From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932503AbcFIPlx (ORCPT ); Thu, 9 Jun 2016 11:41:53 -0400 Received: from mga04.intel.com ([192.55.52.120]:27347 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932173AbcFIPlv (ORCPT ); Thu, 9 Jun 2016 11:41:51 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,445,1459839600"; d="scan'208";a="994392499" Subject: Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page arrival To: "Odzioba, Lukasz" , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "akpm@linux-foundation.org" , "kirill.shutemov@linux.intel.com" , "mhocko@suse.com" , "aarcange@redhat.com" , "vdavydov@parallels.com" , "mingli199x@qq.com" , "minchan@kernel.org" References: <1465396537-17277-1-git-send-email-lukasz.odzioba@intel.com> <57583A49.30809@intel.com> Cc: "Anaczkowski, Lukasz" From: Dave Hansen Message-ID: <57598E3E.3010705@intel.com> Date: Thu, 9 Jun 2016 08:41:50 -0700 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.6.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 06/09/2016 01:50 AM, Odzioba, Lukasz wrote: > On 08-06-16 17:31:00, Dave Hansen wrote: >> Do we have any statistics that tell us how many pages are sitting the >> lru pvecs? Although this helps the problem overall, don't we still have >> a problem with memory being held in such an opaque place? > >>>From what I observed the problem is mainly with lru_add_pvec, the > rest is near empty for most of the time. I added debug code to > lru_add_drain_all(), to see sizes of the lru pvecs when I debugged this. > > Among lru_add_pvec, lru_rotate_pvecs, lru_deactivate_file_pvecs, > lru_deactivate_pvecs, activate_page_pvecs almost all (3-4GB) of the > missing memory was in lru_add_pvec, the rest was almost always empty. Does your workload put large pages in and out of those pvecs, though? If your system doesn't have any activity, then all we've shown is that they're not a problem when not in use. But what about when we use them? Have you, for instance, tried this on a system with memory pressure?