@@ -920,6 +920,11 @@ typedef struct pglist_data {
unsigned long numa_nr_candidate; /* number of promote candidate pages at
* rate limit start time */
unsigned int numa_ts; /* promote rate limit start time in ms */
+ /* promote threshold adjusting start time in ms */
+ unsigned int numa_threshold_ts;
+ unsigned int numa_threshold; /* promote threshold in ms */
+ /* number of promote candidate pages at numa_threshold_ts */
+ unsigned long numa_threshold_nr_candidate;
#endif
/* Fields commonly accessed by the page reclaim scanner */
@@ -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_to_msecs(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);
}
@@ -1491,6 +1491,35 @@ 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, last_th_ts, 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;
+ 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 / MSEC_PER_SEC;
+ nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE);
+ diff_cand = nr_cand - pgdat->numa_threshold_nr_candidate;
+ unit_th = ref_th * 2 / 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 * 2);
+ 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)
{
@@ -1505,19 +1534,26 @@ 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->numa_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->numa_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));
}
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. Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Rik van Riel <riel@surriel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Wei Xu <weixugc@google.com> Cc: osalvador <osalvador@suse.de> Cc: Shakeel Butt <shakeelb@google.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org --- include/linux/mmzone.h | 5 +++++ kernel/sched/core.c | 15 ++++++++++++++ kernel/sched/fair.c | 46 +++++++++++++++++++++++++++++++++++++----- 3 files changed, 61 insertions(+), 5 deletions(-)