On Wed, 13 Jun 2007, Jeff Squyres wrote:
>> I don't mind having some MCA parameters that are never showed by
>> (we already have the hidden ones). Anyway, for TCP by default there
>> is the
>> btl_tcp_latency and btl_tcp_bandwidth which will be used as a default
>> value for all NICs. For the others, a quick google search on our
>> list will return all information about how to set the latency and
>> bandwidth by NIC. MX have a similar mechanism ...
> Are you saying that the TCP and MX BTLs have similar variable MCA
Yes, both TCP and MX have such kind of MCA parameters as they both
support multi-rail configurations.
> I think the "hidden" MCA parameters are a different issue; they were
> created for a different purpose (users are not supposed to see/set
> them). These variable parameters would be intended to be used by the
> users, but they would have no way of finding out a) that they exist,
> and b) what they are. That's why I think that the MCA parameters may
> not be the right mechanism for this kind of information.
I see 2 possible solutions:
1. we update our documentation in such a way that it will clearly describe
these variable MCA parameters for each BTL that support them.
2. We create fake MCA parameters that will never be used, but they will
show up in the ompi_info output so the user will know they exist. For TCP
they can be btl_tcp_latency_* and btl_tcp_bandwidth_* ...
"We must accept finite disappointment, but we must never lose infinite
Martin Luther King