From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752619AbaB1OP5 (ORCPT ); Fri, 28 Feb 2014 09:15:57 -0500 Received: from cantor2.suse.de ([195.135.220.15]:60949 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752451AbaB1OPe (ORCPT ); Fri, 28 Feb 2014 09:15:34 -0500 From: Vlastimil Babka To: Andrew Morton , Mel Gorman , Joonsoo Kim Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Rik van Riel , Johannes Weiner , Minchan Kim , "Kirill A. Shutemov" , Vlastimil Babka Subject: [PATCH 5/6] mm: compaction: do not set pageblock skip bit when already set Date: Fri, 28 Feb 2014 15:15:03 +0100 Message-Id: <1393596904-16537-6-git-send-email-vbabka@suse.cz> X-Mailer: git-send-email 1.8.4.5 In-Reply-To: <1393596904-16537-1-git-send-email-vbabka@suse.cz> References: <1393596904-16537-1-git-send-email-vbabka@suse.cz> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Compaction migratepages scanner calls update_pageblock_skip() for blocks where isolation failed. It currently does that also for blocks where no isolation was attempted because the skip bit was already set. This is wasteful, so this patch reuses the existing skipped_async_unsuitable flag to avoid setting the skip bit again. Signed-off-by: Vlastimil Babka --- mm/compaction.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index f0db73b..20a75ee 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -529,8 +529,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, int mt; last_pageblock_nr = pageblock_nr; - if (!isolation_suitable(cc, page)) + if (!isolation_suitable(cc, page)) { + skipped_async_unsuitable = true; goto next_pageblock; + } /* * For async migration, also only scan in MOVABLE -- 1.8.4.5