This message generated a parse failure. Raw output follows here. Please use 'back' to navigate. From devnull@lkml.org Tue Apr 23 14:00:25 2024 Received: from lml.valinux.com (postfix@lml.valinux.com [198.186.203.19]) by herbie.ucs.indiana.edu (8.9.3/8.9.3) with ESMTP id GAA08307 for ; Sat, 22 Jan 2000 06:04:55 -0500 (EST) Received: from vger.rutgers.edu (vger.rutgers.edu [128.6.190.2]) by lml.valinux.com (Postfix) with ESMTP id 8B7DF6099B; Fri, 21 Jan 2000 14:23:47 -0800 (PST) Received: by vger.rutgers.edu via listexpand id ; Thu, 20 Jan 2000 21:36:41 -0500 Received: by vger.rutgers.edu id ; Thu, 20 Jan 2000 19:19:47 -0500 Received: from mplspop1.mpls.uswest.net ([204.147.80.3]:1442 "HELO mplspop1.mpls.uswest.net") by vger.rutgers.edu with SMTP id ; Thu, 20 Jan 2000 18:47:59 -0500 Received: (qmail 29017 invoked by alias); 20 Jan 2000 23:02:33 -0000 Received: (qmail 23314 invoked by uid 0); 20 Jan 2000 22:59:41 -0000 Received: from 6401pppd87.mpls.uswest.net (HELO uswest.net) (63.224.23.87) by mplspop1.mpls.uswest.net with SMTP; 20 Jan 2000 22:59:41 -0000 Message-Id: <38879372.1AFEC7A9@uswest.net> Date: Thu, 20 Jan 2000 17:00:03 -0600 From: johnforde Reply-To: johnforde@mentalengineering.com X-Mailer: Mozilla 4.05 (Macintosh; U; PPC) Mime-Version: 1.0 To: linux-kernel@vger.rutgers.edu Subject: [Fwd: static int's for proc_change_penalty and tlb_flush_penalty] Content-Type: multipart/mixed; boundary="------------B7C8CA41C639006C4B0EA58B" Sender: owner-linux-kernel@vger.rutgers.edu Precedence: bulk X-Loop: majordomo@vger.rutgers.edu X-Orcpt: rfc822;linux-kernel-outgoing-dig This is a multi-part message in MIME format. --------------B7C8CA41C639006C4B0EA58B Content-Type: text/plain; charset=us-ascii; x-mac-type="54455854"; x-mac-creator="4D4F5353" Content-Transfer-Encoding: 7bit --------------B7C8CA41C639006C4B0EA58B Content-Type: message/rfc822 Content-Transfer-Encoding: 7bit Content-Disposition: inline Return-Path: Delivered-To: crday@mail-mpls.uswest.net Received: (qmail 41204 invoked by uid 0); 20 Jan 2000 21:04:18 -0000 Received: from mail7.uswest.net (204.147.80.25) by mplspop4.mpls.uswest.net with SMTP; 20 Jan 2000 21:04:18 -0000 Received: (qmail 62820 invoked by alias); 20 Jan 2000 21:00:26 -0000 Delivered-To: crday@uswest.net Received: (qmail 62637 invoked by uid 0); 20 Jan 2000 21:00:22 -0000 Received: from rdsl18-gw.ddsl.mr.net (HELO gw.linespeed.com) (137.192.134.70) by mail7.uswest.net with SMTP; 20 Jan 2000 21:00:22 -0000 Received: from lml.valinux.com (postfix@lml.valinux.com [198.186.203.19]) by gw.linespeed.com (8.9.3/8.9.1) with ESMTP id PAA21096 for ; Thu, 20 Jan 2000 15:03:45 -0600 (CST) Received: from vger.rutgers.edu (vger.rutgers.edu [128.6.190.2]) by lml.valinux.com (Postfix) with ESMTP id A5AB81B515; Thu, 20 Jan 2000 03:40:54 -0800 (PST) Received: by vger.rutgers.edu via listexpand id ; Thu, 20 Jan 2000 05:37:32 -0500 Received: by vger.rutgers.edu id ; Thu, 20 Jan 2000 05:06:44 -0500 Received: from service.katren.ru ([212.164.86.3]:4802 "EHLO service.katren.ru") by vger.rutgers.edu with ESMTP id ; Thu, 20 Jan 2000 04:17:50 -0500 Received: from katren.ru (ws140.katren.nsk.ru [172.16.1.140]) by service.katren.ru (8.9.3/8.9.3) with ESMTP id PAA04569 for ; Thu, 20 Jan 2000 15:17:40 +0600 (NOVT) X-Orig-From: mike@katren.ru X-Orig-To: Message-ID: <3886D376.3F25C92F@katren.ru> Date: Thu, 20 Jan 2000 15:20:54 +0600 From: Mike Karmyshev X-Mailer: Mozilla 4.7 [en] (X11; I; Linux 2.2.14 i686) X-Accept-Language: en MIME-Version: 1.0 To: linux-kernel@vger.rutgers.edu Subject: Re: static int's for proc_change_penalty and tlb_flush_penalty References: <3886D28B.34C63CCA@katren.ru> Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: 7bit Sender: owner-linux-kernel@vger.rutgers.edu Precedence: bulk X-Loop: majordomo@vger.rutgers.edu X-Orcpt: rfc822;linux-kernel-outgoing-dig James Manning wrote: > > I was thinking about making the penalties in goodness() for processor > change and TLB flushes into static int's and putting them into /proc > for ppl to be able to "tune" their SMP scheduler (and to find out with > some user feedback if there are more appropriate defaults for them, > or whether it should really be settable per-system) but realized that > even as a pair of static int's, the misses of that cache line may be > adverse enough to ruin any chance of this being a worth-while change, > so I wanted to get your opinion on this. > > Since these are just scheduling policy changes, atomicity WRT the int's > shouldn't matter (although the /proc change function should keep some > reasonable bounds) > > Thoughts? > > James Oops,I've already done it for testing purposes three or maybe four months ago,when I had an Abit BP6 motherboard at home. Moved CPU change penalty from constant to sysctl to be able to change it on the fly.It seems to me that changing PENALTY value doesn't affect SMP performance too much.The difference was less than 2% on PVMPovray benchmark. Somebody still wondering about it? -- WBR,Mike - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/ --------------B7C8CA41C639006C4B0EA58B-- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/