From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>, Jan Kara <jack@suse.cz>,
Wu Fengguang <fengguang.wu@intel.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mm@kvack.org
Subject: [PATCH 4/6] writeback: sync expired inodes first in background writeback
Date: Thu, 22 Jul 2010 13:09:32 +0800 [thread overview]
Message-ID: <20100722061822.906037624@intel.com> (raw)
In-Reply-To: 20100722050928.653312535@intel.com
[-- Attachment #1: writeback-expired-for-background.patch --]
[-- Type: text/plain, Size: 2449 bytes --]
A background flush work may run for ever. So it's reasonable for it to
mimic the kupdate behavior of syncing old/expired inodes first.
The policy is
- enqueue all newly expired inodes at each queue_io() time
- retry with halfed expire interval until get some inodes to sync
CC: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
fs/fs-writeback.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
--- linux-next.orig/fs/fs-writeback.c 2010-07-22 12:56:42.000000000 +0800
+++ linux-next/fs/fs-writeback.c 2010-07-22 13:07:51.000000000 +0800
@@ -217,14 +217,14 @@ static void move_expired_inodes(struct l
struct writeback_control *wbc)
{
unsigned long expire_interval = 0;
- unsigned long older_than_this;
+ unsigned long older_than_this = 0; /* reset to kill gcc warning */
LIST_HEAD(tmp);
struct list_head *pos, *node;
struct super_block *sb = NULL;
struct inode *inode;
int do_sb_sort = 0;
- if (wbc->for_kupdate) {
+ if (wbc->for_kupdate || wbc->for_background) {
expire_interval = msecs_to_jiffies(dirty_expire_interval * 10);
older_than_this = jiffies - expire_interval;
}
@@ -232,8 +232,15 @@ static void move_expired_inodes(struct l
while (!list_empty(delaying_queue)) {
inode = list_entry(delaying_queue->prev, struct inode, i_list);
if (expire_interval &&
- inode_dirtied_after(inode, older_than_this))
- break;
+ inode_dirtied_after(inode, older_than_this)) {
+ if (wbc->for_background &&
+ list_empty(dispatch_queue) && list_empty(&tmp)) {
+ expire_interval >>= 1;
+ older_than_this = jiffies - expire_interval;
+ continue;
+ } else
+ break;
+ }
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
@@ -521,7 +528,8 @@ void writeback_inodes_wb(struct bdi_writ
wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
+
+ if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
queue_io(wb, wbc);
while (!list_empty(&wb->b_io)) {
@@ -550,7 +558,7 @@ static void __writeback_inodes_sb(struct
wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
queue_io(wb, wbc);
writeback_sb_inodes(sb, wb, wbc, true);
spin_unlock(&inode_lock);
WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>, Jan Kara <jack@suse.cz>,
Wu Fengguang <fengguang.wu@intel.com>,
Christoph Hellwig <hch@infradead.org>, Mel Gorman <mel@csn.ul.ie>,
Chris Mason <chris.mason@oracle.com>,
Jens Axboe <jens.axboe@oracle.com>,
LKML <linux-kernel@vger.kernel.org>,
linux-fsdevel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH 4/6] writeback: sync expired inodes first in background writeback
Date: Thu, 22 Jul 2010 13:09:32 +0800 [thread overview]
Message-ID: <20100722061822.906037624@intel.com> (raw)
In-Reply-To: 20100722050928.653312535@intel.com
[-- Attachment #1: writeback-expired-for-background.patch --]
[-- Type: text/plain, Size: 2449 bytes --]
A background flush work may run for ever. So it's reasonable for it to
mimic the kupdate behavior of syncing old/expired inodes first.
The policy is
- enqueue all newly expired inodes at each queue_io() time
- retry with halfed expire interval until get some inodes to sync
CC: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
fs/fs-writeback.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
--- linux-next.orig/fs/fs-writeback.c 2010-07-22 12:56:42.000000000 +0800
+++ linux-next/fs/fs-writeback.c 2010-07-22 13:07:51.000000000 +0800
@@ -217,14 +217,14 @@ static void move_expired_inodes(struct l
struct writeback_control *wbc)
{
unsigned long expire_interval = 0;
- unsigned long older_than_this;
+ unsigned long older_than_this = 0; /* reset to kill gcc warning */
LIST_HEAD(tmp);
struct list_head *pos, *node;
struct super_block *sb = NULL;
struct inode *inode;
int do_sb_sort = 0;
- if (wbc->for_kupdate) {
+ if (wbc->for_kupdate || wbc->for_background) {
expire_interval = msecs_to_jiffies(dirty_expire_interval * 10);
older_than_this = jiffies - expire_interval;
}
@@ -232,8 +232,15 @@ static void move_expired_inodes(struct l
while (!list_empty(delaying_queue)) {
inode = list_entry(delaying_queue->prev, struct inode, i_list);
if (expire_interval &&
- inode_dirtied_after(inode, older_than_this))
- break;
+ inode_dirtied_after(inode, older_than_this)) {
+ if (wbc->for_background &&
+ list_empty(dispatch_queue) && list_empty(&tmp)) {
+ expire_interval >>= 1;
+ older_than_this = jiffies - expire_interval;
+ continue;
+ } else
+ break;
+ }
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
@@ -521,7 +528,8 @@ void writeback_inodes_wb(struct bdi_writ
wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
+
+ if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
queue_io(wb, wbc);
while (!list_empty(&wb->b_io)) {
@@ -550,7 +558,7 @@ static void __writeback_inodes_sb(struct
wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ if (!(wbc->for_kupdate || wbc->for_background) || list_empty(&wb->b_io))
queue_io(wb, wbc);
writeback_sb_inodes(sb, wb, wbc, true);
spin_unlock(&inode_lock);
next prev parent reply other threads:[~2010-07-22 6:19 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-22 5:09 [PATCH 0/6] [RFC] writeback: try to write older pages first Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` [PATCH 1/6] writeback: pass writeback_control down to move_expired_inodes() Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-23 18:16 ` Jan Kara
2010-07-23 18:16 ` Jan Kara
2010-07-26 10:44 ` Mel Gorman
2010-07-26 10:44 ` Mel Gorman
2010-08-01 15:23 ` Minchan Kim
2010-08-01 15:23 ` Minchan Kim
2010-07-22 5:09 ` [PATCH 2/6] writeback: the kupdate expire timestamp should be a moving target Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-23 18:17 ` Jan Kara
2010-07-23 18:17 ` Jan Kara
2010-07-26 10:52 ` Mel Gorman
2010-07-26 10:52 ` Mel Gorman
2010-07-26 11:32 ` Wu Fengguang
2010-07-26 11:32 ` Wu Fengguang
2010-08-01 15:29 ` Minchan Kim
2010-08-01 15:29 ` Minchan Kim
2010-07-22 5:09 ` [PATCH 3/6] writeback: kill writeback_control.more_io Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-23 18:24 ` Jan Kara
2010-07-23 18:24 ` Jan Kara
2010-07-26 10:53 ` Mel Gorman
2010-07-26 10:53 ` Mel Gorman
2010-08-01 15:34 ` Minchan Kim
2010-08-01 15:34 ` Minchan Kim
2010-08-05 14:50 ` Wu Fengguang
2010-08-05 14:50 ` Wu Fengguang
2010-08-05 14:55 ` Wu Fengguang
2010-08-05 14:55 ` Wu Fengguang
2010-08-05 14:56 ` Minchan Kim
2010-08-05 14:56 ` Minchan Kim
2010-08-05 15:26 ` Wu Fengguang
2010-08-05 15:26 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang [this message]
2010-07-22 5:09 ` [PATCH 4/6] writeback: sync expired inodes first in background writeback Wu Fengguang
2010-07-23 18:15 ` Jan Kara
2010-07-23 18:15 ` Jan Kara
2010-07-26 11:51 ` Wu Fengguang
2010-07-26 11:51 ` Wu Fengguang
2010-07-26 12:12 ` Jan Kara
2010-07-26 12:12 ` Jan Kara
2010-07-26 12:29 ` Wu Fengguang
2010-07-26 12:29 ` Wu Fengguang
2010-07-26 10:57 ` Mel Gorman
2010-07-26 10:57 ` Mel Gorman
2010-07-26 12:00 ` Wu Fengguang
2010-07-26 12:00 ` Wu Fengguang
2010-07-26 12:20 ` Jan Kara
2010-07-26 12:20 ` Jan Kara
2010-07-26 12:31 ` Wu Fengguang
2010-07-26 12:31 ` Wu Fengguang
2010-07-26 12:39 ` Jan Kara
2010-07-26 12:39 ` Jan Kara
2010-07-26 12:47 ` Wu Fengguang
2010-07-26 12:47 ` Wu Fengguang
2010-07-26 12:56 ` Wu Fengguang
2010-07-26 12:56 ` Wu Fengguang
2010-07-26 12:59 ` Mel Gorman
2010-07-26 12:59 ` Mel Gorman
2010-07-26 13:11 ` Wu Fengguang
2010-07-26 13:11 ` Wu Fengguang
2010-07-27 9:45 ` Mel Gorman
2010-07-27 9:45 ` Mel Gorman
2010-08-01 15:15 ` Minchan Kim
2010-08-01 15:15 ` Minchan Kim
2010-07-22 5:09 ` [PATCH 5/6] writeback: try more writeback as long as something was written Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-23 17:39 ` Jan Kara
2010-07-23 17:39 ` Jan Kara
2010-07-26 12:39 ` Wu Fengguang
2010-07-26 12:39 ` Wu Fengguang
2010-07-26 11:01 ` Mel Gorman
2010-07-26 11:01 ` Mel Gorman
2010-07-26 11:39 ` Wu Fengguang
2010-07-26 11:39 ` Wu Fengguang
2010-07-22 5:09 ` [PATCH 6/6] writeback: introduce writeback_control.inodes_written Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-22 5:09 ` Wu Fengguang
2010-07-26 11:04 ` Mel Gorman
2010-07-26 11:04 ` Mel Gorman
2010-07-23 10:24 ` [PATCH 0/6] [RFC] writeback: try to write older pages first Mel Gorman
2010-07-23 10:24 ` Mel Gorman
2010-07-26 7:18 ` Wu Fengguang
2010-07-26 7:18 ` Wu Fengguang
2010-07-26 10:42 ` Mel Gorman
2010-07-26 10:42 ` Mel Gorman
2010-07-26 10:28 ` Itaru Kitayama
2010-07-26 10:28 ` Itaru Kitayama
2010-07-26 11:47 ` Wu Fengguang
2010-07-26 11:47 ` 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=20100722061822.906037624@intel.com \
--to=fengguang.wu@intel.com \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=jack@suse.cz \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.