[PATCH 27/52] sched, numa, mm: Count WS scanning against present PTEs, not virtual memory ranges

From: Ingo Molnar
Date: Sun Dec 02 2012 - 13:44:48 EST


From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>

By accounting against the present PTEs, scanning speed reflects the
actual present (mapped) memory.

Suggested-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/sched/fair.c | 37 +++++++++++++++++++++----------------
1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 151a3cd..da28315 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -914,8 +914,8 @@ void task_numa_work(struct callback_head *work)
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
struct vm_area_struct *vma;
- unsigned long offset, end;
- long length;
+ unsigned long start, end;
+ long pages;

WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));

@@ -942,30 +942,35 @@ void task_numa_work(struct callback_head *work)
if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
return;

- offset = mm->numa_scan_offset;
- length = sysctl_sched_numa_scan_size;
- length <<= 20;
+ start = mm->numa_scan_offset;
+ pages = sysctl_sched_numa_scan_size;
+ pages <<= 20 - PAGE_SHIFT; /* MB in pages */
+ if (!pages)
+ return;

down_write(&mm->mmap_sem);
- vma = find_vma(mm, offset);
+ vma = find_vma(mm, start);
if (!vma) {
ACCESS_ONCE(mm->numa_scan_seq)++;
- offset = 0;
+ start = 0;
vma = mm->mmap;
}
- for (; vma && length > 0; vma = vma->vm_next) {
+ for (; vma; vma = vma->vm_next) {
if (!vma_migratable(vma))
continue;

- offset = max(offset, vma->vm_start);
- end = min(ALIGN(offset + length, HPAGE_SIZE), vma->vm_end);
- length -= end - offset;
-
- change_prot_numa(vma, offset, end);
-
- offset = end;
+ do {
+ start = max(start, vma->vm_start);
+ end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
+ end = min(end, vma->vm_end);
+ pages -= change_prot_numa(vma, start, end);
+ start = end;
+ if (pages <= 0)
+ goto out;
+ } while (end != vma->vm_end);
}
- mm->numa_scan_offset = offset;
+out:
+ mm->numa_scan_offset = start;
up_write(&mm->mmap_sem);
}

--
1.7.11.7

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/