Date: Fri, 16 Mar 2007 10:27:50 -0300 From: Marcelo Gardini do Amaral <marcelo@registro.br> To: Robert Watson <rwatson@FreeBSD.org> Cc: freebsd-performance@freebsd.org, Peter_Losher@isc.org, jad@nominet.org.uk Subject: Re: MFC of UDP socket performance test Message-ID: <20070316132750.GK82003@registro.br> In-Reply-To: <20070316122605.G7579@fledge.watson.org> References: <20070315213731.GI82003@registro.br> <20070316122605.G7579@fledge.watson.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Mar 16, 2007 at 12:27:24PM +0100, Robert Watson wrote: > > On Thu, 15 Mar 2007, Marcelo Gardini do Amaral wrote: > > >I repeated that performance test done with bind [1] using now Robert's MFC > >[2]. Another tweak that I was supposed to do was to use libthr instead of > >libpthread (via libmap.conf) and build bind with threads option. In the > >new test I did this. > > > >I used the same methodology, same zone file and same server hardware that > >I used in [3]. > > Whether this patch improves performance or not will depend on the nature of > the workload and hardware configuration. It will only help on CPU-bound > multiprocessor systems, which probably describes top level domain name > servers well, but may describe less loaded systems less well. I'm not sure > what configuration Jinmei was using specifically in his testing and > evaluation; since Jinmei is about to become a FreeBSD developer, hopefully > we can get him involved further in this conversation. Great. I will repeat the test with a larger zone, like a top level domain name. If I see improvement with the patch, I will let you know guys. -- Att., Marcelo Gardini NIC .br
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070316132750.GK82003>