linux-kernel - [PATCH 1/2] vmscan: separate sc.swap_cluster_max and sc.nr_max

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20091009174756.12B5.A69D9226@jp.fujitsu.com>
Date:	Fri,  9 Oct 2009 17:55:53 +0900 (JST)
From:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To:	"Rafael J. Wysocki" <rjw@...k.pl>,
	LKML <linux-kernel@...r.kernel.org>,
	linux-mm <linux-mm@...ck.org>
Cc:	kosaki.motohiro@...fujitsu.com
Subject: [PATCH 1/2] vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim


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 <kosaki.motohiro@...fujitsu.com>
---
 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



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/