mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate

The PTE scanning rate and fault rates are two of the biggest sources of
system CPU overhead with automatic NUMA placement.  Ideally a proper policy
would detect if a workload was properly placed, schedule and adjust the
PTE scanning rate accordingly. We do not track the necessary information
to do that but we at least know if we migrated or not.

This patch scans slower if a page was not migrated as the result of a
NUMA hinting fault up to sysctl_numa_balancing_scan_period_max which is
now higher than the previous default. Once every minute it will reset
the scanner in case of phase changes.

This is hilariously crude and the numbers are arbitrary. Workloads will
converge quite slowly in comparison to what a proper policy should be able
to do. On the plus side, we will chew up less CPU for workloads that have
no need for automatic balancing.

Signed-off-by: Mel Gorman <mgorman@suse.de>

2 files changed, 9 insertions, 5 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 79b96064f8fc..199b261a257e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1068,7 +1068,7 @@ out_unlock:
 	spin_unlock(&mm->page_table_lock);
 	if (page) {
 		put_page(page);
-		task_numa_fault(numa_node_id(), HPAGE_PMD_NR);
+		task_numa_fault(numa_node_id(), HPAGE_PMD_NR, false);
 	}
 	return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 84c6d9eab182..39edb11b63dc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3468,6 +3468,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	int current_nid = -1;
 	int target_nid;
+	bool migrated = false;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3509,12 +3510,13 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	/* Migrate to the requested node */
-	if (migrate_misplaced_page(page, target_nid))
+	migrated = migrate_misplaced_page(page, target_nid);
+	if (migrated)
 		current_nid = target_nid;
 
 out:
 	if (current_nid != -1)
-		task_numa_fault(current_nid, 1);
+		task_numa_fault(current_nid, 1, migrated);
 	return 0;
 }
 
@@ -3554,6 +3556,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct page *page;
 		int curr_nid = local_nid;
 		int target_nid;
+		bool migrated;
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3590,9 +3593,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 		/* Migrate to the requested node */
 		pte_unmap_unlock(pte, ptl);
-		if (migrate_misplaced_page(page, target_nid))
+		migrated = migrate_misplaced_page(page, target_nid);
+		if (migrated)
 			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1);
+		task_numa_fault(curr_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}