From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754525Ab2IKI75 (ORCPT ); Tue, 11 Sep 2012 04:59:57 -0400 Received: from cantor2.suse.de ([195.135.220.15]:50702 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751910Ab2IKI74 (ORCPT ); Tue, 11 Sep 2012 04:59:56 -0400 Date: Tue, 11 Sep 2012 09:59:49 +0100 From: Mel Gorman To: Minchan Kim Cc: Andrew Morton , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Kyungmin Park , Marek Szyprowski , Michal Nazarewicz , Rik van Riel Subject: Re: [PATCH] mm: cma: Discard clean pages during contiguous allocation instead of migration Message-ID: <20120911085948.GF11266@suse.de> References: <1347324112-14134-1-git-send-email-minchan@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <1347324112-14134-1-git-send-email-minchan@kernel.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Sep 11, 2012 at 09:41:52AM +0900, Minchan Kim wrote: > This patch drops clean cache pages instead of migration during > alloc_contig_range() to minimise allocation latency by reducing the amount > of migration is necessary. It's useful for CMA because latency of migration > is more important than evicting the background processes working set. > In addition, as pages are reclaimed then fewer free pages for migration > targets are required so it avoids memory reclaiming to get free pages, > which is a contributory factor to increased latency. > > * from v1 > * drop migrate_mode_t > * add reclaim_clean_pages_from_list instad of MIGRATE_DISCARD support - Mel > > I measured elapsed time of __alloc_contig_migrate_range which migrates > 10M in 40M movable zone in QEMU machine. > > Before - 146ms, After - 7ms > > Cc: Marek Szyprowski > Cc: Michal Nazarewicz > Cc: Rik van Riel > Signed-off-by: Mel Gorman > Signed-off-by: Minchan Kim My signed-off is already on this but in earlier versions I was still asking for changes. This time the patch looks good to me so even though it is a bit redundant. Reviewed-by: Mel Gorman Thanks Minchan. -- Mel Gorman SUSE Labs