Date: Wed, 13 Jun 2001 22:09:20 -0400 From: "Jonathan Fortin" <jfortin@akalink.com> To: <freebsd-chat@freebsd.org> Subject: Re: Sysadmin Article --Which OS is Fastest for High-Performance Network Applications? Message-ID: <003a01c0f477$06ec2a00$08ac6395@alink> References: <SAK.2001.06.13.okngmgad@support10> <00e901c0f43a$9aced2a0$13a86395@alink> <20010613232626.H69527@hades.hell.gr> <p0510032bb74da27c1e24@[194.78.241.123]>
next in thread | previous in thread | raw e-mail | index | archive | help
Ok say if the Fastest network application is Linux for a second, then why would you want it anyway? say It is 10x faster then anything else, It will have 10x more downtime once script kiddies take control of such a security disaster. Irony is as follows, Linux is mounted async by default and their babbling about it's speed in email, but once linux crashes, you could say byebye mail queue! ----- Original Message ----- From: "Brad Knowles" <brad.knowles@skynet.be> To: "Giorgos Keramidas" <keramida@ceid.upatras.gr>; "Jonathan Fortin" <jfortin@akalink.com> Cc: <freebsd-chat@FreeBSD.ORG> Sent: Wednesday, June 13, 2001 7:10 PM Subject: Re: Sysadmin Article --Which OS is Fastest for High-Performance Network Applications? > 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 > 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?003a01c0f477$06ec2a00$08ac6395>