From test-dev-return-1125-apmail-httpd-test-dev-archive=httpd.apache.org@httpd.apache.org Mon Aug 19 15:20:23 2002 Return-Path: Delivered-To: apmail-httpd-test-dev-archive@httpd.apache.org Received: (qmail 87941 invoked by uid 500); 19 Aug 2002 15:20:22 -0000 Mailing-List: contact test-dev-help@httpd.apache.org; run by ezmlm Precedence: bulk Reply-To: test-dev@httpd.apache.org list-help: list-unsubscribe: list-post: Delivered-To: mailing list test-dev@httpd.apache.org Received: (qmail 87930 invoked from network); 19 Aug 2002 15:20:22 -0000 Message-ID: <3D610CBC.6080103@apache.org> Date: Mon, 19 Aug 2002 08:20:28 -0700 From: Ian Holsman User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.0.0) Gecko/20020713 X-Accept-Language: en MIME-Version: 1.0 To: test-dev@httpd.apache.org Subject: Re: mod_specweb99 debugging... References: <3D5D4C1D.80BB421B@apache.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Rating: daedalus.apache.org 1.6.2 0/1000/N Dirk-Willem van Gulik wrote: >>* The harder you drive the server, the more disk space you will need. SPECWeb99 >>touches more files as you ramp up the number of concurrent connections. There >>is a formula here: http://www.spec.org/osg/web99/docs/users_guide.html#Pre-Inst >>Plus you need disk space for logs proportional to the load. > > Thanks... what I was after was more hints on configuring HTTP. ie.. make sure FollowSymLinks is On & AllowOverride off (to avoid unnessecary fileops) and things like this >>* I wouldn't be surprised if there are bugs or bottlenecks in mod_specweb99 >>itself, since it was only recently open sourced. Please feed back any >>info/patches to this list. But you don't need mod_specweb99 if you are only >>doing static content. > > > SpecWeb right now follows the run book very liberally - and there are > certainly shortcuts you could take whilst staying within the run rules. If > you want to I can dig out a list. > > Also - hack the conf to do short runs first ! > > You are going to find plenty of network, kernel and OS bottlenecks. It is > for a good reason that those setups you find on the spec.org side are such > massive beasts. If you clients are not on windows - you may want to talk > to Sander Temme - Covalent had to hack them on FreeBSD to get the byte > counts done reliably > > DW >