On Wed, 2005-01-26 at 17:14, Tom Duffy wrote: > [ Sorry for taking a while to get back to you, I have been fire fighting > other things ] > > On Mon, 2005-01-24 at 18:36 -0500, Hal Rosenstock wrote: > > LID 3 is returning PortState 0 and PortPhysicalState 0 which is no state > > change, which is only valid on a Set not a Get :-( Is that the Solaris > > HCA port ? If so, it looks to me like there is a SMA problem to be fixed > > first. > > OK, I was wrong. Solaris is not on LID 3. That is the switch.
And port state and port physical state are not valid on base switch port 0 which explains their lack of meaning. > Solaris is at LID 2. Hmm. Solaris IB port is active yet I don't recall seeing it join any MC groups so we're back to square 1 in terms of what is going on. The broadcast group (and other groups) appear to be created. Perhaps this is an ordering thing where the Solaris machine is up before the Linux ones which would create the groups but I'm just guessing. -- Hal _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
