2 Replies Latest reply on Jan 26, 2009 10:44 AM by Parineeta Padgilwar

    Replicated Cache - Failover & Failback

    Parineeta Padgilwar Newbie

      We have a 2 node replicated cache i.e.
      node1 --> application instance 1 --> cache instance 1
      node2 --> application instance 2 --> cache instance 2

      According to the configuration below, everything seems to work fine. i.e when node 1 is shutdown and brought back up, any changes made to cache instance 2 are replicated.

      Problem: - However, what if the application server node is still running, but only the cache instance on node 1 has to be shutdown or crashes. I would think that the application on node 1 can access to the cache on node 2. That does'nt happen though. Is it possible to have a configuration wherein, all the instances in the clustered cache are searched for.

      I even tried the ClusteredCacheLoader as shown in the configuration below, but that does not make a difference. Isi'nt that what ClusteredCacheLoader is used for??

      --------------------------------------------------------------------------------
      <?xml version="1.0" encoding="UTF-8"?>
      
      <!-- ===================================================================== -->
      <!-- -->
      <!-- Sample TreeCache Service Configuration -->
      <!-- -->
      <!-- ===================================================================== -->
      
      <server>
      
       <classpath codebase="./lib" archives="jbosscache-core.jar, jboss-common-core.jar, jgroups.jar"/>
       <!-- ==================================================================== -->
       <!-- Defines TreeCache configuration -->
       <!-- ==================================================================== -->
      
       <mbean code="org.jboss.cache.TreeCache"
       name="jboss.cache:service=TreeCache">
      
       <depends>jboss:service=Naming</depends>
       <depends>jboss:service=TransactionManager</depends>
      
       <!--
       Configure the TransactionManager
       -->
       <attribute name="TransactionManagerLookupClass">org.jboss.cache.transaction.DummyTransactionManagerLookup
       </attribute>
      
       <!--
       Node locking level : SERIALIZABLE
       REPEATABLE_READ (default)
       READ_COMMITTED
       READ_UNCOMMITTED
       NONE
       -->
       <attribute name="IsolationLevel">REPEATABLE_READ</attribute>
      
       <!--
       Valid modes are LOCAL, REPL_ASYNC and REPL_SYNC
       -->
       <attribute name="CacheMode">REPL_SYNC</attribute>
      
       <!--
       Just used for async repl: use a replication queue
       -->
       <attribute name="UseReplQueue">false</attribute>
      
       <!--
       Replication interval for replication queue (in ms)
       -->
       <attribute name="ReplQueueInterval">0</attribute>
      
       <!--
       Max number of elements which trigger replication
       -->
       <attribute name="ReplQueueMaxElements">0</attribute>
      
       <!-- Name of cluster. Needs to be the same for all TreeCache nodes in a
       cluster in order to find each other.
       -->
       <attribute name="ClusterName">JBossCache-Cluster</attribute>
      
       <attribute name="ClusterConfig">
       <config>
       <!-- UDP: if you have a multihomed machine,
       set the bind_addr attribute to the appropriate NIC IP address, e.g bind_addr="192.168.0.2".
       The mcast_addr and mcast_port should be different from the cluster address and port to avoid contention.
       -->
       <!-- UDP: On Windows machines, because of the media sense feature
       being broken with multicast (even after disabling media sense)
       set the loopback attribute to true -->
       <UDP mcast_addr="224.10.10.10" mcast_port="45566"
       ip_ttl="64" ip_mcast="true"
       mcast_send_buf_size="150000" mcast_recv_buf_size="80000"
       ucast_send_buf_size="150000" ucast_recv_buf_size="80000"
       loopback="false" bind_addr="127.0.0.1" bind_port="5544" />
       <PING timeout="2000" num_initial_members="3"
       up_thread="false" down_thread="false"/>
       <MERGE2 min_interval="10000" max_interval="20000"/>
       <!-- <FD shun="true" up_thread="true" down_thread="true" />-->
       <FD_SOCK/>
       <VERIFY_SUSPECT timeout="1500"
       up_thread="false" down_thread="false"/>
       <pbcast.NAKACK gc_lag="50" retransmit_timeout="600,1200,2400,4800"
       max_xmit_size="8192" up_thread="false" down_thread="false"/>
       <UNICAST timeout="600,1200,2400" window_size="100" min_threshold="10"
       down_thread="false"/>
       <pbcast.STABLE desired_avg_gossip="20000"
       up_thread="false" down_thread="false"/>
       <FRAG frag_size="8192"
       down_thread="false" up_thread="false"/>
       <pbcast.GMS join_timeout="5000" join_retry_timeout="2000"
       shun="true" print_local_addr="true"/>
       <pbcast.STATE_TRANSFER up_thread="true" down_thread="true"/>
       </config>
       </attribute>
      
       <!--
       Whether or not to fetch state on joining a cluster
       -->
       <attribute name="FetchStateOnStartup">true</attribute>
      
       <!--
       The max amount of time (in milliseconds) we wait until the
       initial state (ie. the contents of the cache) are retrieved from
       existing members in a clustered environment
       -->
       <attribute name="InitialStateRetrievalTimeout">5000</attribute>
      
       <!--
       The max amount of time (in milliseconds) we wait until the
       state (ie. the contents of the cache) are retrieved from
       existing members in a clustered environment
       -->
       <attribute name="StateRetrievalTimeout">20000</attribute>
      
       <!--
       Number of milliseconds to wait until all responses for a
       synchronous call have been received.
       -->
       <attribute name="SyncReplTimeout">20000</attribute>
      
       <!-- Max number of milliseconds to wait for a lock acquisition -->
       <attribute name="CacheLoaderConfig" replace="false">
       <config>
       <cacheloader>
       <class>org.jboss.cache.loader.ClusteredCacheLoader</class>
       <properties>
       timeout=15000
       </properties>
       </cacheloader>
       </config>
       </attribute>
       </mbean>
      </server>
      ------------------------------------------------------------------------------------