Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754046Ab0LHICs (ORCPT ); Wed, 8 Dec 2010 03:02:48 -0500 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:37528 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750892Ab0LHICr (ORCPT ); Wed, 8 Dec 2010 03:02:47 -0500 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: Minchan Kim Subject: Re: [PATCH v4 5/7] add profile information for invalidated page reclaim Cc: kosaki.motohiro@jp.fujitsu.com, Andrew Morton , Rik van Riel , linux-mm , LKML , Wu Fengguang , Johannes Weiner , Nick Piggin , Mel Gorman In-Reply-To: References: Message-Id: <20101208165944.174D.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, 8 Dec 2010 17:02:44 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2845 Lines: 100 > This patch adds profile information about invalidated page reclaim. > It's just for profiling for test so it would be discard when the series > are merged. > > Signed-off-by: Minchan Kim > Cc: Rik van Riel > Cc: KOSAKI Motohiro > Cc: Wu Fengguang > Cc: Johannes Weiner > Cc: Nick Piggin > Cc: Mel Gorman > --- > include/linux/vmstat.h | 4 ++-- > mm/swap.c | 3 +++ > mm/vmstat.c | 3 +++ > 3 files changed, 8 insertions(+), 2 deletions(-) Today, we have tracepoint. tracepoint has no overhead if it's unused. but vmstat has a overhead even if unused. Then, all new vmstat proposal should be described why you think it is frequently used from administrators. > > diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h > index 833e676..c38ad95 100644 > --- a/include/linux/vmstat.h > +++ b/include/linux/vmstat.h > @@ -30,8 +30,8 @@ > > enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, > FOR_ALL_ZONES(PGALLOC), > - PGFREE, PGACTIVATE, PGDEACTIVATE, > - PGFAULT, PGMAJFAULT, > + PGFREE, PGACTIVATE, PGDEACTIVATE, PGINVALIDATE, > + PGRECLAIM, PGFAULT, PGMAJFAULT, > FOR_ALL_ZONES(PGREFILL), > FOR_ALL_ZONES(PGSTEAL), > FOR_ALL_ZONES(PGSCAN_KSWAPD), > diff --git a/mm/swap.c b/mm/swap.c > index 0f23998..2f21e6e 100644 > --- a/mm/swap.c > +++ b/mm/swap.c > @@ -317,6 +317,7 @@ static void lru_deactivate(struct page *page, struct zone *zone) > * is _really_ small and it's non-critical problem. > */ > SetPageReclaim(page); > + __count_vm_event(PGRECLAIM); Um. No. This is not reclaim operation anyway. Userland folks shouldn't know you override PG_reclaim. It's implementaion internal information. > } else { > /* > * The page's writeback ends up during pagevec > @@ -328,6 +329,8 @@ static void lru_deactivate(struct page *page, struct zone *zone) > > if (active) > __count_vm_event(PGDEACTIVATE); > + > + __count_vm_event(PGINVALIDATE); > update_page_reclaim_stat(zone, page, file, 0); I have similar complains as above. If you use PGINVALIDATE, other invalidate pass should update this counter too. > } > > diff --git a/mm/vmstat.c b/mm/vmstat.c > index 3555636..ef6102d 100644 > --- a/mm/vmstat.c > +++ b/mm/vmstat.c > @@ -818,6 +818,9 @@ static const char * const vmstat_text[] = { > "pgactivate", > "pgdeactivate", > > + "pginvalidate", > + "pgreclaim", > + > "pgfault", > "pgmajfault", > > -- > 1.7.0.4 > -- 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/