diff mbox series

[v1,3/7] mm: use refresh interval to rate-limit workingset report aggregation

Message ID 20240504073011.4000534-4-yuanchu@google.com
State New
Headers show
Series mm: workingset reporting | expand

Commit Message

Yuanchu Xie May 4, 2024, 7:30 a.m. UTC
The refresh interval is a rate limiting factor to workingset page age
histogram reads. When a workingset report is generated, a timestamp
is noted, and the same report will be read until it expires beyond
the refresh interval, at which point a new report is generated.

Sysfs interface
/sys/devices/system/node/nodeX/workingset_report/refresh_interval
	time in milliseconds specifying how long the report is valid for

Signed-off-by: Yuanchu Xie <yuanchu@google.com>
---
 include/linux/workingset_report.h |  1 +
 mm/internal.h                     |  2 +-
 mm/vmscan.c                       | 27 +++++++----
 mm/workingset_report.c            | 81 +++++++++++++++++++++++++------
 4 files changed, 85 insertions(+), 26 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/workingset_report.h b/include/linux/workingset_report.h
index d7c2ee14ec87..8bae6a600410 100644
--- a/include/linux/workingset_report.h
+++ b/include/linux/workingset_report.h
@@ -37,6 +37,7 @@  struct wsr_page_age_histo {
 };
 
 struct wsr_state {
+	unsigned long refresh_interval;
 	/* breakdown of workingset by page age */
 	struct mutex page_age_lock;
 	struct wsr_page_age_histo *page_age;
diff --git a/mm/internal.h b/mm/internal.h
index 5e0caba64ee4..151f09c6983e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -210,7 +210,7 @@  extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason
  * in mm/wsr.c
  */
 /* Requires wsr->page_age_lock held */
-void wsr_refresh_scan(struct lruvec *lruvec);
+void wsr_refresh_scan(struct lruvec *lruvec, unsigned long refresh_interval);
 #endif
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9af6793a6534..b7293baac1dd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5620,7 +5620,7 @@  late_initcall(init_lru_gen);
  *                          workingset reporting
  ******************************************************************************/
 #ifdef CONFIG_WORKINGSET_REPORT
-void wsr_refresh_scan(struct lruvec *lruvec)
+void wsr_refresh_scan(struct lruvec *lruvec, unsigned long refresh_interval)
 {
 	DEFINE_MAX_SEQ(lruvec);
 	struct scan_control sc = {
@@ -5633,15 +5633,22 @@  void wsr_refresh_scan(struct lruvec *lruvec)
 	};
 	unsigned int flags;
 
-	set_task_reclaim_state(current, &sc.reclaim_state);
-	flags = memalloc_noreclaim_save();
-	/*
-	 * setting can_swap=true and force_scan=true ensures
-	 * proper workingset stats when the system cannot swap.
-	 */
-	try_to_inc_max_seq(lruvec, max_seq, &sc, true, true);
-	memalloc_noreclaim_restore(flags);
-	set_task_reclaim_state(current, NULL);
+	if (refresh_interval) {
+		int gen = lru_gen_from_seq(max_seq);
+		unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+
+		if (time_is_before_jiffies(birth + refresh_interval)) {
+			set_task_reclaim_state(current, &sc.reclaim_state);
+			flags = memalloc_noreclaim_save();
+			/*
+			 * setting can_swap=true and force_scan=true ensures
+			 * proper workingset stats when the system cannot swap.
+			 */
+			try_to_inc_max_seq(lruvec, max_seq, &sc, true, true);
+			memalloc_noreclaim_restore(flags);
+			set_task_reclaim_state(current, NULL);
+		}
+	}
 }
 #endif /* CONFIG_WORKINGSET_REPORT */
 
diff --git a/mm/workingset_report.c b/mm/workingset_report.c
index 7b872b9fa7da..56155acbe7e9 100644
--- a/mm/workingset_report.c
+++ b/mm/workingset_report.c
@@ -195,7 +195,8 @@  static void collect_page_age(struct wsr_page_age_histo *page_age,
 
 /* First step: hierarchically scan child memcgs. */
 static void refresh_scan(struct wsr_state *wsr, struct mem_cgroup *root,
-			 struct pglist_data *pgdat)
+			 struct pglist_data *pgdat,
+			 unsigned long refresh_interval)
 {
 	struct mem_cgroup *memcg;
 
@@ -203,7 +204,7 @@  static void refresh_scan(struct wsr_state *wsr, struct mem_cgroup *root,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
-		wsr_refresh_scan(lruvec);
+		wsr_refresh_scan(lruvec, refresh_interval);
 		cond_resched();
 	} while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
 }
@@ -257,17 +258,25 @@  bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root,
 			struct pglist_data *pgdat)
 {
 	struct wsr_page_age_histo *page_age;
+	unsigned long refresh_interval = READ_ONCE(wsr->refresh_interval);
 
 	if (!READ_ONCE(wsr->page_age))
 		return false;
 
-	refresh_scan(wsr, root, pgdat);
+	if (!refresh_interval)
+		return false;
+
 	mutex_lock(&wsr->page_age_lock);
 	page_age = READ_ONCE(wsr->page_age);
-	if (page_age) {
-		copy_node_bins(pgdat, page_age);
-		refresh_aggregate(page_age, root, pgdat);
-	}
+	if (!page_age)
+		goto unlock;
+	if (page_age->timestamp &&
+	    time_is_after_jiffies(page_age->timestamp + refresh_interval))
+		goto unlock;
+	refresh_scan(wsr, root, pgdat, refresh_interval);
+	copy_node_bins(pgdat, page_age);
+	refresh_aggregate(page_age, root, pgdat);
+unlock:
 	mutex_unlock(&wsr->page_age_lock);
 	return !!page_age;
 }
@@ -286,6 +295,52 @@  static struct wsr_state *kobj_to_wsr(struct kobject *kobj)
 	return &mem_cgroup_lruvec(NULL, kobj_to_pgdat(kobj))->wsr;
 }
 
+static ssize_t refresh_interval_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *buf)
+{
+	struct wsr_state *wsr = kobj_to_wsr(kobj);
+	unsigned int interval = READ_ONCE(wsr->refresh_interval);
+
+	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(interval));
+}
+
+static ssize_t refresh_interval_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t len)
+{
+	unsigned int interval;
+	int err;
+	struct wsr_state *wsr = kobj_to_wsr(kobj);
+
+	err = kstrtouint(buf, 0, &interval);
+	if (err)
+		return err;
+
+	mutex_lock(&wsr->page_age_lock);
+	if (interval && !wsr->page_age) {
+		struct wsr_page_age_histo *page_age =
+			kzalloc(sizeof(struct wsr_page_age_histo), GFP_KERNEL);
+
+		if (!page_age) {
+			err = -ENOMEM;
+			goto unlock;
+		}
+		wsr->page_age = page_age;
+	}
+	if (!interval && wsr->page_age) {
+		kfree(wsr->page_age);
+		wsr->page_age = NULL;
+	}
+
+	WRITE_ONCE(wsr->refresh_interval, msecs_to_jiffies(interval));
+unlock:
+	mutex_unlock(&wsr->page_age_lock);
+	return err ?: len;
+}
+
+static struct kobj_attribute refresh_interval_attr =
+	__ATTR_RW(refresh_interval);
+
 static ssize_t page_age_intervals_show(struct kobject *kobj,
 				       struct kobj_attribute *attr, char *buf)
 {
@@ -369,13 +424,6 @@  static ssize_t page_age_show(struct kobject *kobj, struct kobj_attribute *attr,
 	int ret = 0;
 	struct wsr_state *wsr = kobj_to_wsr(kobj);
 
-
-	mutex_lock(&wsr->page_age_lock);
-	if (!wsr->page_age)
-		wsr->page_age =
-			kzalloc(sizeof(struct wsr_page_age_histo), GFP_KERNEL);
-	mutex_unlock(&wsr->page_age_lock);
-
 	wsr_refresh_report(wsr, NULL, kobj_to_pgdat(kobj));
 
 	mutex_lock(&wsr->page_age_lock);
@@ -401,7 +449,10 @@  static ssize_t page_age_show(struct kobject *kobj, struct kobj_attribute *attr,
 static struct kobj_attribute page_age_attr = __ATTR_RO(page_age);
 
 static struct attribute *workingset_report_attrs[] = {
-	&page_age_intervals_attr.attr, &page_age_attr.attr, NULL
+	&refresh_interval_attr.attr,
+	&page_age_intervals_attr.attr,
+	&page_age_attr.attr,
+	NULL
 };
 
 static const struct attribute_group workingset_report_attr_group = {