Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932244Ab1BQQKi (ORCPT ); Thu, 17 Feb 2011 11:10:38 -0500 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:36464 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932069Ab1BQQKe (ORCPT ); Thu, 17 Feb 2011 11:10:34 -0500 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 Date: Fri, 18 Feb 2011 01:04:16 +0900 From: KAMEZAWA Hiroyuki To: Minchan Kim Cc: Andrew Morton , linux-mm , LKML , Steven Barrett , Ben Gamari , Peter Zijlstra , Rik van Riel , Mel Gorman , KOSAKI Motohiro , Wu Fengguang , Johannes Weiner , Nick Piggin , Andrea Arcangeli , Balbir Singh Subject: Re: [PATCH v5 2/4] memcg: move memcg reclaimable page into tail of inactive list Message-Id: <20110218010416.230a65df.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <442221b243154ef2546cb921d53b774f2c8f5df5.1297940291.git.minchan.kim@gmail.com> References: <442221b243154ef2546cb921d53b774f2c8f5df5.1297940291.git.minchan.kim@gmail.com> Organization: FUJITSU Co. LTD. X-Mailer: Sylpheed 3.1.0 (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 Content-Length: 5175 Lines: 141 On Fri, 18 Feb 2011 00:08:20 +0900 Minchan Kim wrote: > The rotate_reclaimable_page function moves just written out > pages, which the VM wanted to reclaim, to the end of the > inactive list. That way the VM will find those pages first > next time it needs to free memory. > This patch apply the rule in memcg. > It can help to prevent unnecessary working page eviction of memcg. > > Acked-by: Balbir Singh > Acked-by: KAMEZAWA Hiroyuki > Reviewed-by: Rik van Riel > Cc: KOSAKI Motohiro > Cc: Johannes Weiner > Signed-off-by: Minchan Kim > --- > Changelog since v4: > - add acked-by and reviewed-by > - change description - suggested by Rik > > include/linux/memcontrol.h | 6 ++++++ > mm/memcontrol.c | 27 +++++++++++++++++++++++++++ > mm/swap.c | 3 ++- > 3 files changed, 35 insertions(+), 1 deletions(-) > > diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h > index 3da48ae..5a5ce70 100644 > --- a/include/linux/memcontrol.h > +++ b/include/linux/memcontrol.h > @@ -62,6 +62,7 @@ extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, > gfp_t gfp_mask); > extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru); > extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru); > +extern void mem_cgroup_rotate_reclaimable_page(struct page *page); > extern void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru); > extern void mem_cgroup_del_lru(struct page *page); > extern void mem_cgroup_move_lists(struct page *page, > @@ -215,6 +216,11 @@ static inline void mem_cgroup_del_lru_list(struct page *page, int lru) > return ; > } > > +static inline inline void mem_cgroup_rotate_reclaimable_page(struct page *page) > +{ > + return ; > +} > + > static inline void mem_cgroup_rotate_lru_list(struct page *page, int lru) > { > return ; > diff --git a/mm/memcontrol.c b/mm/memcontrol.c > index 686f1ce..ab8bdff 100644 > --- a/mm/memcontrol.c > +++ b/mm/memcontrol.c > @@ -813,6 +813,33 @@ void mem_cgroup_del_lru(struct page *page) > mem_cgroup_del_lru_list(page, page_lru(page)); > } > > +/* > + * Writeback is about to end against a page which has been marked for immediate > + * reclaim. If it still appears to be reclaimable, move it to the tail of the > + * inactive list. > + */ > +void mem_cgroup_rotate_reclaimable_page(struct page *page) > +{ > + struct mem_cgroup_per_zone *mz; > + struct page_cgroup *pc; > + enum lru_list lru = page_lru_base_type(page); > + > + if (mem_cgroup_disabled()) > + return; > + > + pc = lookup_page_cgroup(page); > + /* > + * Used bit is set without atomic ops but after smp_wmb(). > + * For making pc->mem_cgroup visible, insert smp_rmb() here. > + */ > + smp_rmb(); > + /* unused or root page is not rotated. */ > + if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) > + return; > + mz = page_cgroup_zoneinfo(pc->mem_cgroup, page); > + list_move_tail(&pc->lru, &mz->lists[lru]); > +} > + Hmm, I'm sorry I misunderstand this. IIUC, page_lru_base_type() always returns LRU_INACTIVE_XXX and this function may move page from active LRU to inactive LRU. Then, LRU counters for memcg should be updated. Could you replace after lookup like this ? VM_BUG_ON(!PageCgroupAcctLRU(pc)) /* Implies this pages must be on some LRU */ if (!PageCgroupUsed(pc)) return; /* Used bit check is not necessary, because there is a case Unused page is lazily on LRU. We trust AcctLRU bit. */ mz = page_cgroup_zoneinfo(pc->mem_cgroup, page); MEM_CGROUP_ZSTAT(mz, page_lru(page)) -= 1 << compound_order(page); MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page) if (mem_cgroup_is_root(pc->mem_cgroup)) return; list_move_tail(&pc->lru, &mz->lists[lru]) Thanks, -Kame > void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru) > { > struct mem_cgroup_per_zone *mz; > diff --git a/mm/swap.c b/mm/swap.c > index 4aea806..1b9e4eb 100644 > --- a/mm/swap.c > +++ b/mm/swap.c > @@ -200,8 +200,9 @@ static void pagevec_move_tail(struct pagevec *pvec) > spin_lock(&zone->lru_lock); > } > if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { > - int lru = page_lru_base_type(page); > + enum lru_list lru = page_lru_base_type(page); > list_move_tail(&page->lru, &zone->lru[lru].list); > + mem_cgroup_rotate_reclaimable_page(page); > pgmoved++; > } > } > -- > 1.7.1 > > -- > 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/ > -- 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/