From owner-freebsd-hackers Sun Jun 17 16:15:17 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from smtp5ve.mailsrvcs.net (smtp5vepub.gte.net [206.46.170.26]) by hub.freebsd.org (Postfix) with ESMTP id 468A437B403 for ; Sun, 17 Jun 2001 16:15:09 -0700 (PDT) (envelope-from babkin@bellatlantic.net) Received: from bellatlantic.net (client-151-198-117-204.nnj.dialup.bellatlantic.net [151.198.117.204]) by smtp5ve.mailsrvcs.net (8.9.1/8.9.1) with ESMTP id XAA17415043; Sun, 17 Jun 2001 23:14:54 GMT Message-ID: <3B2D39ED.EE27976A@bellatlantic.net> Date: Sun, 17 Jun 2001 19:14:53 -0400 From: Sergey Babkin X-Mailer: Mozilla 4.7 [en] (X11; U; FreeBSD 4.0-19990626-CURRENT i386) X-Accept-Language: en, ru MIME-Version: 1.0 To: Matt Dillon Cc: "Albert D. Cahalan" , freebsd-hackers@FreeBSD.ORG, mhagerty@voyager.net Subject: Re: Article: Network performance by OS References: <200106162031.f5GKVfm16209@saturn.cs.uml.edu> <200106162104.f5GL4dX02015@earth.backplane.com> <3B2CDC8C.3C7E382A@bellatlantic.net> <200106171721.f5HHLIu06985@earth.backplane.com> Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Matt Dillon wrote: > > :... > :> to know the first thing about the platform he is running his software > :> on is a complete and utter idiot and the company that employs such a > :> person has a hellofalot more to worry about then the performance of an > :> untuned machine. > : > :We are telling people that FreeBSD is primarily a good server OS, > :right ? Then it should come with the standard configuration tuned > :with this purpose in mind. Not "foolproof", not "workstation" but > :"high-performance server". > : > :IMHO this is a big problem with too many Unix (including Linux) > :and generally Open Source programs and systems. They allow to > :do great things after being properly tuned. However the default > :configuration supplied with them is utterly horrible by some > :mysterious reason. So the learning curve for them is quite steep > > But this isn't true at all. How many people need to make thousands > or tens of thousands of simultanious connections to a machine out of the > box? Almost nobody. So to run a benchmark and have it hit these You are essentially saying: out primary target market is small servers. We can accomodate bigger loads as well but this may require some hand tuning. On the other hand, NT's target market is large servers, so it does not need tuning there but performs worse in the smaller configurations. > limitations on an untuned machine and then say that this somehow proves > that the boxes needed to be better-tuned out of the box is just plain > and simply hogwash. Well, of course if tuning the default configuration to allow such high loads would make things worse for smaller machines than there should be a compromise and the existing one is probably good. But if it won't make things worse for the typical smaller machines then the default configuration must accomodate the bigger systems. > Out of the box, FreeBSD (and Linux) work just fine for virtually > anything you need to do, with very few exceptions. If you need to > run a huge multi-gigabyte database, or you need to run an EFNET IRC "Multu-gigabyte" is not "huge" nowadays (think of the single disk sizes). "Huge" is "hundreds of gigabytes" and soon will be "multi-terabyte". > server, or a USENET relay, or a SPAM mailer, then you have a bit of > tuning work to do. Otherwise it will just work. We tune our default > configurations for what most people need. We don't tune them to run > stupid benchmarks. I agree that this benchmark is not a particularly bright one. But I feel not very comfortable when people start defining "stupid benchmarks" as "benchmarks on which our product runs poorly". That reminds me of navel gazing. > :and requires to learn the product in deep and tune it before > :using. Well, I do enjoy learning things, however tuning the > :same things in each new version over and over again for the 10th > :time becomes quite boring. > > Nonsense. If you intend to work a machine to the hilt, and expect to > maintain it for any length of time, and you aren't willing to spend > some time tuning it, then the only thing wrong with the picture is > *you*, Not the machine, Not the OS... but you. Don't blame your problems In other words, "if it works, don't touch it". It's generally a good principle for a production system but still upgrades do happen sometimes. And re-tuning the system again after upgrade is largely a waste of time (and no, just copying the config file usually does not work because some options have been removed so config complains about them and some options have been added, and their default state is sometimes not a sensible one). > on the machine if you aren't willing to lift a finger learning how it > works. A concrete example: I've learned how to set the flags to enable advanced IDE modes. Yet I do not enjoy repeatedly looking them up and setting in the config file each time I do an installation. -SB To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message