vmscan: tracing: add trace events for kswapd wakeup, sleeping and direct reclaim

Add two trace events for kswapd waking up and going asleep for the
purposes of tracking kswapd activity and two trace events for direct
reclaim beginning and ending.  The information can be used to work out how
much time a process or the system is spending on the reclamation of pages
and in the case of direct reclaim, how many pages were reclaimed for that
process.  High frequency triggering of these events could point to memory
pressure problems.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 20 insertions, 4 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6dafa45..c99bc41 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,9 @@
 
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/vmscan.h>
+
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -1883,6 +1886,7 @@ out:
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
+	unsigned long nr_reclaimed;
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
@@ -1895,7 +1899,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.nodemask = nodemask,
 	};
 
-	return do_try_to_free_pages(zonelist, &sc);
+	trace_mm_vmscan_direct_reclaim_begin(order,
+				sc.may_writepage,
+				gfp_mask);
+
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
+	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+
+	return nr_reclaimed;
 }
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
@@ -2294,9 +2306,10 @@ static int kswapd(void *p)
 				 * premature sleep. If not, then go fully
 				 * to sleep until explicitly woken up
 				 */
-				if (!sleeping_prematurely(pgdat, order, remaining))
+				if (!sleeping_prematurely(pgdat, order, remaining)) {
+					trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 					schedule();
-				else {
+				} else {
 					if (remaining)
 						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
 					else
@@ -2316,8 +2329,10 @@ static int kswapd(void *p)
 		 * We can speed up thawing tasks if we don't call balance_pgdat
 		 * after returning from the refrigerator
 		 */
-		if (!ret)
+		if (!ret) {
+			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
 			balance_pgdat(pgdat, order);
+		}
 	}
 	return 0;
 }
@@ -2337,6 +2352,7 @@ void wakeup_kswapd(struct zone *zone, int order)
 		return;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
 	if (!waitqueue_active(&pgdat->kswapd_wait))