Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 14 Jun 2001 01:10:17 +0200
From:      Brad Knowles <brad.knowles@skynet.be>
To:        Giorgos Keramidas <keramida@ceid.upatras.gr>, Jonathan Fortin <jfortin@akalink.com>
Cc:        freebsd-chat@FreeBSD.ORG
Subject:   Re: Sysadmin Article --Which OS is Fastest for High-Performance Network Applications?
Message-ID:  <p0510032bb74da27c1e24@[194.78.241.123]>
In-Reply-To: <20010613232626.H69527@hades.hell.gr>
References:  <SAK.2001.06.13.okngmgad@support10> <00e901c0f43a$9aced2a0$13a86395@alink> <20010613232626.H69527@hades.hell.gr>

next in thread | previous in thread | raw e-mail | index | archive | help
At 11:26 PM +0300 6/13/01, Giorgos Keramidas wrote:

>  o  I am not sure if you do have an option in linux to mount
>     filesystems with synchronous writes.

	Yes, Linux does have this option.  Moreover, you can use "chattr" 
to cause all writes to a particular directory (not necessarily a 
mount point or entire filesystem) to be synchronous.  However, doing 
this absolutely bloody kills performance (at least, in the tests I've 
run), and therefore almost no one ever does it.

>  o  "Where are the raw numbers?"
>     This is usually a killer question, for such statements.
>     No, no, no, simply stating "I've done my tests and have reached the
>     conclusion that BSD is 4 times slower" means absolutely NOTHING to
>     me.  I am a man of numbers.  Hit me with a huge pile o' them.
>     Only then I might consider such statemets a bit more seriously.

	Absolutely.  Not only show me the numbers, but also show me the 
programs that were used to run the benchmarks.  This was a 
significant part of my talk "Design and Implementation of Highly 
Scalable E-Mail Systems" that I gave at LISA 2000 (see 
<http://www.shub-internet.org/brad/papers/dihses/>).

	Indeed, without giving us both the raw numbers and the details of 
the programs used for testing (and the other circumstances of the 
test), any numbers he could possibly generate are totally and 
absolutely worthless in the extreme.

-- 
Brad Knowles, <brad.knowles@skynet.be>

/*        efdtt.c  Author:  Charles M. Hannum <root@ihack.net>          */
/*       Represented as 1045 digit prime number by Phil Carmody         */
/*     Prime as DNS cname chain by Roy Arends and Walter Belgers        */
/*                                                                      */
/*     Usage is:  cat title-key scrambled.vob | efdtt >clear.vob        */
/*   where title-key = "153 2 8 105 225" or other similar 5-byte key    */

dig decss.friet.org|perl -ne'if(/^x/){s/[x.]//g;print pack(H124,$_)}'

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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?p0510032bb74da27c1e24>