Run out of space while coalescing

Whenever I delete a snapshot I receive a notification like this

Field		Value
-----		-----
Name:		No space left on device
Priority:	3
Class:		SR
Object UUID:	76923765-2dc5-5c99-e2b6-45d299348d19
Timestamp:	20160512T03:18:49Z
Message UUID:	805d55fb-7d04-b577-bedd-262f4d08d337
Pool name:	Pool1
Body:		Run out of space while coalescing.

This SR has about 500GB free, and the snapshot I am deleting is of a VM that is only 40GB. Despite receiving the message above, the snapshot is nowhere to be found (giving the appearance that everything succeeded and there is no problem).

However I am concerned about what is actually failing to happen, and how is it affecting my data. I had to rescue VM with filesystem corruption today, and I believe that may have been related.

I am able to reproduce this consistently, so just tell me what information you need and I will provide it.