Btrfs: add a cond_resched() into the worker loop

If we have a constant stream of end_io completions or crc work,
we can hit softlockup messages from the async helper threads.  This
adds a cond_resched() into the loop to avoid them.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit is contained in:
Chris Mason 2011-12-15 09:29:43 -05:00
parent 306424cc88
commit 8f3b65a3d6

View File

@ -331,7 +331,7 @@ static int worker_loop(void *arg)
run_ordered_completions(worker->workers, work);
check_pending_worker_creates(worker);
cond_resched();
}
spin_lock_irq(&worker->lock);