Date: Thu, 18 Nov 2004 19:34:11 -0800 From: Aaron Glenn <aaron.glenn@gmail.com> To: Luke <lukem@cse.unsw.edu.au> Cc: freebsd-performance@freebsd.org Subject: Re: I've ran out of ideas Message-ID: <18f6019404111819343f2a7967@mail.gmail.com> In-Reply-To: <Pine.LNX.4.61.0411191411400.11282@wagner.orchestra.cse.unsw.EDU.AU> References: <20041118101026.55888.qmail@web14121.mail.yahoo.com> <20041118105543.10295.qmail@web41208.mail.yahoo.com> <18f6019404111809224fb97c06@mail.gmail.com> <Pine.LNX.4.61.0411191006310.5596@wagner.orchestra.cse.unsw.EDU.AU> <18f6019404111817533b93cbba@mail.gmail.com> <Pine.LNX.4.61.0411191411400.11282@wagner.orchestra.cse.unsw.EDU.AU>
index | next in thread | previous in thread | raw e-mail
On Fri, 19 Nov 2004 14:16:51 +1100 (EST), Luke <lukem@cse.unsw.edu.au> wrote: > Increasing the block size of the disk need not imply that the application > is issuing larger reads. Hmm, true. > I have not suggested that you increase the blocksize further. Please read > the above points again. > > As Sean pointed out, if your web server supports sendfile then that would > be a good option. Indeed I misread your email. I do have some sort optimized thttpd package that was sent to me off list. I'll try that out in a few minutes here. I'm also searching for the patch on arch@ that Sean mentioned. > Your recent post which showed poor performance from /dev/zero does bring > the theory that your disk is the bottleneck into question, however you may > still find it is worth trying the above suggestions. I neglected to mention those numbers were taken while pushing 45Mbps out the network. If you add them up you get 93Mbps. aaron.glennhome | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?18f6019404111819343f2a7967>