From d6d2ff82069a4b6dc12d9f3f3f3c64dd4d4bfbea Mon Sep 17 00:00:00 2001 From: Arun Murthy Date: Mon, 31 Oct 2011 17:34:25 +0000 Subject: [PATCH] Merge -c 1195579 from trunk to branch-0.23 to fix MAPREDUCE-3275. git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-0.23@1195581 13f79535-47bb-0310-9956-ffa450edef68 --- hadoop-mapreduce-project/CHANGES.txt | 3 + .../src/site/apt/ClusterSetup.apt.vm | 70 +++++++++++++++++-- 2 files changed, 67 insertions(+), 6 deletions(-) diff --git a/hadoop-mapreduce-project/CHANGES.txt b/hadoop-mapreduce-project/CHANGES.txt index fc921fff0d3..06c2cda558f 100644 --- a/hadoop-mapreduce-project/CHANGES.txt +++ b/hadoop-mapreduce-project/CHANGES.txt @@ -407,6 +407,9 @@ Release 0.23.0 - Unreleased MAPREDUCE-3146. Added a MR specific command line to dump logs for a given TaskAttemptID. (Siddharth Seth via vinodkv) + MAPREDUCE-3275. Added documentation for AM WebApp Proxy. (Robert Evans via + acmurthy) + OPTIMIZATIONS MAPREDUCE-2026. Make JobTracker.getJobCounters() and diff --git a/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-site/src/site/apt/ClusterSetup.apt.vm b/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-site/src/site/apt/ClusterSetup.apt.vm index 5ce75d21d07..4643faecbd9 100644 --- a/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-site/src/site/apt/ClusterSetup.apt.vm +++ b/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-site/src/site/apt/ClusterSetup.apt.vm @@ -100,6 +100,8 @@ Hadoop MapReduce Next Generation - Cluster Setup | ResourceManager | YARN_RESOURCEMANAGER_OPTS | *--------------------------------------+--------------------------------------+ | NodeManager | YARN_NODEMANAGER_OPTS | +*--------------------------------------+--------------------------------------+ +| WebAppProxy | YARN_PROXYSERVER_OPTS | *--------------------------------------+--------------------------------------+ For example, To configure Namenode to use parallelGC, the following @@ -450,9 +452,16 @@ Hadoop MapReduce Next Generation - Cluster Setup Run a script to start NodeManagers on all slaves: ---- - $ $YARN_HOME/bin/hdfs start nodemanager --config $HADOOP_CONF_DIR + $ $YARN_HOME/bin/yarn start nodemanager --config $HADOOP_CONF_DIR ---- + Start a standalone WebAppProxy server. If multiple servers + are used with load balancing it should be run on each of them: + +---- + $ $YARN_HOME/bin/yarn start proxyserver --config $HADOOP_CONF_DIR +---- + Start the MapReduce JobHistory Server with the following command, run on the designated server: @@ -485,9 +494,17 @@ Hadoop MapReduce Next Generation - Cluster Setup Run a script to stop NodeManagers on all slaves: ---- - $ $YARN_HOME/bin/hdfs stop nodemanager --config $HADOOP_CONF_DIR + $ $YARN_HOME/bin/yarn stop nodemanager --config $HADOOP_CONF_DIR ---- + Stop the WebAppProxy server. If multiple servers are used with load + balancing it should be run on each of them: + +---- + $ $YARN_HOME/bin/yarn stop proxyserver --config $HADOOP_CONF_DIR +---- + + Stop the MapReduce JobHistory Server with the following command, run on the designated server: @@ -502,7 +519,7 @@ Hadoop MapReduce Next Generation - Cluster Setup to run Hadoop in <> with strong, Kerberos-based authentication. - * <<>> + * <<>> Ensure that HDFS and YARN daemons run as different Unix users, for e.g. <<>> and <<>>. Also, ensure that the MapReduce JobHistory @@ -751,6 +768,31 @@ KVNO Timestamp Principal * <<>> + * WebAppProxy + + The <<>> provides a proxy between the web applications + exported by an application and an end user. If security is enabled + it will warn users before accessing a potentially unsafe web application. + Authentication and authorization using the proxy is handled just like + any other privileged web application. + +*-------------------------+-------------------------+------------------------+ +|| Parameter || Value || Notes | +*-------------------------+-------------------------+------------------------+ +| <<>> | | | +| | <<>> host:port for proxy to AM web apps. | | +| | | if this is the same as <<>>| +| | | or it is not defined then the <<>> will run the proxy| +| | | otherwise a standalone proxy server will need to be launched.| +*-------------------------+-------------------------+------------------------+ +| <<>> | | | +| | | | +| | | Kerberos keytab file for the WebAppProxy. | +*-------------------------+-------------------------+------------------------+ +| <<>> | wap/_HOST@REALM.TLD | | +| | | Kerberos principal name for the WebAppProxy. | +*-------------------------+-------------------------+------------------------+ + * LinuxContainerExecutor A <<>> used by YARN framework which define how any @@ -968,7 +1010,15 @@ KVNO Timestamp Principal Run a script to start NodeManagers on all slaves as : ---- -[yarn]$ $YARN_HOME/bin/hdfs start nodemanager --config $HADOOP_CONF_DIR +[yarn]$ $YARN_HOME/bin/yarn start nodemanager --config $HADOOP_CONF_DIR +---- + + Start a standalone WebAppProxy server. Run on the WebAppProxy + server as . If multiple servers are used with load balancing + it should be run on each of them: + +---- +[yarn]$ $YARN_HOME/bin/yarn start proxyserver --config $HADOOP_CONF_DIR ---- Start the MapReduce JobHistory Server with the following command, run on the @@ -1003,12 +1053,20 @@ KVNO Timestamp Principal Run a script to stop NodeManagers on all slaves as : ---- -[yarn]$ $YARN_HOME/bin/hdfs stop nodemanager --config $HADOOP_CONF_DIR +[yarn]$ $YARN_HOME/bin/yarn stop nodemanager --config $HADOOP_CONF_DIR ---- + Stop the WebAppProxy server. Run on the WebAppProxy server as + . If multiple servers are used with load balancing it + should be run on each of them: + +---- +[yarn]$ $YARN_HOME/bin/yarn stop proxyserver --config $HADOOP_CONF_DIR +---- + Stop the MapReduce JobHistory Server with the following command, run on the designated server as : - + ---- [mapred]$ $YARN_HOME/bin/yarn stop historyserver --config $HADOOP_CONF_DIR ----