Prev: Wrong DIF guard tag on ext2 write
Next: writeback: pass writeback_control down to move_expired_inodes()
From: Wu Fengguang on 26 Jul 2010 08:40
On Mon, Jul 26, 2010 at 08:12:59PM +0800, Jan Kara wrote:
> On Mon 26-07-10 19:51:53, Wu Fengguang wrote:
> > On Sat, Jul 24, 2010 at 02:15:21AM +0800, Jan Kara wrote:
> > > On Thu 22-07-10 13:09:32, Wu Fengguang wrote:
> > > > 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
> > > Hmm, this logic looks a bit arbitrary to me. What I actually don't like
> > > very much about this that when there aren't inodes older than say 2
> > > seconds, you'll end up queueing just inodes between 2s and 1s. So I'd
> > > rather just queue inodes older than the limit and if there are none, just
> > > queue all other dirty inodes.
> >
> > You are proposing
> >
> > - expire_interval >>= 1;
> > + expire_interval = 0;
> >
> > IMO this does not really simplify code or concept. If we can get the
> > "smoother" behavior in original patch without extra cost, why not?
> I agree there's no substantial code simplification. But I see a
> substantial "behavior" simplification (just two sweeps instead of 10 or
> so). But I don't really insist on the two sweeps, it's just that I don't
> see a justification for the exponencial back off here... I mean what's the
> point if the interval we queue gets really small? Why not just use
> expire_interval/2 as a step if you want a smoother behavior?

Yeah, the _non-linear_ backoff is not good. You have a point about the
behavior simplification, and it does remove one line. So I'll follow
your way.

Thanks,
Fengguang
---
Subject: writeback: sync expired inodes first in background writeback
From: Wu Fengguang <fengguang.wu(a)intel.com>
Date: Wed Jul 21 20:11:53 CST 2010

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
- enqueue all dirty inodes if there are no more expired inodes to sync

This will help reduce the number of dirty pages encountered by page
reclaim, eg. the pageout() calls. Normally older inodes contain older
dirty pages, which are more close to the end of the LRU lists. So
syncing older inodes first helps reducing the dirty pages reached by
the page reclaim code.

CC: Jan Kara <jack(a)suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu(a)intel.com>
---
fs/fs-writeback.c | 19 +++++++++++++------
1 file changed, 13 insertions(+), 6 deletions(-)

--- linux-next.orig/fs/fs-writeback.c 2010-07-26 20:19:01.000000000 +0800
+++ linux-next/fs/fs-writeback.c 2010-07-26 20:25:01.000000000 +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 +232,14 @@ 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 = 0;
+ continue;
+ } else
+ break;
+ }
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
@@ -521,7 +527,8 @@ 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 +557,7 @@ 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);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Jan Kara on 26 Jul 2010 08:50
On Mon 26-07-10 20:31:41, Wu Fengguang wrote:
> On Mon, Jul 26, 2010 at 08:20:54PM +0800, Jan Kara wrote:
> > On Mon 26-07-10 20:00:11, Wu Fengguang wrote:
> > > On Mon, Jul 26, 2010 at 06:57:37PM +0800, Mel Gorman wrote:
> > > > On Thu, Jul 22, 2010 at 01:09:32PM +0800, Wu Fengguang wrote:
> > > > > 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(a)suse.cz>
> > > > > Signed-off-by: Wu Fengguang <fengguang.wu(a)intel.com>
> > > >
> > > > Ok, intuitively this would appear to tie into pageout where we want
> > > > older inodes to be cleaned first by background flushers to limit the
> > > > number of dirty pages encountered by page reclaim. If this is accurate,
> > > > it should be detailed in the changelog.
> > >
> > > Good suggestion. I'll add these lines:
> > >
> > > This is to help reduce the number of dirty pages encountered by page
> > > reclaim, eg. the pageout() calls. Normally older inodes contain older
> > > dirty pages, which are more close to the end of the LRU lists. So
> > Well, this kind of implicitely assumes that once page is written, it
> > doesn't get accessed anymore, right?
>
> No, this patch is not evicting the page :)
Sorry, I probably wasn't clear enough :) I meant: The claim that "older
inodes contain older dirty pages, which are more close to the end of the
LRU lists" assumes that once page is written it doesn't get accessed
again. For example files which get continual random access (like DB files)
can have rather old dirtied_when but some of their pages are accessed quite
often...

> > Which I imagine is often true but
> > not for all workloads... Anyway I think this behavior is a good start
> > also because it is kind of natural to users to see "old" files written
> > first.

Honza
--
Jan Kara <jack(a)suse.cz>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Wu Fengguang on 26 Jul 2010 08:50
On Mon, Jul 26, 2010 at 08:39:07PM +0800, Jan Kara wrote:
> On Mon 26-07-10 20:31:41, Wu Fengguang wrote:
> > On Mon, Jul 26, 2010 at 08:20:54PM +0800, Jan Kara wrote:
> > > On Mon 26-07-10 20:00:11, Wu Fengguang wrote:
> > > > On Mon, Jul 26, 2010 at 06:57:37PM +0800, Mel Gorman wrote:
> > > > > On Thu, Jul 22, 2010 at 01:09:32PM +0800, Wu Fengguang wrote:
> > > > > > 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(a)suse.cz>
> > > > > > Signed-off-by: Wu Fengguang <fengguang.wu(a)intel.com>
> > > > >
> > > > > Ok, intuitively this would appear to tie into pageout where we want
> > > > > older inodes to be cleaned first by background flushers to limit the
> > > > > number of dirty pages encountered by page reclaim. If this is accurate,
> > > > > it should be detailed in the changelog.
> > > >
> > > > Good suggestion. I'll add these lines:
> > > >
> > > > This is to help reduce the number of dirty pages encountered by page
> > > > reclaim, eg. the pageout() calls. Normally older inodes contain older
> > > > dirty pages, which are more close to the end of the LRU lists. So
> > > Well, this kind of implicitely assumes that once page is written, it
> > > doesn't get accessed anymore, right?
> >
> > No, this patch is not evicting the page :)
> Sorry, I probably wasn't clear enough :) I meant: The claim that "older
> inodes contain older dirty pages, which are more close to the end of the
> LRU lists" assumes that once page is written it doesn't get accessed
> again. For example files which get continual random access (like DB files)
> can have rather old dirtied_when but some of their pages are accessed quite
> often...

Ah yes. That leads to another fact: smaller inodes tend to have more
strong correlations between its inode dirty age and pages' dirty age.

This is one of the reason to not sync huge dirty inode in one shot.
Instead of

sync 1G for inode A
sync 10M for inode B
sync 10M for inode C
sync 10M for inode D

It's better to

sync 128M for inode A
sync 10M for inode B
sync 10M for inode C
sync 10M for inode D
sync 128M for inode A
sync 128M for inode A
sync 128M for inode A
sync 10M for inode E (newly expired)
sync 128M for inode A
...

Thanks,
Fengguang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Wu Fengguang on 26 Jul 2010 09:00
> > @@ -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;
> > + }
>
> This needs a comment.
>
> I think what it is saying is that if background flush is active but no
> inodes are old enough, consider newer inodes. This is on the assumption
> that page reclaim has encountered dirty pages and the dirty inodes are
> still too young.

Yes this should be commented. How about this one?

@@ -232,8 +232,20 @@ 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))
+ inode_dirtied_after(inode, older_than_this)) {
+ /*
+ * background writeback will start with expired inodes,
+ * and then fresh inodes. This order helps reducing
+ * the number of dirty pages reaching the end of LRU
+ * lists and cause trouble to the page reclaim.
+ */
+ if (wbc->for_background &&
+ list_empty(dispatch_queue) && list_empty(&tmp)) {
+ expire_interval = 0;
+ continue;
+ }
break;
+ }
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;

Thanks,
Fengguang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Wu Fengguang on 26 Jul 2010 09:20
On Mon, Jul 26, 2010 at 08:59:55PM +0800, Mel Gorman wrote:
> On Mon, Jul 26, 2010 at 08:56:35PM +0800, Wu Fengguang wrote:
> > > > @@ -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;
> > > > + }
> > >
> > > This needs a comment.
> > >
> > > I think what it is saying is that if background flush is active but no
> > > inodes are old enough, consider newer inodes. This is on the assumption
> > > that page reclaim has encountered dirty pages and the dirty inodes are
> > > still too young.
> >
> > Yes this should be commented. How about this one?
> >
> > @@ -232,8 +232,20 @@ 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))
> > + inode_dirtied_after(inode, older_than_this)) {
> > + /*
> > + * background writeback will start with expired inodes,
> > + * and then fresh inodes. This order helps reducing
> > + * the number of dirty pages reaching the end of LRU
> > + * lists and cause trouble to the page reclaim.
> > + */
>
> s/reducing/reduce/
>
> Otherwise, it's enough detail to know what is going on. Thanks

Thanks. Here is the updated patch.
---
Subject: writeback: sync expired inodes first in background writeback
From: Wu Fengguang <fengguang.wu(a)intel.com>
Date: Wed Jul 21 20:11:53 CST 2010

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
- enqueue all dirty inodes if there are no more expired inodes to sync

This will help reduce the number of dirty pages encountered by page
reclaim, eg. the pageout() calls. Normally older inodes contain older
dirty pages, which are more close to the end of the LRU lists. So
syncing older inodes first helps reducing the dirty pages reached by
the page reclaim code.

CC: Jan Kara <jack(a)suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu(a)intel.com>
---
fs/fs-writeback.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)

--- linux-next.orig/fs/fs-writeback.c 2010-07-26 20:19:01.000000000 +0800
+++ linux-next/fs/fs-writeback.c 2010-07-26 21:10:42.000000000 +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 +232,20 @@ 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))
+ inode_dirtied_after(inode, older_than_this)) {
+ /*
+ * background writeback will start with expired inodes,
+ * and then fresh inodes. This order helps reduce the
+ * number of dirty pages reaching the end of LRU lists
+ * and cause trouble to the page reclaim.
+ */
+ if (wbc->for_background &&
+ list_empty(dispatch_queue) && list_empty(&tmp)) {
+ expire_interval = 0;
+ continue;
+ }
break;
+ }
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
@@ -521,7 +533,8 @@ 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 +563,7 @@ 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);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
First  |  Prev  |  Next  |  Last
Pages: 1 2 3
Prev: Wrong DIF guard tag on ext2 write
Next: writeback: pass writeback_control down to move_expired_inodes()