On Tue, 2 Aug 2005, Guy German wrote:
Guy, can you investigate why the ib_mthca module doesn't have a
reference count and see if it relates to hotplug? I think
kdapl_ib and
ib_mthca should have the same policy regarding this issue.
As I understand, consumers are working over ib_core and not over
ib_mthca directly. So, if (from a hotplug reason) ib_mthca goes
down, ib_core consumers can get notified of the event, by an upcall.
Correct. Is the fact that ib_mthca always has a reference count of 0 a
concious design decision to support hotplug? I think the answer is
yes, I just want to make sure.
If you take this model to dapl, I think it would influence the way
dapl consumers need to do things (like registering an upcall and
know what to do in case kdapl_ib is down).
I also don't know how many consumers really need "dapl hotplug"...
Long term, kDAPL should support hotplug. As you say, we will need to
modify the API to support this (as noted in the kDAPL TODO list in the
Wiki).
As the code stands now, we should protect users from accidently
removing kdapl_ib.
Are you re-working your patch for this?
I've thought about this some more. To be safe, I think the module
reference counts should be adjusted in dat_registry_add_provider() and
dat_registry_remove_provider().
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
