Hal Rosenstock wrote: > > Yes, but AFAIK the only "bad" case is if the LID stays the same but > LMC changes to a lower > value. In this case the path refresh will not happen when it is > supposed to. > > > What's the impact of that ? > > Also the LID can change at the same time as the LMC. > > I can't tell if all the possible cases are handled properly. Are they ? >
Let's see: Only LID changes - handled correctly. LMC (and possibly LID) change - either we "catch" this, or we don't. If we do, the path and LMC will be refreshed so we will not keep refreshing the path forever (like it could have been if we didn't refresh the LMC). If we don't - ipoib packets will not reach the neighbour, which is the same situation there is today. _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
