[ofa-general] Nodes dropping out of IPoIB mcast group

Or Gerlitz ogerlitz at voltaire.com
Mon Apr 28 23:57:58 PDT 2008


Ira Weiny wrote:
>> OK, good. Does this problem exist in the released openSM? if yes, what 
>> would be the trigger for the SM to "really discover" (i.e do PortInfo 
>> SET) this sub-fabric and how much time would it take to reach this 
>> trigger, worst case wise?
> Yes, this is in the current released version of OpenSM, AFAICT.  The trigger
> is: the single link separating the partial sub net will come up and that trap
> will cause OpenSM to resweep.  I believe this will happen on the next resweep
> cycle which is by default 10 sec.  (But this is configurable.)  I don't think
> there is an issue with allowing OpenSM to resweep as designed.

And when openSM does the heavy sweep, what nodes would have their client 
rereg bit set, only the ones beyond the recovered link? also will openSM 
cycle the logical link state of those nodes (which is active!) through 
armed-active again or the only SET would be for the rereg bit?

Or.






More information about the general mailing list