While running some stress tests I started getting hung task messages.
This is because the delete unused bg's code has to take the
delete_unused_bgs_mutex to do it's work, which is taken by balance to
make sure we don't delete block groups while we're balancing.
The problem is a balance can take a while, and so we were getting hung
task warnings. We don't need to block and run these things, and the
cleaner is needed to do other work, so trylock on this mutex and just
bail if we can't acquire it right away.
Reviewed-by: Nikolay Borisov <nbori...@suse.com>
Signed-off-by: Josef Bacik <jo...@toxicpanda.com>
---
fs/btrfs/block-group.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 52f2198d44c9..f61e275bd792 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1254,6 +1254,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info
*fs_info)
if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
return;
+ /*
+ * Long running balances can keep us blocked here for eternity, so
+ * simply skip deletion if we're unable to get the mutex.
+ */
+ if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex))
+ return;
+
spin_lock(&fs_info->unused_bgs_lock);
while (!list_empty(&fs_info->unused_bgs)) {
int trimming;
@@ -1273,8 +1280,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info
*fs_info)
btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group);
- mutex_lock(&fs_info->delete_unused_bgs_mutex);
-
/* Don't want to race with allocators so take the groups_sem */
down_write(&space_info->groups_sem);
@@ -1420,11 +1425,11 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info
*fs_info)
end_trans:
btrfs_end_transaction(trans);
next:
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
btrfs_put_block_group(block_group);
spin_lock(&fs_info->unused_bgs_lock);
}
spin_unlock(&fs_info->unused_bgs_lock);
+ mutex_unlock(&fs_info->delete_unused_bgs_mutex);
return;
flip_async:
--
2.26.2
