From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756137AbaIDWzv (ORCPT ); Thu, 4 Sep 2014 18:55:51 -0400 Received: from mga09.intel.com ([134.134.136.24]:47890 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751520AbaIDWzt (ORCPT ); Thu, 4 Sep 2014 18:55:49 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.04,469,1406617200"; d="scan'208";a="598206660" Message-ID: <5408ED7A.5010908@intel.com> Date: Thu, 04 Sep 2014 15:53:46 -0700 From: Dave Hansen User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Dave Hansen , Michal Hocko CC: Johannes Weiner , Hugh Dickins , Tejun Heo , Linux-MM , Andrew Morton , Linus Torvalds , Vladimir Davydov , LKML Subject: Re: regression caused by cgroups optimization in 3.17-rc2 References: <54061505.8020500@sr71.net> <5406262F.4050705@intel.com> <54062F32.5070504@sr71.net> <20140904142721.GB14548@dhcp22.suse.cz> <5408CB2E.3080101@sr71.net> In-Reply-To: <5408CB2E.3080101@sr71.net> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/04/2014 01:27 PM, Dave Hansen wrote: > On 09/04/2014 07:27 AM, Michal Hocko wrote: >> Ouch. free_pages_and_swap_cache completely kills the uncharge batching >> because it reduces it to PAGEVEC_SIZE batches. >> >> I think we really do not need PAGEVEC_SIZE batching anymore. We are >> already batching on tlb_gather layer. That one is limited so I think >> the below should be safe but I have to think about this some more. There >> is a risk of prolonged lru_lock wait times but the number of pages is >> limited to 10k and the heavy work is done outside of the lock. If this >> is really a problem then we can tear LRU part and the actual >> freeing/uncharging into a separate functions in this path. >> >> Could you test with this half baked patch, please? I didn't get to test >> it myself unfortunately. > > 3.16 settled out at about 11.5M faults/sec before the regression. This > patch gets it back up to about 10.5M, which is good. The top spinlock > contention in the kernel is still from the resource counter code via > mem_cgroup_commit_charge(), though. > > I'm running Johannes' patch now. This looks pretty good. The area where it plateaus (above 80 threads where hyperthreading kicks in) might be a bit slower than it was in 3.16, but that could easily be from other things. > https://www.sr71.net/~dave/intel/bb.html?1=3.16.0-rc4-g67b9d76/&2=3.17.0-rc3-g57b252f Feel free to add my Tested-by: