Date: Sun, 24 Mar 2013 09:11:53 +0100 From: Davide D'Amico <davide.damico@contactlab.com> To: Daniel Bilik <daniel.bilik@neosystem.cz> Cc: freebsd-performance@freebsd.org Subject: Re: FreeBSD 9.1 vs CentOS 6.3 Message-ID: <f6c080db-4f32-4d4f-966a-b0af4a8c9b99@email.android.com> In-Reply-To: <20130324083802.8289efb593ff186bd358cb87@neosystem.cz> References: <514C1E5F.8040504@contactlab.com> <CAF3xD3nDDUYB94TS9AUUQ=CPztB1S8mU4fRwNB5GupmK8MgwXg@mail.gmail.com> <142597a8659b43db8665aa1f055d2ff1@sys.tomatointeractive.it> <20130324083802.8289efb593ff186bd358cb87@neosystem.cz>
next in thread | previous in thread | raw e-mail | index | archive | help
Ok, I'll try tomorrow and I'll post results here. Some particular parameter to use? Daniel Bilik <daniel.bilik@neosystem.cz> ha scritto: >On Sun, 24 Mar 2013 06:59:29 +0100 >Davide D'Amico <davide.damico@contactlab.com> wrote: > >> I'll try the 'simple' dataset, but do you think I have some chance to > >> "solve" the issue? > >Not sure. But in case you'll get much more similar (CentOS vs. FreeBSD) >results from "simple" OLTP test, as opposed to very differrent numbers >for "complex", it's probable that the cause can be somewhere in >jemalloc, >as we've observed in our tests. And at this point, we can rule out >anything else (ZFS, scheduler, etc.) and knowledgeable people can focus >on one specific piece of code. > >-- > Daniel Bilik > neosystem.cz -- d.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?f6c080db-4f32-4d4f-966a-b0af4a8c9b99>