From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760316AbZJII4f (ORCPT ); Fri, 9 Oct 2009 04:56:35 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758761AbZJII4e (ORCPT ); Fri, 9 Oct 2009 04:56:34 -0400 Received: from fgwmail7.fujitsu.co.jp ([192.51.44.37]:34280 "EHLO fgwmail7.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754653AbZJII4d (ORCPT ); Fri, 9 Oct 2009 04:56:33 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: "Rafael J. Wysocki" , LKML , linux-mm Subject: [PATCH 1/2] vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim Cc: kosaki.motohiro@jp.fujitsu.com Message-Id: <20091009174756.12B5.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: Fri, 9 Oct 2009 17:55:53 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Rafael, Can you please review this patch series? I found shrink_all_memory() is not fast at all on my numa system. I think this patch series fixes it. ============================================================== Currently, sc.scap_cluster_max has double meanings. 1) reclaim batch size as isolate_lru_pages()'s argument 2) reclaim baling out thresolds The two meanings pretty unrelated. Thus, Let's separate it. this patch doesn't change any behavior. Signed-off-by: KOSAKI Motohiro --- mm/vmscan.c | 19 ++++++++++++++----- 1 files changed, 14 insertions(+), 5 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index ba8228e..80e727d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -55,6 +55,9 @@ struct scan_control { /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; + /* How many pages shrink_list() should reclaim */ + unsigned long nr_to_reclaim; + /* This context's GFP mask */ gfp_t gfp_mask; @@ -1526,6 +1529,7 @@ static void shrink_zone(int priority, struct zone *zone, enum lru_list l; unsigned long nr_reclaimed = sc->nr_reclaimed; unsigned long swap_cluster_max = sc->swap_cluster_max; + unsigned long nr_to_reclaim = sc->nr_to_reclaim; int noswap = 0; /* If we have no swap space, do not bother scanning anon pages. */ @@ -1572,8 +1576,7 @@ static void shrink_zone(int priority, struct zone *zone, * with multiple processes reclaiming pages, the total * freeing target can get unreasonably large. */ - if (nr_reclaimed > swap_cluster_max && - priority < DEF_PRIORITY && !current_is_kswapd()) + if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY) break; } @@ -1671,6 +1674,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct zoneref *z; struct zone *zone; enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask); + unsigned long writeback_threshold; delayacct_freepages_start(); @@ -1706,7 +1710,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, } } total_scanned += sc->nr_scanned; - if (sc->nr_reclaimed >= sc->swap_cluster_max) { + if (sc->nr_reclaimed >= sc->nr_to_reclaim) { ret = sc->nr_reclaimed; goto out; } @@ -1718,8 +1722,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, * that's undesirable in laptop mode, where we *want* lumpy * writeout. So in laptop mode, write out the whole world. */ - if (total_scanned > sc->swap_cluster_max + - sc->swap_cluster_max / 2) { + writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2; + if (total_scanned > writeback_threshold) { wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); sc->may_writepage = 1; } @@ -1765,6 +1769,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .gfp_mask = gfp_mask, .may_writepage = !laptop_mode, .swap_cluster_max = SWAP_CLUSTER_MAX, + .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, .may_swap = 1, .swappiness = vm_swappiness, @@ -1789,6 +1794,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .may_unmap = 1, .may_swap = !noswap, .swap_cluster_max = SWAP_CLUSTER_MAX, + .nr_to_reclaim = SWAP_CLUSTER_MAX, .swappiness = swappiness, .order = 0, .mem_cgroup = mem_cont, @@ -1837,6 +1843,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) .may_unmap = 1, .may_swap = 1, .swap_cluster_max = SWAP_CLUSTER_MAX, + .nr_to_reclaim = ULONG_MAX, .swappiness = vm_swappiness, .order = order, .mem_cgroup = NULL, @@ -2413,6 +2420,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .may_swap = 1, .swap_cluster_max = max_t(unsigned long, nr_pages, SWAP_CLUSTER_MAX), + .nr_to_reclaim = max_t(unsigned long, nr_pages, + SWAP_CLUSTER_MAX), .gfp_mask = gfp_mask, .swappiness = vm_swappiness, .order = order, -- 1.6.2.5