From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 17:24:39 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 28C2637B401 for ; Wed, 30 Apr 2003 17:24:39 -0700 (PDT) Received: from heron.mail.pas.earthlink.net (heron.mail.pas.earthlink.net [207.217.120.189]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8B44B43FBF for ; Wed, 30 Apr 2003 17:24:38 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0055.cvx22-bradley.dialup.earthlink.net ([209.179.198.55] helo=mindspring.com) by heron.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19B1sF-0005Pz-00; Wed, 30 Apr 2003 17:24:32 -0700 Message-ID: <3EB0685D.B88C7D3C@mindspring.com> Date: Wed, 30 Apr 2003 17:20:45 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Benjamin Krueger References: <200304281054.48976.ryba@kompakt.pl> <3EB05582.297F50AE@lbl.gov> <20030430231522.GO11702@surreal.seattlefenix.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a46442b4a032ab4b4ebc99b4a4fc62c29ca2d4e88014a4647c350badd9bab72f9c350badd9bab72f9c cc: Adrian Filipi-Martin cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 00:24:39 -0000 Benjamin Krueger wrote: > * Jin Guojun [DSD] (j_guojun@lbl.gov) [030430 15:54]: > > For server, 2x may be required, and typically 2.5x is needed. > > In what instance can you expect to have server processes that are ok to > page to disk? Maybe I'm wrong, but I've always considered a server that > is paging my important processes to disk a broken server in need of ram. When your boss won't buy you more hardware, and expects you to do your job anyway, and your job involves deploying services on the available machinery. As long as the processing load, when swap is included, doesn't impact user-visible performance, it probably doesn't matter if you are swapping or not. So I'm going to say there's a fair bit of distance between "user experience broken", "organization broken", and "server broken", with "server broken" being last in line... 8-). -- Terry