From owner-freebsd-current@FreeBSD.ORG Tue Jan 31 06:00:43 2006 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 58BE016A420; Tue, 31 Jan 2006 06:00:43 +0000 (GMT) (envelope-from jasone@freebsd.org) Received: from lh.synack.net (lh.synack.net [204.152.188.37]) by mx1.FreeBSD.org (Postfix) with ESMTP id F3B2D43D4C; Tue, 31 Jan 2006 06:00:42 +0000 (GMT) (envelope-from jasone@freebsd.org) Received: by lh.synack.net (Postfix, from userid 100) id C7A5F5E48ED; Mon, 30 Jan 2006 22:00:42 -0800 (PST) Received: from [192.168.168.203] (moscow-cuda-gen2-68-64-60-20.losaca.adelphia.net [68.64.60.20]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (No client certificate requested) by lh.synack.net (Postfix) with ESMTP id D4BC75E48DA; Mon, 30 Jan 2006 22:00:37 -0800 (PST) In-Reply-To: <200601311616.10870.doconnor@gsoft.com.au> References: <200601301652.16237.doconnor@gsoft.com.au> <20060130215554.GA68540@xor.obsecurity.org> <200601310914.39886.doconnor@gsoft.com.au> <200601311616.10870.doconnor@gsoft.com.au> Mime-Version: 1.0 (Apple Message framework v746.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <1713BECB-9E36-4D12-A063-46AB2EC0AB2F@freebsd.org> Content-Transfer-Encoding: 7bit From: Jason Evans Date: Mon, 30 Jan 2006 22:00:35 -0800 To: Daniel O'Connor X-Mailer: Apple Mail (2.746.2) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on lh.synack.net X-Spam-Level: * X-Spam-Status: No, score=1.8 required=5.0 tests=RCVD_IN_NJABL_DUL, RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: freebsd-current@freebsd.org, Michael Nottebrock , Kris Kennaway Subject: Re: KDE 3.5.0 seems much chubbier than 3.4.2 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 31 Jan 2006 06:00:43 -0000 [Apologies for the duplicate emails.] On Jan 30, 2006, at 9:46 PM, Daniel O'Connor wrote: > [ fixed CC ] > On Tuesday 31 January 2006 09:14, Daniel O'Connor wrote: >> On Tuesday 31 January 2006 08:25, Kris Kennaway wrote: >>>> I did have a kernel from before the new malloc and it still seemed >>>> quite sluggish. I remember being stuck because a commit to the AGP >>>> driver on 20/12/05 prevented the nvidia driver building. >>> >>> new malloc = userland, not kernel. >> >> Yeah but I don't install world without first doing install kernel :) > > I think I was crack smoking here.. > Recompiling the new libc with NO_MALLOC_EXTRAS reduced the memory > usage > *significantly*. Yes, I'd expect the memory usage to decrease if you build with NO_MALLOC_EXTRAS, since redzone overhead is 32 bytes per object. Do you see any evidence of unbounded X memory usage though? > A make.conf knob would be highly appreciated here :) Why not just append to CFLAGS in make.conf? NO_MALLOC_EXTRAS is a development-only flag, since the malloc debug features will be disabled for releases, so a make.conf knob would have no relevance to releases. Unless there's serious worry about cpp namespace pollution, I don't understand the need for the patch you provided. Thanks, Jason