Re: [BUG] XFS (delalloc) writeback livelock writing to -ENOSPC on dm-thin

[Dave Chinner <david@fromorbit.com>]

On Fri, Apr 21, 2023 at 07:02:39AM -0400, Brian Foster wrote:
> Hi all,
> 
> The test case is a simple sequential write to XFS backed by a thin
> volume. The test vm is running latest 6.3.0-rc7, has 8xcpu and 8GB RAM,
> and the thin volume is backed by sufficient space in the thin pool.
> I.e.:
> 
> lvcreate --type thin-pool -n tpool -L30G test
> lvcreate -V 20G -n tvol test/tpool
> mkfs.xfs /dev/test/tvol
> mount /dev/test/tvol /mnt
> dd if=/dev/zero of=/mnt/file bs=1M
> 
> The dd command writes until ~1GB or so free space is left in the fs and
> then seems to hit a livelock. From a quick look at tracepoints, XFS
> seems to be spinning in the xfs_convert_blocks() writeback path. df
> shows space consumption no longer changing, the flush worker is spinning
> at 100% and dd is blocked in balance_dirty_pages(). If I kill dd, the
> writeback worker continues spinning and an fsync of the file blocks
> indefinitely.
> 
> If I reset the vm, remount and run the following:
> 
> dd if=/dev/zero of=/mnt/file bs=1M conv=notrunc oflag=append
> 
> ... it then runs to -ENOSPC, as expected.
> 
> I haven't seen this occur when running on a non-thin lvm volume, not
> sure why.

thinp volumes trigger stripe alignment in mkfs, which then use
different allocation strategies at writeback time.

Patch to fix it already sent to the list.

-Dave.
-- 
Dave Chinner
david@fromorbit.com