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 <mgorman@xxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
---
include/linux/vm_event_item.h | 6 ++++++
mm/huge_memory.c | 1 +
mm/memory.c | 12 ++++++++++++
mm/mempolicy.c | 5 +++++
mm/migrate.c | 3 ++-
mm/vmstat.c | 6 ++++++
6 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index a1f750b..dded0af 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -38,6 +38,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
KSWAPD_SKIP_CONGESTION_WAIT,
PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+#ifdef CONFIG_BALANCE_NUMA
+ NUMA_PTE_UPDATES,
+ NUMA_HINT_FAULTS,
+ NUMA_HINT_FAULTS_LOCAL,
+ NUMA_PAGE_MIGRATE,
+#endif
#ifdef CONFIG_MIGRATION
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 833a601..f45f25b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1033,6 +1033,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
page = pmd_page(pmd);
get_page(page);
spin_unlock(&mm->page_table_lock);
+ count_vm_event(NUMA_HINT_FAULTS);
target_nid = mpol_misplaced(page, vma, haddr);
if (target_nid == -1)
diff --git a/mm/memory.c b/mm/memory.c
index 73fa203..95c9abb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3457,11 +3457,14 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (unlikely(!pte_same(*ptep, pte)))
goto out_unlock;
+ count_vm_event(NUMA_HINT_FAULTS);
page = vm_normal_page(vma, addr, pte);
BUG_ON(!page);
get_page(page);
current_nid = page_to_nid(page);
+ if (current_nid == numa_node_id())
+ count_vm_event(NUMA_HINT_FAULTS_LOCAL);
target_nid = mpol_misplaced(page, vma, addr);
if (target_nid == -1) {
/*
@@ -3520,6 +3523,9 @@ 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;
spin_lock(&mm->page_table_lock);
pmd = *pmdp;
@@ -3566,10 +3572,16 @@ 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, false);
+ 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_events(NUMA_HINT_FAULTS, nr_faults);
+ count_vm_events(NUMA_HINT_FAULTS_LOCAL, nr_faults_local);
return 0;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 11052ea..860341e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -583,6 +583,7 @@ change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long _address, end;
spinlock_t *ptl;
int ret = 0;
+ int nr_pte_updates = 0;
VM_BUG_ON(address & ~PAGE_MASK);
@@ -626,6 +627,7 @@ change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
set_pmd_at(mm, address, pmd, pmd_mknuma(*pmd));
ret += HPAGE_PMD_NR;
+ nr_pte_updates++;
/* defer TLB flush to lower the overhead */
spin_unlock(&mm->page_table_lock);
goto out;
@@ -652,6 +654,7 @@ change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
continue;
set_pte_at(mm, _address, _pte, pte_mknuma(pteval));
+ nr_pte_updates++;
/* defer TLB flush to lower the overhead */
ret++;
@@ -666,6 +669,8 @@ change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
}
out:
+ if (nr_pte_updates)
+ count_vm_events(NUMA_PTE_UPDATES, nr_pte_updates);
return ret;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 631b2c5..a890429 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1517,7 +1517,8 @@ struct page *migrate_misplaced_page(struct page *page, int node)
if (nr_remaining) {
putback_lru_pages(&migratepages);
req.newpage = NULL;
- }
+ } else
+ count_vm_event(NUMA_PAGE_MIGRATE);
}
BUG_ON(!list_empty(&migratepages));
out:
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 3a067fa..cfa386da 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -774,6 +774,12 @@ const char * const vmstat_text[] = {
"pgrotated",
+#ifdef CONFIG_BALANCE_NUMA
+ "numa_pte_updates",
+ "numa_hint_faults",
+ "numa_hint_faults_local",
+ "numa_pages_migrated",
+#endif
#ifdef CONFIG_MIGRATION
"pgmigrate_success",
"pgmigrate_fail",
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>