[Top] [All Lists]

Re: benchmarks

To: s-luppescu@xxxxxxxxxxxx
Subject: Re: benchmarks
From: Steve Lord <lord@xxxxxxx>
Date: Fri, 13 Jul 2001 10:50:42 -0500
Cc: Seth Mos <knuffie@xxxxxxxxx>, linux-xfs@xxxxxxxxxxx, "P.Dixon" <P.Dixon@xxxxxxxxx>
Comments: In-reply-to s-luppescu@uchicago.edu message dated "Fri, 13 Jul 2001 10:42:23 -0500."
References: <XFMail.20010713104223.s-luppescu@uchicago.edu>
Sender: owner-linux-xfs@xxxxxxxxxxx
> On 13-Jul-2001 Seth Mos wrote:
> > At 09:23 13-7-2001 +0100, P.Dixon wrote:
> >>Hello,
> >>
> >>Any idea why xfs appears to be very much slower than reiserfs with these
> >>benchmarks:
> >>
> >>http://www.namesys.com/benchmarks/mongo/2.4.5-xfs-ext2_vs_reiserfs.html
> >>
> >>Admittedly, the benchmarks were done by namesys...
> > 
> > I don't know what mount options were used.
> > if you have enough memory and mount the fs with logbufs=8 or 4 it goes
> > faster.
> > use mkfs -t xfs -l size=32768b /dev/hdn to create a larger log for 
> > increased speed.
> This is very interesting, but as I've already made my filesystem (and don't
> relish the thought of wiping it out and doing it over again) the option on mk
> fs
> is not useful to me. But I might be able to use the logbufs option. Do I just
> put it in my /etc/fstab file and then reboot? How much memory is ``enough''?
> How do I tell how many log buffers I've got at present?

An external log is growable, an internal one unfortunately is not, and
we keep kicking SGI support people who build multi-terabyte filesystems
without reading the man page.

Unless you specified otherwise you have two logbufs, all you need to do
to get the number changed is remount with the new option, so yes, edit
fstab and reboot.

If you use O_SYNC anywhere then osyncisdsync as a mount option will
make xfs O_SYNC behave more like other linux filesystems.


<Prev in Thread] Current Thread [Next in Thread>