The promotion hot threshold may be workload 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.
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Cc: Wei Xu <weixugc@xxxxxxxxxx>
Cc: osalvador <osalvador@xxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
---
include/linux/mmzone.h | 3 ++
include/linux/sched/sysctl.h | 2 ++
kernel/sched/core.c | 15 +++++++++
kernel/sched/fair.c | 62 +++++++++++++++++++++++++++++++++---
4 files changed, 78 insertions(+), 4 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e9b4767619bc..4abf1af20372 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -919,6 +919,9 @@ typedef struct pglist_data {
#ifdef CONFIG_NUMA_BALANCING
unsigned long numa_ts;
unsigned long numa_nr_candidate;
+ unsigned long numa_threshold_ts;
+ unsigned long numa_threshold_nr_candidate;
+ unsigned long numa_threshold;
#endif
/* Fields commonly accessed by the page reclaim scanner */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index b25ce13e646a..58c1937ba09f 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -67,6 +67,8 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
+int sysctl_numa_balancing_threshold(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos);
int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..179cc4c16e24 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4364,6 +4364,18 @@ 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->numa_threshold = 0;
+ pgdat->numa_threshold_nr_candidate =
+ node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ pgdat->numa_threshold_ts = jiffies;
+ }
+}
+
int sysctl_numa_balancing(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
@@ -4380,6 +4392,9 @@ 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 a1e7cbfb2647..a01216d95bd7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1456,6 +1456,54 @@ static bool numa_migration_check_rate_limit(struct pglist_data *pgdat,
return true;
}
+int sysctl_numa_balancing_threshold(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int err;
+ struct pglist_data *pgdat;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (err < 0 || !write)
+ return err;
+
+ for_each_online_pgdat(pgdat)
+ pgdat->numa_threshold = 0;
+
+ return err;
+}
+
+#define NUMA_MIGRATION_ADJUST_STEPS 16
+
+static void numa_migration_adjust_threshold(struct pglist_data *pgdat,
+ unsigned long rate_limit,
+ unsigned long ref_th)
+{
+ unsigned long now = jiffies, last_th_ts, th_period;
+ unsigned long unit_th, th;
+ unsigned long nr_cand, ref_cand, diff_cand;
+
+ th_period = msecs_to_jiffies(sysctl_numa_balancing_scan_period_max);
+ last_th_ts = pgdat->numa_threshold_ts;
+ if (now > last_th_ts + th_period &&
+ cmpxchg(&pgdat->numa_threshold_ts, last_th_ts, now) == last_th_ts) {
+ ref_cand = rate_limit *
+ sysctl_numa_balancing_scan_period_max / 1000;
+ nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ diff_cand = nr_cand - pgdat->numa_threshold_nr_candidate;
+ unit_th = ref_th / NUMA_MIGRATION_ADJUST_STEPS;
+ th = pgdat->numa_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);
+ pgdat->numa_threshold_nr_candidate = nr_cand;
+ pgdat->numa_threshold = th;
+ }
+}
+
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int src_nid, int dst_cpu)
{
@@ -1470,18 +1518,24 @@ 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, 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->numa_threshold = 0;
return true;
+ }
+
+ def_th = sysctl_numa_balancing_hot_threshold;
+ rate_limit = sysctl_numa_balancing_rate_limit << (20 - PAGE_SHIFT);
+ numa_migration_adjust_threshold(pgdat, rate_limit, def_th);
- th = sysctl_numa_balancing_hot_threshold;
+ th = pgdat->numa_threshold ? : def_th;
latency = numa_hint_fault_latency(page);
if (latency >= th)
return false;
- rate_limit = sysctl_numa_balancing_rate_limit << (20 - PAGE_SHIFT);
return numa_migration_check_rate_limit(pgdat, rate_limit,
thp_nr_pages(page));
}
--
2.30.2
