memory tiering: adjust hot threshold automatically

The promotion hot threshold is workload and system configuration
dependent.  So in this patch, a method to adjust the hot threshold
automatically is implemented.  The basic idea is to control the number of
the candidate promotion pages to match the promotion rate limit.  If the
hint page fault latency of a page is less than the hot threshold, we will
try to promote the page, and the page is called the candidate promotion
page.

If the number of the candidate promotion pages in the statistics interval
is much more than the promotion rate limit, the hot threshold will be
decreased to reduce the number of the candidate promotion pages. 
Otherwise, the hot threshold will be increased to increase the number of
the candidate promotion pages.

To make the above method works, in each statistics interval, the total
number of the pages to check (on which the hint page faults occur) and the
hot/cold distribution need to be stable.  Because the page tables are
scanned linearly in NUMA balancing, but the hot/cold distribution isn't
uniform along the address usually, the statistics interval should be
larger than the NUMA balancing scan period.  So in the patch, the max scan
period is used as statistics interval and it works well in our tests.

Link: https://lkml.kernel.org/r/20220713083954.34196-4-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: osalvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zhong Jiang <zhongjiang-ali@linux.alibaba.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 55 insertions, 5 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee28253c9ac0..8fccd8721bb8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4396,6 +4396,17 @@ void set_numabalancing_state(bool enabled)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
+static void reset_memory_tiering(void)
+{
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat) {
+		pgdat->nbp_threshold = 0;
+		pgdat->nbp_th_nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+		pgdat->nbp_th_start = jiffies_to_msecs(jiffies);
+	}
+}
+
 int sysctl_numa_balancing(struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -4412,6 +4423,9 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 	if (err < 0)
 		return err;
 	if (write) {
+		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
+		    (state & NUMA_BALANCING_MEMORY_TIERING))
+			reset_memory_tiering();
 		sysctl_numa_balancing_mode = state;
 		__set_numabalancing_state(state);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1d1dd88daaab..d642e9ff2829 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1527,6 +1527,35 @@ static bool numa_promotion_rate_limit(struct pglist_data *pgdat,
 	return false;
 }
 
+#define NUMA_MIGRATION_ADJUST_STEPS	16
+
+static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
+					    unsigned long rate_limit,
+					    unsigned int ref_th)
+{
+	unsigned int now, start, th_period, unit_th, th;
+	unsigned long nr_cand, ref_cand, diff_cand;
+
+	now = jiffies_to_msecs(jiffies);
+	th_period = sysctl_numa_balancing_scan_period_max;
+	start = pgdat->nbp_th_start;
+	if (now - start > th_period &&
+	    cmpxchg(&pgdat->nbp_th_start, start, now) == start) {
+		ref_cand = rate_limit *
+			sysctl_numa_balancing_scan_period_max / MSEC_PER_SEC;
+		nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+		diff_cand = nr_cand - pgdat->nbp_th_nr_cand;
+		unit_th = ref_th * 2 / NUMA_MIGRATION_ADJUST_STEPS;
+		th = pgdat->nbp_threshold ? : ref_th;
+		if (diff_cand > ref_cand * 11 / 10)
+			th = max(th - unit_th, unit_th);
+		else if (diff_cand < ref_cand * 9 / 10)
+			th = min(th + unit_th, ref_th * 2);
+		pgdat->nbp_th_nr_cand = nr_cand;
+		pgdat->nbp_threshold = th;
+	}
+}
+
 bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 				int src_nid, int dst_cpu)
 {
@@ -1541,19 +1570,26 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
 	    !node_is_toptier(src_nid)) {
 		struct pglist_data *pgdat;
-		unsigned long rate_limit, latency, th;
+		unsigned long rate_limit;
+		unsigned int latency, th, def_th;
 
 		pgdat = NODE_DATA(dst_nid);
-		if (pgdat_free_space_enough(pgdat))
+		if (pgdat_free_space_enough(pgdat)) {
+			/* workload changed, reset hot threshold */
+			pgdat->nbp_threshold = 0;
 			return true;
+		}
+
+		def_th = sysctl_numa_balancing_hot_threshold;
+		rate_limit = sysctl_numa_balancing_promote_rate_limit << \
+			(20 - PAGE_SHIFT);
+		numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
 
-		th = sysctl_numa_balancing_hot_threshold;
+		th = pgdat->nbp_threshold ? : def_th;
 		latency = numa_hint_fault_latency(page);
 		if (latency >= th)
 			return false;
 
-		rate_limit = sysctl_numa_balancing_promote_rate_limit << \
-			(20 - PAGE_SHIFT);
 		return !numa_promotion_rate_limit(pgdat, rate_limit,
 						  thp_nr_pages(page));
 	}