drbd: wait for meta data IO completion even with failed disk, unless force-detached
authorLars Ellenberg <lars.ellenberg@linbit.com>
Thu, 27 Sep 2012 13:07:11 +0000 (15:07 +0200)
committerPhilipp Reisner <philipp.reisner@linbit.com>
Fri, 9 Nov 2012 13:11:40 +0000 (14:11 +0100)
The intention of force-detach is to be able to deal with a completely
unresponsive lower level IO stack, which does not even deliver error
completions anymore, but no completion at all.

In all other cases, we must still wait for the meta data IO completion.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

No differences found