Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756207Ab0DIGV3 (ORCPT ); Fri, 9 Apr 2010 02:21:29 -0400 Received: from ozlabs.org ([203.10.76.45]:46425 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750806Ab0DIGVX (ORCPT ); Fri, 9 Apr 2010 02:21:23 -0400 To: Peter Zijlstra , Benjamin Herrenschmidt From: Michael Neuling Date: Fri, 09 Apr 2010 16:21:18 +1000 Subject: [PATCH 0/5] sched: asymmetrical packing for POWER7 SMT4 Message-Id: <1270794078.794237.347827867455.qpush@pale> CC: , , Ingo Molnar , Suresh Siddha , Gautham R Shenoy Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 922 Lines: 20 This patch series implements asymmetric SMT packing which ensures consistently good performance on POWER7. I'm no scheduler expert so these probably need some review. It works for my simple test case on a POWER7 with SMT4. I can now run a number of CPU bound processes and they are pulled down to lower threads giving the best performance consistently. Suresh: some of this touches code you changed recently, so you may want to test in your environment. The 1st patch is a fix for SMT4 in general. The 2nd adds actual the asymmetrical packing infrastructure. The 3rd adds the powerpc specific hooks for POWER7. The 4th and 5th are fixes required for packing to work. -- 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/