Adding mapreduce example

mapreduce-example/.gitignore

@@ -0,0 +1 @@
+output

mapreduce-example/input/capacity-scheduler.xml

@@ -0,0 +1,98 @@
+<?xml version="1.0"?>
+
+<!-- This is the configuration file for the resource manager in Hadoop. -->
+<!-- You can configure various scheduling parameters related to queues. -->
+<!-- The properties for a queue follow a naming convention,such as, -->
+<!-- mapred.capacity-scheduler.queue.<queue-name>.property-name. -->
+
+<configuration>
+
+  <property>
+    <name>mapred.capacity-scheduler.queue.default.capacity</name>
+    <value>100</value>
+    <description>Percentage of the number of slots in the cluster that are
+      to be available for jobs in this queue.
+    </description>    
+  </property>
+
+  <property>
+    <name>mapred.capacity-scheduler.queue.default.supports-priority</name>
+    <value>false</value>
+    <description>If true, priorities of jobs will be taken into 
+      account in scheduling decisions.
+    </description>
+  </property>
+
+  <property>
+    <name>mapred.capacity-scheduler.queue.default.minimum-user-limit-percent</name>
+    <value>100</value>
+    <description> Each queue enforces a limit on the percentage of resources 
+    allocated to a user at any given time, if there is competition for them. 
+    This user limit can vary between a minimum and maximum value. The former
+    depends on the number of users who have submitted jobs, and the latter is
+    set to this property value. For example, suppose the value of this 
+    property is 25. If two users have submitted jobs to a queue, no single 
+    user can use more than 50% of the queue resources. If a third user submits
+    a job, no single user can use more than 33% of the queue resources. With 4 
+    or more users, no user can use more than 25% of the queue's resources. A 
+    value of 100 implies no user limits are imposed. 
+    </description>
+  </property>
+  <property>
+    <name>mapred.capacity-scheduler.queue.default.maximum-initialized-jobs-per-user</name>
+    <value>2</value>
+    <description>The maximum number of jobs to be pre-initialized for a user
+    of the job queue.
+    </description>
+  </property>
+
+  <!-- The default configuration settings for the capacity task scheduler -->
+  <!-- The default values would be applied to all the queues which don't have -->
+  <!-- the appropriate property for the particular queue -->
+  <property>
+    <name>mapred.capacity-scheduler.default-supports-priority</name>
+    <value>false</value>
+    <description>If true, priorities of jobs will be taken into 
+      account in scheduling decisions by default in a job queue.
+    </description>
+  </property>
+
+  <property>
+    <name>mapred.capacity-scheduler.default-minimum-user-limit-percent</name>
+    <value>100</value>
+    <description>The percentage of the resources limited to a particular user
+      for the job queue at any given point of time by default.
+    </description>
+  </property>
+
+  <property>
+    <name>mapred.capacity-scheduler.default-maximum-initialized-jobs-per-user</name>
+    <value>2</value>
+    <description>The maximum number of jobs to be pre-initialized for a user
+    of the job queue.
+    </description>
+  </property>
+
+
+  <!-- Capacity scheduler Job Initialization configuration parameters -->
+  <property>
+    <name>mapred.capacity-scheduler.init-poll-interval</name>
+    <value>5000</value>
+    <description>The amount of time in miliseconds which is used to poll 
+    the job queues for jobs to initialize.
+    </description>
+  </property>
+  <property>
+    <name>mapred.capacity-scheduler.init-worker-threads</name>
+    <value>5</value>
+    <description>Number of worker threads which would be used by
+    Initialization poller to initialize jobs in a set of queue.
+    If number mentioned in property is equal to number of job queues
+    then a single thread would initialize jobs in a queue. If lesser
+    then a thread would get a set of queues assigned. If the number
+    is greater then number of threads would be equal to number of 
+    job queues.
+    </description>
+  </property>
+
+</configuration>

mapreduce-example/input/configuration.xsl

@@ -0,0 +1,24 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
+<xsl:output method="html"/>
+<xsl:template match="configuration">
+<html>
+<body>
+<table border="1">
+<tr>
+ <td>name</td>
+ <td>value</td>
+ <td>description</td>
+</tr>
+<xsl:for-each select="property">
+<tr>
+  <td><a name="{name}"><xsl:value-of select="name"/></a></td>
+  <td><xsl:value-of select="value"/></td>
+  <td><xsl:value-of select="description"/></td>
+</tr>
+</xsl:for-each>
+</table>
+</body>
+</html>
+</xsl:template>
+</xsl:stylesheet>

mapreduce-example/input/core-site.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+</configuration>

mapreduce-example/input/hadoop-env.sh

@@ -0,0 +1,54 @@
+# Set Hadoop-specific environment variables here.
+
+# The only required environment variable is JAVA_HOME.  All others are
+# optional.  When running a distributed configuration it is best to
+# set JAVA_HOME in this file, so that it is correctly defined on
+# remote nodes.
+
+# The java implementation to use.  Required.
+# export JAVA_HOME=/usr/lib/j2sdk1.5-sun
+
+# Extra Java CLASSPATH elements.  Optional.
+# export HADOOP_CLASSPATH=
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+# export HADOOP_HEAPSIZE=2000
+
+# Extra Java runtime options.  Empty by default.
+# export HADOOP_OPTS=-server
+
+# Command specific options appended to HADOOP_OPTS when specified
+export HADOOP_NAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_NAMENODE_OPTS"
+export HADOOP_SECONDARYNAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_SECONDARYNAMENODE_OPTS"
+export HADOOP_DATANODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_DATANODE_OPTS"
+export HADOOP_BALANCER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_BALANCER_OPTS"
+export HADOOP_JOBTRACKER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_JOBTRACKER_OPTS"
+# export HADOOP_TASKTRACKER_OPTS=
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+# export HADOOP_CLIENT_OPTS
+
+# Extra ssh options.  Empty by default.
+# export HADOOP_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR"
+
+# Where log files are stored.  $HADOOP_HOME/logs by default.
+# export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
+
+# File naming remote slave hosts.  $HADOOP_HOME/conf/slaves by default.
+# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
+
+# host:path where hadoop code should be rsync'd from.  Unset by default.
+# export HADOOP_MASTER=master:/home/$USER/src/hadoop
+
+# Seconds to sleep between slave commands.  Unset by default.  This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HADOOP_SLAVE_SLEEP=0.1
+
+# The directory where pid files are stored. /tmp by default.
+# export HADOOP_PID_DIR=/var/hadoop/pids
+
+# A string representing this instance of hadoop. $USER by default.
+# export HADOOP_IDENT_STRING=$USER
+
+# The scheduling priority for daemon processes.  See 'man nice'.
+# export HADOOP_NICENESS=10

mapreduce-example/input/hadoop-metrics.properties

@@ -0,0 +1,40 @@
+# Configuration of the "dfs" context for null
+dfs.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "dfs" context for file
+#dfs.class=org.apache.hadoop.metrics.file.FileContext
+#dfs.period=10
+#dfs.fileName=/tmp/dfsmetrics.log
+
+# Configuration of the "dfs" context for ganglia
+# dfs.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# dfs.period=10
+# dfs.servers=localhost:8649
+
+
+# Configuration of the "mapred" context for null
+mapred.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "mapred" context for file
+#mapred.class=org.apache.hadoop.metrics.file.FileContext
+#mapred.period=10
+#mapred.fileName=/tmp/mrmetrics.log
+
+# Configuration of the "mapred" context for ganglia
+# mapred.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# mapred.period=10
+# mapred.servers=localhost:8649
+
+
+# Configuration of the "jvm" context for null
+jvm.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "jvm" context for file
+#jvm.class=org.apache.hadoop.metrics.file.FileContext
+#jvm.period=10
+#jvm.fileName=/tmp/jvmmetrics.log
+
+# Configuration of the "jvm" context for ganglia
+# jvm.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# jvm.period=10
+# jvm.servers=localhost:8649

mapreduce-example/input/hadoop-policy.xml

@@ -0,0 +1,97 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+  <property>
+    <name>security.client.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ClientProtocol, which is used by user code 
+    via the DistributedFileSystem. 
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.client.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ClientDatanodeProtocol, the client-to-datanode protocol 
+    for block recovery.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for DatanodeProtocol, which is used by datanodes to 
+    communicate with the namenode.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.inter.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for InterDatanodeProtocol, the inter-datanode protocol
+    for updating generation timestamp.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.namenode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for NamenodeProtocol, the protocol used by the secondary
+    namenode to communicate with the namenode.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.inter.tracker.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for InterTrackerProtocol, used by the tasktrackers to 
+    communicate with the jobtracker.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.job.submission.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for JobSubmissionProtocol, used by job clients to 
+    communciate with the jobtracker for job submission, querying job status etc.
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.task.umbilical.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for TaskUmbilicalProtocol, used by the map and reduce 
+    tasks to communicate with the parent tasktracker. 
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.refresh.policy.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for RefreshAuthorizationPolicyProtocol, used by the 
+    dfsadmin and mradmin commands to refresh the security policy in-effect. 
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+</configuration>

mapreduce-example/input/hdfs-site.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+  <!-- Matthew 2010-01-13 -->
+  <property>
+         <name>fs.default.name</name>
+         <value>localhost:9000</value>
+  </property>
+  <property>
+         <name>mapred.job.tracker</name>
+         <value>localhost:9001</value>
+  </property>
+  <property>
+        <name>dfs.replication</name>
+        <value>1</value>
+  </property>
+</configuration>