* [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
@ 2009-09-01 11:18 ` Jens Axboe
2009-09-01 11:55 ` Theodore Tso
2009-09-01 21:51 ` Christoph Hellwig
2009-09-01 11:19 ` [PATCH 2/8] writeback: move dirty inodes from super_block to backing_dev_info Jens Axboe
` (6 subsequent siblings)
7 siblings, 2 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:18 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
drivers/staging/pohmelfs/inode.c | 3 ++-
fs/fs-writeback.c | 14 +++++++-------
fs/ubifs/budget.c | 5 +++--
fs/ubifs/super.c | 3 ++-
include/linux/fs.h | 3 +--
include/linux/writeback.h | 2 ++
6 files changed, 17 insertions(+), 13 deletions(-)
diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
index 7b60579..9a94c5a 100644
--- a/drivers/staging/pohmelfs/inode.c
+++ b/drivers/staging/pohmelfs/inode.c
@@ -1951,12 +1951,13 @@ static int pohmelfs_get_sb(struct file_system_type *fs_type,
static void pohmelfs_kill_super(struct super_block *sb)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_ALL,
.range_start = 0,
.range_end = LLONG_MAX,
.nr_to_write = LONG_MAX,
};
- generic_sync_sb_inodes(sb, &wbc);
+ generic_sync_sb_inodes(&wbc);
kill_anon_super(sb);
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c54226b..8c43ca4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -458,9 +458,9 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
* on the writer throttling path, and we get decent balancing between many
* throttled threads: we don't want them all piling up on inode_sync_wait.
*/
-void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+void generic_sync_sb_inodes(struct writeback_control *wbc)
{
+ struct super_block *sb = wbc->sb;
const unsigned long start = jiffies; /* livelock avoidance */
int sync = wbc->sync_mode == WB_SYNC_ALL;
@@ -595,10 +595,9 @@ void generic_sync_sb_inodes(struct super_block *sb,
}
EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
-static void sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static void sync_sb_inodes(struct writeback_control *wbc)
{
- generic_sync_sb_inodes(sb, wbc);
+ generic_sync_sb_inodes(wbc);
}
/*
@@ -640,7 +639,7 @@ restart:
*/
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root)
- sync_sb_inodes(sb, wbc);
+ sync_sb_inodes(wbc);
up_read(&sb->s_umount);
}
spin_lock(&sb_lock);
@@ -666,6 +665,7 @@ restart:
void sync_inodes_sb(struct super_block *sb, int wait)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -680,7 +680,7 @@ void sync_inodes_sb(struct super_block *sb, int wait)
} else
wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
- sync_sb_inodes(sb, &wbc);
+ sync_sb_inodes(&wbc);
}
/**
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index eaf6d89..0f680b9 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -66,12 +66,13 @@ static int shrink_liability(struct ubifs_info *c, int nr_to_write)
{
int nr_written;
struct writeback_control wbc = {
+ .sb = c->vfs_sb,
.sync_mode = WB_SYNC_NONE,
.range_end = LLONG_MAX,
.nr_to_write = nr_to_write,
};
- generic_sync_sb_inodes(c->vfs_sb, &wbc);
+ generic_sync_sb_inodes(&wbc);
nr_written = nr_to_write - wbc.nr_to_write;
if (!nr_written) {
@@ -83,7 +84,7 @@ static int shrink_liability(struct ubifs_info *c, int nr_to_write)
wbc.sync_mode = WB_SYNC_ALL;
wbc.range_end = LLONG_MAX;
wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(c->vfs_sb, &wbc);
+ generic_sync_sb_inodes(&wbc);
nr_written = nr_to_write - wbc.nr_to_write;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 26d2e0d..06e80e3 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -439,6 +439,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
int i, err;
struct ubifs_info *c = sb->s_fs_info;
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_ALL,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -462,7 +463,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
* the user be able to get more accurate results of 'statfs()' after
* they synchronize the file system.
*/
- generic_sync_sb_inodes(sb, &wbc);
+ generic_sync_sb_inodes(&wbc);
/*
* Synchronize write buffers, because 'ubifs_run_commit()' does not
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 73e9b64..b0da459 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2070,8 +2070,7 @@ static inline void invalidate_remote_inode(struct inode *inode)
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
-extern void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc);
+extern void generic_sync_sb_inodes(struct writeback_control *wbc);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3224820..5b4ceef 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -40,6 +40,8 @@ enum writeback_sync_modes {
struct writeback_control {
struct backing_dev_info *bdi; /* If !NULL, only write back this
queue */
+ struct super_block *sb; /* if !NULL, only write inodes from
+ this super_block */
enum writeback_sync_modes sync_mode;
unsigned long *older_than_this; /* If !NULL, only write back inodes
older than this */
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 11:18 ` [PATCH 1/8] writeback: move super_block argument to struct writeback_control Jens Axboe
@ 2009-09-01 11:55 ` Theodore Tso
2009-09-01 11:57 ` Theodore Tso
2009-09-01 21:51 ` Christoph Hellwig
1 sibling, 1 reply; 22+ messages in thread
From: Theodore Tso @ 2009-09-01 11:55 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-kernel, linux-fsdevel, chris.mason, david, hch, akpm, jack
On Tue, Sep 01, 2009 at 01:18:59PM +0200, Jens Axboe wrote:
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
> ---
> fs/ubifs/super.c | 3 ++-
> include/linux/fs.h | 3 +--
>
> diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
> @@ -462,7 +463,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
> * the user be able to get more accurate results of 'statfs()' after
> * they synchronize the file system.
> */
> - generic_sync_sb_inodes(sb, &wbc);
> + generic_sync_sb_inodes(&wbc);
>
> /*
> * Synchronize write buffers, because 'ubifs_run_commit()' does not
I just tried compiling per-bdi v15 against the latest git HEAD, and
the compilation failed:
fs/ubifs/super.c: In function ‘ubifs_sync_fs’:
fs/ubifs/super.c:465: warning: passing argument 1 of ‘generic_sync_sb_inodes’ from incompatible pointer type
fs/ubifs/super.c:465: error: too many arguments to function ‘generic_sync_sb_inodes’
Looks like the latest version of fs/ubifs/super.c added a call to
generic_sync_sb_inodes that needs to be fixed up. Line 465:
generic_sync_sb_inodes(sb, &wbc);
- Ted
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 11:55 ` Theodore Tso
@ 2009-09-01 11:57 ` Theodore Tso
2009-09-01 12:05 ` Jens Axboe
0 siblings, 1 reply; 22+ messages in thread
From: Theodore Tso @ 2009-09-01 11:57 UTC (permalink / raw)
To: Jens Axboe, linux-kernel, linux-fsdevel, chris.mason, david, hch,
akpm
On Tue, Sep 01, 2009 at 07:55:51AM -0400, Theodore Tso wrote:
>
> I just tried compiling per-bdi v15 against the latest git HEAD, and
> the compilation failed:
Oops, never mind. I just realized you had already fixed this in v16.
- Ted
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 11:57 ` Theodore Tso
@ 2009-09-01 12:05 ` Jens Axboe
2009-09-01 14:06 ` Theodore Tso
0 siblings, 1 reply; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 12:05 UTC (permalink / raw)
To: Theodore Tso
Cc: linux-kernel, linux-fsdevel, chris.mason, david, hch, akpm, jack
On Tue, Sep 01 2009, Theodore Tso wrote:
> On Tue, Sep 01, 2009 at 07:55:51AM -0400, Theodore Tso wrote:
> >
> > I just tried compiling per-bdi v15 against the latest git HEAD, and
> > the compilation failed:
>
> Oops, never mind. I just realized you had already fixed this in v16.
Yeah, I didn't realize we had out-of-core callers of
generic_sync_sb_inodes(), should be alright now :-)
--
Jens Axboe
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 12:05 ` Jens Axboe
@ 2009-09-01 14:06 ` Theodore Tso
0 siblings, 0 replies; 22+ messages in thread
From: Theodore Tso @ 2009-09-01 14:06 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-kernel, linux-fsdevel, chris.mason, david, hch, akpm, jack
On Tue, Sep 01, 2009 at 02:05:11PM +0200, Jens Axboe wrote:
> On Tue, Sep 01 2009, Theodore Tso wrote:
> > On Tue, Sep 01, 2009 at 07:55:51AM -0400, Theodore Tso wrote:
> > >
> > > I just tried compiling per-bdi v15 against the latest git HEAD, and
> > > the compilation failed:
> >
> > Oops, never mind. I just realized you had already fixed this in v16.
>
> Yeah, I didn't realize we had out-of-core callers of
> generic_sync_sb_inodes(), should be alright now :-)
I just sent out a call for benchmarking/testing to the ext4 list, and
cc'ed LKML.
git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git test-bdi
http://git.kernel.org/?p=linux/kernel/git/tytso/ext4.git
This contains the v16 per-bdi patches plus the ext4 patches I plan to
push for 2.6.32.
I'm also running it through XFSQA using ext4; it's been a clean run so
far.
- Ted
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 11:18 ` [PATCH 1/8] writeback: move super_block argument to struct writeback_control Jens Axboe
2009-09-01 11:55 ` Theodore Tso
@ 2009-09-01 21:51 ` Christoph Hellwig
2009-09-02 6:45 ` Jens Axboe
1 sibling, 1 reply; 22+ messages in thread
From: Christoph Hellwig @ 2009-09-01 21:51 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-kernel, linux-fsdevel, chris.mason, david, hch, tytso, akpm,
jack
On Tue, Sep 01, 2009 at 01:18:59PM +0200, Jens Axboe wrote:
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
> ---
> drivers/staging/pohmelfs/inode.c | 3 ++-
> fs/fs-writeback.c | 14 +++++++-------
> fs/ubifs/budget.c | 5 +++--
> fs/ubifs/super.c | 3 ++-
> include/linux/fs.h | 3 +--
> include/linux/writeback.h | 2 ++
I think we need better calling conventions here. Currently this whole
area is on crack, we have from highest to lowest layer:
- sync_inodes_sb - does two totally different things based on the
wait flag. If the wait flag is set does a WB_SYNC_ALL writeout
of all pages. If not does a WB_SYNC_NONE based on some whacky
heuristics despite actually wanting to write out everything.
- sync_sb_inodes - toally useless wrapper. Introduces because reiser4
eventually wanted to hook in there, but that needs some major
rethinking before it can happen.
- generic_sync_inodes_sb - used to implement both cases of
sync_inodes_sb, plus:
- UBIFS budgeting writeouts, in either blocking or non-blocking
way
- UBIFS sync use that is gone in -next because we fixed sync
- a complete crackpot usage in pohmelfs, which we fortunately can
simply ignore because it's in -staging.
So instead of exporting generic_sync_sb_inodes which now takes just
a wbc we should just export two helpers to either data integrity sync
and SB or do a SYNC_NONE on it, both taking no other parameter than
the superblock.
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 1/8] writeback: move super_block argument to struct writeback_control
2009-09-01 21:51 ` Christoph Hellwig
@ 2009-09-02 6:45 ` Jens Axboe
0 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-02 6:45 UTC (permalink / raw)
To: Christoph Hellwig
Cc: linux-kernel, linux-fsdevel, chris.mason, david, tytso, akpm,
jack
On Tue, Sep 01 2009, Christoph Hellwig wrote:
> On Tue, Sep 01, 2009 at 01:18:59PM +0200, Jens Axboe wrote:
> > Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
> > ---
> > drivers/staging/pohmelfs/inode.c | 3 ++-
> > fs/fs-writeback.c | 14 +++++++-------
> > fs/ubifs/budget.c | 5 +++--
> > fs/ubifs/super.c | 3 ++-
> > include/linux/fs.h | 3 +--
> > include/linux/writeback.h | 2 ++
>
> I think we need better calling conventions here. Currently this whole
> area is on crack, we have from highest to lowest layer:
>
>
> - sync_inodes_sb - does two totally different things based on the
> wait flag. If the wait flag is set does a WB_SYNC_ALL writeout
> of all pages. If not does a WB_SYNC_NONE based on some whacky
> heuristics despite actually wanting to write out everything.
> - sync_sb_inodes - toally useless wrapper. Introduces because reiser4
> eventually wanted to hook in there, but that needs some major
> rethinking before it can happen.
> - generic_sync_inodes_sb - used to implement both cases of
> sync_inodes_sb, plus:
>
> - UBIFS budgeting writeouts, in either blocking or non-blocking
> way
> - UBIFS sync use that is gone in -next because we fixed sync
> - a complete crackpot usage in pohmelfs, which we fortunately can
> simply ignore because it's in -staging.
>
>
> So instead of exporting generic_sync_sb_inodes which now takes just
> a wbc we should just export two helpers to either data integrity sync
> and SB or do a SYNC_NONE on it, both taking no other parameter than
> the superblock.
Agreed, that would clean it up nicely. I'll do that as a prep patch,
too.
--
Jens Axboe
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH 2/8] writeback: move dirty inodes from super_block to backing_dev_info
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
2009-09-01 11:18 ` [PATCH 1/8] writeback: move super_block argument to struct writeback_control Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 3/8] writeback: switch to per-bdi threads for flushing data Jens Axboe
` (5 subsequent siblings)
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
This is a first step at introducing per-bdi flusher threads. We should
have no change in behaviour, although sb_has_dirty_inodes() is now
ridiculously expensive, as there's no easy way to answer that question.
Not a huge problem, since it'll be deleted in subsequent patches.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/fs-writeback.c | 194 +++++++++++++++++++++++++++---------------
fs/super.c | 3 -
include/linux/backing-dev.h | 9 ++
include/linux/fs.h | 5 +-
mm/backing-dev.c | 24 ++++++
mm/page-writeback.c | 11 +--
6 files changed, 163 insertions(+), 83 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8c43ca4..b83eb44 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -25,6 +25,7 @@
#include <linux/buffer_head.h>
#include "internal.h"
+#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
/**
* writeback_acquire - attempt to get exclusive writeback access to a device
@@ -165,12 +166,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
goto out;
/*
- * If the inode was already on s_dirty/s_io/s_more_io, don't
- * reposition it (that would break s_dirty time-ordering).
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
*/
if (!was_dirty) {
inode->dirtied_when = jiffies;
- list_move(&inode->i_list, &sb->s_dirty);
+ list_move(&inode->i_list,
+ &inode_to_bdi(inode)->b_dirty);
}
}
out:
@@ -191,31 +193,30 @@ static int write_inode(struct inode *inode, int sync)
* furthest end of its superblock's dirty-inode list.
*
* Before stamping the inode's ->dirtied_when, we check to see whether it is
- * already the most-recently-dirtied inode on the s_dirty list. If that is
+ * already the most-recently-dirtied inode on the b_dirty list. If that is
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
static void redirty_tail(struct inode *inode)
{
- struct super_block *sb = inode->i_sb;
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
- if (!list_empty(&sb->s_dirty)) {
- struct inode *tail_inode;
+ if (!list_empty(&bdi->b_dirty)) {
+ struct inode *tail;
- tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
- if (time_before(inode->dirtied_when,
- tail_inode->dirtied_when))
+ tail = list_entry(bdi->b_dirty.next, struct inode, i_list);
+ if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &sb->s_dirty);
+ list_move(&inode->i_list, &bdi->b_dirty);
}
/*
- * requeue inode for re-scanning after sb->s_io list is exhausted.
+ * requeue inode for re-scanning after bdi->b_io list is exhausted.
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode->i_sb->s_more_io);
+ list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -262,18 +263,50 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct super_block *sb,
- unsigned long *older_than_this)
+static void queue_io(struct backing_dev_info *bdi,
+ unsigned long *older_than_this)
{
- list_splice_init(&sb->s_more_io, sb->s_io.prev);
- move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+ list_splice_init(&bdi->b_more_io, bdi->b_io.prev);
+ move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
+}
+
+static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
+{
+ struct inode *inode;
+ int ret = 0;
+
+ spin_lock(&inode_lock);
+ list_for_each_entry(inode, list, i_list) {
+ if (inode->i_sb == sb) {
+ ret = 1;
+ break;
+ }
+ }
+ spin_unlock(&inode_lock);
+ return ret;
}
int sb_has_dirty_inodes(struct super_block *sb)
{
- return !list_empty(&sb->s_dirty) ||
- !list_empty(&sb->s_io) ||
- !list_empty(&sb->s_more_io);
+ struct backing_dev_info *bdi;
+ int ret = 0;
+
+ /*
+ * This is REALLY expensive right now, but it'll go away
+ * when the bdi writeback is introduced
+ */
+ mutex_lock(&bdi_lock);
+ list_for_each_entry(bdi, &bdi_list, bdi_list) {
+ if (sb_on_inode_list(sb, &bdi->b_dirty) ||
+ sb_on_inode_list(sb, &bdi->b_io) ||
+ sb_on_inode_list(sb, &bdi->b_more_io)) {
+ ret = 1;
+ break;
+ }
+ }
+ mutex_unlock(&bdi_lock);
+
+ return ret;
}
EXPORT_SYMBOL(sb_has_dirty_inodes);
@@ -322,11 +355,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
if (inode->i_state & I_SYNC) {
/*
* If this inode is locked for writeback and we are not doing
- * writeback-for-data-integrity, move it to s_more_io so that
+ * writeback-for-data-integrity, move it to b_more_io so that
* writeback can proceed with the other inodes on s_io.
*
* We'll have another go at writing back this inode when we
- * completed a full scan of s_io.
+ * completed a full scan of b_io.
*/
if (!wait) {
requeue_io(inode);
@@ -371,11 +404,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything. Redirty
- * the inode; Move it from s_io onto s_more_io/s_dirty.
+ * the inode; Move it from b_io onto b_more_io/b_dirty.
*/
/*
* akpm: if the caller was the kupdate function we put
- * this inode at the head of s_dirty so it gets first
+ * this inode at the head of b_dirty so it gets first
* consideration. Otherwise, move it to the tail, for
* the reasons described there. I'm not really sure
* how much sense this makes. Presumably I had a good
@@ -385,7 +418,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
if (wbc->for_kupdate) {
/*
* For the kupdate function we move the inode
- * to s_more_io so it will get more writeout as
+ * to b_more_io so it will get more writeout as
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
@@ -433,51 +466,33 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
-/*
- * Write out a superblock's list of dirty inodes. A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If we're a pdflush thread, then implement pdflush collision avoidance
- * against the entire list.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched. For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
- *
- * The inodes to be written are parked on sb->s_io. They are moved back onto
- * sb->s_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
-void generic_sync_sb_inodes(struct writeback_control *wbc)
+static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
+ struct writeback_control *wbc)
{
struct super_block *sb = wbc->sb;
+ const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
- int sync = wbc->sync_mode == WB_SYNC_ALL;
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&sb->s_io))
- queue_io(sb, wbc->older_than_this);
+ if (!wbc->for_kupdate || list_empty(&bdi->b_io))
+ queue_io(bdi, wbc->older_than_this);
- while (!list_empty(&sb->s_io)) {
- struct inode *inode = list_entry(sb->s_io.prev,
+ while (!list_empty(&bdi->b_io)) {
+ struct inode *inode = list_entry(bdi->b_io.prev,
struct inode, i_list);
- struct address_space *mapping = inode->i_mapping;
- struct backing_dev_info *bdi = mapping->backing_dev_info;
long pages_skipped;
+ /*
+ * super block given and doesn't match, skip this inode
+ */
+ if (sb && sb != inode->i_sb) {
+ redirty_tail(inode);
+ continue;
+ }
+
if (!bdi_cap_writeback_dirty(bdi)) {
redirty_tail(inode);
- if (sb_is_blkdev_sb(sb)) {
+ if (is_blkdev_sb) {
/*
* Dirty memory-backed blockdev: the ramdisk
* driver does this. Skip just this inode
@@ -499,14 +514,14 @@ void generic_sync_sb_inodes(struct writeback_control *wbc)
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
- if (!sb_is_blkdev_sb(sb))
+ if (!is_blkdev_sb)
break; /* Skip a congested fs */
requeue_io(inode);
continue; /* Skip a congested blockdev */
}
if (wbc->bdi && bdi != wbc->bdi) {
- if (!sb_is_blkdev_sb(sb))
+ if (!is_blkdev_sb)
break; /* fs has the wrong queue */
requeue_io(inode);
continue; /* blockdev has wrong queue */
@@ -544,13 +559,56 @@ void generic_sync_sb_inodes(struct writeback_control *wbc)
wbc->more_io = 1;
break;
}
- if (!list_empty(&sb->s_more_io))
+ if (!list_empty(&bdi->b_more_io))
wbc->more_io = 1;
}
- if (sync) {
+ spin_unlock(&inode_lock);
+ /* Leave any unwritten inodes on b_io */
+}
+
+/*
+ * Write out a superblock's list of dirty inodes. A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * against the entire list.
+ *
+ * If `bdi' is non-zero then we're being asked to writeback a specific queue.
+ * This function assumes that the blockdev superblock's inodes are backed by
+ * a variety of queues, so all inodes are searched. For other superblocks,
+ * assume that all inodes are backed by the same queue.
+ *
+ * FIXME: this linear search could get expensive with many fileystems. But
+ * how to fix? We need to go from an address_space to all inodes which share
+ * a queue with that address_space. (Easy: have a global "dirty superblocks"
+ * list).
+ *
+ * The inodes to be written are parked on bdi->b_io. They are moved back onto
+ * bdi->b_dirty as they are selected for writing. This way, none can be missed
+ * on the writer throttling path, and we get decent balancing between many
+ * throttled threads: we don't want them all piling up on inode_sync_wait.
+ */
+void generic_sync_sb_inodes(struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi;
+
+ if (!wbc->bdi) {
+ mutex_lock(&bdi_lock);
+ list_for_each_entry(bdi, &bdi_list, bdi_list)
+ generic_sync_bdi_inodes(bdi, wbc);
+ mutex_unlock(&bdi_lock);
+ } else
+ generic_sync_bdi_inodes(wbc->bdi, wbc);
+
+ if (wbc->sync_mode == WB_SYNC_ALL) {
struct inode *inode, *old_inode = NULL;
+ spin_lock(&inode_lock);
+
/*
* Data integrity sync. Must wait for all pages under writeback,
* because there may have been pages dirtied before our sync
@@ -558,7 +616,7 @@ void generic_sync_sb_inodes(struct writeback_control *wbc)
* In which case, the inode may not be on the dirty list, but
* we still have to wait for that writeout.
*/
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ list_for_each_entry(inode, &wbc->sb->s_inodes, i_sb_list) {
struct address_space *mapping;
if (inode->i_state &
@@ -588,10 +646,8 @@ void generic_sync_sb_inodes(struct writeback_control *wbc)
}
spin_unlock(&inode_lock);
iput(old_inode);
- } else
- spin_unlock(&inode_lock);
+ }
- return; /* Leave any unwritten inodes on s_io */
}
EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
@@ -605,8 +661,8 @@ static void sync_sb_inodes(struct writeback_control *wbc)
*
* Note:
* We don't need to grab a reference to superblock here. If it has non-empty
- * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
+ * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
+ * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
* empty. Since __sync_single_inode() regains inode_lock before it finally moves
* inode from superblock lists we are OK.
*
diff --git a/fs/super.c b/fs/super.c
index 2761d3e..0d22ce3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -62,9 +62,6 @@ static struct super_block *alloc_super(struct file_system_type *type)
s = NULL;
goto out;
}
- INIT_LIST_HEAD(&s->s_dirty);
- INIT_LIST_HEAD(&s->s_io);
- INIT_LIST_HEAD(&s->s_more_io);
INIT_LIST_HEAD(&s->s_files);
INIT_LIST_HEAD(&s->s_instances);
INIT_HLIST_HEAD(&s->s_anon);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1d52425..928cd54 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -40,6 +40,8 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
struct backing_dev_info {
+ struct list_head bdi_list;
+
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
@@ -58,6 +60,10 @@ struct backing_dev_info {
struct device *dev;
+ struct list_head b_dirty; /* dirty inodes */
+ struct list_head b_io; /* parked for writeback */
+ struct list_head b_more_io; /* parked for more writeback */
+
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
struct dentry *debug_stats;
@@ -72,6 +78,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+extern struct mutex bdi_lock;
+extern struct list_head bdi_list;
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b0da459..0a40b80 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -715,7 +715,7 @@ struct posix_acl;
struct inode {
struct hlist_node i_hash;
- struct list_head i_list;
+ struct list_head i_list; /* backing dev IO list */
struct list_head i_sb_list;
struct list_head i_dentry;
unsigned long i_ino;
@@ -1336,9 +1336,6 @@ struct super_block {
struct xattr_handler **s_xattr;
struct list_head s_inodes; /* all inodes */
- struct list_head s_dirty; /* dirty inodes */
- struct list_head s_io; /* parked for writeback */
- struct list_head s_more_io; /* parked for more writeback */
struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */
struct list_head s_files;
/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c86edd2..6f163e0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -22,6 +22,8 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
+DEFINE_MUTEX(bdi_lock);
+LIST_HEAD(bdi_list);
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
@@ -211,6 +213,10 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
+ mutex_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_list);
+ mutex_unlock(&bdi_lock);
+
bdi->dev = dev;
bdi_debug_register(bdi, dev_name(dev));
@@ -225,9 +231,17 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
}
EXPORT_SYMBOL(bdi_register_dev);
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+ mutex_lock(&bdi_lock);
+ list_del(&bdi->bdi_list);
+ mutex_unlock(&bdi_lock);
+}
+
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
+ bdi_remove_from_list(bdi);
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -245,6 +259,10 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ INIT_LIST_HEAD(&bdi->bdi_list);
+ INIT_LIST_HEAD(&bdi->b_io);
+ INIT_LIST_HEAD(&bdi->b_dirty);
+ INIT_LIST_HEAD(&bdi->b_more_io);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -259,6 +277,8 @@ int bdi_init(struct backing_dev_info *bdi)
err:
while (i--)
percpu_counter_destroy(&bdi->bdi_stat[i]);
+
+ bdi_remove_from_list(bdi);
}
return err;
@@ -269,6 +289,10 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
+ WARN_ON(!list_empty(&bdi->b_dirty));
+ WARN_ON(!list_empty(&bdi->b_io));
+ WARN_ON(!list_empty(&bdi->b_more_io));
+
bdi_unregister(bdi);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 81627eb..f8341b6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -320,15 +320,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
/*
*
*/
-static DEFINE_SPINLOCK(bdi_lock);
static unsigned int bdi_min_ratio;
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- unsigned long flags;
- spin_lock_irqsave(&bdi_lock, flags);
+ mutex_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -340,27 +338,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ mutex_unlock(&bdi_lock);
return ret;
}
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
{
- unsigned long flags;
int ret = 0;
if (max_ratio > 100)
return -EINVAL;
- spin_lock_irqsave(&bdi_lock, flags);
+ mutex_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ mutex_unlock(&bdi_lock);
return ret;
}
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 3/8] writeback: switch to per-bdi threads for flushing data
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
2009-09-01 11:18 ` [PATCH 1/8] writeback: move super_block argument to struct writeback_control Jens Axboe
2009-09-01 11:19 ` [PATCH 2/8] writeback: move dirty inodes from super_block to backing_dev_info Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 4/8] writeback: get rid of pdflush completely Jens Axboe
` (4 subsequent siblings)
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
This is an experiment to see if we get better writeout behaviour with
per-bdi flushing. Some initial tests look pretty encouraging. A sample
ffsb workload that does random writes to files is about 8% faster here
on a simple SATA drive during the benchmark phase. File layout also seems
a LOT more smooth in vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
So apart from seemingly behaving better for buffered writeout, this also
allows us to potentially have more than one bdi thread flushing out data.
This may be useful for NUMA type setups.
A 10 disk test with btrfs performs 26% faster with per-bdi flushing. Other
tests pending. mmap heavy writing also improves considerably.
A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/buffer.c | 2 +-
fs/fs-writeback.c | 851 ++++++++++++++++++++++++++++++-------------
fs/sync.c | 2 +-
include/linux/backing-dev.h | 56 +++-
include/linux/fs.h | 2 +-
include/linux/writeback.h | 4 +-
mm/backing-dev.c | 340 ++++++++++++++++-
mm/page-writeback.c | 165 ++-------
mm/vmscan.c | 2 +-
9 files changed, 1006 insertions(+), 418 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 28f320f..90a9886 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -281,7 +281,7 @@ static void free_more_memory(void)
struct zone *zone;
int nid;
- wakeup_pdflush(1024);
+ wakeup_flusher_threads(1024);
yield();
for_each_online_node(nid) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index b83eb44..0acc684 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -19,6 +19,8 @@
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -27,165 +29,213 @@
#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue. Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own. Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
+/*
+ * Work items for the bdi_writeback threads
*/
-static int writeback_acquire(struct backing_dev_info *bdi)
+struct bdi_work {
+ struct list_head list;
+ struct list_head wait_list;
+ struct rcu_head rcu_head;
+
+ unsigned long seen;
+ atomic_t pending;
+
+ struct super_block *sb;
+ unsigned long nr_pages;
+ enum writeback_sync_modes sync_mode;
+
+ unsigned long state;
+};
+
+enum {
+ WS_USED_B = 0,
+ WS_ONSTACK_B,
+};
+
+#define WS_USED (1 << WS_USED_B)
+#define WS_ONSTACK (1 << WS_ONSTACK_B)
+
+static inline bool bdi_work_on_stack(struct bdi_work *work)
+{
+ return test_bit(WS_ONSTACK_B, &work->state);
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+ struct writeback_control *wbc)
{
- return !test_and_set_bit(BDI_pdflush, &bdi->state);
+ INIT_RCU_HEAD(&work->rcu_head);
+ work->sb = wbc->sb;
+ work->nr_pages = wbc->nr_to_write;
+ work->sync_mode = wbc->sync_mode;
+ work->state = WS_USED;
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+ struct writeback_control *wbc)
+{
+ bdi_work_init(work, wbc);
+ work->state |= WS_ONSTACK;
}
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
*
- * Determine whether there is writeback in progress against a backing device.
+ * Determine whether there is writeback waiting to be handled against a
+ * backing device.
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
- return test_bit(BDI_pdflush, &bdi->state);
+ return !list_empty(&bdi->work_list);
}
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
- */
-static void writeback_release(struct backing_dev_info *bdi)
+static void bdi_work_clear(struct bdi_work *work)
{
- BUG_ON(!writeback_in_progress(bdi));
- clear_bit(BDI_pdflush, &bdi->state);
+ clear_bit(WS_USED_B, &work->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&work->state, WS_USED_B);
}
-static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+static void bdi_work_free(struct rcu_head *head)
{
- if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
- struct dentry *dentry;
- const char *name = "?";
+ struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
- dentry = d_find_alias(inode);
- if (dentry) {
- spin_lock(&dentry->d_lock);
- name = (const char *) dentry->d_name.name;
- }
- printk(KERN_DEBUG
- "%s(%d): dirtied inode %lu (%s) on %s\n",
- current->comm, task_pid_nr(current), inode->i_ino,
- name, inode->i_sb->s_id);
- if (dentry) {
- spin_unlock(&dentry->d_lock);
- dput(dentry);
- }
- }
+ if (!bdi_work_on_stack(work))
+ kfree(work);
+ else
+ bdi_work_clear(work);
}
-/**
- * __mark_inode_dirty - internal function
- * @inode: inode to mark
- * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
- * Mark an inode as dirty. Callers should use mark_inode_dirty or
- * mark_inode_dirty_sync.
- *
- * Put the inode on the super block's dirty list.
- *
- * CAREFUL! We mark it dirty unconditionally, but move it onto the
- * dirty list only if it is hashed or if it refers to a blockdev.
- * If it was not hashed, it will never be added to the dirty list
- * even if it is later hashed, as it will have been marked dirty already.
- *
- * In short, make sure you hash any inodes _before_ you start marking
- * them dirty.
- *
- * This function *must* be atomic for the I_DIRTY_PAGES case -
- * set_page_dirty() is called under spinlock in several places.
- *
- * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
- * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
- * the kernel-internal blockdev inode represents the dirtying time of the
- * blockdev's pages. This is why for I_DIRTY_PAGES we always use
- * page->mapping->host, so the page-dirtying time is recorded in the internal
- * blockdev inode.
- */
-void __mark_inode_dirty(struct inode *inode, int flags)
+static void wb_work_complete(struct bdi_work *work)
{
- struct super_block *sb = inode->i_sb;
+ const enum writeback_sync_modes sync_mode = work->sync_mode;
/*
- * Don't do this for I_DIRTY_PAGES - that doesn't actually
- * dirty the inode itself
+ * For allocated work, we can clear the done/seen bit right here.
+ * For on-stack work, we need to postpone both the clear and free
+ * to after the RCU grace period, since the stack could be invalidated
+ * as soon as bdi_work_clear() has done the wakeup.
*/
- if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- if (sb->s_op->dirty_inode)
- sb->s_op->dirty_inode(inode);
- }
+ if (!bdi_work_on_stack(work))
+ bdi_work_clear(work);
+ if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work))
+ call_rcu(&work->rcu_head, bdi_work_free);
+}
+static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
+{
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * The caller has retrieved the work arguments from this work,
+ * drop our reference. If this is the last ref, delete and free it
*/
- smp_mb();
+ if (atomic_dec_and_test(&work->pending)) {
+ struct backing_dev_info *bdi = wb->bdi;
- /* avoid the locking if we can */
- if ((inode->i_state & flags) == flags)
- return;
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&work->list);
+ spin_unlock(&bdi->wb_lock);
- if (unlikely(block_dump))
- block_dump___mark_inode_dirty(inode);
+ wb_work_complete(work);
+ }
+}
- spin_lock(&inode_lock);
- if ((inode->i_state & flags) != flags) {
- const int was_dirty = inode->i_state & I_DIRTY;
+static void wb_start_writeback(struct bdi_writeback *wb, struct bdi_work *work)
+{
+ /*
+ * If we failed allocating the bdi work item, wake up the wb thread
+ * always. As a safety precaution, it'll flush out everything
+ */
+ if (!wb_has_dirty_io(wb) && work)
+ wb_clear_pending(wb, work);
+ else if (wb->task)
+ wake_up_process(wb->task);
+}
- inode->i_state |= flags;
+static void bdi_sched_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ wb_start_writeback(&bdi->wb, work);
+}
- /*
- * If the inode is being synced, just update its dirty state.
- * The unlocker will place the inode on the appropriate
- * superblock list, based upon its state.
- */
- if (inode->i_state & I_SYNC)
- goto out;
+static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ if (work) {
+ work->seen = bdi->wb_mask;
+ BUG_ON(!work->seen);
+ atomic_set(&work->pending, bdi->wb_cnt);
+ BUG_ON(!bdi->wb_cnt);
/*
- * Only add valid (hashed) inodes to the superblock's
- * dirty list. Add blockdev inodes as well.
+ * Make sure stores are seen before it appears on the list
*/
- if (!S_ISBLK(inode->i_mode)) {
- if (hlist_unhashed(&inode->i_hash))
- goto out;
- }
- if (inode->i_state & (I_FREEING|I_CLEAR))
- goto out;
+ smp_mb();
- /*
- * If the inode was already on b_dirty/b_io/b_more_io, don't
- * reposition it (that would break b_dirty time-ordering).
- */
- if (!was_dirty) {
- inode->dirtied_when = jiffies;
- list_move(&inode->i_list,
- &inode_to_bdi(inode)->b_dirty);
- }
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&work->list, &bdi->work_list);
+ spin_unlock(&bdi->wb_lock);
}
-out:
- spin_unlock(&inode_lock);
+
+ /*
+ * If the default thread isn't there, make sure we add it. When
+ * it gets created and wakes up, we'll run this work.
+ */
+ if (unlikely(list_empty_careful(&bdi->wb_list)))
+ wake_up_process(default_backing_dev_info.wb.task);
+ else
+ bdi_sched_work(bdi, work);
}
-EXPORT_SYMBOL(__mark_inode_dirty);
+/*
+ * Used for on-stack allocated work items. The caller needs to wait until
+ * the wb threads have acked the work before it's safe to continue.
+ */
+static void bdi_wait_on_work_clear(struct bdi_work *work)
+{
+ wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+}
-static int write_inode(struct inode *inode, int sync)
+static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, sync);
- return 0;
+ struct bdi_work *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work)
+ bdi_work_init(work, wbc);
+
+ return work;
+}
+
+void bdi_start_writeback(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct bdi_work work_stack, *work = NULL;
+
+ if (!must_wait)
+ work = bdi_alloc_work(wbc);
+
+ if (!work) {
+ work = &work_stack;
+ bdi_work_init_on_stack(work, wbc);
+ }
+
+ bdi_queue_work(wbc->bdi, work);
+
+ /*
+ * If the sync mode is WB_SYNC_ALL, block waiting for the work to
+ * complete. If not, we only need to wait for the work to be started,
+ * if we allocated it on-stack. We use the same mechanism, if the
+ * wait bit is set in the bdi_work struct, then threads will not
+ * clear pending until after they are done.
+ *
+ * Note that work == &work_stack if must_wait is true, so we don't
+ * need to do call_rcu() here ever, since the completion path will
+ * have done that for us.
+ */
+ if (must_wait || work == &work_stack) {
+ bdi_wait_on_work_clear(work);
+ if (work != &work_stack)
+ call_rcu(&work->rcu_head, bdi_work_free);
+ }
}
/*
@@ -199,16 +249,16 @@ static int write_inode(struct inode *inode, int sync)
*/
static void redirty_tail(struct inode *inode)
{
- struct backing_dev_info *bdi = inode_to_bdi(inode);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
- if (!list_empty(&bdi->b_dirty)) {
+ if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
- tail = list_entry(bdi->b_dirty.next, struct inode, i_list);
+ tail = list_entry(wb->b_dirty.next, struct inode, i_list);
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &bdi->b_dirty);
+ list_move(&inode->i_list, &wb->b_dirty);
}
/*
@@ -216,7 +266,9 @@ static void redirty_tail(struct inode *inode)
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ list_move(&inode->i_list, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -263,52 +315,18 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct backing_dev_info *bdi,
- unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
- list_splice_init(&bdi->b_more_io, bdi->b_io.prev);
- move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
+ list_splice_init(&wb->b_more_io, wb->b_io.prev);
+ move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}
-static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
-{
- struct inode *inode;
- int ret = 0;
-
- spin_lock(&inode_lock);
- list_for_each_entry(inode, list, i_list) {
- if (inode->i_sb == sb) {
- ret = 1;
- break;
- }
- }
- spin_unlock(&inode_lock);
- return ret;
-}
-
-int sb_has_dirty_inodes(struct super_block *sb)
+static int write_inode(struct inode *inode, int sync)
{
- struct backing_dev_info *bdi;
- int ret = 0;
-
- /*
- * This is REALLY expensive right now, but it'll go away
- * when the bdi writeback is introduced
- */
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list) {
- if (sb_on_inode_list(sb, &bdi->b_dirty) ||
- sb_on_inode_list(sb, &bdi->b_io) ||
- sb_on_inode_list(sb, &bdi->b_more_io)) {
- ret = 1;
- break;
- }
- }
- mutex_unlock(&bdi_lock);
-
- return ret;
+ if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
+ return inode->i_sb->s_op->write_inode(inode, sync);
+ return 0;
}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
* Wait for writeback on an inode to complete.
@@ -466,19 +484,20 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
-static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
- struct writeback_control *wbc)
+static void generic_sync_wb_inodes(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
{
struct super_block *sb = wbc->sb;
const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&bdi->b_io))
- queue_io(bdi, wbc->older_than_this);
- while (!list_empty(&bdi->b_io)) {
- struct inode *inode = list_entry(bdi->b_io.prev,
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
+
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
struct inode, i_list);
long pages_skipped;
@@ -490,7 +509,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (!bdi_cap_writeback_dirty(bdi)) {
+ if (!bdi_cap_writeback_dirty(wb->bdi)) {
redirty_tail(inode);
if (is_blkdev_sb) {
/*
@@ -512,7 +531,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
wbc->encountered_congestion = 1;
if (!is_blkdev_sb)
break; /* Skip a congested fs */
@@ -520,13 +539,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue; /* Skip a congested blockdev */
}
- if (wbc->bdi && bdi != wbc->bdi) {
- if (!is_blkdev_sb)
- break; /* fs has the wrong queue */
- requeue_io(inode);
- continue; /* blockdev has wrong queue */
- }
-
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
@@ -534,16 +546,10 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
if (inode_dirtied_after(inode, start))
break;
- /* Is another pdflush already flushing this queue? */
- if (current_is_pdflush() && !writeback_acquire(bdi))
- break;
-
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
- if (current_is_pdflush())
- writeback_release(bdi);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
@@ -559,7 +565,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
wbc->more_io = 1;
break;
}
- if (!list_empty(&bdi->b_more_io))
+ if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
@@ -567,6 +573,388 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
/* Leave any unwritten inodes on b_io */
}
+void generic_sync_bdi_inodes(struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = wbc->bdi;
+
+ generic_sync_wb_inodes(&bdi->wb, wbc);
+}
+
+/*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation. We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode. Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES 1024
+
+static inline bool over_bground_thresh(void)
+{
+ unsigned long background_thresh, dirty_thresh;
+
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+
+ return (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
+}
+
+/*
+ * Explicit flushing or periodic writeback of "old" data.
+ *
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space. So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
+ *
+ * Try to run once per dirty_writeback_interval. But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
+ *
+ * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
+ */
+static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
+ struct super_block *sb,
+ enum writeback_sync_modes sync_mode, int for_kupdate)
+{
+ struct writeback_control wbc = {
+ .bdi = wb->bdi,
+ .sb = sb,
+ .sync_mode = sync_mode,
+ .older_than_this = NULL,
+ .for_kupdate = for_kupdate,
+ .range_cyclic = 1,
+ };
+ unsigned long oldest_jif;
+ long wrote = 0;
+
+ if (wbc.for_kupdate) {
+ wbc.older_than_this = &oldest_jif;
+ oldest_jif = jiffies -
+ msecs_to_jiffies(dirty_expire_interval * 10);
+ }
+
+ for (;;) {
+ if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 &&
+ !over_bground_thresh())
+ break;
+
+ wbc.more_io = 0;
+ wbc.encountered_congestion = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.pages_skipped = 0;
+ generic_sync_wb_inodes(wb, &wbc);
+ nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+
+ /*
+ * If we ran out of stuff to write, bail unless more_io got set
+ */
+ if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+ if (wbc.more_io && !wbc.for_kupdate)
+ continue;
+ break;
+ }
+ }
+
+ return wrote;
+}
+
+/*
+ * Return the next bdi_work struct that hasn't been processed by this
+ * wb thread yet
+ */
+static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct bdi_work *work, *ret = NULL;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(work, &bdi->work_list, list) {
+ if (!test_and_clear_bit(wb->nr, &work->seen))
+ continue;
+
+ ret = work;
+ break;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+/*
+ * Retrieve work items and do the writeback they describe
+ */
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+{
+ struct backing_dev_info *bdi = wb->bdi;
+ struct bdi_work *work;
+ long nr_pages, wrote = 0;
+
+ while ((work = get_next_work_item(bdi, wb)) != NULL) {
+ enum writeback_sync_modes sync_mode;
+
+ nr_pages = work->nr_pages;
+
+ /*
+ * Override sync mode, in case we must wait for completion
+ */
+ if (force_wait)
+ work->sync_mode = sync_mode = WB_SYNC_ALL;
+ else
+ sync_mode = work->sync_mode;
+
+ /*
+ * If this isn't a data integrity operation, just notify
+ * that we have seen this work and we are now starting it.
+ */
+ if (sync_mode == WB_SYNC_NONE)
+ wb_clear_pending(wb, work);
+
+ wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
+
+ /*
+ * This is a data integrity writeback, so only do the
+ * notification when we have completed the work.
+ */
+ if (sync_mode == WB_SYNC_ALL)
+ wb_clear_pending(wb, work);
+ }
+
+ /*
+ * Check for periodic writeback, kupdated() style
+ */
+ if (!wrote) {
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ wrote = wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
+ }
+
+ return wrote;
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
+ */
+int bdi_writeback_task(struct bdi_writeback *wb)
+{
+ unsigned long last_active = jiffies;
+ unsigned long wait_jiffies = -1UL;
+ long pages_written;
+
+ while (!kthread_should_stop()) {
+ pages_written = wb_do_writeback(wb, 0);
+
+ if (pages_written)
+ last_active = jiffies;
+ else if (wait_jiffies != -1UL) {
+ unsigned long max_idle;
+
+ /*
+ * Longest period of inactivity that we tolerate. If we
+ * see dirty data again later, the task will get
+ * recreated automatically.
+ */
+ max_idle = max(5UL * 60 * HZ, wait_jiffies);
+ if (time_after(jiffies, max_idle + last_active))
+ break;
+ }
+
+ wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(wait_jiffies);
+ try_to_freeze();
+ }
+
+ return 0;
+}
+
+/*
+ * Schedule writeback for all backing devices. Expensive! If this is a data
+ * integrity operation, writeback will be complete when this returns. If
+ * we are simply called for WB_SYNC_NONE, then writeback will merely be
+ * scheduled to run.
+ */
+void bdi_writeback_all(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct backing_dev_info *bdi;
+ struct bdi_work *work;
+ LIST_HEAD(list);
+
+restart:
+ spin_lock(&bdi_lock);
+
+ list_for_each_entry(bdi, &bdi_list, bdi_list) {
+ struct bdi_work *work;
+
+ if (!bdi_has_dirty_io(bdi))
+ continue;
+
+ /*
+ * If work allocation fails, do the writes inline. We drop
+ * the lock and restart the list writeout. This should be OK,
+ * since this happens rarely and because the writeout should
+ * eventually make more free memory available.
+ */
+ work = bdi_alloc_work(wbc);
+ if (!work) {
+ struct writeback_control __wbc = *wbc;
+
+ /*
+ * Not a data integrity writeout, just continue
+ */
+ if (!must_wait)
+ continue;
+
+ spin_unlock(&bdi_lock);
+ __wbc = *wbc;
+ __wbc.bdi = bdi;
+ generic_sync_bdi_inodes(&__wbc);
+ goto restart;
+ }
+ if (must_wait)
+ list_add_tail(&work->wait_list, &list);
+
+ bdi_queue_work(bdi, work);
+ }
+
+ spin_unlock(&bdi_lock);
+
+ /*
+ * If this is for WB_SYNC_ALL, wait for pending work to complete
+ * before returning.
+ */
+ while (!list_empty(&list)) {
+ work = list_entry(list.next, struct bdi_work, wait_list);
+ list_del(&work->wait_list);
+ bdi_wait_on_work_clear(work);
+ call_rcu(&work->rcu_head, bdi_work_free);
+ }
+}
+
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+ if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+ struct dentry *dentry;
+ const char *name = "?";
+
+ dentry = d_find_alias(inode);
+ if (dentry) {
+ spin_lock(&dentry->d_lock);
+ name = (const char *) dentry->d_name.name;
+ }
+ printk(KERN_DEBUG
+ "%s(%d): dirtied inode %lu (%s) on %s\n",
+ current->comm, task_pid_nr(current), inode->i_ino,
+ name, inode->i_sb->s_id);
+ if (dentry) {
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ }
+ }
+}
+
+/**
+ * __mark_inode_dirty - internal function
+ * @inode: inode to mark
+ * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
+ * Mark an inode as dirty. Callers should use mark_inode_dirty or
+ * mark_inode_dirty_sync.
+ *
+ * Put the inode on the super block's dirty list.
+ *
+ * CAREFUL! We mark it dirty unconditionally, but move it onto the
+ * dirty list only if it is hashed or if it refers to a blockdev.
+ * If it was not hashed, it will never be added to the dirty list
+ * even if it is later hashed, as it will have been marked dirty already.
+ *
+ * In short, make sure you hash any inodes _before_ you start marking
+ * them dirty.
+ *
+ * This function *must* be atomic for the I_DIRTY_PAGES case -
+ * set_page_dirty() is called under spinlock in several places.
+ *
+ * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
+ * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
+ * the kernel-internal blockdev inode represents the dirtying time of the
+ * blockdev's pages. This is why for I_DIRTY_PAGES we always use
+ * page->mapping->host, so the page-dirtying time is recorded in the internal
+ * blockdev inode.
+ */
+void __mark_inode_dirty(struct inode *inode, int flags)
+{
+ struct super_block *sb = inode->i_sb;
+
+ /*
+ * Don't do this for I_DIRTY_PAGES - that doesn't actually
+ * dirty the inode itself
+ */
+ if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ if (sb->s_op->dirty_inode)
+ sb->s_op->dirty_inode(inode);
+ }
+
+ /*
+ * make sure that changes are seen by all cpus before we test i_state
+ * -- mikulas
+ */
+ smp_mb();
+
+ /* avoid the locking if we can */
+ if ((inode->i_state & flags) == flags)
+ return;
+
+ if (unlikely(block_dump))
+ block_dump___mark_inode_dirty(inode);
+
+ spin_lock(&inode_lock);
+ if ((inode->i_state & flags) != flags) {
+ const int was_dirty = inode->i_state & I_DIRTY;
+
+ inode->i_state |= flags;
+
+ /*
+ * If the inode is being synced, just update its dirty state.
+ * The unlocker will place the inode on the appropriate
+ * superblock list, based upon its state.
+ */
+ if (inode->i_state & I_SYNC)
+ goto out;
+
+ /*
+ * Only add valid (hashed) inodes to the superblock's
+ * dirty list. Add blockdev inodes as well.
+ */
+ if (!S_ISBLK(inode->i_mode)) {
+ if (hlist_unhashed(&inode->i_hash))
+ goto out;
+ }
+ if (inode->i_state & (I_FREEING|I_CLEAR))
+ goto out;
+
+ /*
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
+ */
+ if (!was_dirty) {
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ inode->dirtied_when = jiffies;
+ list_move(&inode->i_list, &wb->b_dirty);
+ }
+ }
+out:
+ spin_unlock(&inode_lock);
+}
+
+EXPORT_SYMBOL(__mark_inode_dirty);
+
/*
* Write out a superblock's list of dirty inodes. A wait will be performed
* upon no inodes, all inodes or the final one, depending upon sync_mode.
@@ -582,27 +970,17 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
* a variety of queues, so all inodes are searched. For other superblocks,
* assume that all inodes are backed by the same queue.
*
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
- *
* The inodes to be written are parked on bdi->b_io. They are moved back onto
* bdi->b_dirty as they are selected for writing. This way, none can be missed
* on the writer throttling path, and we get decent balancing between many
* throttled threads: we don't want them all piling up on inode_sync_wait.
*/
-void generic_sync_sb_inodes(struct writeback_control *wbc)
+static void __generic_sync_sb_inodes(struct writeback_control *wbc)
{
- struct backing_dev_info *bdi;
-
- if (!wbc->bdi) {
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list)
- generic_sync_bdi_inodes(bdi, wbc);
- mutex_unlock(&bdi_lock);
- } else
- generic_sync_bdi_inodes(wbc->bdi, wbc);
+ if (wbc->bdi)
+ bdi_start_writeback(wbc);
+ else
+ bdi_writeback_all(wbc);
if (wbc->sync_mode == WB_SYNC_ALL) {
struct inode *inode, *old_inode = NULL;
@@ -649,63 +1027,30 @@ void generic_sync_sb_inodes(struct writeback_control *wbc)
}
}
-EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
-static void sync_sb_inodes(struct writeback_control *wbc)
+void generic_sync_sb_inodes(struct writeback_control *wbc)
{
- generic_sync_sb_inodes(wbc);
-}
+ struct super_block *sb = wbc->sb;
-/*
- * Start writeback of dirty pagecache data against all unlocked inodes.
- *
- * Note:
- * We don't need to grab a reference to superblock here. If it has non-empty
- * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
- * empty. Since __sync_single_inode() regains inode_lock before it finally moves
- * inode from superblock lists we are OK.
- *
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
- *
- * If `bdi' is non-zero then we will scan the first inode against each
- * superblock until we find the matching ones. One group will be the dirty
- * inodes against a filesystem. Then when we hit the dummy blockdev superblock,
- * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not
- * super-efficient but we're about to do a ton of I/O...
- */
-void
-writeback_inodes(struct writeback_control *wbc)
-{
- struct super_block *sb;
+ if (sb) {
+ spin_lock(&sb_lock);
+ sb->s_count++;
+ spin_unlock(&sb_lock);
+ }
- might_sleep();
- spin_lock(&sb_lock);
-restart:
- list_for_each_entry_reverse(sb, &super_blocks, s_list) {
- if (sb_has_dirty_inodes(sb)) {
- /* we're making our own get_super here */
- sb->s_count++;
- spin_unlock(&sb_lock);
- /*
- * If we can't get the readlock, there's no sense in
- * waiting around, most of the time the FS is going to
- * be unmounted by the time it is released.
- */
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- sync_sb_inodes(wbc);
- up_read(&sb->s_umount);
- }
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
- }
- if (wbc->nr_to_write <= 0)
- break;
+ __generic_sync_sb_inodes(wbc);
+
+ if (sb) {
+ spin_lock(&sb_lock);
+ __put_super_and_need_restart(sb);
+ spin_unlock(&sb_lock);
}
- spin_unlock(&sb_lock);
+}
+EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
+
+static void sync_sb_inodes(struct writeback_control *wbc)
+{
+ generic_sync_sb_inodes(wbc);
}
/*
diff --git a/fs/sync.c b/fs/sync.c
index 3422ba6..bf03fc7 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -118,7 +118,7 @@ restart:
*/
SYSCALL_DEFINE0(sync)
{
- wakeup_pdflush(0);
+ wakeup_flusher_threads(0);
sync_filesystems(0);
sync_filesystems(1);
if (unlikely(laptop_mode))
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 928cd54..8158623 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,8 @@
#include <linux/proportions.h>
#include <linux/kernel.h>
#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
#include <asm/atomic.h>
struct page;
@@ -23,7 +25,8 @@ struct dentry;
* Bits in backing_dev_info.state
*/
enum bdi_state {
- BDI_pdflush, /* A pdflush thread is working this device */
+ BDI_pending, /* On its way to being activated */
+ BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
BDI_unused, /* Available bits start here */
@@ -39,9 +42,22 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
+struct bdi_writeback {
+ struct list_head list; /* hangs off the bdi */
+
+ struct backing_dev_info *bdi; /* our parent bdi */
+ unsigned int nr;
+
+ struct task_struct *task; /* writeback task */
+ struct list_head b_dirty; /* dirty inodes */
+ struct list_head b_io; /* parked for writeback */
+ struct list_head b_more_io; /* parked for more writeback */
+};
+
+#define BDI_MAX_FLUSHERS 32
+
struct backing_dev_info {
struct list_head bdi_list;
-
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
@@ -58,11 +74,15 @@ struct backing_dev_info {
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
- struct device *dev;
+ struct bdi_writeback wb; /* default writeback info for this bdi */
+ spinlock_t wb_lock; /* protects update side of wb_list */
+ struct list_head wb_list; /* the flusher threads hanging off this bdi */
+ unsigned long wb_mask; /* bitmask of registered tasks */
+ unsigned int wb_cnt; /* number of registered tasks */
- struct list_head b_dirty; /* dirty inodes */
- struct list_head b_io; /* parked for writeback */
- struct list_head b_more_io; /* parked for more writeback */
+ struct list_head work_list;
+
+ struct device *dev;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
@@ -77,10 +97,21 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct writeback_control *wbc);
+int bdi_writeback_task(struct bdi_writeback *wb);
+void bdi_writeback_all( struct writeback_control *wbc);
+int bdi_has_dirty_io(struct backing_dev_info *bdi);
-extern struct mutex bdi_lock;
+extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
+static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+{
+ return !list_empty(&wb->b_dirty) ||
+ !list_empty(&wb->b_io) ||
+ !list_empty(&wb->b_more_io);
+}
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
@@ -270,6 +301,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
return bdi->capabilities & BDI_CAP_SWAP_BACKED;
}
+static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
+{
+ return bdi == &default_backing_dev_info;
+}
+
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -285,4 +321,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping)
return bdi_cap_swap_backed(mapping->backing_dev_info);
}
+static inline int bdi_sched_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0a40b80..06bea4b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2068,6 +2068,7 @@ extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
extern void generic_sync_sb_inodes(struct writeback_control *wbc);
+extern void generic_sync_bdi_inodes(struct writeback_control *wbc);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
@@ -2182,7 +2183,6 @@ extern int bdev_read_only(struct block_device *);
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 5b4ceef..a2cb35f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -78,9 +78,11 @@ struct writeback_control {
/*
* fs/fs-writeback.c
*/
+struct bdi_writeback;
void writeback_inodes(struct writeback_control *wbc);
int inode_wait(void *);
void sync_inodes_sb(struct super_block *, int wait);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
@@ -100,7 +102,7 @@ static inline void inode_sync_wait(struct inode *inode)
/*
* mm/page-writeback.c
*/
-int wakeup_pdflush(long nr_pages);
+void wakeup_flusher_threads(long nr_pages);
void laptop_io_completion(void);
void laptop_sync_completion(void);
void throttle_vm_writeout(gfp_t gfp_mask);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6f163e0..c5cc60b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,8 +1,11 @@
#include <linux/wait.h>
#include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/writeback.h>
@@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
-DEFINE_MUTEX(bdi_lock);
+DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
+LIST_HEAD(bdi_pending_list);
+
+static struct task_struct *sync_supers_tsk;
+static struct timer_list sync_supers_timer;
+
+static int bdi_sync_supers(void *);
+static void sync_supers_timer_fn(unsigned long);
+static void arm_supers_timer(void);
+
+static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
@@ -187,6 +200,13 @@ static int __init default_bdi_init(void)
{
int err;
+ sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
+ BUG_ON(IS_ERR(sync_supers_tsk));
+
+ init_timer(&sync_supers_timer);
+ setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
+ arm_supers_timer();
+
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
@@ -195,6 +215,241 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ INIT_LIST_HEAD(&wb->b_io);
+ INIT_LIST_HEAD(&wb->b_more_io);
+}
+
+static void bdi_task_init(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct task_struct *tsk = current;
+
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&wb->list, &bdi->wb_list);
+ spin_unlock(&bdi->wb_lock);
+
+ tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
+ set_freezable();
+
+ /*
+ * Our parent may run at a different priority, just set us to normal
+ */
+ set_user_nice(tsk, 0);
+}
+
+static int bdi_start_fn(void *ptr)
+{
+ struct bdi_writeback *wb = ptr;
+ struct backing_dev_info *bdi = wb->bdi;
+ int ret;
+
+ /*
+ * Add us to the active bdi_list
+ */
+ spin_lock(&bdi_lock);
+ list_add(&bdi->bdi_list, &bdi_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_task_init(bdi, wb);
+
+ /*
+ * Clear pending bit and wakeup anybody waiting to tear us down
+ */
+ clear_bit(BDI_pending, &bdi->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&bdi->state, BDI_pending);
+
+ ret = bdi_writeback_task(wb);
+
+ /*
+ * Remove us from the list
+ */
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&wb->list);
+ spin_unlock(&bdi->wb_lock);
+
+ /*
+ * Flush any work that raced with us exiting. No new work
+ * will be added, since this bdi isn't discoverable anymore.
+ */
+ if (!list_empty(&bdi->work_list))
+ wb_do_writeback(wb, 1);
+
+ wb->task = NULL;
+ return ret;
+}
+
+int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+ return wb_has_dirty_io(&bdi->wb);
+}
+
+static void bdi_flush_io(struct backing_dev_info *bdi)
+{
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ .nr_to_write = 1024,
+ };
+
+ generic_sync_bdi_inodes(&wbc);
+}
+
+/*
+ * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * or we risk deadlocking on ->s_umount. The longer term solution would be
+ * to implement sync_supers_bdi() or similar and simply do it from the
+ * bdi writeback tasks individually.
+ */
+static int bdi_sync_supers(void *unused)
+{
+ set_user_nice(current, 0);
+
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+
+ /*
+ * Do this periodically, like kupdated() did before.
+ */
+ sync_supers();
+ }
+
+ return 0;
+}
+
+static void arm_supers_timer(void)
+{
+ unsigned long next;
+
+ next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
+ mod_timer(&sync_supers_timer, round_jiffies_up(next));
+}
+
+static void sync_supers_timer_fn(unsigned long unused)
+{
+ wake_up_process(sync_supers_tsk);
+ arm_supers_timer();
+}
+
+static int bdi_forker_task(void *ptr)
+{
+ struct bdi_writeback *me = ptr;
+
+ bdi_task_init(me->bdi, me);
+
+ for (;;) {
+ struct backing_dev_info *bdi, *tmp;
+ struct bdi_writeback *wb;
+
+ /*
+ * Temporary measure, we want to make sure we don't see
+ * dirty data on the default backing_dev_info
+ */
+ if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+ wb_do_writeback(me, 0);
+
+ spin_lock(&bdi_lock);
+
+ /*
+ * Check if any existing bdi's have dirty data without
+ * a thread registered. If so, set that up.
+ */
+ list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
+ if (bdi->wb.task)
+ continue;
+ if (list_empty(&bdi->work_list) &&
+ !bdi_has_dirty_io(bdi))
+ continue;
+
+ bdi_add_default_flusher_task(bdi);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (list_empty(&bdi_pending_list)) {
+ unsigned long wait;
+
+ spin_unlock(&bdi_lock);
+ wait = msecs_to_jiffies(dirty_writeback_interval * 10);
+ schedule_timeout(wait);
+ try_to_freeze();
+ continue;
+ }
+
+ __set_current_state(TASK_RUNNING);
+
+ /*
+ * This is our real job - check for pending entries in
+ * bdi_pending_list, and create the tasks that got added
+ */
+ bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
+ bdi_list);
+ list_del_init(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+
+ wb = &bdi->wb;
+ wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
+ dev_name(bdi->dev));
+ /*
+ * If task creation fails, then readd the bdi to
+ * the pending list and force writeout of the bdi
+ * from this forker thread. That will free some memory
+ * and we can try again.
+ */
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+
+ /*
+ * Add this 'bdi' to the back, so we get
+ * a chance to flush other bdi's to free
+ * memory.
+ */
+ spin_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_flush_io(bdi);
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Add the default flusher task that gets created for any bdi
+ * that has dirty data pending writeout
+ */
+void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
+{
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * Check with the helper whether to proceed adding a task. Will only
+ * abort if we two or more simultanous calls to
+ * bdi_add_default_flusher_task() occured, further additions will block
+ * waiting for previous additions to finish.
+ */
+ if (!test_and_set_bit(BDI_pending, &bdi->state)) {
+ list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+
+ /*
+ * We are now on the pending list, wake up bdi_forker_task()
+ * to finish the job and add us back to the active bdi_list
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+ }
+}
+
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
@@ -213,13 +468,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
list_add_tail(&bdi->bdi_list, &bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
bdi->dev = dev;
- bdi_debug_register(bdi, dev_name(dev));
+ /*
+ * Just start the forker thread for our default backing_dev_info,
+ * and add other bdi's to the list. They will get a thread created
+ * on-demand when they need it.
+ */
+ if (bdi_cap_flush_forker(bdi)) {
+ struct bdi_writeback *wb = &bdi->wb;
+
+ wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+ dev_name(dev));
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+ ret = -ENOMEM;
+
+ spin_lock(&bdi_lock);
+ list_del(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+ goto exit;
+ }
+ }
+
+ bdi_debug_register(bdi, dev_name(dev));
exit:
return ret;
}
@@ -231,17 +507,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
}
EXPORT_SYMBOL(bdi_register_dev);
-static void bdi_remove_from_list(struct backing_dev_info *bdi)
+/*
+ * Remove bdi from the global list and shutdown any threads we have running
+ */
+static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- mutex_lock(&bdi_lock);
+ struct bdi_writeback *wb;
+
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * If setup is pending, wait for that to complete first
+ */
+ wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+
+ /*
+ * Make sure nobody finds us on the bdi_list anymore
+ */
+ spin_lock(&bdi_lock);
list_del(&bdi->bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
+
+ /*
+ * Finally, kill the kernel threads. We don't need to be RCU
+ * safe anymore, since the bdi is gone from visibility.
+ */
+ list_for_each_entry(wb, &bdi->wb_list, list)
+ kthread_stop(wb->task);
}
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
- bdi_remove_from_list(bdi);
+ if (!bdi_cap_flush_forker(bdi))
+ bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -251,18 +552,25 @@ EXPORT_SYMBOL(bdi_unregister);
int bdi_init(struct backing_dev_info *bdi)
{
- int i;
- int err;
+ int i, err;
bdi->dev = NULL;
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ spin_lock_init(&bdi->wb_lock);
INIT_LIST_HEAD(&bdi->bdi_list);
- INIT_LIST_HEAD(&bdi->b_io);
- INIT_LIST_HEAD(&bdi->b_dirty);
- INIT_LIST_HEAD(&bdi->b_more_io);
+ INIT_LIST_HEAD(&bdi->wb_list);
+ INIT_LIST_HEAD(&bdi->work_list);
+
+ bdi_wb_init(&bdi->wb, bdi);
+
+ /*
+ * Just one thread support for now, hard code mask and count
+ */
+ bdi->wb_mask = 1;
+ bdi->wb_cnt = 1;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -277,8 +585,6 @@ int bdi_init(struct backing_dev_info *bdi)
err:
while (i--)
percpu_counter_destroy(&bdi->bdi_stat[i]);
-
- bdi_remove_from_list(bdi);
}
return err;
@@ -289,9 +595,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
- WARN_ON(!list_empty(&bdi->b_dirty));
- WARN_ON(!list_empty(&bdi->b_io));
- WARN_ON(!list_empty(&bdi->b_more_io));
+ WARN_ON(bdi_has_dirty_io(bdi));
bdi_unregister(bdi);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f8341b6..0fce7df 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,15 +36,6 @@
#include <linux/pagevec.h>
/*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
-/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
@@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
-static void background_writeout(unsigned long _min_pages);
-
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
@@ -326,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -338,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -350,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
if (max_ratio > 100)
return -EINVAL;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -543,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping)
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes(&wbc);
+ generic_sync_bdi_inodes(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
@@ -572,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping)
if (pages_written >= write_chunk)
break; /* We've done our duty */
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ schedule_timeout(1);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -593,8 +582,15 @@ static void balance_dirty_pages(struct address_space *mapping)
if ((laptop_mode && pages_written) ||
(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS)
- > background_thresh)))
- pdflush_operation(background_writeout, 0);
+ > background_thresh))) {
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ };
+
+
+ bdi_start_writeback(&wbc);
+ }
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -679,152 +675,53 @@ void throttle_vm_writeout(gfp_t gfp_mask)
}
/*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
+ * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
+ * the whole world.
*/
-static void background_writeout(unsigned long _min_pages)
+void wakeup_flusher_threads(long nr_pages)
{
- long min_pages = _min_pages;
struct writeback_control wbc = {
- .bdi = NULL,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
- .nr_to_write = 0,
- .nonblocking = 1,
.range_cyclic = 1,
};
- for ( ; ; ) {
- unsigned long background_thresh;
- unsigned long dirty_thresh;
-
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
- if (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) < background_thresh
- && min_pages <= 0)
- break;
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- wbc.pages_skipped = 0;
- writeback_inodes(&wbc);
- min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- /* Wrote less than expected */
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break;
- }
- }
-}
-
-/*
- * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
- * the whole world. Returns 0 if a pdflush thread was dispatched. Returns
- * -1 if all pdflush threads were busy.
- */
-int wakeup_pdflush(long nr_pages)
-{
if (nr_pages == 0)
nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
- return pdflush_operation(background_writeout, nr_pages);
+ wbc.nr_to_write = nr_pages;
+ bdi_writeback_all(&wbc);
}
-static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space. So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval. But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write. So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
- unsigned long oldest_jif;
- unsigned long start_jif;
- unsigned long next_jif;
- long nr_to_write;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = &oldest_jif,
- .nr_to_write = 0,
- .nonblocking = 1,
- .for_kupdate = 1,
- .range_cyclic = 1,
- };
-
- sync_supers();
-
- oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
- start_jif = jiffies;
- next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
- nr_to_write = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- while (nr_to_write > 0) {
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- writeback_inodes(&wbc);
- if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break; /* All the old data is written */
- }
- nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- }
- if (time_before(next_jif, jiffies + HZ))
- next_jif = jiffies + HZ;
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, next_jif);
-}
-
-/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, file, buffer, length, ppos);
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies +
- msecs_to_jiffies(dirty_writeback_interval * 10));
- else
- del_timer(&wb_timer);
return 0;
}
-static void wb_timer_fn(unsigned long unused)
+static void do_laptop_sync(struct work_struct *work)
{
- if (pdflush_operation(wb_kupdate, 0) < 0)
- mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
-{
- sys_sync();
+ wakeup_flusher_threads(0);
+ kfree(work);
}
static void laptop_timer_fn(unsigned long unused)
{
- pdflush_operation(laptop_flush, 0);
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_laptop_sync);
+ schedule_work(work);
+ }
}
/*
@@ -907,8 +804,6 @@ void __init page_writeback_init(void)
{
int shift;
- mod_timer(&wb_timer,
- jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 94e86dd..ba8228e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
*/
if (total_scanned > sc->swap_cluster_max +
sc->swap_cluster_max / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 4/8] writeback: get rid of pdflush completely
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
` (2 preceding siblings ...)
2009-09-01 11:19 ` [PATCH 3/8] writeback: switch to per-bdi threads for flushing data Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 5/8] writeback: add some debug inode list counters to bdi stats Jens Axboe
` (3 subsequent siblings)
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
It is now unused, so kill it off.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/fs-writeback.c | 5 +
include/linux/writeback.h | 12 --
mm/Makefile | 2 +-
mm/pdflush.c | 269 ---------------------------------------------
4 files changed, 6 insertions(+), 282 deletions(-)
delete mode 100644 mm/pdflush.c
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0acc684..c127735 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -30,6 +30,11 @@
#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
+/*
* Work items for the bdi_writeback threads
*/
struct bdi_work {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a2cb35f..34c59f9 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -14,17 +14,6 @@ extern struct list_head inode_in_use;
extern struct list_head inode_unused;
/*
- * Yes, writeback.h requires sched.h
- * No, sched.h is not included from here.
- */
-static inline int task_is_pdflush(struct task_struct *task)
-{
- return task->flags & PF_FLUSHER;
-}
-
-#define current_is_pdflush() task_is_pdflush(current)
-
-/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
@@ -154,7 +143,6 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
void *data);
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int write_cache_pages(struct address_space *mapping,
diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd64..147a7a7 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -8,7 +8,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \
vmalloc.o
obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
- maccess.o page_alloc.o page-writeback.o pdflush.o \
+ maccess.o page_alloc.o page-writeback.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
page_isolation.o mm_init.o $(mmu-y)
diff --git a/mm/pdflush.c b/mm/pdflush.c
deleted file mode 100644
index 235ac44..0000000
--- a/mm/pdflush.c
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * mm/pdflush.c - worker threads for writing back filesystem data
- *
- * Copyright (C) 2002, Linus Torvalds.
- *
- * 09Apr2002 Andrew Morton
- * Initial version
- * 29Feb2004 kaos@sgi.com
- * Move worker thread creation to kthread to avoid chewing
- * up stack space with nested calls to kernel_thread.
- */
-
-#include <linux/sched.h>
-#include <linux/list.h>
-#include <linux/signal.h>
-#include <linux/spinlock.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/fs.h> /* Needed by writeback.h */
-#include <linux/writeback.h> /* Prototypes pdflush_operation() */
-#include <linux/kthread.h>
-#include <linux/cpuset.h>
-#include <linux/freezer.h>
-
-
-/*
- * Minimum and maximum number of pdflush instances
- */
-#define MIN_PDFLUSH_THREADS 2
-#define MAX_PDFLUSH_THREADS 8
-
-static void start_one_pdflush_thread(void);
-
-
-/*
- * The pdflush threads are worker threads for writing back dirty data.
- * Ideally, we'd like one thread per active disk spindle. But the disk
- * topology is very hard to divine at this level. Instead, we take
- * care in various places to prevent more than one pdflush thread from
- * performing writeback against a single filesystem. pdflush threads
- * have the PF_FLUSHER flag set in current->flags to aid in this.
- */
-
-/*
- * All the pdflush threads. Protected by pdflush_lock
- */
-static LIST_HEAD(pdflush_list);
-static DEFINE_SPINLOCK(pdflush_lock);
-
-/*
- * The count of currently-running pdflush threads. Protected
- * by pdflush_lock.
- *
- * Readable by sysctl, but not writable. Published to userspace at
- * /proc/sys/vm/nr_pdflush_threads.
- */
-int nr_pdflush_threads = 0;
-
-/*
- * The time at which the pdflush thread pool last went empty
- */
-static unsigned long last_empty_jifs;
-
-/*
- * The pdflush thread.
- *
- * Thread pool management algorithm:
- *
- * - The minimum and maximum number of pdflush instances are bound
- * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
- *
- * - If there have been no idle pdflush instances for 1 second, create
- * a new one.
- *
- * - If the least-recently-went-to-sleep pdflush thread has been asleep
- * for more than one second, terminate a thread.
- */
-
-/*
- * A structure for passing work to a pdflush thread. Also for passing
- * state information between pdflush threads. Protected by pdflush_lock.
- */
-struct pdflush_work {
- struct task_struct *who; /* The thread */
- void (*fn)(unsigned long); /* A callback function */
- unsigned long arg0; /* An argument to the callback */
- struct list_head list; /* On pdflush_list, when idle */
- unsigned long when_i_went_to_sleep;
-};
-
-static int __pdflush(struct pdflush_work *my_work)
-{
- current->flags |= PF_FLUSHER | PF_SWAPWRITE;
- set_freezable();
- my_work->fn = NULL;
- my_work->who = current;
- INIT_LIST_HEAD(&my_work->list);
-
- spin_lock_irq(&pdflush_lock);
- for ( ; ; ) {
- struct pdflush_work *pdf;
-
- set_current_state(TASK_INTERRUPTIBLE);
- list_move(&my_work->list, &pdflush_list);
- my_work->when_i_went_to_sleep = jiffies;
- spin_unlock_irq(&pdflush_lock);
- schedule();
- try_to_freeze();
- spin_lock_irq(&pdflush_lock);
- if (!list_empty(&my_work->list)) {
- /*
- * Someone woke us up, but without removing our control
- * structure from the global list. swsusp will do this
- * in try_to_freeze()->refrigerator(). Handle it.
- */
- my_work->fn = NULL;
- continue;
- }
- if (my_work->fn == NULL) {
- printk("pdflush: bogus wakeup\n");
- continue;
- }
- spin_unlock_irq(&pdflush_lock);
-
- (*my_work->fn)(my_work->arg0);
-
- spin_lock_irq(&pdflush_lock);
-
- /*
- * Thread creation: For how long have there been zero
- * available threads?
- *
- * To throttle creation, we reset last_empty_jifs.
- */
- if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
- if (list_empty(&pdflush_list)) {
- if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) {
- last_empty_jifs = jiffies;
- nr_pdflush_threads++;
- spin_unlock_irq(&pdflush_lock);
- start_one_pdflush_thread();
- spin_lock_irq(&pdflush_lock);
- }
- }
- }
-
- my_work->fn = NULL;
-
- /*
- * Thread destruction: For how long has the sleepiest
- * thread slept?
- */
- if (list_empty(&pdflush_list))
- continue;
- if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
- continue;
- pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
- if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
- /* Limit exit rate */
- pdf->when_i_went_to_sleep = jiffies;
- break; /* exeunt */
- }
- }
- nr_pdflush_threads--;
- spin_unlock_irq(&pdflush_lock);
- return 0;
-}
-
-/*
- * Of course, my_work wants to be just a local in __pdflush(). It is
- * separated out in this manner to hopefully prevent the compiler from
- * performing unfortunate optimisations against the auto variables. Because
- * these are visible to other tasks and CPUs. (No problem has actually
- * been observed. This is just paranoia).
- */
-static int pdflush(void *dummy)
-{
- struct pdflush_work my_work;
- cpumask_var_t cpus_allowed;
-
- /*
- * Since the caller doesn't even check kthread_run() worked, let's not
- * freak out too much if this fails.
- */
- if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
- printk(KERN_WARNING "pdflush failed to allocate cpumask\n");
- return 0;
- }
-
- /*
- * pdflush can spend a lot of time doing encryption via dm-crypt. We
- * don't want to do that at keventd's priority.
- */
- set_user_nice(current, 0);
-
- /*
- * Some configs put our parent kthread in a limited cpuset,
- * which kthread() overrides, forcing cpus_allowed == cpu_all_mask.
- * Our needs are more modest - cut back to our cpusets cpus_allowed.
- * This is needed as pdflush's are dynamically created and destroyed.
- * The boottime pdflush's are easily placed w/o these 2 lines.
- */
- cpuset_cpus_allowed(current, cpus_allowed);
- set_cpus_allowed_ptr(current, cpus_allowed);
- free_cpumask_var(cpus_allowed);
-
- return __pdflush(&my_work);
-}
-
-/*
- * Attempt to wake up a pdflush thread, and get it to do some work for you.
- * Returns zero if it indeed managed to find a worker thread, and passed your
- * payload to it.
- */
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
-{
- unsigned long flags;
- int ret = 0;
-
- BUG_ON(fn == NULL); /* Hard to diagnose if it's deferred */
-
- spin_lock_irqsave(&pdflush_lock, flags);
- if (list_empty(&pdflush_list)) {
- ret = -1;
- } else {
- struct pdflush_work *pdf;
-
- pdf = list_entry(pdflush_list.next, struct pdflush_work, list);
- list_del_init(&pdf->list);
- if (list_empty(&pdflush_list))
- last_empty_jifs = jiffies;
- pdf->fn = fn;
- pdf->arg0 = arg0;
- wake_up_process(pdf->who);
- }
- spin_unlock_irqrestore(&pdflush_lock, flags);
-
- return ret;
-}
-
-static void start_one_pdflush_thread(void)
-{
- struct task_struct *k;
-
- k = kthread_run(pdflush, NULL, "pdflush");
- if (unlikely(IS_ERR(k))) {
- spin_lock_irq(&pdflush_lock);
- nr_pdflush_threads--;
- spin_unlock_irq(&pdflush_lock);
- }
-}
-
-static int __init pdflush_init(void)
-{
- int i;
-
- /*
- * Pre-set nr_pdflush_threads... If we fail to create,
- * the count will be decremented.
- */
- nr_pdflush_threads = MIN_PDFLUSH_THREADS;
-
- for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
- start_one_pdflush_thread();
- return 0;
-}
-
-module_init(pdflush_init);
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 5/8] writeback: add some debug inode list counters to bdi stats
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
` (3 preceding siblings ...)
2009-09-01 11:19 ` [PATCH 4/8] writeback: get rid of pdflush completely Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 6/8] writeback: add name to backing_dev_info Jens Axboe
` (2 subsequent siblings)
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
Add some debug entries to be able to inspect the internal state of
the writeback details.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
mm/backing-dev.c | 38 ++++++++++++++++++++++++++++++++++----
1 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c5cc60b..85f48e8 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -52,9 +52,29 @@ static void bdi_debug_init(void)
static int bdi_debug_stats_show(struct seq_file *m, void *v)
{
struct backing_dev_info *bdi = m->private;
+ struct bdi_writeback *wb;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
+ unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+ struct inode *inode;
+
+ /*
+ * inode lock is enough here, the bdi->wb_list is protected by
+ * RCU on the reader side
+ */
+ nr_wb = nr_dirty = nr_io = nr_more_io = 0;
+ spin_lock(&inode_lock);
+ list_for_each_entry(wb, &bdi->wb_list, list) {
+ nr_wb++;
+ list_for_each_entry(inode, &wb->b_dirty, i_list)
+ nr_dirty++;
+ list_for_each_entry(inode, &wb->b_io, i_list)
+ nr_io++;
+ list_for_each_entry(inode, &wb->b_more_io, i_list)
+ nr_more_io++;
+ }
+ spin_unlock(&inode_lock);
get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
@@ -64,12 +84,22 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
"BdiReclaimable: %8lu kB\n"
"BdiDirtyThresh: %8lu kB\n"
"DirtyThresh: %8lu kB\n"
- "BackgroundThresh: %8lu kB\n",
+ "BackgroundThresh: %8lu kB\n"
+ "WriteBack threads:%8lu\n"
+ "b_dirty: %8lu\n"
+ "b_io: %8lu\n"
+ "b_more_io: %8lu\n"
+ "bdi_list: %8u\n"
+ "state: %8lx\n"
+ "wb_mask: %8lx\n"
+ "wb_list: %8u\n"
+ "wb_cnt: %8u\n",
(unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
(unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
- K(bdi_thresh),
- K(dirty_thresh),
- K(background_thresh));
+ K(bdi_thresh), K(dirty_thresh),
+ K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io,
+ !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask,
+ !list_empty(&bdi->wb_list), bdi->wb_cnt);
#undef K
return 0;
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 6/8] writeback: add name to backing_dev_info
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
` (4 preceding siblings ...)
2009-09-01 11:19 ` [PATCH 5/8] writeback: add some debug inode list counters to bdi stats Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 7/8] writeback: check for registered bdi in flusher add and inode dirty Jens Axboe
2009-09-01 11:19 ` [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages Jens Axboe
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
This enables us to track who does what and print info. Its main use
is catching dirty inodes on the default_backing_dev_info, so we can
fix that up.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
block/blk-core.c | 1 +
drivers/block/aoe/aoeblk.c | 1 +
drivers/char/mem.c | 1 +
fs/btrfs/disk-io.c | 1 +
fs/char_dev.c | 1 +
fs/configfs/inode.c | 1 +
fs/fuse/inode.c | 1 +
fs/hugetlbfs/inode.c | 1 +
fs/nfs/client.c | 1 +
fs/ocfs2/dlm/dlmfs.c | 1 +
fs/ramfs/inode.c | 1 +
fs/sysfs/inode.c | 1 +
fs/ubifs/super.c | 1 +
include/linux/backing-dev.h | 2 ++
kernel/cgroup.c | 1 +
mm/backing-dev.c | 1 +
mm/swap_state.c | 1 +
17 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index e3299a7..e695634 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,6 +501,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.name = "block";
err = bdi_init(&q->backing_dev_info);
if (err) {
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 2307a27..0efb8fc 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -265,6 +265,7 @@ aoeblk_gdalloc(void *vp)
}
blk_queue_make_request(&d->blkq, aoeblk_make_request);
+ d->blkq.backing_dev_info.name = "aoe";
if (bdi_init(&d->blkq.backing_dev_info))
goto err_mempool;
spin_lock_irqsave(&d->lock, flags);
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index afa8813..645237b 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -822,6 +822,7 @@ static const struct file_operations zero_fops = {
* - permits private mappings, "copies" are taken of the source of zeros
*/
static struct backing_dev_info zero_bdi = {
+ .name = "char/mem",
.capabilities = BDI_CAP_MAP_COPY,
};
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e83be2e..15831d5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1352,6 +1352,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
{
int err;
+ bdi->name = "btrfs";
bdi->capabilities = BDI_CAP_MAP_COPY;
err = bdi_init(bdi);
if (err)
diff --git a/fs/char_dev.c b/fs/char_dev.c
index a173551..7c27a8e 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -31,6 +31,7 @@
* - no readahead or I/O queue unplugging required
*/
struct backing_dev_info directly_mappable_cdev_bdi = {
+ .name = "char",
.capabilities = (
#ifdef CONFIG_MMU
/* permit private copies of the data to be taken */
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 4921e74..a2f7460 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -51,6 +51,7 @@ static const struct address_space_operations configfs_aops = {
};
static struct backing_dev_info configfs_backing_dev_info = {
+ .name = "configfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f91ccc4..4567db6 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -801,6 +801,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
{
int err;
+ fc->bdi.name = "fuse";
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
fc->bdi.unplug_io_fn = default_unplug_io_fn;
/* fuse does it's own writeback accounting */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cb88dac..a93b885 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -44,6 +44,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
static struct backing_dev_info hugetlbfs_backing_dev_info = {
+ .name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8d25ccb..c6be84a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -879,6 +879,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
server->rsize = NFS_MAX_FILE_IO_SIZE;
server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ server->backing_dev_info.name = "nfs";
server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
if (server->wsize > max_rpc_payload)
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 1c9efb4..02bf178 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -325,6 +325,7 @@ clear_fields:
}
static struct backing_dev_info dlmfs_backing_dev_info = {
+ .name = "ocfs2-dlmfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 0ff7566..a7f0110 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -46,6 +46,7 @@ static const struct super_operations ramfs_ops;
static const struct inode_operations ramfs_dir_inode_operations;
static struct backing_dev_info ramfs_backing_dev_info = {
+ .name = "ramfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK |
BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 555f0ff..e57f98e 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -29,6 +29,7 @@ static const struct address_space_operations sysfs_aops = {
};
static struct backing_dev_info sysfs_backing_dev_info = {
+ .name = "sysfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 06e80e3..85aa478 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1972,6 +1972,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
*
* Read-ahead will be disabled because @c->bdi.ra_pages is 0.
*/
+ c->bdi.name = "ubifs",
c->bdi.capabilities = BDI_CAP_MAP_COPY;
c->bdi.unplug_io_fn = default_unplug_io_fn;
err = bdi_init(&c->bdi);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 8158623..28b2542 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -66,6 +66,8 @@ struct backing_dev_info {
void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
void *unplug_io_data;
+ char *name;
+
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
struct prop_local_percpu completions;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b6eadfe..c7ece8f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
+ .name = "cgroup",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 85f48e8..44efc3e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -17,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
EXPORT_SYMBOL(default_unplug_io_fn);
struct backing_dev_info default_backing_dev_info = {
+ .name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 42cd38e..5ae6b8b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -34,6 +34,7 @@ static const struct address_space_operations swap_aops = {
};
static struct backing_dev_info swap_backing_dev_info = {
+ .name = "swap",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = swap_unplug_io_fn,
};
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 7/8] writeback: check for registered bdi in flusher add and inode dirty
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
` (5 preceding siblings ...)
2009-09-01 11:19 ` [PATCH 6/8] writeback: add name to backing_dev_info Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 11:19 ` [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages Jens Axboe
7 siblings, 0 replies; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
Also a debugging aid. We want to catch dirty inodes being added to
backing devices that don't do writeback.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/fs-writeback.c | 7 +++++++
include/linux/backing-dev.h | 1 +
mm/backing-dev.c | 6 ++++++
3 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c127735..38cb758 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -949,6 +949,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
*/
if (!was_dirty) {
struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+ struct backing_dev_info *bdi = wb->bdi;
+
+ if (bdi_cap_writeback_dirty(bdi) &&
+ !test_bit(BDI_registered, &bdi->state)) {
+ WARN_ON(1);
+ printk("bdi-%s not registered\n", bdi->name);
+ }
inode->dirtied_when = jiffies;
list_move(&inode->i_list, &wb->b_dirty);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 28b2542..8bab34e 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -29,6 +29,7 @@ enum bdi_state {
BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
+ BDI_registered, /* bdi_register() was done */
BDI_unused, /* Available bits start here */
};
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 44efc3e..a5f31e6 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -464,6 +464,11 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
if (!bdi_cap_writeback_dirty(bdi))
return;
+ if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
+ printk("bdi %p/%s is not registered!\n", bdi, bdi->name);
+ return;
+ }
+
/*
* Check with the helper whether to proceed adding a task. Will only
* abort if we two or more simultanous calls to
@@ -527,6 +532,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
}
bdi_debug_register(bdi, dev_name(dev));
+ set_bit(BDI_registered, &bdi->state);
exit:
return ret;
}
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 11:18 [PATCH 0/8] Per-bdi writeback flusher threads v16 Jens Axboe
` (6 preceding siblings ...)
2009-09-01 11:19 ` [PATCH 7/8] writeback: check for registered bdi in flusher add and inode dirty Jens Axboe
@ 2009-09-01 11:19 ` Jens Axboe
2009-09-01 18:38 ` Peter Zijlstra
7 siblings, 1 reply; 22+ messages in thread
From: Jens Axboe @ 2009-09-01 11:19 UTC (permalink / raw)
To: linux-kernel, linux-fsdevel
Cc: chris.mason, david, hch, tytso, akpm, jack, Jens Axboe
From: Theodore Ts'o <tytso@mit.edu>
Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
concern of not holding I_SYNC for too long. (At least, that was the
comment previously.) This doesn't make sense now because the only
time we wait for I_SYNC is if we are calling sync or fsync, and in
that case we need to write out all of the data anyway. Previously
there may have been other code paths that waited on I_SYNC, but not
any more.
According to Christoph, the current writeback size is way too small,
and XFS had a hack that bumped out nr_to_write to four times the value
sent by the VM to be able to saturate medium-sized RAID arrays. This
value was also problematic for ext4 as well, as it caused large files
to be come interleaved on disk by in 8 megabyte chunks (we bumped up
the nr_to_write by a factor of two).
So, in this patch, we make the MAX_WRITEBACK_PAGES a tunable, and
change the default to be 32768 blocks.
http://bugzilla.kernel.org/show_bug.cgi?id=13930
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/fs-writeback.c | 15 +++------------
include/linux/writeback.h | 1 +
kernel/sysctl.c | 8 ++++++++
mm/page-writeback.c | 6 ++++++
4 files changed, 18 insertions(+), 12 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 38cb758..9703136 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -585,15 +585,6 @@ void generic_sync_bdi_inodes(struct writeback_control *wbc)
generic_sync_wb_inodes(&bdi->wb, wbc);
}
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
static inline bool over_bground_thresh(void)
{
unsigned long background_thresh, dirty_thresh;
@@ -647,11 +638,11 @@ static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
wbc.more_io = 0;
wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.nr_to_write = max_writeback_pages;
wbc.pages_skipped = 0;
generic_sync_wb_inodes(wb, &wbc);
- nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ nr_pages -= max_writeback_pages - wbc.nr_to_write;
+ wrote += max_writeback_pages - wbc.nr_to_write;
/*
* If we ran out of stuff to write, bail unless more_io got set
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 34c59f9..c5b54e2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -103,6 +103,7 @@ extern int vm_dirty_ratio;
extern unsigned long vm_dirty_bytes;
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
+extern unsigned int max_writeback_pages;
extern int vm_highmem_is_dirtyable;
extern int block_dump;
extern int laptop_mode;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be760..06d1c4c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1104,6 +1104,14 @@ static struct ctl_table vm_table[] = {
.proc_handler = &proc_dointvec,
},
{
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "max_writeback_pages",
+ .data = &max_writeback_pages,
+ .maxlen = sizeof(max_writeback_pages),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
.ctl_name = VM_NR_PDFLUSH_THREADS,
.procname = "nr_pdflush_threads",
.data = &nr_pdflush_threads,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0fce7df..40b7e0a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -55,6 +55,12 @@ static inline long sync_writeback_pages(void)
/* The following parameters are exported via /proc/sys/vm */
/*
+ * The maximum number of pages to write out in a single bdflush/kupdate
+ * operation.
+ */
+unsigned int max_writeback_pages = 32768;
+
+/*
* Start background writeback (via pdflush) at this percentage
*/
int dirty_background_ratio = 10;
--
1.6.4.1.207.g68ea
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 11:19 ` [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages Jens Axboe
@ 2009-09-01 18:38 ` Peter Zijlstra
2009-09-01 18:44 ` Christoph Hellwig
0 siblings, 1 reply; 22+ messages in thread
From: Peter Zijlstra @ 2009-09-01 18:38 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-kernel, linux-fsdevel, chris.mason, david, hch, tytso, akpm,
jack
On Tue, 2009-09-01 at 13:19 +0200, Jens Axboe wrote:
> Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
> concern of not holding I_SYNC for too long. (At least, that was the
> comment previously.) This doesn't make sense now because the only
> time we wait for I_SYNC is if we are calling sync or fsync, and in
> that case we need to write out all of the data anyway. Previously
> there may have been other code paths that waited on I_SYNC, but not
> any more.
>
> According to Christoph, the current writeback size is way too small,
> and XFS had a hack that bumped out nr_to_write to four times the value
> sent by the VM to be able to saturate medium-sized RAID arrays. This
> value was also problematic for ext4 as well, as it caused large files
> to be come interleaved on disk by in 8 megabyte chunks (we bumped up
> the nr_to_write by a factor of two).
>
> So, in this patch, we make the MAX_WRITEBACK_PAGES a tunable, and
> change the default to be 32768 blocks.
Do we really need a tunable for this?
I guess we need a limit to avoid it writing out everything, but can't we
have something automagic?
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 18:38 ` Peter Zijlstra
@ 2009-09-01 18:44 ` Christoph Hellwig
2009-09-01 20:27 ` Theodore Tso
2009-09-01 23:52 ` Jamie Lokier
0 siblings, 2 replies; 22+ messages in thread
From: Christoph Hellwig @ 2009-09-01 18:44 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Jens Axboe, linux-kernel, linux-fsdevel, chris.mason, david, hch,
tytso, akpm, jack
On Tue, Sep 01, 2009 at 08:38:55PM +0200, Peter Zijlstra wrote:
> Do we really need a tunable for this?
It will make increasing it in the field a lot easier. And having deal
with really large systems I have the fear that there are I/O topologies
outhere for which every "reasonable" value is too low.
> I guess we need a limit to avoid it writing out everything, but can't we
> have something automagic?
Some automatic adjustment would be nice. But finding the right auto
tuning will be an interesting exercise.
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 18:44 ` Christoph Hellwig
@ 2009-09-01 20:27 ` Theodore Tso
2009-09-02 7:32 ` Peter Zijlstra
2009-09-01 23:52 ` Jamie Lokier
1 sibling, 1 reply; 22+ messages in thread
From: Theodore Tso @ 2009-09-01 20:27 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Peter Zijlstra, Jens Axboe, linux-kernel, linux-fsdevel,
chris.mason, david, akpm, jack
On Tue, Sep 01, 2009 at 02:44:55PM -0400, Christoph Hellwig wrote:
> On Tue, Sep 01, 2009 at 08:38:55PM +0200, Peter Zijlstra wrote:
> > Do we really need a tunable for this?
>
> It will make increasing it in the field a lot easier. And having deal
> with really large systems I have the fear that there are I/O topologies
> outhere for which every "reasonable" value is too low.
>
> > I guess we need a limit to avoid it writing out everything, but can't we
> > have something automagic?
>
> Some automatic adjustment would be nice. But finding the right auto
> tuning will be an interesting exercise.
The fact that limit is on a per-inode basis is part of the problem.
Right now, we are only writing out X pages per inode, so depending on
whether we have one really gargantuan inode that needs writout, or ten
big inodes which are dirty, or million small inodes, the fact that we
are imposing a limit based the number of pages in a single inode that
we will write out seems like the wrong design choice.
So perhaps the best argument for not making this be a tunable is that
in the long run, we will need to put in a better algorithm for
controlling how much writeback we want to do before we start
saturating RAID arrays, and in that new algorithm this tunable may no
longer make sense. Fine; at that point, we can make it go away. For
now, though, it seems to be the best way to tweak what is going on,
since I doubt we'll be able to come up with one magic number that will
satisfy everyone.
- Ted
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 20:27 ` Theodore Tso
@ 2009-09-02 7:32 ` Peter Zijlstra
2009-09-02 7:35 ` Peter Zijlstra
0 siblings, 1 reply; 22+ messages in thread
From: Peter Zijlstra @ 2009-09-02 7:32 UTC (permalink / raw)
To: Theodore Tso
Cc: Christoph Hellwig, Jens Axboe, linux-kernel, linux-fsdevel,
chris.mason, david, akpm, jack
On Tue, 2009-09-01 at 16:27 -0400, Theodore Tso wrote:
> On Tue, Sep 01, 2009 at 02:44:55PM -0400, Christoph Hellwig wrote:
> > On Tue, Sep 01, 2009 at 08:38:55PM +0200, Peter Zijlstra wrote:
> > > Do we really need a tunable for this?
> >
> > It will make increasing it in the field a lot easier. And having deal
> > with really large systems I have the fear that there are I/O topologies
> > outhere for which every "reasonable" value is too low.
> >
> > > I guess we need a limit to avoid it writing out everything, but can't we
> > > have something automagic?
> >
> > Some automatic adjustment would be nice. But finding the right auto
> > tuning will be an interesting exercise.
>
> The fact that limit is on a per-inode basis is part of the problem.
I would think that it would be a BDI based property, since it basically
depends on the speed of the backing dev you're writing to.
> Right now, we are only writing out X pages per inode, so depending on
> whether we have one really gargantuan inode that needs writout, or ten
> big inodes which are dirty, or million small inodes, the fact that we
> are imposing a limit based the number of pages in a single inode that
> we will write out seems like the wrong design choice.
Agreed, number of chunks, where a chunk is some optimum write size for
the device in question, and number of seeks, seem a more suitable
criteria.
Basically limiting the time spend on writeout and not much else.
> So perhaps the best argument for not making this be a tunable is that
> in the long run, we will need to put in a better algorithm for
> controlling how much writeback we want to do before we start
> saturating RAID arrays, and in that new algorithm this tunable may no
> longer make sense. Fine; at that point, we can make it go away. For
> now, though, it seems to be the best way to tweak what is going on,
> since I doubt we'll be able to come up with one magic number that will
> satisfy everyone.
Thing is, will this single tunable be sufficient for people who have
both a RAID array and an USB stick on the same machine?
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-02 7:32 ` Peter Zijlstra
@ 2009-09-02 7:35 ` Peter Zijlstra
0 siblings, 0 replies; 22+ messages in thread
From: Peter Zijlstra @ 2009-09-02 7:35 UTC (permalink / raw)
To: Theodore Tso
Cc: Christoph Hellwig, Jens Axboe, linux-kernel, linux-fsdevel,
chris.mason, david, akpm, jack
> On Tue, 2009-09-01 at 16:27 -0400, Theodore Tso wrote:
> > So perhaps the best argument for not making this be a tunable is that
> > in the long run, we will need to put in a better algorithm for
> > controlling how much writeback we want to do before we start
> > saturating RAID arrays, and in that new algorithm this tunable may no
> > longer make sense. Fine; at that point, we can make it go away. For
> > now, though, it seems to be the best way to tweak what is going on,
> > since I doubt we'll be able to come up with one magic number that will
> > satisfy everyone.
Also, what is the incentive to actually improve the situation once we
merge this? People will say, turn the knob and don't bother us.
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 18:44 ` Christoph Hellwig
2009-09-01 20:27 ` Theodore Tso
@ 2009-09-01 23:52 ` Jamie Lokier
2009-09-01 23:56 ` Jamie Lokier
1 sibling, 1 reply; 22+ messages in thread
From: Jamie Lokier @ 2009-09-01 23:52 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Peter Zijlstra, Jens Axboe, linux-kernel, linux-fsdevel,
chris.mason, david, tytso, akpm, jack
Christoph Hellwig wrote:
> On Tue, Sep 01, 2009 at 08:38:55PM +0200, Peter Zijlstra wrote:
> > Do we really need a tunable for this?
>
> It will make increasing it in the field a lot easier. And having deal
> with really large systems I have the fear that there are I/O topologies
> outhere for which every "reasonable" value is too low.
>
> > I guess we need a limit to avoid it writing out everything, but can't we
> > have something automagic?
>
> Some automatic adjustment would be nice. But finding the right auto
> tuning will be an interesting exercise.
I have embedded systems with 32MB RAM and no MMU, where I deliberately
make the equivalent of max_writeback_pages *smaller* to limit the
number of dirty pages causing fragmentation and preventing allocation
of high-order pages... Write performance is less important than being
able to allocate contiguous memory for reads.
They are still using 2.4 kernels, but the principle still applies.
maybe even more on 2.6 which is more prone to fragmentation on small
no-MMU devices.
-- Jamie
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_pages
2009-09-01 23:52 ` Jamie Lokier
@ 2009-09-01 23:56 ` Jamie Lokier
0 siblings, 0 replies; 22+ messages in thread
From: Jamie Lokier @ 2009-09-01 23:56 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Peter Zijlstra, Jens Axboe, linux-kernel, linux-fsdevel,
chris.mason, david, tytso, akpm, jack
Jamie Lokier wrote:
> Christoph Hellwig wrote:
> > On Tue, Sep 01, 2009 at 08:38:55PM +0200, Peter Zijlstra wrote:
> > > Do we really need a tunable for this?
> >
> > It will make increasing it in the field a lot easier. And having deal
> > with really large systems I have the fear that there are I/O topologies
> > outhere for which every "reasonable" value is too low.
> >
> > > I guess we need a limit to avoid it writing out everything, but can't we
> > > have something automagic?
> >
> > Some automatic adjustment would be nice. But finding the right auto
> > tuning will be an interesting exercise.
>
> I have embedded systems with 32MB RAM and no MMU, where I deliberately
> make the equivalent of max_writeback_pages *smaller* to limit the
> number of dirty pages causing fragmentation and preventing allocation
> of high-order pages... Write performance is less important than being
> able to allocate contiguous memory for reads.
>
> They are still using 2.4 kernels, but the principle still applies.
> maybe even more on 2.6 which is more prone to fragmentation on small
> no-MMU devices.
Sorry, I must get more sleep. I confused max_writeback_pages with the
limit on dirty pages in the system, which is completely different.
So please ignore my previous mail.
*little*,
-- Jamie
^ permalink raw reply [flat|nested] 22+ messages in thread