From owner-freebsd-current@FreeBSD.ORG Thu Mar 29 19:29:16 2007 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9C8C716A403 for ; Thu, 29 Mar 2007 19:29:16 +0000 (UTC) (envelope-from jasone@frebsd.org) Received: from canonware.com (24-38-119-150-st.losaca.adelphia.net [24.38.119.150]) by mx1.freebsd.org (Postfix) with ESMTP id 8065D13C455 for ; Thu, 29 Mar 2007 19:29:16 +0000 (UTC) (envelope-from jasone@frebsd.org) Received: from [10.0.0.2] (24-38-119-150-st.losaca.adelphia.net [24.38.119.150]) by canonware.com (Postfix) with ESMTP id E35501298E3; Thu, 29 Mar 2007 12:29:38 -0700 (PDT) Message-ID: <460C138B.7010802@frebsd.org> Date: Thu, 29 Mar 2007 12:29:15 -0700 From: Jason Evans User-Agent: Thunderbird 1.5.0.10 (X11/20070302) MIME-Version: 1.0 To: Ivan Voras References: <200703281955.l2SJt7Ua086062@repoman.freebsd.org> <460AE766.6050409@frebsd.org> In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Thu, 29 Mar 2007 20:25:56 +0000 Cc: freebsd-current@freebsd.org Subject: Re: malloc(3) (hopefully) set for 7.0 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: Thu, 29 Mar 2007 19:29:16 -0000 Ivan Voras wrote: > [...] I'd really like if you could manage to implement > those ideas before 7.0, and here's why: > > - The standard for new servers here is 4 cores (in various socket > arrangements), and we're not at all high-tech. This is likely to go up. > - If you include hyperthreading, even all *desktops* are SMPs! In short, > even including desktops, I haven't installed a UP kernel in about a year. > - It's too long to wait for 8.0 for something as important as this. I already implemented features in malloc that greatly _reduce_ malloc-related contention, so I don't think it is necessary to rush further enhancements that would nearly _eliminate_ contention. We are already in pretty good shape. Also, of the enhancements I have in mind, those with highest (predicted) payoff are self-contained enough that backporting to RELENG_7 might be feasible. Jason