Date: Fri, 1 Jun 2001 15:45:23 +0200 From: "Karsten W. Rohrbach" <karsten@rohrbach.de> To: Alexander Langer <alex@big.endian.de>, chat@FreeBSD.ORG Subject: Re: interesting os comparison charts Message-ID: <20010601154523.A10477@mail.webmonster.de> In-Reply-To: <20010531233829.A58131@zerogravity.kawo2.rwth-aachen.d>; from alex@big.endian.de on Thu, May 31, 2001 at 11:38:29PM %2B0200 References: <20010529214403.L85298@mail.webmonster.de> <20010530205056.G29853@mail.webmonster.de> <20010530210351.C65759@rapier.smartspace.co.za> <20010531233829.A58131@zerogravity.kawo2.rwth-aachen.d>
next in thread | previous in thread | raw e-mail | index | archive | help
--rwEMma7ioTxnRzrJ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Alexander Langer(alex@big.endian.de)@2001.05.31 23:38:29 +0000: > Thus spake Neil Blakey-Milner (nbm@mithrandr.moria.org): >=20 > > I'm reasonably famous for being the cause for better network performance > > at my university society. ;) >=20 > btw, what is a recommended value for a webserver with average load? value for what? MAXUSERS? NMBCLUSTERS? cpu core voltage? i have the core on high capacity servers running at 110 volts which leads to transaction times of one tenth and less compared with the standard setting of 2.0 volts ;-) no, seriously, what machine in terms of cpu/ram and network connectivity, what server software (apache/...), applications (php/mod_python), database, how many object requests per sec? session support? etc... i had one smp box with 2* piii-500 and a gig of ram, 3 fxp cards and apache running with ~5000 object requests/sec (http), mean object size was around 1k (a lot of interface graphics) and it kept going that way at a load of >900 for one week until the loadbalancer was delivered and we started pulling the web site apart onto several boxes ;-) the database load of the mysql server in the background was the problem in the first place so we split that up to another box first. well, things like FD_SETSIZE are the biggest problem there i think. with MAXUSERS=3D256 and NMBCLUSTERS=3D32768 and some minor tweaks the box ran. the shell was a little slow but every http transfer was fast like hell, i guess this behaviour is caused by apache using sendfile(). please Cc: me in replies, i am not on -chat /k --=20 > Jesus died for your sins. Make it worth his time. KR433/KR11-RIPE -- WebMonster Community Founder -- nGENn GmbH Senior Techie http://www.webmonster.de/ -- ftp://ftp.webmonster.de/ -- http://www.ngenn.n= et/ karsten&rohrbach.de -- alpha&ngenn.net -- alpha&scene.org -- catch@spam.de GnuPG 0x2964BF46 2001-03-15 42F9 9FFF 50D4 2F38 DBEE DF22 3340 4F4E 2964 B= F46 --rwEMma7ioTxnRzrJ Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.0.6 (FreeBSD) Comment: For info see http://www.gnupg.org iD8DBQE7F5xzM0BPTilkv0YRArt1AJ447gq4A+GOzFzpngj1Amj6i5EuRgCfW/O8 yJxhMPJ0UHMu8M/3SNS2wxk= =J9q4 -----END PGP SIGNATURE----- --rwEMma7ioTxnRzrJ-- 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?20010601154523.A10477>