Date: Wed, 26 Oct 2005 16:09:31 +0100 From: Joao Barros <joao.barros@gmail.com> To: Alexander Leidinger <Alexander@leidinger.net> Cc: freebsd-current@freebsd.org, Robert Atkinson <phreaki@gmail.com>, Samuel Clements <sclements@linkline.com> Subject: Re: Poor Samba throughput on 6.0 RC1 Message-ID: <70e8236f0510260809j7612cf4di5d7bb00c986efa0c@mail.gmail.com> In-Reply-To: <20051026163759.hlvgwsmbokswk8ww@netchild.homeip.net> References: <70e8236f0510241518x7b280938jd15f7e8c3224cbd@mail.gmail.com> <435D64B2.2020703@linkline.com> <6fb2b4650510242021l72a1ceb9m91e72a0420458982@mail.gmail.com> <70e8236f0510251636k1002cc96yd357492a138e1933@mail.gmail.com> <20051026163759.hlvgwsmbokswk8ww@netchild.homeip.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 10/26/05, Alexander Leidinger <Alexander@leidinger.net> wrote: > I haven't read the entire thread, but by looking at this I assume there's > another FS than NTFS involved. Benchmarking with NTFS (or MSDOSFS) as the > underlying FS doesn't make sense (unless you want to measure the performa= nce > of NTFS or MSDOSFS), since it's slow (for NTFS you should be happy to at > least be able to read something, there's no open documentation about it > available). > > So I suggest you try with a good FS (ufs 1 or 2) only and don't bother ab= out > NTFS, to make sure the FS isn't the bottleneck. > > Bye, > Alexander. Your right, you didn't read the entire thread :D My first test was with ufs. I just popped an IDE disk into the machine to have means to compare. /dev/da0s1a on / (ufs, local) devfs on /dev (devfs, local) /dev/da0s1e on /tmp (ufs, local, soft-updates) /dev/da0s1f on /usr (ufs, local, soft-updates) /dev/da0s1d on /var (ufs, local, soft-updates) /dev/amrd0s1c on /storage (ufs, local, soft-updates) /dev/ad0s1 on /mnt/temp (ntfs, local) -- Joao Barros
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?70e8236f0510260809j7612cf4di5d7bb00c986efa0c>