From owner-freebsd-current@FreeBSD.ORG Sat Oct 6 07:57:28 2007 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C198816A417 for ; Sat, 6 Oct 2007 07:57:28 +0000 (UTC) (envelope-from marc@blackend.org) Received: from abigail.blackend.org (ns0.blackend.org [82.227.222.164]) by mx1.freebsd.org (Postfix) with ESMTP id 4476613C4A3 for ; Sat, 6 Oct 2007 07:57:28 +0000 (UTC) (envelope-from marc@blackend.org) Received: from gothic.blackend.org (gothic.blackend.org [192.168.1.203]) by abigail.blackend.org (8.13.4/8.13.3) with ESMTP id l967iZek078802; Sat, 6 Oct 2007 09:44:35 +0200 (CEST) (envelope-from marc@abigail.blackend.org) Received: from gothic.blackend.org (localhost [127.0.0.1]) by gothic.blackend.org (8.14.1/8.14.1) with ESMTP id l967iZ31054193; Sat, 6 Oct 2007 09:44:35 +0200 (CEST) (envelope-from marc@gothic.blackend.org) Received: (from marc@localhost) by gothic.blackend.org (8.14.1/8.14.1/Submit) id l967iTTd054192; Sat, 6 Oct 2007 09:44:29 +0200 (CEST) (envelope-from marc) Date: Sat, 6 Oct 2007 09:44:29 +0200 From: Marc Fonvieille To: Jeff Roberson Message-ID: <20071006074429.GB976@gothic.blackend.org> References: <20071002165007.D587@10.0.0.1> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20071002165007.D587@10.0.0.1> X-Useless-Header: blackend.org X-Operating-System: FreeBSD 7.0-CURRENT User-Agent: Mutt/1.5.16 (2007-06-09) Cc: current@freebsd.org Subject: Re: ULE/yielding patch for testing. 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: Sat, 06 Oct 2007 07:57:28 -0000 On Tue, Oct 02, 2007 at 04:53:33PM -0700, Jeff Roberson wrote: > Enclosed is a patch that does two things: > > 1) Reduces UP context switch time by over 10% making it faster than 4BSD > on UP. On SMP it's hard to compare since ULE can do as many as 30x as many > switches per second on my 8way system. > > 2) Restores old sched_yield() behavior from 6.x. This was changed in > -current unintentionally I think. > > I'd appreciate any extra testing. The ULE context switch time improvements > required some changes to the frequency that we recalculate priorities. I'm > mostly interested in hearing whether this causes any regression in normal > workloads. > [tested with _ULE] This seems to help a bit the things for me (desktop use during compilations). But 6.X is still faster, i.e, less lags and less jerky mouse movements during port builds. Thanks for spending time improving things, I really appreciate it. -- Marc