Re: [jgroups-dev] jgroup cluster - throughput is not increased
krishna <[email protected]> Mon, 21 Apr 2014 22:27:07 -0700 (PDT)
| Newsgroups | gmane.comp.java.javagroups.devel |
|---|---|
| Message-ID | <[email protected]> |
i want to measure the number of messages processed by the each java instance. Scenario i have a batch job when running in a standalone jvm , is able to process 220 messsages per second. absolutely there is no bottle neck either in application layer or oracle database layer. i profilled and verifed the thread dumps for the run. i want to increase the throughput further, then i created a jgroups cluster with two nodes. But to my surprise the throughput is still only at 240 per second, i expected a big jump in throughput because now the batch is running with 2 nodes and there are no synchronization issues. the configuration i used in both the nodes is as follows. -Djava.net.preferIPv4Stack=true -Djgroups.start_port=8100 -Djgroups.bind_addr=172.19.112.232 -Djgroups.tcpping.initial_hosts=172.19.112.232[8100],172.19.112.234[8101] i am using the default tcp.xml for the configuration, similarly i tested with 2.12 but the performance is not improved. even i changed the property enable_bundling from true to false because i a using old jar, but there is no fruitful results. -- View this message in context: http://jgroups.1086181.n5.nabble.com/jgroup-cluster-throughput-is-not-increased-tp10150p10153.html Sent from the JGroups - Dev mailing list archive at Nabble.com. ------------------------------------------------------------------------------ Start Your Social Network Today - Download eXo Platform Build your Enterprise Intranet with eXo Platform Software Java Based Open Source Intranet - Social, Extensible, Cloud Ready Get Started Now And Turn Your Intranet Into A Collaboration Platform http://p.sf.net/sfu/ExoPlatform _______________________________________________ Javagroups-development mailing list