lkml.org 
[lkml]   [2009]   [Dec]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC][PATCH v2 8/8] Don't deactivate many touched page
Date
Changelog
o from v1
- Fix comments.
- Rename too_many_young_bit_found() with too_many_referenced()
[as Rik's mention].
o from andrea's original patch
- Rebase topon my patches.
- Use list_cut_position/list_splice_tail pair instead
list_del/list_add to make pte scan fairness.
- Only use max young threshold when soft_try is true.
It avoid wrong OOM sideeffect.
- Return SWAP_AGAIN instead successful result if max
young threshold exceed. It prevent the pages without clear
pte young bit will be deactivated wrongly.
- Add to treat ksm page logic

Many shared and frequently used page don't need deactivate and
try_to_unamp(). It's pointless while VM pressure is low, the page
might reactivate soon. it's only makes cpu wasting.

Then, This patch makes to stop pte scan if wipe_page_reference()
found lots young pte bit.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
include/linux/rmap.h | 18 ++++++++++++++++++
mm/ksm.c | 4 ++++
mm/rmap.c | 19 +++++++++++++++++++
3 files changed, 41 insertions(+), 0 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 499972e..ddf2578 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -128,6 +128,24 @@ int wipe_page_reference_one(struct page *page,
struct page_reference_context *refctx,
struct vm_area_struct *vma, unsigned long address);

+#define MAX_YOUNG_BIT_CLEARED 64
+/*
+ * If VM pressure is low and the page has lots of active users, we only
+ * clear up to MAX_YOUNG_BIT_CLEARED accessed bits at a time. Clearing
+ * accessed bits takes CPU time, needs TLB invalidate IPIs and could
+ * cause lock contention. Since a heavily shared page is very likely
+ * to be used again soon, the cost outweighs the benefit of making such
+ * a heavily shared page a candidate for eviction.
+ */
+static inline
+int too_many_referenced(struct page_reference_context *refctx)
+{
+ if (refctx->soft_try &&
+ refctx->referenced >= MAX_YOUNG_BIT_CLEARED)
+ return 1;
+ return 0;
+}
+
enum ttu_flags {
TTU_UNMAP = 0, /* unmap mode */
TTU_MIGRATION = 1, /* migration mode */
diff --git a/mm/ksm.c b/mm/ksm.c
index 19559ae..e959c41 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1586,6 +1586,10 @@ again:
rmap_item->address);
if (ret != SWAP_SUCCESS)
goto out;
+ if (too_many_referenced(refctx)) {
+ ret = SWAP_AGAIN;
+ goto out;
+ }
mapcount--;
if (!search_new_forks || !mapcount)
break;
diff --git a/mm/rmap.c b/mm/rmap.c
index cfda0a0..d66b8dc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -473,6 +473,21 @@ static int wipe_page_reference_anon(struct page *page,
ret = wipe_page_reference_one(page, refctx, vma, address);
if (ret != SWAP_SUCCESS)
break;
+ if (too_many_referenced(refctx)) {
+ LIST_HEAD(tmp_list);
+
+ /*
+ * Rotating the anon vmas around help spread out lock
+ * pressure in the VM. It help to reduce heavy lock
+ * contention.
+ */
+ list_cut_position(&tmp_list,
+ &vma->anon_vma_node,
+ &anon_vma->head);
+ list_splice_tail(&tmp_list, &vma->anon_vma_node);
+ ret = SWAP_AGAIN;
+ break;
+ }
mapcount--;
if (!mapcount || refctx->maybe_mlocked)
break;
@@ -543,6 +558,10 @@ static int wipe_page_reference_file(struct page *page,
ret = wipe_page_reference_one(page, refctx, vma, address);
if (ret != SWAP_SUCCESS)
break;
+ if (too_many_referenced(refctx)) {
+ ret = SWAP_AGAIN;
+ break;
+ }
mapcount--;
if (!mapcount || refctx->maybe_mlocked)
break;
--
1.6.5.2




\
 
 \ /
  Last update: 2009-12-10 08:39    [W:0.080 / U:0.160 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site