Hi Hal, On 11:33 Mon 23 Jul , Hal Rosenstock wrote: > > > > > > Not for "fast" switch reboot. > > > > > > Hmm, I think we could try to detect this by comparing > > > SwitchInfo:LinerFDBTop with current p_sw->max_lid_ho or even by seeing > > > that PortInfo:LID is not set. > > > > > > Not sure about checking PortInfo:LID. Wouldn't that approach need to be > > qualified by PortState (armed or active) ? LFTTop seems better to me or > > perhaps a combination of the two but I may be missing something. > > > > Another thought on this :-( > > Not sure that resetting either LID or LFTTop is required by the spec either > so this is relying on "beyond the spec" behavior and may not be true for all > switch implementations.
Yes, it is similar to my findings. Suggested in your previous email PortState check seems only reliable reboot detection criteria (for ports and switches). Sasha _______________________________________________ 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
