From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753378AbdIDIWA (ORCPT ); Mon, 4 Sep 2017 04:22:00 -0400 Received: from mail-wm0-f67.google.com ([74.125.82.67]:34680 "EHLO mail-wm0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753292AbdIDIV5 (ORCPT ); Mon, 4 Sep 2017 04:21:57 -0400 X-Google-Smtp-Source: ADKCNb5rAjJzwQflzjxyLXYJk1dj4vKbZ/2JpchE0cL4hbyF/MqNdv60KrVeMG/2MgH5TtO1KqknpQ== From: Michal Hocko To: Andrew Morton Cc: KAMEZAWA Hiroyuki , Reza Arbab , Yasuaki Ishimatsu , qiuxishi@huawei.com, Igor Mammedov , Vitaly Kuznetsov , , LKML Subject: [PATCH 0/2] mm, memory_hotplug: redefine memory offline retry logic Date: Mon, 4 Sep 2017 10:21:46 +0200 Message-Id: <20170904082148.23131-1-mhocko@kernel.org> X-Mailer: git-send-email 2.14.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, while testing memory hotplug on a large 4TB machine we have noticed that memory offlining is just too eager to fail. The primary reason is that the retry logic is just too easy to give up. We have 4 ways out of the offline - we have a permanent failure (isolation or memory notifiers fail, or hugetlb pages cannot be dropped) - userspace sends a signal - a hardcoded 120s timeout expires - page migration fails 5 times This is way too convoluted and it doesn't scale very well. We have seen both temporary migration failures as well as 120s being triggered. After removing those restrictions we were able to pass stress testing during memory hot remove without any other negative side effects observed. Therefore I suggest dropping both hard coded policies. I couldn't have found any specific reason for them in the changelog. I neither didn't get any response [1] from Kamezawa. If we need some upper bound - e.g. timeout based - then we should have a proper and user defined policy for that. In any case there should be a clear use case when introducing it. Any comments, objections? Shortlog Michal Hocko (2): mm, memory_hotplug: do not fail offlining too early mm, memory_hotplug: remove timeout from __offline_memory Diffstat mm/memory_hotplug.c | 48 ++++++++++++------------------------------------ 1 file changed, 12 insertions(+), 36 deletions(-) [1] http://lkml.kernel.org/r/20170828094316.GF17097@dhcp22.suse.cz