path: root/mm/memory.c
diff options
authorMel Gorman <>2012-11-02 14:52:48 +0000
committerMel Gorman <>2012-12-11 14:42:48 +0000
commit03c5a6e16322c997bf8f264851bfa3f532ad515f (patch)
treedf5b09acdcd6d171286afa3f77a7ff56336c8ca6 /mm/memory.c
parent4b96a29ba891dd59734cb7be80a900fe93aa2d9f (diff)
mm: numa: Add pte updates, hinting and migration stats
It is tricky to quantify the basic cost of automatic NUMA placement in a meaningful manner. This patch adds some vmstats that can be used as part of a basic costing model. u = basic unit = sizeof(void *) Ca = cost of struct page access = sizeof(struct page) / u Cpte = Cost PTE access = Ca Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock) where Cpte is incurred twice for a read and a write and Wlock is a constant representing the cost of taking or releasing a lock Cnumahint = Cost of a minor page fault = some high constant e.g. 1000 Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u Ci = Cost of page isolation = Ca + Wi where Wi is a constant that should reflect the approximate cost of the locking operation Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma) where Wnuma is the approximate NUMA factor. 1 is local. 1.2 would imply that remote accesses are 20% more expensive Balancing cost = Cpte * numa_pte_updates + Cnumahint * numa_hint_faults + Ci * numa_pages_migrated + Cpagecopy * numa_pages_migrated Note that numa_pages_migrated is used as a measure of how many pages were isolated even though it would miss pages that failed to migrate. A vmstat counter could have been added for it but the isolation cost is pretty marginal in comparison to the overall cost so it seemed overkill. The ideal way to measure automatic placement benefit would be to count the number of remote accesses versus local accesses and do something like benefit = (remote_accesses_before - remove_access_after) * Wnuma but the information is not readily available. As a workload converges, the expection would be that the number of remote numa hints would reduce to 0. convergence = numa_hint_faults_local / numa_hint_faults where this is measured for the last N number of numa hints recorded. When the workload is fully converged the value is 1. This can measure if the placement policy is converging and how fast it is doing it. Signed-off-by: Mel Gorman <> Acked-by: Rik van Riel <>
Diffstat (limited to 'mm/memory.c')
1 files changed, 12 insertions, 0 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 8012c1907895..8a7b4ccbe136 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3477,6 +3477,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
set_pte_at(mm, addr, ptep, pte);
update_mmu_cache(vma, addr, ptep);
+ count_vm_numa_event(NUMA_HINT_FAULTS);
page = vm_normal_page(vma, addr, pte);
if (!page) {
pte_unmap_unlock(ptep, ptl);
@@ -3485,6 +3486,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
current_nid = page_to_nid(page);
+ if (current_nid == numa_node_id())
+ count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
target_nid = mpol_misplaced(page, vma, addr);
pte_unmap_unlock(ptep, ptl);
if (target_nid == -1) {
@@ -3517,6 +3520,9 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long offset;
spinlock_t *ptl;
bool numa = false;
+ int local_nid = numa_node_id();
+ unsigned long nr_faults = 0;
+ unsigned long nr_faults_local = 0;
pmd = *pmdp;
@@ -3565,10 +3571,16 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
curr_nid = page_to_nid(page);
task_numa_fault(curr_nid, 1);
+ nr_faults++;
+ if (curr_nid == local_nid)
+ nr_faults_local++;
pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
pte_unmap_unlock(orig_pte, ptl);
+ count_vm_numa_events(NUMA_HINT_FAULTS, nr_faults);
+ count_vm_numa_events(NUMA_HINT_FAULTS_LOCAL, nr_faults_local);
return 0;