From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752176AbaHDRXp (ORCPT ); Mon, 4 Aug 2014 13:23:45 -0400 Received: from shelob.surriel.com ([74.92.59.67]:57979 "EHLO shelob.surriel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751163AbaHDRXn (ORCPT ); Mon, 4 Aug 2014 13:23:43 -0400 From: riel@redhat.com To: linux-kernel@vger.kernel.org Cc: peterz@infradead.org, mgorman@suse.de, mingo@kernel.org, vincent.guittot@linaro.org, Morten.Rasmussen@arm.com, nicolas.pitre@linaro.org, efault@gmx.de Subject: [PATCH 0/2] node capacity fixes for NUMA balancing Date: Mon, 4 Aug 2014 13:23:26 -0400 Message-Id: <1407173008-9334-1-git-send-email-riel@redhat.com> X-Mailer: git-send-email 1.9.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The NUMA balancing code has a few issues with determining the capacity of nodes, and using it when doing a task move. First the NUMA balancing code does not have the equivalent of c61037e9 to fix the "phantom cores" phenomenon in the presence of SMT. Secondly, the NUMA balancing code will happily move a task from a node that is loaded to capacity, to another node that is loaded to capacity. This can leave the second node overloaded.