From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932104AbaIEJ2s (ORCPT ); Fri, 5 Sep 2014 05:28:48 -0400 Received: from mail-we0-f179.google.com ([74.125.82.179]:56428 "EHLO mail-we0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756183AbaIEJ2p (ORCPT ); Fri, 5 Sep 2014 05:28:45 -0400 Date: Fri, 5 Sep 2014 11:28:41 +0200 From: Michal Hocko To: Dave Hansen Cc: Dave Hansen , 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 Message-ID: <20140905092841.GD26243@dhcp22.suse.cz> References: <54061505.8020500@sr71.net> <5406262F.4050705@intel.com> <54062F32.5070504@sr71.net> <20140904142721.GB14548@dhcp22.suse.cz> <5408CB2E.3080101@sr71.net> <5408ED7A.5010908@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <5408ED7A.5010908@intel.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu 04-09-14 15:53:46, Dave Hansen wrote: > 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. Good news indeed. But I think it would be safer to apply Johannes' revert for now. Both changes are still worth having anyway because they have potential to improve memcg case. > > 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: Thanks a lot! I have posted another patch which reduces the batching for LRU handling because this would be too risky. So I haven't added your Tested-by yet. -- Michal Hocko SUSE Labs