From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-io0-f198.google.com (mail-io0-f198.google.com [209.85.223.198]) by kanga.kvack.org (Postfix) with ESMTP id 3694F6B007E for ; Wed, 8 Jun 2016 04:04:53 -0400 (EDT) Received: by mail-io0-f198.google.com with SMTP id w64so3824029iow.1 for ; Wed, 08 Jun 2016 01:04:53 -0700 (PDT) Received: from lgeamrelo12.lge.com (LGEAMRELO12.lge.com. [156.147.23.52]) by mx.google.com with ESMTP id xk1si55715pab.53.2016.06.08.01.04.51 for ; Wed, 08 Jun 2016 01:04:52 -0700 (PDT) Date: Wed, 8 Jun 2016 17:03:58 +0900 From: Minchan Kim Subject: Re: [PATCH 06/10] mm: remove unnecessary use-once cache bias from LRU balancing Message-ID: <20160608080358.GB28620@bbox> References: <20160606194836.3624-1-hannes@cmpxchg.org> <20160606194836.3624-7-hannes@cmpxchg.org> MIME-Version: 1.0 In-Reply-To: <20160606194836.3624-7-hannes@cmpxchg.org> Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline Sender: owner-linux-mm@kvack.org List-ID: To: Johannes Weiner Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton , Rik van Riel , Mel Gorman , Andrea Arcangeli , Andi Kleen , Michal Hocko , Tim Chen , kernel-team@fb.com On Mon, Jun 06, 2016 at 03:48:32PM -0400, Johannes Weiner wrote: > When the splitlru patches divided page cache and swap-backed pages > into separate LRU lists, the pressure balance between the lists was > biased to account for the fact that streaming IO can cause memory > pressure with a flood of pages that are used only once. New page cache > additions would tip the balance toward the file LRU, and repeat access > would neutralize that bias again. This ensured that page reclaim would > always go for used-once cache first. > > Since e9868505987a ("mm,vmscan: only evict file pages when we have > plenty"), page reclaim generally skips over swap-backed memory > entirely as long as there is used-once cache present, and will apply > the LRU balancing when only repeatedly accessed cache pages are left - > at which point the previous use-once bias will have been neutralized. > > This makes the use-once cache balancing bias unnecessary. Remove it. > > Signed-off-by: Johannes Weiner Acked-by: Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756085AbcFHIFg (ORCPT ); Wed, 8 Jun 2016 04:05:36 -0400 Received: from LGEAMRELO12.lge.com ([156.147.23.52]:47607 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752275AbcFHIEy (ORCPT ); Wed, 8 Jun 2016 04:04:54 -0400 X-Original-SENDERIP: 156.147.1.121 X-Original-MAILFROM: minchan@kernel.org X-Original-SENDERIP: 165.244.98.76 X-Original-MAILFROM: minchan@kernel.org X-Original-SENDERIP: 10.177.223.161 X-Original-MAILFROM: minchan@kernel.org Date: Wed, 8 Jun 2016 17:03:58 +0900 From: Minchan Kim To: Johannes Weiner CC: , , Andrew Morton , Rik van Riel , Mel Gorman , Andrea Arcangeli , Andi Kleen , Michal Hocko , Tim Chen , Subject: Re: [PATCH 06/10] mm: remove unnecessary use-once cache bias from LRU balancing Message-ID: <20160608080358.GB28620@bbox> References: <20160606194836.3624-1-hannes@cmpxchg.org> <20160606194836.3624-7-hannes@cmpxchg.org> MIME-Version: 1.0 In-Reply-To: <20160606194836.3624-7-hannes@cmpxchg.org> User-Agent: Mutt/1.5.21 (2010-09-15) X-MIMETrack: Itemize by SMTP Server on LGEKRMHUB03/LGE/LG Group(Release 8.5.3FP6|November 21, 2013) at 2016/06/08 17:03:01, Serialize by Router on LGEKRMHUB03/LGE/LG Group(Release 8.5.3FP6|November 21, 2013) at 2016/06/08 17:03:01, Serialize complete at 2016/06/08 17:03:01 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jun 06, 2016 at 03:48:32PM -0400, Johannes Weiner wrote: > When the splitlru patches divided page cache and swap-backed pages > into separate LRU lists, the pressure balance between the lists was > biased to account for the fact that streaming IO can cause memory > pressure with a flood of pages that are used only once. New page cache > additions would tip the balance toward the file LRU, and repeat access > would neutralize that bias again. This ensured that page reclaim would > always go for used-once cache first. > > Since e9868505987a ("mm,vmscan: only evict file pages when we have > plenty"), page reclaim generally skips over swap-backed memory > entirely as long as there is used-once cache present, and will apply > the LRU balancing when only repeatedly accessed cache pages are left - > at which point the previous use-once bias will have been neutralized. > > This makes the use-once cache balancing bias unnecessary. Remove it. > > Signed-off-by: Johannes Weiner Acked-by: Minchan Kim