From owner-freebsd-questions@FreeBSD.ORG Mon Oct 4 19:30:39 2004 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B779916A4CE for ; Mon, 4 Oct 2004 19:30:39 +0000 (GMT) Received: from smtpout.mac.com (smtpout.mac.com [17.250.248.85]) by mx1.FreeBSD.org (Postfix) with ESMTP id A30AE43D1F for ; Mon, 4 Oct 2004 19:30:39 +0000 (GMT) (envelope-from cswiger@mac.com) Received: from mac.com (smtpin07-en2 [10.13.10.152]) by smtpout.mac.com (Xserve/MantshX 2.0) with ESMTP id i94JUdvV001328; Mon, 4 Oct 2004 12:30:39 -0700 (PDT) Received: from [10.1.1.245] (nfw2.codefab.com [199.103.21.225] (may be forged)) (authenticated bits=0)i94JUcZd008839; Mon, 4 Oct 2004 12:30:39 -0700 (PDT) In-Reply-To: <4161A218.6060506@josh.aros.net> References: <1096915733.41619b153c86a@webmail.inf.ufrgs.br> <20041004145927.74ad8b47.wmoran@potentialtech.com> <4161A218.6060506@josh.aros.net> Mime-Version: 1.0 (Apple Message framework v619) Content-Type: text/plain; charset=US-ASCII; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Charles Swiger Date: Mon, 4 Oct 2004 15:30:35 -0400 To: Josh Hansen X-Mailer: Apple Mail (2.619) cc: FreeBSD Questions Mail List Subject: Re: C compiler X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 Oct 2004 19:30:39 -0000 On Oct 4, 2004, at 3:18 PM, Josh Hansen wrote: [ ...5.2.1 being slower than Linux... ] > I really don't think the problem is that simple. How about either > giving him a real answer or none at all? Sigh. The malloc debugging options in 5.2.1 really will slow down userland programs which heavily utilize dynamic memory by a significant amount, as will kernel options used for debugging such as WITNESS and INVARIANTS. It's not hard to measure these effects if you bother to try. If you want to test FreeBSD's performance in a meaningful fashion, and you are unwilling to disable the debugging options enabled in 5.x, using 4.10 is good advice. Or wait for 5.3 to finish the current beta testing cycle and be released, and then test that. -- -Chuck