linux-kernel - [PATCH 13/14] mm: Throttle direct reclaimers if PF_MEMALLOC reserves are low and swap is backed by network storage

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

Message-Id: <1307606573-24704-14-git-send-email-mgorman@suse.de>
Date:	Thu,  9 Jun 2011 09:02:52 +0100
From:	Mel Gorman <mgorman@...e.de>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Linux-MM <linux-mm@...ck.org>,
	Linux-Netdev <netdev@...r.kernel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	David Miller <davem@...emloft.net>, Neil Brown <neilb@...e.de>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Mel Gorman <mgorman@...e.de>
Subject: [PATCH 13/14] mm: Throttle direct reclaimers if PF_MEMALLOC reserves are low and swap is backed by network storage

If swap is backed by network storage such as NBD, there is a risk that a
large number of reclaimers can hang the system by consuming all
PF_MEMALLOC reserves. To avoid these hangs, the administrator must tune
min_free_kbytes in advance. This patch will throttle direct reclaimers
if half the PF_MEMALLOC reserves are in use as the system is at risk of
hanging.

Signed-off-by: Mel Gorman <mgorman@...e.de>
---
 include/linux/mmzone.h |    1 +
 mm/page_alloc.c        |    1 +
 mm/vmscan.c            |   54 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 0 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c928dac..5b32906 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -633,6 +633,7 @@ typedef struct pglist_data {
 					     range, including holes */
 	int node_id;
 	wait_queue_head_t kswapd_wait;
+	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ac779f5..00eea0f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4288,6 +4288,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	pgdat_resize_init(pgdat);
 	pgdat->nr_zones = 0;
 	init_waitqueue_head(&pgdat->kswapd_wait);
+	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat->kswapd_max_order = 0;
 	pgdat_page_cgroup_init(pgdat);
 	
diff --git a/mm/vmscan.c b/mm/vmscan.c
index faa0a08..fe95e4f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2154,6 +2154,45 @@ out:
 	return 0;
 }
 
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat, int high_zoneidx)
+{
+	struct zone *zone;
+	unsigned long pfmemalloc_reserve = 0;
+	unsigned long free_pages = 0;
+	int i;
+
+	for (i = 0; i <= high_zoneidx; i++) {
+		zone = &pgdat->node_zones[i];
+		pfmemalloc_reserve += min_wmark_pages(zone);
+		free_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	return (free_pages > pfmemalloc_reserve / 2) ? true : false;
+}
+
+/*
+ * Throttle direct reclaimers if backing storage is backed by the network
+ * and the PFMEMALLOC reserve for the preferred node is getting dangerously
+ * depleted. kswapd will continue to make progress and wake the processes
+ * when the low watermark is reached
+ */
+static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+					nodemask_t *nodemask)
+{
+	struct zone *zone;
+	int high_zoneidx = gfp_zone(gfp_mask);
+	DEFINE_WAIT(wait);
+
+	/* Check if the pfmemalloc reserves are ok */
+	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+	if (pfmemalloc_watermark_ok(zone->zone_pgdat, high_zoneidx))
+		return;
+
+	/* Throttle */
+	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+		pfmemalloc_watermark_ok(zone->zone_pgdat, high_zoneidx));
+}
+
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
@@ -2173,6 +2212,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = sc.gfp_mask,
 	};
 
+	throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
+
+	/*
+	 * Do not enter reclaim if fatal signal is pending. 1 is returned so
+	 * that the page allocator does not consider triggering OOM
+	 */
+	if (fatal_signal_pending(current))
+		return 1;
+
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
 				gfp_mask);
@@ -2541,6 +2589,12 @@ loop_again:
 			}
 
 		}
+
+		/* Wake throttled direct reclaimers if low watermark is met */
+		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
+				pfmemalloc_watermark_ok(pgdat, MAX_NR_ZONES - 1))
+			wake_up_interruptible(&pgdat->pfmemalloc_wait);
+
 		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
-- 
1.7.3.4

--
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/