On 2005-03-19T00:46:51, Michael Tokarev <mjt@xxxxxxxxxx> wrote:
> o DRBD allows local drive to be a bit ahead compared to remote one
> (configurable), while md will wait for all drives to complete a write.
The async writes have been added to md recently my Paul too.
> There's a case which is questionable in the first place: what to
> do if local part of the mirror fails? Md will happily run on
> single remote component in degraded mode, while DRBD will probably
> fail...
drbd will continue correctly; it'll detach the local drive and run all
IO over the network. Also, the direction of the sync has been decoupled
from the primary/secondary status for a while, and the drbd-0.8
(development branch) is almost 90% there to allow both nodes IO access
to the device.
(I think; maybe it's also already done. It's been a while since I tried
playing with that particular version.)
Sincerely,
Lars Marowsky-Brée <lmb@xxxxxxx>
--
High Availability & Clustering
SUSE Labs, Research and Development
SUSE LINUX Products GmbH - A Novell Business
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
