Thanks for your answer. Now it makes sense.
I guess you could do some optimization to avoid sending a barrier too often.

nicolae


On Fri, Sep 24, 2010 at 8:53 PM, Lars Ellenberg
<[email protected]> wrote:
>
> DRBD's usage of barriers/cache flushes is to make sure
> we won't "forget" to resync parts that need to be synced
> after a node crash.
>
> --
_______________________________________________
drbd-user mailing list
[email protected]
http://lists.linbit.com/mailman/listinfo/drbd-user

Reply via email to