this identifer is expected to remain set to 

src/mapred/org/apache/hadoop/mapred/Mapper.java

@@ -145,7 +145,7 @@ public interface Mapper<K1, V1, K2, V2> extends JobConfigurable, Closeable {
    * takes an insignificant amount of time to process individual key/value 
    * pairs, this is crucial since the framework might assume that the task has 
    * timed-out and kill that task. The other way of avoiding this is to set 
-   * <a href="{@docRoot}/../hadoop-default.html#mapred.task.timeout">
+   * <a href="{@docRoot}/../mapred-default.html#mapred.task.timeout">
    * mapred.task.timeout</a> to a high-enough value (or even zero for no 
    * time-outs).</p>
    * 

src/mapred/org/apache/hadoop/mapred/Reducer.java

@@ -185,7 +185,7 @@ public interface Reducer<K2, V2, K3, V3> extends JobConfigurable, Closeable {
    * takes an insignificant amount of time to process individual key/value 
    * pairs, this is crucial since the framework might assume that the task has 
    * timed-out and kill that task. The other way of avoiding this is to set 
-   * <a href="{@docRoot}/../hadoop-default.html#mapred.task.timeout">
+   * <a href="{@docRoot}/../mapred-default.html#mapred.task.timeout">
    * mapred.task.timeout</a> to a high-enough value (or even zero for no 
    * time-outs).</p>
    * 

src/mapred/org/apache/hadoop/mapreduce/InputFormat.java

@@ -50,7 +50,7 @@ import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
  * bytes, of the input files. However, the {@link FileSystem} blocksize of  
  * the input files is treated as an upper bound for input splits. A lower bound 
  * on the split size can be set via 
- * <a href="{@docRoot}/../hadoop-default.html#mapred.min.split.size">
+ * <a href="{@docRoot}/../mapred-default.html#mapred.min.split.size">
  * mapred.min.split.size</a>.</p>
  * 
  * <p>Clearly, logical splits based on input-size is insufficient for many 

src/test/hadoop-site.xml

@@ -1,9 +1,11 @@
 <?xml version="1.0"?>
 <?xml-stylesheet type="text/xsl" href="nutch-conf.xsl"?>
 
-<!-- Values used when running unit tests.  This is mostly empty, to -->
-<!-- use of the default values, overriding the potentially -->
-<!-- user-editted hadoop-site.xml in the conf/ directory.  -->
+<!-- DO NOT PUT ANY PROPERTY IN THIS FILE. INSTEAD USE -->
+<!-- core-site.xml, mapred-site.xml OR hdfs-site.xml -->
+<!-- This empty script is to avoid picking properties from  -->
+<!-- conf/hadoop-site.xml This would be removed once support  -->
+<!-- for hadoop-site.xml is removed.  -->
 
 <configuration>