I am encountering a deadlock issue as shown below. There is a commit
344150999b7f ("f2fs: fix to avoid potential deadlock") can fix this issue.
However, from log analysis, it appears that this is more likely a fake
progress issue similar to commit 68f4c6eba70d ("fs-writeback:
writeback_sb_inodes: Recalculate 'wrote' according skipped pages"). In each
writeback iteration, nothing is written, while writeback_sb_inodes()
increases 'total_wrote' each time, causing an infinite loop. This patch
fixes this issue by not increasing 'total_wrote' when nothing is written.
wb_writeback fsync (inode-Y)
blk_start_plug(&plug)
for (;;) {
iter i-1: some reqs with page-X added into plug->mq_list // f2fs node page-X with PG_writeback
filemap_fdatawrite
__filemap_fdatawrite_range // write inode-Y with sync_mode WB_SYNC_ALL
do_writepages
f2fs_write_data_pages
__f2fs_write_data_pages // wb_sync_req[DATA]++ for WB_SYNC_ALL
f2fs_write_cache_pages
f2fs_write_single_data_page
f2fs_do_write_data_page
f2fs_outplace_write_data
f2fs_update_data_blkaddr
f2fs_wait_on_page_writeback
wait_on_page_writeback // wait for f2fs node page-X
iter i:
progress = __writeback_inodes_wb(wb, work)
. writeback_sb_inodes
. __writeback_single_inode // write inode-Y with sync_mode WB_SYNC_NONE
. . do_writepages
. . f2fs_write_data_pages
. . . __f2fs_write_data_pages // skip writepages due to (wb_sync_req[DATA]>0)
. . . wbc->pages_skipped += get_dirty_pages(inode) // wbc->pages_skipped = 1
. if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC | I_SYNC_QUEUED
. total_wrote++; // total_wrote = 1
. requeue_inode // requeue inode-Y to wb->b_dirty queue due to non-zero pages_skipped
if (progress) // progress = 1
continue;
iter i+1:
queue_io
// similar process with iter i, infinite for-loop !
}
blk_finish_plug(&plug) // flush plug won't be called
Signed-off-by: Chunhai Guo <[email protected]>
---
fs/fs-writeback.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 969ce991b0b0..54cdee906be9 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct super_block *sb,
struct inode *inode = wb_inode(wb->b_io.prev);
struct bdi_writeback *tmp_wb;
long wrote;
+ bool is_dirty_before;
if (inode->i_sb != sb) {
if (work->sb) {
@@ -1881,6 +1882,7 @@ static long writeback_sb_inodes(struct super_block *sb,
continue;
}
inode->i_state |= I_SYNC;
+ is_dirty_before = inode->i_state & I_DIRTY_ALL;
wbc_attach_and_unlock_inode(&wbc, inode);
write_chunk = writeback_chunk_size(wb, work);
@@ -1918,7 +1920,7 @@ static long writeback_sb_inodes(struct super_block *sb,
*/
tmp_wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
- if (!(inode->i_state & I_DIRTY_ALL))
+ if (!(inode->i_state & I_DIRTY_ALL) && is_dirty_before)
total_wrote++;
requeue_inode(inode, tmp_wb, &wbc);
inode_sync_complete(inode);
--
2.25.1
[+Cc Jan]
On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> I am encountering a deadlock issue as shown below. There is a commit
> 344150999b7f ("f2fs: fix to avoid potential deadlock") can fix this issue.
> However, from log analysis, it appears that this is more likely a fake
> progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> writeback_sb_inodes: Recalculate 'wrote' according skipped pages"). In each
> writeback iteration, nothing is written, while writeback_sb_inodes()
> increases 'total_wrote' each time, causing an infinite loop. This patch
> fixes this issue by not increasing 'total_wrote' when nothing is written.
>
> wb_writeback fsync (inode-Y)
> blk_start_plug(&plug)
> for (;;) {
> iter i-1: some reqs with page-X added into plug->mq_list // f2fs node page-X with PG_writeback
> filemap_fdatawrite
> __filemap_fdatawrite_range // write inode-Y with sync_mode WB_SYNC_ALL
> do_writepages
> f2fs_write_data_pages
> __f2fs_write_data_pages // wb_sync_req[DATA]++ for WB_SYNC_ALL
> f2fs_write_cache_pages
> f2fs_write_single_data_page
> f2fs_do_write_data_page
> f2fs_outplace_write_data
> f2fs_update_data_blkaddr
> f2fs_wait_on_page_writeback
> wait_on_page_writeback // wait for f2fs node page-X
> iter i:
> progress = __writeback_inodes_wb(wb, work)
> . writeback_sb_inodes
> . __writeback_single_inode // write inode-Y with sync_mode WB_SYNC_NONE
> . . do_writepages
> . . f2fs_write_data_pages
> . . . __f2fs_write_data_pages // skip writepages due to (wb_sync_req[DATA]>0)
> . . . wbc->pages_skipped += get_dirty_pages(inode) // wbc->pages_skipped = 1
> . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC | I_SYNC_QUEUED
> . total_wrote++; // total_wrote = 1
> . requeue_inode // requeue inode-Y to wb->b_dirty queue due to non-zero pages_skipped
> if (progress) // progress = 1
> continue;
> iter i+1:
> queue_io
> // similar process with iter i, infinite for-loop !
> }
> blk_finish_plug(&plug) // flush plug won't be called
>
> Signed-off-by: Chunhai Guo <[email protected]>
> ---
> fs/fs-writeback.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 969ce991b0b0..54cdee906be9 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> struct inode *inode = wb_inode(wb->b_io.prev);
> struct bdi_writeback *tmp_wb;
> long wrote;
> + bool is_dirty_before;
>
> if (inode->i_sb != sb) {
> if (work->sb) {
> @@ -1881,6 +1882,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> continue;
> }
> inode->i_state |= I_SYNC;
> + is_dirty_before = inode->i_state & I_DIRTY_ALL;
> wbc_attach_and_unlock_inode(&wbc, inode);
>
> write_chunk = writeback_chunk_size(wb, work);
> @@ -1918,7 +1920,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> */
> tmp_wb = inode_to_wb_and_lock_list(inode);
> spin_lock(&inode->i_lock);
> - if (!(inode->i_state & I_DIRTY_ALL))
> + if (!(inode->i_state & I_DIRTY_ALL) && is_dirty_before)
> total_wrote++;
> requeue_inode(inode, tmp_wb, &wbc);
> inode_sync_complete(inode);
> --
> 2.25.1
>
On Wed 13-09-23 10:42:21, Christian Brauner wrote:
> [+Cc Jan]
Thanks!
> On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> > I am encountering a deadlock issue as shown below. There is a commit
> > 344150999b7f ("f2fs: fix to avoid potential deadlock") can fix this issue.
> > However, from log analysis, it appears that this is more likely a fake
> > progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> > writeback_sb_inodes: Recalculate 'wrote' according skipped pages"). In each
> > writeback iteration, nothing is written, while writeback_sb_inodes()
> > increases 'total_wrote' each time, causing an infinite loop. This patch
> > fixes this issue by not increasing 'total_wrote' when nothing is written.
> >
> > wb_writeback fsync (inode-Y)
> > blk_start_plug(&plug)
> > for (;;) {
> > iter i-1: some reqs with page-X added into plug->mq_list // f2fs node page-X with PG_writeback
> > filemap_fdatawrite
> > __filemap_fdatawrite_range // write inode-Y with sync_mode WB_SYNC_ALL
> > do_writepages
> > f2fs_write_data_pages
> > __f2fs_write_data_pages // wb_sync_req[DATA]++ for WB_SYNC_ALL
> > f2fs_write_cache_pages
> > f2fs_write_single_data_page
> > f2fs_do_write_data_page
> > f2fs_outplace_write_data
> > f2fs_update_data_blkaddr
> > f2fs_wait_on_page_writeback
> > wait_on_page_writeback // wait for f2fs node page-X
> > iter i:
> > progress = __writeback_inodes_wb(wb, work)
> > . writeback_sb_inodes
> > . __writeback_single_inode // write inode-Y with sync_mode WB_SYNC_NONE
> > . . do_writepages
> > . . f2fs_write_data_pages
> > . . . __f2fs_write_data_pages // skip writepages due to (wb_sync_req[DATA]>0)
> > . . . wbc->pages_skipped += get_dirty_pages(inode) // wbc->pages_skipped = 1
> > . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC | I_SYNC_QUEUED
> > . total_wrote++; // total_wrote = 1
> > . requeue_inode // requeue inode-Y to wb->b_dirty queue due to non-zero pages_skipped
> > if (progress) // progress = 1
> > continue;
> > iter i+1:
> > queue_io
> > // similar process with iter i, infinite for-loop !
> > }
> > blk_finish_plug(&plug) // flush plug won't be called
> >
> > Signed-off-by: Chunhai Guo <[email protected]>
Thanks for the patch but did you test this patch fixed your deadlock?
Because the patch seems like a noop to me. Look:
> > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> > index 969ce991b0b0..54cdee906be9 100644
> > --- a/fs/fs-writeback.c
> > +++ b/fs/fs-writeback.c
> > @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> > struct inode *inode = wb_inode(wb->b_io.prev);
> > struct bdi_writeback *tmp_wb;
> > long wrote;
> > + bool is_dirty_before;
> >
> > if (inode->i_sb != sb) {
> > if (work->sb) {
> > @@ -1881,6 +1882,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> > continue;
> > }
> > inode->i_state |= I_SYNC;
> > + is_dirty_before = inode->i_state & I_DIRTY_ALL;
is_dirty_before is going to be set if there's anything dirty - inode, page,
timestamp. So it can be unset only if there are no dirty pages, in which
case there are no pages that can be skipped during page writeback, which means
that requeue_inode() will go and remove inode from b_io/b_dirty lists and
it will not participate in writeback anymore.
So I don't see how this patch can be helping anything... Please correct me
if I'm missing anything.
Honza
> > wbc_attach_and_unlock_inode(&wbc, inode);
> >
> > write_chunk = writeback_chunk_size(wb, work);
> > @@ -1918,7 +1920,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> > */
> > tmp_wb = inode_to_wb_and_lock_list(inode);
> > spin_lock(&inode->i_lock);
> > - if (!(inode->i_state & I_DIRTY_ALL))
> > + if (!(inode->i_state & I_DIRTY_ALL) && is_dirty_before)
> > total_wrote++;
> > requeue_inode(inode, tmp_wb, &wbc);
> > inode_sync_complete(inode);
> > --
> > 2.25.1
> >
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Wed 13-09-23 07:15:01, Chunhai Guo wrote:
> > On Wed 13-09-23 10:42:21, Christian Brauner wrote:
> > > [+Cc Jan]
> >
> > Thanks!
> >
> > > On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> > > > I am encountering a deadlock issue as shown below. There is a commit
> > > > 344150999b7f ("f2fs: fix to avoid potential deadlock") can fix this
> > > > issue.
> > > > However, from log analysis, it appears that this is more likely a
> > > > fake progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> > > > writeback_sb_inodes: Recalculate 'wrote' according skipped pages").
> > > > In each writeback iteration, nothing is written, while
> > > > writeback_sb_inodes() increases 'total_wrote' each time, causing an
> > > > infinite loop. This patch fixes this issue by not increasing
> > > > 'total_wrote' when nothing is written.
> > > >
> > > > wb_writeback fsync (inode-Y)
> > > > blk_start_plug(&plug)
> > > > for (;;) {
> > > > iter i-1: some reqs with page-X added into plug->mq_list // f2fs node
> > > > page-X with PG_writeback
> > > > filemap_fdatawrite
> > > > __filemap_fdatawrite_range // write inode-Y
> > > > with sync_mode WB_SYNC_ALL
> > > > do_writepages
> > > > f2fs_write_data_pages
> > > > __f2fs_write_data_pages //
> > > > wb_sync_req[DATA]++ for WB_SYNC_ALL
> > > > f2fs_write_cache_pages
> > > > f2fs_write_single_data_page
> > > > f2fs_do_write_data_page
> > > > f2fs_outplace_write_data
> > > > f2fs_update_data_blkaddr
> > > > f2fs_wait_on_page_writeback
> > > > wait_on_page_writeback // wait for
> > > > f2fs node page-X
> > > > iter i:
> > > > progress = __writeback_inodes_wb(wb, work)
> > > > . writeback_sb_inodes
> > > > . __writeback_single_inode // write inode-Y with sync_mode
> > > > WB_SYNC_NONE
> > > > . . do_writepages
> > > > . . f2fs_write_data_pages
> > > > . . . __f2fs_write_data_pages // skip writepages due to
> > > > (wb_sync_req[DATA]>0)
> > > > . . . wbc->pages_skipped += get_dirty_pages(inode) //
> > > > wbc->pages_skipped = 1
> > > > . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC |
> > > > I_SYNC_QUEUED
> > > > . total_wrote++; // total_wrote = 1
> > > > . requeue_inode // requeue inode-Y to wb->b_dirty queue due to
> > > > non-zero pages_skipped
> > > > if (progress) // progress = 1
> > > > continue;
> > > > iter i+1:
> > > > queue_io
> > > > // similar process with iter i, infinite for-loop !
> > > > }
> > > > blk_finish_plug(&plug) // flush plug won't be called
> > > >
> > > > Signed-off-by: Chunhai Guo <[email protected]>
> >
> > Thanks for the patch but did you test this patch fixed your deadlock?
> > Because the patch seems like a noop to me. Look:
>
> Yes. I have tested this patch and it indeed fixed this deadlock issue, too.
OK, thanks for letting me know!
> > > > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index
> > > > 969ce991b0b0..54cdee906be9 100644
> > > > --- a/fs/fs-writeback.c
> > > > +++ b/fs/fs-writeback.c
> > > > @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct
> > > > super_block *sb,
> > > > struct inode *inode = wb_inode(wb->b_io.prev);
> > > > struct bdi_writeback *tmp_wb;
> > > > long wrote;
> > > > + bool is_dirty_before;
> > > >
> > > > if (inode->i_sb != sb) {
> > > > if (work->sb) {
> > > > @@ -1881,6 +1882,7 @@ static long writeback_sb_inodes(struct
> > > > super_block *sb,
> > > > continue;
> > > > }
> > > > inode->i_state |= I_SYNC;
> > > > + is_dirty_before = inode->i_state & I_DIRTY_ALL;
> >
> > is_dirty_before is going to be set if there's anything dirty - inode, page,
> > timestamp. So it can be unset only if there are no dirty pages, in which
> > case there are no pages that can be skipped during page writeback, which
> > means that requeue_inode() will go and remove inode from b_io/b_dirty lists
> > and it will not participate in writeback anymore.
> >
> > So I don't see how this patch can be helping anything... Please correct me
> > if I'm missing anything.
> > Honza
>
> From the dump info, there are only two pages as shown below. One is updated
> and another is under writeback. Maybe f2fs counts the writeback page as a
> dirty one, so get_dirty_pages() got one. As you said, maybe this is
> unreasonable.
>
> Jaegeuk & Chao, what do you think of this?
>
>
> crash_32> files -p 0xE5A44678
> INODE NRPAGES
> e5a44678 2
>
> PAGE PHYSICAL MAPPING INDEX CNT FLAGS
> e8d0e338 641de000 e5a44810 0 5 a095 locked,waiters,uptodate,lru,private,writeback
> e8ad59a0 54528000 e5a44810 1 2 2036 referenced,uptodate,lru,active,private
Indeed, incrementing pages_skipped when there's no dirty page is a bit odd.
That being said we could also harden requeue_inode() - in particular we
could do there:
if (wbc->pages_skipped) {
/*
* Writeback is not making progress due to locked buffers.
* Skip this inode for now. Although having skipped pages
* is odd for clean inodes, it can happen for some
* filesystems so handle that gracefully.
*/
if (inode->i_state & I_DIRTY_ALL)
redirty_tail_locked(inode, wb);
else
inode_cgwb_move_to_attached(inode, wb);
}
Does this fix your problem as well?
Honza
>
> Thanks,
>
> >
> >
> > > > wbc_attach_and_unlock_inode(&wbc, inode);
> > > >
> > > > write_chunk = writeback_chunk_size(wb, work); @@ -1918,7
> > > > +1920,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> > > > */
> > > > tmp_wb = inode_to_wb_and_lock_list(inode);
> > > > spin_lock(&inode->i_lock);
> > > > - if (!(inode->i_state & I_DIRTY_ALL))
> > > > + if (!(inode->i_state & I_DIRTY_ALL) && is_dirty_before)
> > > > total_wrote++;
> > > > requeue_inode(inode, tmp_wb, &wbc);
> > > > inode_sync_complete(inode);
> > > > --
> > > > 2.25.1
> > > >
> > --
> > Jan Kara <[email protected]>
> > SUSE Labs, CR
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
Test2
> On Wed 13-09-23 07:15:01, Chunhai Guo wrote:
> > > On Wed 13-09-23 10:42:21, Christian Brauner wrote:
> > > > [+Cc Jan]
> > >
> > > Thanks!
> > >
> > > > On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> > > > > I am encountering a deadlock issue as shown below. There is a
> > > > > commit 344150999b7f ("f2fs: fix to avoid potential deadlock")
> > > > > can fix this issue.
> > > > > However, from log analysis, it appears that this is more likely
> > > > > a fake progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> > > > > writeback_sb_inodes: Recalculate 'wrote' according skipped pages").
> > > > > In each writeback iteration, nothing is written, while
> > > > > writeback_sb_inodes() increases 'total_wrote' each time, causing
> > > > > an infinite loop. This patch fixes this issue by not increasing
> > > > > 'total_wrote' when nothing is written.
> > > > >
> > > > > wb_writeback fsync (inode-Y)
> > > > > blk_start_plug(&plug)
> > > > > for (;;) {
> > > > > iter i-1: some reqs with page-X added into plug->mq_list // f2fs node
> > > > > page-X with PG_writeback
> > > > > filemap_fdatawrite
> > > > > __filemap_fdatawrite_range // write inode-Y
> > > > > with sync_mode WB_SYNC_ALL
> > > > > do_writepages
> > > > > f2fs_write_data_pages
> > > > > __f2fs_write_data_pages //
> > > > > wb_sync_req[DATA]++ for WB_SYNC_ALL
> > > > > f2fs_write_cache_pages
> > > > > f2fs_write_single_data_page
> > > > > f2fs_do_write_data_page
> > > > > f2fs_outplace_write_data
> > > > > f2fs_update_data_blkaddr
> > > > > f2fs_wait_on_page_writeback
> > > > > wait_on_page_writeback // wait for
> > > > > f2fs node page-X
> > > > > iter i:
> > > > > progress = __writeback_inodes_wb(wb, work)
> > > > > . writeback_sb_inodes
> > > > > . __writeback_single_inode // write inode-Y with sync_mode
> > > > > WB_SYNC_NONE
> > > > > . . do_writepages
> > > > > . . f2fs_write_data_pages
> > > > > . . . __f2fs_write_data_pages // skip writepages due to
> > > > > (wb_sync_req[DATA]>0)
> > > > > . . . wbc->pages_skipped += get_dirty_pages(inode) //
> > > > > wbc->pages_skipped = 1
> > > > > . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC |
> > > > > I_SYNC_QUEUED
> > > > > . total_wrote++; // total_wrote = 1
> > > > > . requeue_inode // requeue inode-Y to wb->b_dirty queue due to
> > > > > non-zero pages_skipped
> > > > > if (progress) // progress = 1
> > > > > continue;
> > > > > iter i+1:
> > > > > queue_io
> > > > > // similar process with iter i, infinite for-loop !
> > > > > }
> > > > > blk_finish_plug(&plug) // flush plug won't be called
> > > > >
> > > > > Signed-off-by: Chunhai Guo <[email protected]>
> > >
> > > Thanks for the patch but did you test this patch fixed your deadlock?
> > > Because the patch seems like a noop to me. Look:
> >
> > Yes. I have tested this patch and it indeed fixed this deadlock issue, too.
>
> OK, thanks for letting me know!
>
> > > > > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index
> > > > > 969ce991b0b0..54cdee906be9 100644
> > > > > --- a/fs/fs-writeback.c
> > > > > +++ b/fs/fs-writeback.c
> > > > > @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct
> > > > > super_block *sb,
> > > > > struct inode *inode = wb_inode(wb->b_io.prev);
> > > > > struct bdi_writeback *tmp_wb;
> > > > > long wrote;
> > > > > + bool is_dirty_before;
> > > > >
> > > > > if (inode->i_sb != sb) {
> > > > > if (work->sb) { @@ -1881,6 +1882,7 @@ static
> > > > > long writeback_sb_inodes(struct super_block *sb,
> > > > > continue;
> > > > > }
> > > > > inode->i_state |= I_SYNC;
> > > > > + is_dirty_before = inode->i_state & I_DIRTY_ALL;
> > >
> > > is_dirty_before is going to be set if there's anything dirty -
> > > inode, page, timestamp. So it can be unset only if there are no
> > > dirty pages, in which case there are no pages that can be skipped
> > > during page writeback, which means that requeue_inode() will go and
> > > remove inode from b_io/b_dirty lists and it will not participate in writeback
> anymore.
> > >
> > > So I don't see how this patch can be helping anything... Please
> > > correct me if I'm missing anything.
> > >
> > > Honza
> >
> > From the dump info, there are only two pages as shown below. One is
> > updated and another is under writeback. Maybe f2fs counts the
> > writeback page as a dirty one, so get_dirty_pages() got one. As you
> > said, maybe this is unreasonable.
> >
> > Jaegeuk & Chao, what do you think of this?
> >
> >
> > crash_32> files -p 0xE5A44678
> > INODE NRPAGES
> > e5a44678 2
> >
> > PAGE PHYSICAL MAPPING INDEX CNT FLAGS
> > e8d0e338 641de000 e5a44810 0 5 a095
> locked,waiters,uptodate,lru,private,writeback
> > e8ad59a0 54528000 e5a44810 1 2 2036
> referenced,uptodate,lru,active,private
>
> Indeed, incrementing pages_skipped when there's no dirty page is a bit odd.
> That being said we could also harden requeue_inode() - in particular we could do
> there:
>
> if (wbc->pages_skipped) {
> /*
> * Writeback is not making progress due to locked buffers.
> * Skip this inode for now. Although having skipped pages
> * is odd for clean inodes, it can happen for some
> * filesystems so handle that gracefully.
> */
> if (inode->i_state & I_DIRTY_ALL)
> redirty_tail_locked(inode, wb);
> else
> inode_cgwb_move_to_attached(inode, wb);
> }
>
> Does this fix your problem as well?
>
> Honza
> >
> > Thanks,
> >
> > >
> > >
> > > > > wbc_attach_and_unlock_inode(&wbc, inode);
> > > > >
> > > > > write_chunk = writeback_chunk_size(wb, work); @@
> > > > > -1918,7
> > > > > +1920,7 @@ static long writeback_sb_inodes(struct super_block
> > > > > +*sb,
> > > > > */
> > > > > tmp_wb = inode_to_wb_and_lock_list(inode);
> > > > > spin_lock(&inode->i_lock);
> > > > > - if (!(inode->i_state & I_DIRTY_ALL))
> > > > > + if (!(inode->i_state & I_DIRTY_ALL) &&
> > > > > + is_dirty_before)
> > > > > total_wrote++;
> > > > > requeue_inode(inode, tmp_wb, &wbc);
> > > > > inode_sync_complete(inode);
> > > > > --
> > > > > 2.25.1
> > > > >
> > > --
> > > Jan Kara <[email protected]>
> > > SUSE Labs, CR
> >
> --
> Jan Kara <[email protected]>
> SUSE Labs, CR
> On Wed 13-09-23 10:42:21, Christian Brauner wrote:
> > [+Cc Jan]
>
> Thanks!
>
> > On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> > > I am encountering a deadlock issue as shown below. There is a commit
> > > 344150999b7f ("f2fs: fix to avoid potential deadlock") can fix this
> > > issue.
> > > However, from log analysis, it appears that this is more likely a
> > > fake progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> > > writeback_sb_inodes: Recalculate 'wrote' according skipped pages").
> > > In each writeback iteration, nothing is written, while
> > > writeback_sb_inodes() increases 'total_wrote' each time, causing an
> > > infinite loop. This patch fixes this issue by not increasing
> > > 'total_wrote' when nothing is written.
> > >
> > > wb_writeback fsync (inode-Y)
> > > blk_start_plug(&plug)
> > > for (;;) {
> > > iter i-1: some reqs with page-X added into plug->mq_list // f2fs node
> > > page-X with PG_writeback
> > > filemap_fdatawrite
> > > __filemap_fdatawrite_range // write inode-Y
> > > with sync_mode WB_SYNC_ALL
> > > do_writepages
> > > f2fs_write_data_pages
> > > __f2fs_write_data_pages //
> > > wb_sync_req[DATA]++ for WB_SYNC_ALL
> > > f2fs_write_cache_pages
> > > f2fs_write_single_data_page
> > > f2fs_do_write_data_page
> > > f2fs_outplace_write_data
> > > f2fs_update_data_blkaddr
> > > f2fs_wait_on_page_writeback
> > > wait_on_page_writeback // wait for
> > > f2fs node page-X
> > > iter i:
> > > progress = __writeback_inodes_wb(wb, work)
> > > . writeback_sb_inodes
> > > . __writeback_single_inode // write inode-Y with sync_mode
> > > WB_SYNC_NONE
> > > . . do_writepages
> > > . . f2fs_write_data_pages
> > > . . . __f2fs_write_data_pages // skip writepages due to
> > > (wb_sync_req[DATA]>0)
> > > . . . wbc->pages_skipped += get_dirty_pages(inode) //
> > > wbc->pages_skipped = 1
> > > . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC |
> > > I_SYNC_QUEUED
> > > . total_wrote++; // total_wrote = 1
> > > . requeue_inode // requeue inode-Y to wb->b_dirty queue due to
> > > non-zero pages_skipped
> > > if (progress) // progress = 1
> > > continue;
> > > iter i+1:
> > > queue_io
> > > // similar process with iter i, infinite for-loop !
> > > }
> > > blk_finish_plug(&plug) // flush plug won't be called
> > >
> > > Signed-off-by: Chunhai Guo <[email protected]>
>
> Thanks for the patch but did you test this patch fixed your deadlock?
> Because the patch seems like a noop to me. Look:
Yes. I have tested this patch and it indeed fixed this deadlock issue, too.
>
> > > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index
> > > 969ce991b0b0..54cdee906be9 100644
> > > --- a/fs/fs-writeback.c
> > > +++ b/fs/fs-writeback.c
> > > @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct
> > > super_block *sb,
> > > struct inode *inode = wb_inode(wb->b_io.prev);
> > > struct bdi_writeback *tmp_wb;
> > > long wrote;
> > > + bool is_dirty_before;
> > >
> > > if (inode->i_sb != sb) {
> > > if (work->sb) {
> > > @@ -1881,6 +1882,7 @@ static long writeback_sb_inodes(struct
> > > super_block *sb,
> > > continue;
> > > }
> > > inode->i_state |= I_SYNC;
> > > + is_dirty_before = inode->i_state & I_DIRTY_ALL;
>
> is_dirty_before is going to be set if there's anything dirty - inode, page,
> timestamp. So it can be unset only if there are no dirty pages, in which
> case there are no pages that can be skipped during page writeback, which
> means that requeue_inode() will go and remove inode from b_io/b_dirty lists
> and it will not participate in writeback anymore.
>
> So I don't see how this patch can be helping anything... Please correct me
> if I'm missing anything.
> Honza
From the dump info, there are only two pages as shown below. One is updated
and another is under writeback. Maybe f2fs counts the writeback page as a
dirty one, so get_dirty_pages() got one. As you said, maybe this is
unreasonable.
Jaegeuk & Chao, what do you think of this?
crash_32> files -p 0xE5A44678
INODE NRPAGES
e5a44678 2
PAGE PHYSICAL MAPPING INDEX CNT FLAGS
e8d0e338 641de000 e5a44810 0 5 a095 locked,waiters,uptodate,lru,private,writeback
e8ad59a0 54528000 e5a44810 1 2 2036 referenced,uptodate,lru,active,private
Thanks,
>
>
> > > wbc_attach_and_unlock_inode(&wbc, inode);
> > >
> > > write_chunk = writeback_chunk_size(wb, work); @@ -1918,7
> > > +1920,7 @@ static long writeback_sb_inodes(struct super_block *sb,
> > > */
> > > tmp_wb = inode_to_wb_and_lock_list(inode);
> > > spin_lock(&inode->i_lock);
> > > - if (!(inode->i_state & I_DIRTY_ALL))
> > > + if (!(inode->i_state & I_DIRTY_ALL) && is_dirty_before)
> > > total_wrote++;
> > > requeue_inode(inode, tmp_wb, &wbc);
> > > inode_sync_complete(inode);
> > > --
> > > 2.25.1
> > >
> --
> Jan Kara <[email protected]>
> SUSE Labs, CR
> On Wed 13-09-23 07:15:01, Chunhai Guo wrote:
> > > On Wed 13-09-23 10:42:21, Christian Brauner wrote:
> > > > [+Cc Jan]
> > >
> > > Thanks!
> > >
> > > > On Tue, Sep 12, 2023 at 08:20:43AM -0600, Chunhai Guo wrote:
> > > > > I am encountering a deadlock issue as shown below. There is a
> > > > > commit 344150999b7f ("f2fs: fix to avoid potential deadlock")
> > > > > can fix this issue.
> > > > > However, from log analysis, it appears that this is more likely
> > > > > a fake progress issue similar to commit 68f4c6eba70d ("fs-writeback:
> > > > > writeback_sb_inodes: Recalculate 'wrote' according skipped pages").
> > > > > In each writeback iteration, nothing is written, while
> > > > > writeback_sb_inodes() increases 'total_wrote' each time, causing
> > > > > an infinite loop. This patch fixes this issue by not increasing
> > > > > 'total_wrote' when nothing is written.
> > > > >
> > > > > wb_writeback fsync (inode-Y)
> > > > > blk_start_plug(&plug)
> > > > > for (;;) {
> > > > > iter i-1: some reqs with page-X added into plug->mq_list // f2fs node
> > > > > page-X with PG_writeback
> > > > > filemap_fdatawrite
> > > > > __filemap_fdatawrite_range // write inode-Y
> > > > > with sync_mode WB_SYNC_ALL
> > > > > do_writepages
> > > > > f2fs_write_data_pages
> > > > > __f2fs_write_data_pages //
> > > > > wb_sync_req[DATA]++ for WB_SYNC_ALL
> > > > > f2fs_write_cache_pages
> > > > > f2fs_write_single_data_page
> > > > > f2fs_do_write_data_page
> > > > > f2fs_outplace_write_data
> > > > > f2fs_update_data_blkaddr
> > > > > f2fs_wait_on_page_writeback
> > > > > wait_on_page_writeback // wait for
> > > > > f2fs node page-X
> > > > > iter i:
> > > > > progress = __writeback_inodes_wb(wb, work)
> > > > > . writeback_sb_inodes
> > > > > . __writeback_single_inode // write inode-Y with sync_mode
> > > > > WB_SYNC_NONE
> > > > > . . do_writepages
> > > > > . . f2fs_write_data_pages
> > > > > . . . __f2fs_write_data_pages // skip writepages due to
> > > > > (wb_sync_req[DATA]>0)
> > > > > . . . wbc->pages_skipped += get_dirty_pages(inode) //
> > > > > wbc->pages_skipped = 1
> > > > > . if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC |
> > > > > I_SYNC_QUEUED
> > > > > . total_wrote++; // total_wrote = 1
> > > > > . requeue_inode // requeue inode-Y to wb->b_dirty queue due to
> > > > > non-zero pages_skipped
> > > > > if (progress) // progress = 1
> > > > > continue;
> > > > > iter i+1:
> > > > > queue_io
> > > > > // similar process with iter i, infinite for-loop !
> > > > > }
> > > > > blk_finish_plug(&plug) // flush plug won't be called
> > > > >
> > > > > Signed-off-by: Chunhai Guo <[email protected]>
> > >
> > > Thanks for the patch but did you test this patch fixed your deadlock?
> > > Because the patch seems like a noop to me. Look:
> >
> > Yes. I have tested this patch and it indeed fixed this deadlock issue, too.
>
> OK, thanks for letting me know!
>
> > > > > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index
> > > > > 969ce991b0b0..54cdee906be9 100644
> > > > > --- a/fs/fs-writeback.c
> > > > > +++ b/fs/fs-writeback.c
> > > > > @@ -1820,6 +1820,7 @@ static long writeback_sb_inodes(struct
> > > > > super_block *sb,
> > > > > struct inode *inode = wb_inode(wb->b_io.prev);
> > > > > struct bdi_writeback *tmp_wb;
> > > > > long wrote;
> > > > > + bool is_dirty_before;
> > > > >
> > > > > if (inode->i_sb != sb) {
> > > > > if (work->sb) { @@ -1881,6 +1882,7 @@ static
> > > > > long writeback_sb_inodes(struct super_block *sb,
> > > > > continue;
> > > > > }
> > > > > inode->i_state |= I_SYNC;
> > > > > + is_dirty_before = inode->i_state & I_DIRTY_ALL;
> > >
> > > is_dirty_before is going to be set if there's anything dirty -
> > > inode, page, timestamp. So it can be unset only if there are no
> > > dirty pages, in which case there are no pages that can be skipped
> > > during page writeback, which means that requeue_inode() will go and
> > > remove inode from b_io/b_dirty lists and it will not participate in writeback
> anymore.
> > >
> > > So I don't see how this patch can be helping anything... Please
> > > correct me if I'm missing anything.
> > >
> > > Honza
> >
> > From the dump info, there are only two pages as shown below. One is
> > updated and another is under writeback. Maybe f2fs counts the
> > writeback page as a dirty one, so get_dirty_pages() got one. As you
> > said, maybe this is unreasonable.
> >
> > Jaegeuk & Chao, what do you think of this?
> >
> >
> > crash_32> files -p 0xE5A44678
> > INODE NRPAGES
> > e5a44678 2
> >
> > PAGE PHYSICAL MAPPING INDEX CNT FLAGS
> > e8d0e338 641de000 e5a44810 0 5 a095
> locked,waiters,uptodate,lru,private,writeback
> > e8ad59a0 54528000 e5a44810 1 2 2036
> referenced,uptodate,lru,active,private
>
> Indeed, incrementing pages_skipped when there's no dirty page is a bit odd.
> That being said we could also harden requeue_inode() - in particular we could do
> there:
>
> if (wbc->pages_skipped) {
> /*
> * Writeback is not making progress due to locked buffers.
> * Skip this inode for now. Although having skipped pages
> * is odd for clean inodes, it can happen for some
> * filesystems so handle that gracefully.
> */
> if (inode->i_state & I_DIRTY_ALL)
> redirty_tail_locked(inode, wb);
> else
> inode_cgwb_move_to_attached(inode, wb);
> }
>
> Does this fix your problem as well?
>
> Honza
Thank you for your reply. Did you forget the 'return' statement? Since I encountered this issue on the 4.19 kernel and there is not inode_cgwb_move_to_attached() yet, I replaced it with inode_io_list_del_locked(). So, below is the test patch I am applying. Please have a check. By the way, the test will take some time. I will provide feedback when it is finished. Thanks.
if (wbc->pages_skipped) {
/*
* writeback is not making progress due to locked
* buffers. Skip this inode for now.
*/
- redirty_tail_locked(inode, wb);
+ if (inode->i_state & I_DIRTY_ALL)
+ redirty_tail_locked(inode, wb);
+ else
+ inode_io_list_del_locked(inode, wb);
return;
}
> >
> > Thanks,
> >
> > >
> > >
> > > > > wbc_attach_and_unlock_inode(&wbc, inode);
> > > > >
> > > > > write_chunk = writeback_chunk_size(wb, work); @@
> > > > > -1918,7
> > > > > +1920,7 @@ static long writeback_sb_inodes(struct super_block
> > > > > +*sb,
> > > > > */
> > > > > tmp_wb = inode_to_wb_and_lock_list(inode);
> > > > > spin_lock(&inode->i_lock);
> > > > > - if (!(inode->i_state & I_DIRTY_ALL))
> > > > > + if (!(inode->i_state & I_DIRTY_ALL) &&
> > > > > + is_dirty_before)
> > > > > total_wrote++;
> > > > > requeue_inode(inode, tmp_wb, &wbc);
> > > > > inode_sync_complete(inode);
> > > > > --
> > > > > 2.25.1
> > > > >
> > > --
> > > Jan Kara <[email protected]>
> > > SUSE Labs, CR
> >
> --
> Jan Kara <[email protected]>
> SUSE Labs, CR