From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933832AbZHEJ0i (ORCPT ); Wed, 5 Aug 2009 05:26:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932964AbZHEJ0g (ORCPT ); Wed, 5 Aug 2009 05:26:36 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:37318 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932946AbZHEJ0f (ORCPT ); Wed, 5 Aug 2009 05:26:35 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: Mel Gorman Subject: Re: [PATCH 2/4] tracing, mm: Add trace events for anti-fragmentation falling back to other migratetypes Cc: kosaki.motohiro@jp.fujitsu.com, Larry Woodman , Andrew Morton , riel@redhat.com, Ingo Molnar , Peter Zijlstra , LKML , linux-mm@kvack.org In-Reply-To: <1249409546-6343-3-git-send-email-mel@csn.ul.ie> References: <1249409546-6343-1-git-send-email-mel@csn.ul.ie> <1249409546-6343-3-git-send-email-mel@csn.ul.ie> Message-Id: <20090805182518.5BD0.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.50.07 [ja] Date: Wed, 5 Aug 2009 18:26:32 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Fragmentation avoidance depends on being able to use free pages from > lists of the appropriate migrate type. In the event this is not > possible, __rmqueue_fallback() selects a different list and in some > circumstances change the migratetype of the pageblock. Simplistically, > the more times this event occurs, the more likely that fragmentation > will be a problem later for hugepage allocation at least but there are > other considerations such as the order of page being split to satisfy > the allocation. > > This patch adds a trace event for __rmqueue_fallback() that reports what > page is being used for the fallback, the orders of relevant pages, the > desired migratetype and the migratetype of the lists being used, whether > the pageblock changed type and whether this event is important with > respect to fragmentation avoidance or not. This information can be used > to help analyse fragmentation avoidance and help decide whether > min_free_kbytes should be increased or not. > > Signed-off-by: Mel Gorman > Acked-by: Rik van Riel Looks good to me. but I don't put my reviewed-by because I am not so familiar this area.