Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757668Ab0LJBQV (ORCPT ); Thu, 9 Dec 2010 20:16:21 -0500 Received: from mail-iw0-f172.google.com ([209.85.214.172]:63260 "EHLO mail-iw0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755020Ab0LJBQU convert rfc822-to-8bit (ORCPT ); Thu, 9 Dec 2010 20:16:20 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=n2NPUt8MEcWVw4LKqZtUu0I8zuxm/tsInvGXd1CujjTLbPYGFEw0XU8FAvYlqKv2Cn p8dvcJjmAZqib8TrHLk5XYeTaYJozLKNvz+OL4e0OTGkOQnnFkebIc0/Aaj1Br8CB2uG im/f1DeXpAbI4nOuvyV6pj6/u05pTPug/e/cI= MIME-Version: 1.0 In-Reply-To: <1291893500-12342-4-git-send-email-mel@csn.ul.ie> References: <1291893500-12342-1-git-send-email-mel@csn.ul.ie> <1291893500-12342-4-git-send-email-mel@csn.ul.ie> Date: Fri, 10 Dec 2010 10:16:19 +0900 Message-ID: Subject: Re: [PATCH 3/6] mm: kswapd: Use the order that kswapd was reclaiming at for sleeping_prematurely() From: Minchan Kim To: Mel Gorman Cc: Simon Kirby , KOSAKI Motohiro , Shaohua Li , Dave Hansen , Johannes Weiner , Andrew Morton , linux-mm , linux-kernel Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2683 Lines: 72 On Thu, Dec 9, 2010 at 8:18 PM, Mel Gorman wrote: > Before kswapd goes to sleep, it uses sleeping_prematurely() to check if > there was a race pushing a zone below its watermark. If the race > happened, it stays awake. However, balance_pgdat() can decide to reclaim > at a lower order if it decides that high-order reclaim is not working as Could you specify "order-0" explicitly instead of "a lower order"? It makes more clear to me. > expected. This information is not passed back to sleeping_prematurely(). > The impact is that kswapd remains awake reclaiming pages long after it > should have gone to sleep. This patch passes the adjusted order to > sleeping_prematurely and uses the same logic as balance_pgdat to decide > if it's ok to go to sleep. > > Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim A comment below. > --- > ?mm/vmscan.c | ? 14 ++++++++++---- > ?1 files changed, 10 insertions(+), 4 deletions(-) > > diff --git a/mm/vmscan.c b/mm/vmscan.c > index b4472a1..52e229e 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -2132,7 +2132,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced) > ?} > > ?/* is kswapd sleeping prematurely? */ > -static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) > +static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) > ?{ > ? ? ? ?int i; > ? ? ? ?unsigned long balanced = 0; > @@ -2142,7 +2142,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) > ? ? ? ?if (remaining) > ? ? ? ? ? ? ? ?return 1; > > - ? ? ? /* If after HZ/10, a zone is below the high mark, it's premature */ > + ? ? ? /* Check the watermark levels */ > ? ? ? ?for (i = 0; i < pgdat->nr_zones; i++) { > ? ? ? ? ? ? ? ?struct zone *zone = pgdat->node_zones + i; > > @@ -2427,7 +2427,13 @@ out: > ? ? ? ? ? ? ? ?} > ? ? ? ?} > > - ? ? ? return sc.nr_reclaimed; > + ? ? ? /* > + ? ? ? ?* Return the order we were reclaiming at so sleeping_prematurely() > + ? ? ? ?* makes a decision on the order we were last reclaiming at. However, > + ? ? ? ?* if another caller entered the allocator slow path while kswapd > + ? ? ? ?* was awake, order will remain at the higher level > + ? ? ? ?*/ > + ? ? ? return order; > ?} Please change return value description of balance_pgdat. "Returns the number of pages which were actually freed" -- Kind regards, Minchan Kim -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/