Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 24 Apr 2001 11:47:24 -0500
From:      Douglas Egan <degan@calcon.net>
To:        questions@FreeBSD.ORG
Subject:   Re: How Is The FeeBSD OS Like and Different Than Say Redhat or Suse  LINUX
Message-ID:  <3AE5AE1C.AE5DF04A@calcon.net>
References:  <15077.43308.609040.214405@guru.mired.org>

next in thread | previous in thread | raw e-mail | index | archive | help
I have found that most linux filesystems benchmarks have been run with the
standard "async" mount option for the filesystem under test.

The only way I have found to benchmark and compare apples to apples is to mount
the linux fs as sync and also mount the bsd fs as sync (both async).  This way
all data and metadata are written synchronously and should allow a worst case
filesystem/driver test and comparison.

Or mount them both async as described below.

The defaults of the 2 are definitely not equivalent.

Doug Egan

Mike Meyer wrote:

> Dave Leimbach <dleimbac@earthlink.net> types:
> > FreeBSD 4.2 still beats linux in every network benchmark except email
> > handling... <don't know why there.... :)> even in the 2.4.x kernels.
>
> It's probably the file system, which email handling exercies
> heavily. Linux runs their file systems in async mode by default (I'm
> not sure if this can be fixed), which makes the file system faster but
> less robust. If you're doing benchmarks, you can mount FreeBSD file
> systems async so long as you don't have softupdates enabled on the
> file system.
>
>         <mike
> --
> Mike Meyer <mwm@mired.org>                      http://www.mired.org/home/mwm/
> Independent WWW/Perforce/FreeBSD/Unix consultant, email for more information.
>
> To Unsubscribe: send mail to majordomo@FreeBSD.org
> with "unsubscribe freebsd-questions" in the body of the message


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?3AE5AE1C.AE5DF04A>