[openib-general] RE: osmtest/OpenSM: ServiceGID and busy status

Hal Rosenstock halr at voltaire.com
Fri Sep 9 13:14:01 PDT 2005


On Fri, 2005-09-09 at 16:05, Eitan Zahavi wrote:
> > I may be wrong but:
> > ServiceGID says port GID for service. A port GID must meet the
> > requirements in the addressing section.
> [EZ] I think the spec intentionally leaves this open. The intent is to
> use this as GID but no check is defined. According to your
> interpretation no "proxy" - where node A publish services of node B -
> is allowed

Proxy would be allowed. There are 2 possibilities:
1. Allow valid looking GIDs
or
2. Only allow GIDs present in the subnet

> > For busy, it might be possible but is there one timeout retry
> strategy
> > or should this be left to the client ? For other errors, I think it
> > needs to be left to the client/application to determine whether it
> is in
> > error.
> 
> [EZ] Agree about the need to pass up the error codes. Just handle the
> BUSY at a lower level which is probably common to most applications.
> But we might at least make it an optional service of the low level?

The OpenSM SA client API needs changing to make it optional. Other than
that it is a matter of the default policy: retries and timeout (with
backoff) to be used.

-- Hal




More information about the general mailing list