Return-Path: Delivered-To: apmail-httpd-dev-archive@httpd.apache.org Received: (qmail 2188 invoked by uid 500); 25 Aug 2001 08:40:19 -0000 Mailing-List: contact dev-help@httpd.apache.org; run by ezmlm Precedence: bulk Reply-To: dev@httpd.apache.org list-help: list-unsubscribe: list-post: Delivered-To: mailing list dev@httpd.apache.org Received: (qmail 2063 invoked from network); 25 Aug 2001 08:40:18 -0000 Date: Sat, 25 Aug 2001 01:40:00 -0700 From: Justin Erenkrantz To: test-dev@httpd.apache.org Cc: dev@httpd.apache.org Subject: mod_include test with new pool code. Message-ID: <20010825014000.F17570@ebuilt.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i X-AntiVirus: scanned for viruses by AMaViS 0.2.1-pre3 (http://amavis.org/) X-Spam-Rating: h31.sny.collab.net 1.6.2 0/1000/N Status: O X-Status: X-Keywords: X-UID: 1295 On Cliff's suggestion, I used big.shtml from httpd-test/perl-framework (took httpd-test/perl-framework/t/htdocs/modules/include directory and made it include-test). This shifted the load back to the CPU, so our MP hardware can actually be useful now. Gory details at: http://www.apache.org/~jerenkrantz/ So, ~1% overall gain and a ~2-3% gain with a mod_included URL due to Sander's patch. Worker MPM has problems handling a connection at first. Threaded MPM has problems with mod_include. Lots more info on the link above. HTH. I'm going to sleep now. -- justin