From owner-freebsd-current Mon Oct 5 10:20:39 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA15368 for freebsd-current-outgoing; Mon, 5 Oct 1998 10:20:39 -0700 (PDT) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from skraldespand.demos.su (skraldespand.demos.su [194.87.5.19]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id KAA15361 for ; Mon, 5 Oct 1998 10:20:32 -0700 (PDT) (envelope-from mishania@skraldespand.demos.su) Received: by skraldespand.demos.su id VAA09105; (8.8.8/D) Mon, 5 Oct 1998 21:19:32 +0400 (MSD) Message-ID: <19981005211931.51777@demos.su> Date: Mon, 5 Oct 1998 21:19:31 +0400 From: "Mikhail A. Sokolov" To: dg@root.com Cc: "Mikhail A. Sokolov" , current@FreeBSD.ORG Subject: Re: -current panics.. References: <19981005201017.53803@demos.su> <199810051702.KAA13253@implode.root.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <199810051702.KAA13253@implode.root.com>; from David Greenman on Mon, Oct 05, 1998 at 10:02:52AM -0700 Organization: Demos Company, Ltd., Moscow, Russian Federation. X-Point-of-View: Gravity is myth, - the earth sucks. X-Useless-Header: Look ma! It's a # sign! Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Mon, Oct 05, 1998 at 10:02:52AM -0700, David Greenman wrote: # ># Wcarchive does NOT run a standard kernel. It has various tweaks, such as # ># greatly expanded kernel virtual address space, which are specific to that # ># machine and not appropriate for 99.999% of FreeBSD users. NMBCLUSTERS on # ># wcarchive is currently set to 80000, but will need to be doubled again to # ># 160000 before we can support 10000 concurrent users. The VM is evenly split # ># for 2GB for user processes and 2GB for the kernel (contrast that with # ># standard FreeBSD which is 3.75GB user and .25GB kernel). # > # >Could it be an option then, since it looks like we, the 0.001% of FreeBSD # >users seem to exist. # # Making FreeBSD more dynamically configuring has always been a long term # goal. There isn't any magic configuration option that I can make for "big # systems", because there are many factors to consider and the system simply # has to be tuned to the specific work load. The analysis and tuning is complex # enough that it's something that I charge money to do for people. There was a 2.1.0 when we used to have the same squid with approximately the same quantity of clients and there was working dealloc methodic which was gone in 2.2.x and, of course, 3.0. It now looks like there's still problems with mbuf allocation/leeks and so on (see PR's) and the OS will not work when it is supposed to be 'a big system' out of the box. Can I read the answer as "FreeBSD is not supposed to be working as huge networking servers out of the box"? # David Greenman -- -mishania, who's not trying to be aggressive or something, just very puzzled. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message