From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753216AbZHTDPr (ORCPT ); Wed, 19 Aug 2009 23:15:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752571AbZHTDPr (ORCPT ); Wed, 19 Aug 2009 23:15:47 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:41939 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752136AbZHTDPq (ORCPT ); Wed, 19 Aug 2009 23:15:46 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 Date: Thu, 20 Aug 2009 12:13:47 +0900 From: KAMEZAWA Hiroyuki To: Wu Fengguang Cc: Andrew Morton , Balbir Singh , KOSAKI Motohiro , Rik van Riel , Johannes Weiner , Avi Kivity , Andrea Arcangeli , "Dike, Jeffrey G" , Hugh Dickins , Christoph Lameter , Mel Gorman , LKML , linux-mm , "nishimura@mxp.nes.nec.co.jp" , "lizf@cn.fujitsu.com" , "menage@google.com" Subject: Re: [PATCH] mm: do batched scans for mem_cgroup Message-Id: <20090820121347.8a886e4b.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <20090820024929.GA19793@localhost> References: <20090820024929.GA19793@localhost> Organization: FUJITSU Co. LTD. X-Mailer: Sylpheed 2.5.0 (GTK+ 2.10.14; i686-pc-mingw32) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 20 Aug 2009 10:49:29 +0800 Wu Fengguang wrote: > For mem_cgroup, shrink_zone() may call shrink_list() with nr_to_scan=1, > in which case shrink_list() _still_ calls isolate_pages() with the much > larger SWAP_CLUSTER_MAX. It effectively scales up the inactive list > scan rate by up to 32 times. > > For example, with 16k inactive pages and DEF_PRIORITY=12, (16k >> 12)=4. > So when shrink_zone() expects to scan 4 pages in the active/inactive > list, it will be scanned SWAP_CLUSTER_MAX=32 pages in effect. > > The accesses to nr_saved_scan are not lock protected and so not 100% > accurate, however we can tolerate small errors and the resulted small > imbalanced scan rates between zones. > > This batching won't blur up the cgroup limits, since it is driven by > "pages reclaimed" rather than "pages scanned". When shrink_zone() > decides to cancel (and save) one smallish scan, it may well be called > again to accumulate up nr_saved_scan. > > It could possibly be a problem for some tiny mem_cgroup (which may be > _full_ scanned too much times in order to accumulate up nr_saved_scan). > > CC: Rik van Riel > CC: Minchan Kim > CC: Balbir Singh > CC: KOSAKI Motohiro > CC: KAMEZAWA Hiroyuki > Signed-off-by: Wu Fengguang > --- Hmm, how about this ? == Now, nr_saved_scan is tied to zone's LRU. But, considering how vmscan works, it should be tied to reclaim_stat. By this, memcg can make use of nr_saved_scan information seamlessly. --- include/linux/mmzone.h | 2 +- mm/vmscan.c | 19 ++++++++++--------- 2 files changed, 11 insertions(+), 10 deletions(-) Index: linux-2.6.31-rc6/include/linux/mmzone.h =================================================================== --- linux-2.6.31-rc6.orig/include/linux/mmzone.h 2009-08-17 15:14:21.000000000 +0900 +++ linux-2.6.31-rc6/include/linux/mmzone.h 2009-08-20 12:10:44.000000000 +0900 @@ -269,6 +269,7 @@ */ unsigned long recent_rotated[2]; unsigned long recent_scanned[2]; + unsigned long nr_saved_scan[NR_LRU_LISTS];/* accumulated for batching */ }; struct zone { @@ -323,7 +324,6 @@ spinlock_t lru_lock; struct zone_lru { struct list_head list; - unsigned long nr_saved_scan; /* accumulated for batching */ } lru[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; Index: linux-2.6.31-rc6/mm/vmscan.c =================================================================== --- linux-2.6.31-rc6.orig/mm/vmscan.c 2009-08-17 15:14:21.000000000 +0900 +++ linux-2.6.31-rc6/mm/vmscan.c 2009-08-20 12:17:47.000000000 +0900 @@ -1521,6 +1521,7 @@ enum lru_list l; unsigned long nr_reclaimed = sc->nr_reclaimed; unsigned long swap_cluster_max = sc->swap_cluster_max; + struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); int noswap = 0; /* If we have no swap space, do not bother scanning anon pages. */ @@ -1540,12 +1541,9 @@ scan >>= priority; scan = (scan * percent[file]) / 100; } - if (scanning_global_lru(sc)) - nr[l] = nr_scan_try_batch(scan, - &zone->lru[l].nr_saved_scan, - swap_cluster_max); - else - nr[l] = scan; + nr[l] = nr_scan_try_batch(scan, + &recalim_stat->nr_saved_scan[l], + swap_cluster_max); } while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || @@ -2128,6 +2126,7 @@ { struct zone *zone; unsigned long nr_reclaimed = 0; + struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); for_each_populated_zone(zone) { enum lru_list l; @@ -2144,11 +2143,13 @@ l == LRU_ACTIVE_FILE)) continue; - zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1; - if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) { + reclaim_stat->nr_saved_scan[l] += + (lru_pages >> prio) + 1; + if (reclaim_stat->nr_saved_scan[l] + >= nr_pages || pass > 3) { unsigned long nr_to_scan; - zone->lru[l].nr_saved_scan = 0; + reclaim_stat->nr_saved_scan[l] = 0; nr_to_scan = min(nr_pages, lru_pages); nr_reclaimed += shrink_list(l, nr_to_scan, zone, sc, prio);