Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755915AbYLEIwR (ORCPT ); Fri, 5 Dec 2008 03:52:17 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751204AbYLEIwG (ORCPT ); Fri, 5 Dec 2008 03:52:06 -0500 Received: from viefep20-int.chello.at ([62.179.121.40]:42306 "EHLO viefep20-int.chello.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750852AbYLEIwF (ORCPT ); Fri, 5 Dec 2008 03:52:05 -0500 X-SourceIP: 213.46.9.244 Subject: Re: [patch] make wake-affine a sysctl variable From: Peter Zijlstra To: Ken Chen Cc: Ingo Molnar , Linux Kernel Mailing List In-Reply-To: References: <1228463394.18899.17.camel@twins> Content-Type: text/plain Date: Fri, 05 Dec 2008 09:51:57 +0100 Message-Id: <1228467117.18899.30.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1026 Lines: 23 On Fri, 2008-12-05 at 00:44 -0800, Ken Chen wrote: > On Thu, Dec 4, 2008 at 11:49 PM, Peter Zijlstra wrote: > > This patch looks like utter rubbish, sorry. > > Yeah, I think turning off wake-affine completely is a lot cleaner and > is a preferred solution. I proposed sysctl variable earlier so that > it can give people a knob to adjust and is more flexible. Hehe, right, I guess I deserved that. What I meant was, sysctl_sched_features is a horrid user interface. If you want to expose it as a sysctl - which I still don't think we want - create a new one that goes on/off, like sysctl_sched_wake_affine. Anyway, is this thing you're seeing the same as pgbench, if not, care to cook a benchmark? I really think the 1:N waker issue is solvable (not saying its easy though). -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/