From: Wu Fengguang <wfg@mail.ustc.edu.cn>
To: linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@osdl.org>, Wu Fengguang <wfg@mail.ustc.edu.cn>
Subject: [PATCH 01/16] mm: delayed page activation
Date: Sat, 03 Dec 2005 15:14:45 +0800 [thread overview]
Message-ID: <20051203071609.755741000@localhost.localdomain> (raw)
In-Reply-To: 20051203071444.260068000@localhost.localdomain
[-- Attachment #1: mm-delayed-activation.patch --]
[-- Type: text/plain, Size: 4625 bytes --]
When a page is referenced the second time in inactive_list, mark it with
PG_activate instead of moving it into active_list immediately. The actual
moving work is delayed to vmscan time.
This implies two essential changes:
- keeps the adjecency of pages in lru;
- lifts the page reference counter max from 1 to 3.
And leads to the following improvements:
- read-ahead for a leading reader will not be disturbed by a following reader;
- enables the thrashing protection logic to save pages for following readers;
- keeping relavant pages together helps improve I/O efficiency;
- and also helps decrease vm fragmantation;
- increased refcnt space might help page replacement algorithms.
Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---
include/linux/page-flags.h | 31 +++++++++++++++++++++++++++++++
mm/page_alloc.c | 1 +
mm/swap.c | 9 ++++-----
mm/vmscan.c | 6 ++++++
4 files changed, 42 insertions(+), 5 deletions(-)
--- linux.orig/include/linux/page-flags.h
+++ linux/include/linux/page-flags.h
@@ -76,6 +76,7 @@
#define PG_reclaim 17 /* To be reclaimed asap */
#define PG_nosave_free 18 /* Free, should not be written */
#define PG_uncached 19 /* Page has been mapped as uncached */
+#define PG_activate 20 /* delayed activate */
/*
* Global page accounting. One instance per CPU. Only unsigned longs are
@@ -314,6 +315,12 @@ extern void __mod_page_state(unsigned lo
#define SetPageUncached(page) set_bit(PG_uncached, &(page)->flags)
#define ClearPageUncached(page) clear_bit(PG_uncached, &(page)->flags)
+#define PageActivate(page) test_bit(PG_activate, &(page)->flags)
+#define SetPageActivate(page) set_bit(PG_activate, &(page)->flags)
+#define ClearPageActivate(page) clear_bit(PG_activate, &(page)->flags)
+#define TestClearPageActivate(page) test_and_clear_bit(PG_activate, &(page)->flags)
+#define TestSetPageActivate(page) test_and_set_bit(PG_activate, &(page)->flags)
+
struct page; /* forward declaration */
int test_clear_page_dirty(struct page *page);
@@ -339,4 +346,28 @@ static inline void set_page_writeback(st
#define ClearPageFsMisc(page) clear_bit(PG_fs_misc, &(page)->flags)
#define TestClearPageFsMisc(page) test_and_clear_bit(PG_fs_misc, &(page)->flags)
+#if PG_activate < PG_referenced
+#error unexpected page flags order
+#endif
+
+#define PAGE_REFCNT_0 0
+#define PAGE_REFCNT_1 (1 << PG_referenced)
+#define PAGE_REFCNT_2 (1 << PG_activate)
+#define PAGE_REFCNT_3 ((1 << PG_activate) | (1 << PG_referenced))
+#define PAGE_REFCNT_MASK PAGE_REFCNT_3
+
+/*
+ * STATUS REFERENCE COUNT
+ * __ 0
+ * _R PAGE_REFCNT_1
+ * A_ PAGE_REFCNT_2
+ * AR PAGE_REFCNT_3
+ *
+ * A/R: Active / Referenced
+ */
+static inline unsigned long page_refcnt(struct page *page)
+{
+ return page->flags & PAGE_REFCNT_MASK;
+}
+
#endif /* PAGE_FLAGS_H */
--- linux.orig/mm/page_alloc.c
+++ linux/mm/page_alloc.c
@@ -543,6 +543,7 @@ static int prep_new_page(struct page *pa
page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
1 << PG_referenced | 1 << PG_arch_1 |
+ 1 << PG_activate |
1 << PG_checked | 1 << PG_mappedtodisk);
set_page_private(page, 0);
set_page_refs(page, order);
--- linux.orig/mm/swap.c
+++ linux/mm/swap.c
@@ -29,7 +29,6 @@
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
-#include <linux/init.h>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
@@ -115,13 +114,13 @@ void fastcall activate_page(struct page
* Mark a page as having seen activity.
*
* inactive,unreferenced -> inactive,referenced
- * inactive,referenced -> active,unreferenced
- * active,unreferenced -> active,referenced
+ * inactive,referenced -> activate,unreferenced
+ * activate,unreferenced -> activate,referenced
*/
void fastcall mark_page_accessed(struct page *page)
{
- if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
- activate_page(page);
+ if (!PageActivate(page) && PageReferenced(page) && PageLRU(page)) {
+ SetPageActivate(page);
ClearPageReferenced(page);
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
--- linux.orig/mm/vmscan.c
+++ linux/mm/vmscan.c
@@ -454,6 +454,12 @@ static int shrink_list(struct list_head
if (PageWriteback(page))
goto keep_locked;
+ if (PageActivate(page)) {
+ ClearPageActivate(page);
+ ClearPageReferenced(page);
+ goto activate_locked;
+ }
+
referenced = page_referenced(page, 1);
/* In active use or really unfreeable? Activate it. */
if (referenced && page_mapping_inuse(page))
--
next prev parent reply other threads:[~2005-12-03 7:10 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-03 7:14 [PATCH 00/16] Adaptive read-ahead V9 Wu Fengguang
2005-12-03 7:14 ` Wu Fengguang [this message]
2005-12-04 12:11 ` [PATCH 01/16] mm: delayed page activation Nikita Danilov
2005-12-04 13:48 ` Wu Fengguang
2005-12-04 15:03 ` Nikita Danilov
2005-12-04 15:37 ` Help!Unable to handle kernel NULL pointer tony
2005-12-04 19:10 ` [PATCH 01/16] mm: delayed page activation Peter Zijlstra
2005-12-05 1:48 ` Wu Fengguang
2005-12-06 17:55 ` Nikita Danilov
2005-12-07 1:42 ` Wu Fengguang
2005-12-07 9:46 ` Andrew Morton
2005-12-07 10:36 ` Wu Fengguang
2005-12-07 12:44 ` Nikita Danilov
2005-12-07 13:53 ` Wu Fengguang
2005-12-03 7:14 ` [PATCH 02/16] radixtree: sync with mainline Wu Fengguang
2005-12-04 23:57 ` Andrew Morton
2005-12-05 1:43 ` Wu Fengguang
2005-12-05 4:05 ` Wu Fengguang
2005-12-05 17:22 ` Christoph Lameter
2005-12-05 10:44 ` Wu Fengguang
2005-12-05 17:24 ` Christoph Lameter
2005-12-06 2:23 ` Wu Fengguang
2005-12-03 7:14 ` [PATCH 03/16] radixtree: look-aside cache Wu Fengguang
2005-12-03 7:14 ` [PATCH 04/16] readahead: some preparation Wu Fengguang
2005-12-03 7:14 ` [PATCH 05/16] readahead: call scheme Wu Fengguang
2005-12-03 7:14 ` [PATCH 06/16] readahead: parameters Wu Fengguang
2005-12-03 7:14 ` [PATCH 07/16] readahead: state based method Wu Fengguang
2005-12-03 7:14 ` [PATCH 08/16] readahead: context " Wu Fengguang
2005-12-03 7:14 ` [PATCH 09/16] readahead: read-around method for mmap file Wu Fengguang
2005-12-03 7:14 ` [PATCH 10/16] readahead: other methods Wu Fengguang
2005-12-03 7:14 ` [PATCH 11/16] readahead: detect and rescue live pages Wu Fengguang
2005-12-03 7:14 ` [PATCH 12/16] readahead: events accounting Wu Fengguang
2005-12-03 7:14 ` [PATCH 13/16] readahead: laptop mode support Wu Fengguang
2005-12-03 7:14 ` [PATCH 14/16] readahead: disable look-ahead for loopback file Wu Fengguang
2005-12-03 7:14 ` [PATCH 15/16] readahead: nfsd support Wu Fengguang
2005-12-03 7:15 ` [PATCH 16/16] io: prevent too much latency in the read-ahead code Wu Fengguang
-- strict thread matches above, loose matches on Subject: below --
2005-11-09 13:49 [PATCH 00/16] Adaptive read-ahead V7 Wu Fengguang
2005-11-09 13:49 ` [PATCH 01/16] mm: delayed page activation Wu Fengguang
2005-11-10 0:21 ` Nick Piggin
2005-11-10 3:15 ` Wu Fengguang
2005-11-10 9:17 ` Peter Zijlstra
2005-11-10 10:30 ` Wu Fengguang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20051203071609.755741000@localhost.localdomain \
--to=wfg@mail.ustc.edu.cn \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox