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@xxxxxxx>
---
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 be1ac8d..d502217 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -639,6 +639,7 @@ 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 17c8f93..d0685b9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4302,6 +4302,7 @@ 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 b7719ec..ddf2be0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2236,6 +2236,45 @@ 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)
{
@@ -2254,6 +2293,15 @@ 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);
@@ -2641,6 +2689,12 @@ 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, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>