Hi Radim, On 06/13/2013 09:24 AM, Radim Vansa wrote: > Seems that it's somewhat better (6050 writes/s) but not at the previous level.
during this run, have you used the old bundler in JGroups? > I am trying to cherry-pick it directly on the commit that failed it and see > where is the difference, then maybe I'll have to generate alternative branch > with ISPN-3221 commit after ISPN-2848 > 73da108cdcf9db4f3edbcd6dbda6938d6e45d148 and iterate to next regression > origin. > > Pedro: I've noticed that in JGroupsTransport:577 you're changing the third > parameter of CommandAwareRpcDispatcher.constructMessage from false (as found > in 113842c8cf91cbb5a1bbd26e05fab7024fdec081) to true (as appears in later > commits), is this desired? It was not changed by me but yes I think that is ok. See ISPN-3043 (https://issues.jboss.org/browse/ISPN-3043) Cheers, Pedro ps. it's holiday in Lisbon so I'll not be online all day. > > Radim > > ----- Original Message ----- > | From: "Mircea Markus" <mmar...@redhat.com> > | To: "infinispan -Dev List" <infinispan-dev@lists.jboss.org> > | Sent: Wednesday, June 12, 2013 5:51:13 PM > | Subject: Re: [infinispan-dev] New bundler performance > | > | Radim, can you please give Pedro's branch a try? > | https://github.com/infinispan/infinispan/pull/1896 > | If all good we'll release CR2 from that one. > | > | On 12 Jun 2013, at 16:02, Bela Ban <b...@redhat.com> wrote: > | > > | > > | > On 06/12/2013 10:57 AM, Mircea Markus wrote: > | > > | >>> I think we should treat this as a bug and I'll look into this, but I > | >>> won't have much time until after JBW. If you want to write code that can > | >>> handle both old and new bundler, that would be good, although that code > | >>> should be removed after the bug has been fixed. > | >> The only thing I'm aware of that's needed to support old bundling is to > | >> add DONT_BUNDLE to sync messages, which seems pretty straight forward. > | >> I remember discussing that DONT_BUNDLE + sync messages + new bundler is > | >> suboptimal for some reason (batching?) - am I wrong saying that? > | > > | > > | > This will generate more messages than necessary if multiple threads are > | > invoking sync RPCs, but other than that it should be ok. The main > | > advantage of the new bundler is that we can remove the need for > | > DONT_BUNDLE. > | > > | > > | >> We're currently holding the 5.3.0.CR2 release for this. I'm thinking to: > | >> - support old bundling as well > | >> - based on the when the jgroups perf problem is fixed we might release > CR3 > | >> or include the fix in 5.3.1.Final > | > > | > OK, sounds good > | > > | > -- > | > Bela Ban > | > Lead JGroups / Clustering Team > | > JBoss > | > _______________________________________________ > | > infinispan-dev mailing list > | > infinispan-dev@lists.jboss.org > | > https://lists.jboss.org/mailman/listinfo/infinispan-dev > | > | Cheers, > | -- > | Mircea Markus > | Infinispan lead (www.infinispan.org) > | > | > | > | > | > | _______________________________________________ > | infinispan-dev mailing list > | infinispan-dev@lists.jboss.org > | https://lists.jboss.org/mailman/listinfo/infinispan-dev > | > _______________________________________________ > infinispan-dev mailing list > infinispan-dev@lists.jboss.org > https://lists.jboss.org/mailman/listinfo/infinispan-dev > _______________________________________________ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
