From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933554AbaE3PBa (ORCPT ); Fri, 30 May 2014 11:01:30 -0400 Received: from qmta03.emeryville.ca.mail.comcast.net ([76.96.30.32]:56663 "EHLO qmta03.emeryville.ca.mail.comcast.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933182AbaE3PB2 (ORCPT ); Fri, 30 May 2014 11:01:28 -0400 Date: Fri, 30 May 2014 10:01:26 -0500 (CDT) From: Christoph Lameter To: Vladimir Davydov cc: akpm@linux-foundation.org, hannes@cmpxchg.org, mhocko@suse.cz, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH -mm 8/8] slab: reap dead memcg caches aggressively In-Reply-To: <23a736c90a81e13a2252d35d9fc3dc04a9ed7d7c.1401457502.git.vdavydov@parallels.com> Message-ID: References: <23a736c90a81e13a2252d35d9fc3dc04a9ed7d7c.1401457502.git.vdavydov@parallels.com> Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 30 May 2014, Vladimir Davydov wrote: > There is no use in keeping free objects/slabs on dead memcg caches, > because they will never be allocated. So let's make cache_reap() shrink > as many free objects from such caches as possible. > > Note the difference between SLAB and SLUB handling of dead memcg caches. > For SLUB, dead cache destruction is scheduled as soon as the last object > is freed, because dead caches do not cache free objects. For SLAB, dead > caches can keep some free objects on per cpu arrays, so that an empty > dead cache will be hanging around until cache_reap() drains it. Calling kmem_cache_shrink() should drain all caches though. Reduce the size of the queues to zero or so before calling shrink so that no new caches are build up? > We don't disable free objects caching for SLAB, because it would force > kfree to always take a spin lock, which would degrade performance > significantly. You can use a similar approach than in SLUB. Reduce the size of the per cpu array objects to zero. Then SLAB will always fall back to its slow path in cache_flusharray() where you may be able to do something with less of an impact on performace.