Author: gourksaha
Date: Tue Nov 11 19:13:25 2014
New Revision: 1638285
URL: http://svn.apache.org/r1638285
Log:
RM, NN HA and RM NM work preserving restart
Modified:
incubator/slider/site/trunk/content/docs/high_availability.md
Modified: incubator/slider/site/trunk/content/docs/high_availability.md
URL:
http://svn.apache.org/viewvc/incubator/slider/site/trunk/content/docs/high_availability.md?rev=1638285&r1=1638284&r2=1638285&view=diff
==============================================================================
--- incubator/slider/site/trunk/content/docs/high_availability.md (original)
+++ incubator/slider/site/trunk/content/docs/high_availability.md Tue Nov 11
19:13:25 2014
@@ -16,8 +16,102 @@ Notice: Licensed to the Apache Softwa
specific language governing permissions and limitations
under the License.
-#High Availability: Setup RM HA, NN HA, Work Preserving RM and Work Preserving
NM
-Setting up High Availability ensures uninterrupted service provided by long
running applications installed by Slider
-in the event of Resource Manager or Name Node failure. This document provides
an overview of High Availability
-of YARN's ResourceManager, and details how to configure and use this feature.
+# High Availability: Setup Resource Manager HA, Name Node HA, work preserving
Resource Manager restart and work preserving Node Manager restart.
+
+Setting up High Availability ensures uninterrupted service provided
+by long running applications installed by Slider in the event of any or all of
Resource Manager, Name Node
+and Node Manager failure. This document provides
+details on how to configure YARN's RM HA.
+
+Following are the properties required to be set as YARN properties in order to
setup:
+
+### Resource Manager HA
+
+ <property>
+ <name>yarn.resourcemanager.ha.enabled</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.ha.rm-ids</name>
+ <value>rm1,rm2</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.hostname.rm1</name>
+ <value>192.168.1.9</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.hostname.rm2</name>
+ <value>192.168.1.10</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.recovery.enabled</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.store.class</name>
+
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.zk-address</name>
+ <value>192.168.1.9:2181,192.168.1.10:2181</value>
+ <description>For multiple zk services, separate them with
comma</description>
+ </property>
+
+ <property>
+ <name>yarn.resourcemanager.cluster-id</name>
+ <value>yarn-cluster</value>
+ </property>
+
+
+### Name Node HA
+
+ TODO
+
+### Work Preserving RM Restart
+
+ <property>
+ <description>Enable RM to recover state after starting. If true,
then yarn.resourcemanager.store.class must be specified</description>
+ <name>yarn.resourcemanager.recovery.enabled</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <description>Enable RM work preserving recovery. This
configuration is private to YARN for experimenting the feature. NOTE: this
config has to be set on both RM and ALL NMs. </description>
+
<name>yarn.resourcemanager.workÂpreservingÂrecovery.enabled</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <description>The class to use as the persistent
store.</description>
+ <name>yarn.resourcemanager.store.class</name>
+
<!ÂÂvalue>org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore</valueÂ-->
+
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
+ </property>
+
+ <property>
+ <description>Host:Port of the ZooKeeper server where RM state
will be stored. This must be supplied when using
org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore as the
value for yarn.resourcemanager.store.class</description>
+ <name>yarn.resourcemanager.zkÂaddress</name>
+ <value>127.0.0.1:2181</value>
+ </property>
+
+
+### Work Preserving NM Restart
+
+ <property>
+ <description>Enable the node manager to recover after
starting</description>
+ <name>yarn.nodemanager.recovery.enabled</name>
+ <value>false</value>
+ </property>
+
+ <property>
+ <description>The local filesystem directory in which the node
manager will store state when recovery is enabled.</description>
+ <name>yarn.nodemanager.recovery.dir</name>
+ <value>${hadoop.tmp.dir}/yarn-nm-recovery</value>
+ </property>