system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-09-20 02:57:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

xfs: Non-blocking inode locking in IO completion

Browse source 
The introduction of barriers to loop devices has created a new IO
order completion dependency that XFS does not handle. The loop
device implements barriers using fsync and so turns a log IO in the
XFS filesystem on the loop device into a data IO in the backing
filesystem. That is, the completion of log IOs in the loop
filesystem are now dependent on completion of data IO in the backing
filesystem.

This can cause deadlocks when a flush daemon issues a log force with
an inode locked because the IO completion of IO on the inode is
blocked by the inode lock. This in turn prevents further data IO
completion from occuring on all XFS filesystems on that CPU (due to
the shared nature of the completion queues). This then prevents the
log IO from completing because the log is waiting for data IO
completion as well.

The fix for this new completion order dependency issue is to make
the IO completion inode locking non-blocking. If the inode lock
can't be grabbed, simply requeue the IO completion back to the work
queue so that it can be processed later. This prevents the
completion queue from being blocked and allows data IO completion on
other inodes to proceed, hence avoiding completion order dependent
deadlocks.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
This commit is contained in:
Dave Chinner 2010-02-17 05:36:29 +00:00 committed by Alex Elder
parent 66d834ea60
commit 77d7a0c2ee
1 changed files with 62 additions and 43 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

105
fs/xfs/linux-2.6/xfs_aops.c
View file

@ -163,14 +163,17 @@ xfs_ioend_new_eof(
}
/*
* Update on-disk file size now that data has been written to disk.
* The current in-memory file size is i_size. If a write is beyond
* eof i_new_size will be the intended file size until i_size is
* updated. If this write does not extend all the way to the valid
* file size then restrict this update to the end of the write.
* Update on-disk file size now that data has been written to disk. The
* current in-memory file size is i_size. If a write is beyond eof i_new_size
* will be the intended file size until i_size is updated. If this write does
* not extend all the way to the valid file size then restrict this update to
* the end of the write.
*
* This function does not block as blocking on the inode lock in IO completion
* can lead to IO completion order dependency deadlocks.. If it can't get the
* inode ilock it will return EAGAIN. Callers must handle this.
*/
STATIC void
STATIC int
xfs_setfilesize(
xfs_ioend_t *ioend)
{
@ -181,9 +184,11 @@ xfs_setfilesize(
ASSERT(ioend->io_type != IOMAP_READ);
if (unlikely(ioend->io_error))
return;
return 0;
if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
return EAGAIN;
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_ioend_new_eof(ioend);
if (isize) {
ip->i_d.di_size = isize;
@ -191,40 +196,7 @@ xfs_setfilesize(
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
/*
* IO write completion.
*/
STATIC void
xfs_end_io(
struct work_struct *work)
{
xfs_ioend_t *ioend =
container_of(work, xfs_ioend_t, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
/*
* For unwritten extents we need to issue transactions to convert a
* range to normal written extens after the data I/O has finished.
*/
if (ioend->io_type == IOMAP_UNWRITTEN &&
likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
int error;
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
if (error)
ioend->io_error = error;
}
/*
* We might have to update the on-disk file size after extending
* writes.
*/
if (ioend->io_type != IOMAP_READ)
xfs_setfilesize(ioend);
xfs_destroy_ioend(ioend);
return 0;
}
/*
@ -248,6 +220,53 @@ xfs_finish_ioend(
}
}
/*
* IO write completion.
*/
STATIC void
xfs_end_io(
struct work_struct *work)
{
xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
int error;
/*
* For unwritten extents we need to issue transactions to convert a
* range to normal written extens after the data I/O has finished.
*/
if (ioend->io_type == IOMAP_UNWRITTEN &&
likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
if (error)
ioend->io_error = error;
}
/*
* We might have to update the on-disk file size after extending
* writes.
*/
if (ioend->io_type != IOMAP_READ) {
error = xfs_setfilesize(ioend);
ASSERT(!error || error == EAGAIN);
}
/*
* If we didn't complete processing of the ioend, requeue it to the
* tail of the workqueue for another attempt later. Otherwise destroy
* it.
*/
if (error == EAGAIN) {
atomic_inc(&ioend->io_remaining);
xfs_finish_ioend(ioend, 0);
/* ensure we don't spin on blocked ioends */
delay(1);
} else
xfs_destroy_ioend(ioend);
}
/*
* Allocate and initialise an IO completion structure.
* We need to track unwritten extent write completion here initially.