[RFC v2 2/4] mm/damon: Account age of target regions

[SeongJae Park]

From: SeongJae Park <sjpark@xxxxxxxxx>

DAMON can be used as a primitive for data access pattern awared memory
maangement optimizations.  However, users who want such optimizations
should run DAMON, read the monitoring results, analyze it, plan a new
memory management scheme, and apply the new scheme by themselves.  It
would not be too hard, but still require some level of efforts.  For
complicated optimizations, this effort is inevitable.

That said, in many cases, users would simply want to apply an actions to
a memory region of a specific size having a specific access frequency
for a specific time.  For example, "page out a memory region larger than
100 MiB but having a low access frequency more than 10 minutes", or "Use
THP for a memory region larger than 2 MiB having a high access frequency
for more than 2 seconds".

For such optimizations, users will need to first account the age of each
region themselves.  To reduce such efforts, this commit implements a
simple age account of each region in DAMON.  For each aggregation step,
DAMON compares the access frequency and start/end address of each region
with those from last aggregation and reset the age of the region if the
change is significant.  Else, the age is incremented.

Signed-off-by: SeongJae Park <sjpark@xxxxxxxxx>
---
 include/linux/damon.h |  5 ++++
 mm/damon.c            | 58 +++++++++++++++++++++++++++++++++++++++----
 2 files changed, 58 insertions(+), 5 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 78785cb88d42..50fbe308590e 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -22,6 +22,11 @@ struct damon_region {
 	unsigned long sampling_addr;
 	unsigned int nr_accesses;
 	struct list_head list;
+
+	unsigned int age;
+	unsigned long last_vm_start;
+	unsigned long last_vm_end;
+	unsigned int last_nr_accesses;
 };
 
 /* Represents a monitoring target task */
diff --git a/mm/damon.c b/mm/damon.c
index ca9a32ecc61d..c9bce7c97709 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -87,6 +87,10 @@ static struct damon_region *damon_new_region(struct damon_ctx *ctx,
 	ret->sampling_addr = damon_rand(ctx, vm_start, vm_end);
 	INIT_LIST_HEAD(&ret->list);
 
+	ret->age = 0;
+	ret->last_vm_start = vm_start;
+	ret->last_vm_end = vm_end;
+
 	return ret;
 }
 
@@ -600,11 +604,44 @@ static void kdamond_flush_aggregated(struct damon_ctx *c)
 			damon_write_rbuf(c, &r->vm_end, sizeof(r->vm_end));
 			damon_write_rbuf(c, &r->nr_accesses,
 					sizeof(r->nr_accesses));
+			r->last_nr_accesses = r->nr_accesses;
 			r->nr_accesses = 0;
 		}
 	}
 }
 
+#define diff_of(a, b) (a > b ? a - b : b - a)
+
+/*
+ * Increase or reset the age of the given monitoring target region
+ *
+ * If the area or '->nr_accesses' has changed significantly, reset the '->age'.
+ * Else, increase the age.
+ */
+static void damon_do_count_age(struct damon_region *r, unsigned int threshold)
+{
+	unsigned long sz_threshold = (r->vm_end - r->vm_start) / 5;
+
+	if (diff_of(r->vm_start, r->last_vm_start) +
+			diff_of(r->vm_end, r->last_vm_end) > sz_threshold)
+		r->age = 0;
+	else if (diff_of(r->nr_accesses, r->last_nr_accesses) > threshold)
+		r->age = 0;
+	else
+		r->age++;
+}
+
+static void kdamond_count_age(struct damon_ctx *c, unsigned int threshold)
+{
+	struct damon_task *t;
+	struct damon_region *r;
+
+	damon_for_each_task(c, t) {
+		damon_for_each_region(r, t)
+			damon_do_count_age(r, threshold);
+	}
+}
+
 #define sz_damon_region(r) (r->vm_end - r->vm_start)
 
 /*
@@ -613,15 +650,19 @@ static void kdamond_flush_aggregated(struct damon_ctx *c)
 static void damon_merge_two_regions(struct damon_region *l,
 				struct damon_region *r)
 {
-	l->nr_accesses = (l->nr_accesses * sz_damon_region(l) +
-			r->nr_accesses * sz_damon_region(r)) /
-			(sz_damon_region(l) + sz_damon_region(r));
+	unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r);
+
+	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
+			(sz_l + sz_r);
+	l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r);
+	if (sz_l < sz_r) {
+		l->last_vm_start = r->last_vm_start;
+		l->last_vm_end = r->last_vm_end;
+	}
 	l->vm_end = r->vm_end;
 	damon_destroy_region(r);
 }
 
-#define diff_of(a, b) (a > b ? a - b : b - a)
-
 /*
  * Merge adjacent regions having similar access frequencies
  *
@@ -674,6 +715,12 @@ static void damon_split_region_at(struct damon_ctx *ctx,
 	struct damon_region *new;
 
 	new = damon_new_region(ctx, r->vm_start + sz_r, r->vm_end);
+	new->age = r->age;
+	new->last_vm_start = r->vm_start;
+	new->last_nr_accesses = r->last_nr_accesses;
+
+	r->last_vm_start = r->vm_start;
+	r->last_vm_end = r->vm_end;
 	r->vm_end = new->vm_start;
 
 	damon_add_region(new, r, damon_next_region(r));
@@ -865,6 +912,7 @@ static int kdamond_fn(void *data)
 
 		if (kdamond_aggregate_interval_passed(ctx)) {
 			kdamond_merge_regions(ctx, max_nr_accesses / 10);
+			kdamond_count_age(ctx, max_nr_accesses / 10);
 			if (ctx->aggregate_cb)
 				ctx->aggregate_cb(ctx);
 			kdamond_flush_aggregated(ctx);
-- 
2.17.1