[infinispan-issues] [JBoss JIRA] (ISPN-2015) Upgrade to Netty 3.4.2 when ready

Norman Maurer (JIRA) jira-events at lists.jboss.org
Wed May 2 04:19:20 EDT 2012


    [ https://issues.jboss.org/browse/ISPN-2015?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12689382#comment-12689382 ] 

Norman Maurer commented on ISPN-2015:
-------------------------------------

@Galder I took some time today to benchmark and I must say that I can not see a performance drop. I even had some performance gain with 3.4.2.Final here ( but its really small). Maybe it depends on the cpu count ?

I tested with two infinispan distributions. 
1) git reset --hard de4d48b7c0c4d91e2886e4130cf589e66d7888de (which is exactly one commit before upgrade to netty 3.4.2.Final)
2) git checkout t_2015_m
                
> Upgrade to Netty 3.4.2 when ready
> ---------------------------------
>
>                 Key: ISPN-2015
>                 URL: https://issues.jboss.org/browse/ISPN-2015
>             Project: Infinispan
>          Issue Type: Component  Upgrade
>          Components: Cache Server
>    Affects Versions: 5.1.3.FINAL
>            Reporter: Galder ZamarreƱo
>            Assignee: Galder ZamarreƱo
>             Fix For: 5.1.x, 5.2.0.FINAL
>
>
> According to Norman, there's some important memory optimisations coming in this version, that should in theory allow us to get rid of the custom replaying decoder.
> I'll do the upgrade in a separate branch and I'll pass on to QE to run:
> * Data stress tests and compare with current version
> * Client stress tests and compare with native Memcached and previous versions
> Depending on the results of this, we can potentially consider doing the upgrade in 5.1.x.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.jboss.org/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

       



More information about the infinispan-issues mailing list