[10/26] mm: factor shrinker work calculations

Commit Message

Dave Chinner Oct. 9, 2019, 3:21 a.m. UTC

From: Dave Chinner <[e-mail]>

Start to clean up the shrinker code by factoring out the calculation
that determines how much work to do. This separates the calculation
from clamping and other adjustments that are done before the
shrinker work is run. Document the scan batch size calculation
better while we are there.

Also convert the calculation for the amount of work to be done to
use 64 bit logic so we don't have to keep jumping through hoops to
keep calculations within 32 bits on 32 bit systems.

Signed-off-by: Dave Chinner <[e-mail]>
---
 mm/vmscan.c | 97 ++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 70 insertions(+), 27 deletions(-)

Patch

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1445bc7578c0..de6b09ad97ed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -458,13 +458,68 @@  EXPORT_SYMBOL(unregister_shrinker);
 
 #define SHRINK_BATCH 128
 
+/*
+ * Calculate the number of new objects to scan this time around. Return
+ * the work to be done. If there are freeable objects, return that number in
+ * @freeable_objects.
+ */
+static int64_t shrink_scan_count(struct shrink_control *shrinkctl,
+			    struct shrinker *shrinker, int priority,
+			    int64_t *freeable_objects)
+{
+	int64_t delta;
+	int64_t freeable;
+
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0 || freeable == SHRINK_EMPTY)
+		return freeable;
+
+	if (shrinker->seeks) {
+		/*
+		 * shrinker->seeks is a measure of how much IO is required to
+		 * reinstantiate the object in memory. The default value is 2
+		 * which is typical for a cold inode requiring a directory read
+		 * and an inode read to re-instantiate.
+		 *
+		 * The scan batch size is defined by the shrinker priority, but
+		 * to be able to bias the reclaim we increase the default batch
+		 * size by 4. Hence we end up with a scan batch multipler that
+		 * scales like so:
+		 *
+		 * ->seeks	scan batch multiplier
+		 *    1		      4.00x
+		 *    2               2.00x
+		 *    3               1.33x
+		 *    4               1.00x
+		 *    8               0.50x
+		 *
+		 * IOWs, the more seeks it takes to pull the item into cache,
+		 * the smaller the reclaim scan batch. Hence we put more reclaim
+		 * pressure on caches that are fast to repopulate and to keep a
+		 * rough balance between caches that have different costs.
+		 */
+		delta = freeable >> (priority - 2);
+		do_div(delta, shrinker->seeks);
+	} else {
+		/*
+		 * These objects don't require any IO to create. Trim them
+		 * aggressively under memory pressure to keep them from causing
+		 * refetches in the IO caches.
+		 */
+		delta = freeable / 2;
+	}
+
+	*freeable_objects = freeable;
+	return delta > 0 ? delta : 0;
+}
+
 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 				    struct shrinker *shrinker, int priority)
 {
 	unsigned long freed = 0;
-	unsigned long long delta;
 	long total_scan;
-	long freeable;
+	int64_t freeable_objects = 0;
+	int64_t scan_count;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
@@ -475,9 +530,10 @@  static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
 		nid = 0;
 
-	freeable = shrinker->count_objects(shrinker, shrinkctl);
-	if (freeable == 0 || freeable == SHRINK_EMPTY)
-		return freeable;
+	scan_count = shrink_scan_count(shrinkctl, shrinker, priority,
+					&freeable_objects);
+	if (scan_count == 0 || scan_count == SHRINK_EMPTY)
+		return scan_count;
 
 	/*
 	 * copy the current shrinker scan count into a local variable
@@ -486,25 +542,11 @@  static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 */
 	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
 
-	total_scan = nr;
-	if (shrinker->seeks) {
-		delta = freeable >> priority;
-		delta *= 4;
-		do_div(delta, shrinker->seeks);
-	} else {
-		/*
-		 * These objects don't require any IO to create. Trim
-		 * them aggressively under memory pressure to keep
-		 * them from causing refetches in the IO caches.
-		 */
-		delta = freeable / 2;
-	}
-
-	total_scan += delta;
+	total_scan = nr + scan_count;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = freeable;
+		total_scan = scan_count;
 		next_deferred = nr;
 	} else
 		next_deferred = total_scan;
@@ -521,19 +563,20 @@  static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < freeable / 4)
-		total_scan = min(total_scan, freeable / 2);
+	if (scan_count < freeable_objects / 4)
+		total_scan = min_t(long, total_scan, freeable_objects / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > freeable * 2)
-		total_scan = freeable * 2;
+	if (total_scan > freeable_objects * 2)
+		total_scan = freeable_objects * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
-				   freeable, delta, total_scan, priority);
+				   freeable_objects, scan_count,
+				   total_scan, priority);
 
 	/*
 	 * If the shrinker can't run (e.g. due to gfp_mask constraints), then
@@ -558,7 +601,7 @@  static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 * possible.
 	 */
 	while (total_scan >= batch_size ||
-	       total_scan >= freeable) {
+	       total_scan >= freeable_objects) {
 		unsigned long ret;
 		unsigned long nr_to_scan = min(batch_size, total_scan);