Infinispan replication timeout on cluster with 3 nodes
We have a problem with infinispan replication timeout on wildfly 10.1.0 while operating with a cluster configuration with 3 nodes.
We have no problem when run the configuration with 2 nodes but as soon as we add the third nodes, after a while we get the following error:
Exception:org.infinispan.util.concurrent.TimeoutException: Replication timeout for tinnaboo7-c5n000}: org.infinispan.util.concurrent.TimeoutException: Replication timeout for tinnaboo7-c5n000
at org.infinispan.remoting.transport.jgroups.JGroupsTransport.checkRsp(JGroupsTransport.java:801)
at org.infinispan.remoting.transport.jgroups.JGroupsTransport.lambda$invokeRemotelyAsync$1(JGroupsTransport.java:642)
at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:602)
at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1962)
at org.infinispan.remoting.transport.jgroups.RspListFuture.call(RspListFuture.java:47)
at org.infinispan.remoting.transport.jgroups.RspListFuture.call(RspListFuture.java:16)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$201(ScheduledThreadPoolExecutor.java:180)
at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:293)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Following our the infinispan configuration of the standalone.xml:
<subsystem xmlns="urn:jboss:domain:infinispan:4.0">
<cache-container name="server" aliases="singleton cluster" default-cache="default" module="org.wildfly.clustering.server" statistics-enabled="true">
<transport lock-timeout="60000"/>
<replicated-cache name="default" mode="SYNC">
<transaction mode="BATCH"/>
</replicated-cache>
</cache-container>
<cache-container name="web" default-cache="dist" module="org.wildfly.clustering.web.infinispan">
<transport lock-timeout="60000"/>
<distributed-cache name="dist" mode="ASYNC" l1-lifespan="0" owners="2">
<locking isolation="REPEATABLE_READ"/>
<transaction mode="BATCH"/>
<file-store/>
</distributed-cache>
<distributed-cache name="concurrent" mode="SYNC" l1-lifespan="0" owners="2">
<file-store/>
</distributed-cache>
</cache-container>
<cache-container name="ejb" aliases="sfsb" default-cache="dist" module="org.wildfly.clustering.ejb.infinispan">
<transport lock-timeout="60000"/>
<distributed-cache name="dist" mode="ASYNC" l1-lifespan="0" owners="2">
<locking isolation="REPEATABLE_READ"/>
<transaction mode="BATCH"/>
<file-store/>
</distributed-cache>
</cache-container>
<cache-container name="hibernate" default-cache="local-query" module="org.hibernate.infinispan">
<transport lock-timeout="60000"/>
<local-cache name="local-query">
<eviction strategy="LRU" max-entries="10000"/>
<expiration max-idle="100000"/>
</local-cache>
<invalidation-cache name="entity" mode="SYNC">
<transaction mode="NON_XA"/>
<eviction strategy="LRU" max-entries="10000"/>
<expiration max-idle="100000"/>
</invalidation-cache>
<replicated-cache name="timestamps" mode="ASYNC"/>
</cache-container>
</subsystem>
Does any one have had a similar problem and can give me any suggestion how resolve the problem?
Thank you
Best regards