From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751528AbcEKHiS (ORCPT ); Wed, 11 May 2016 03:38:18 -0400 Received: from mail-wm0-f66.google.com ([74.125.82.66]:32943 "EHLO mail-wm0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751228AbcEKHiQ (ORCPT ); Wed, 11 May 2016 03:38:16 -0400 Date: Wed, 11 May 2016 09:38:14 +0200 From: Michal Hocko To: "Odzioba, Lukasz" Cc: "Hansen, Dave" , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "Shutemov, Kirill" , "Anaczkowski, Lukasz" Subject: Re: mm: pages are not freed from lru_add_pvecs after process termination Message-ID: <20160511073814.GD16677@dhcp22.suse.cz> References: <5720F2A8.6070406@intel.com> <20160428143710.GC31496@dhcp22.suse.cz> <20160502130006.GD25265@dhcp22.suse.cz> <20160504203643.GI21490@dhcp22.suse.cz> <20160505072122.GA4386@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.6.0 (2016-04-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu 05-05-16 17:25:07, Odzioba, Lukasz wrote: > On Thu 05-05-16 09:21:00, Michal Hocko wrote: > > OK, it wasn't that tricky afterall. Maybe I have missed something but > > the following should work. Or maybe the async nature of flushing turns > > out to be just impractical and unreliable and we will end up skipping > > THP (or all compound pages) for pcp LRU add cache. Let's see... > > Initially this issue was found on RH's 3.10.x kernel, but now I am using > 4.6-rc6. > > In overall it does help and under heavy load it is slightly better than the > second patch. Unfortunately I am still able to hit 10-20% oom kills with it - > (went down from 30-50%) partially due to earlier vmstat_update call > - it went up to 25-25% with this patch below: This simply shows that this is not a viable option. So I guess we really want to rather skip THP (compound pages) from LRU add pcp cache. Thanks for your effort and testing! -- Michal Hocko SUSE Labs