Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 6 Apr 2001 14:31:43 +0100
From:      John <freebsd-questions@i-zone.demon.co.uk>
To:        freebsd-questions@freebsd.org
Subject:   Re: how can you say ufs is faster?
Message-ID:  <20010406143143.A16361@i-zone.demon.co.uk>
In-Reply-To: <13713697115.20010406121725@21cn.com>; from bsddiy@21cn.com on Fri, Apr 06, 2001 at 12:17:25PM %2B0800
References:  <Pine.BSO.4.21.0104012107450.31373-100000@gandalf.bravenet.com> <13713697115.20010406121725@21cn.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Apr 06, 2001 at 12:17:25PM +0800, David Xu wrote:
> Hello Dan,
> 
> Monday, April 02, 2001, 12:14:17 PM, you wrote:
> 
> DP> I am not disagreeing with you for your case study or OS for that matter as
> DP> I do prefer freebsd much over linux anyday. IN a test I did where qmail
> DP> was overloaded with mail on both a linux fs then a freebsd fs, linux fs
> DP> outperformed freebsd no problems. Ufs , maybe i am wrong but is way slower
> DP> when writing to files. Maybe reading sure.....but i am convinced writing
> DP> there is no way. What i ended up doing was just striping 3 scsi drives
> DP> together with vinum on freebsd because i try not to use linux unless
> DP> SMP is a major factor. IF you look over current SMP code in kernel
> DP> i can say linux and solaris do it way better......and there is no way fbsd
> DP> can do it without a complete re-write of kernel which they are promising
> DP> in  5.0....but we will see. I really question your benchmark program....
> DP> what do you use and your stats were based on more than 1 benchmark test
> DP> right?
> 
> evaluting a FS performance is difficult, I don't think ext2fs is
> fast, you may not test deleting large file in ext2fs, it is a slowest
> file system I ever saw, but UFS in FreeBSD is very fast at removing a

Hi.

In order to compare like with like, set the ufs in fstab to async. This is 
enabled automatically on linux systems but not on freebsd (as far as I 
remember). You do it like this:

/dev/yourdrive       /               ufs     rw,async        1       1
/dev/yourotherdrive  /usr            ufs     rw,async        2       2

note the async. I do it for all drives apart from /proc which causes 
weirdness, nfs, swap and cdrom.

I beleive there is a small but non-zero risk of data loss in certain 
situations with this setting, but I have been using it since 2.2.8 and 
haven't had a problem.


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-questions" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010406143143.A16361>