On 2026/03/10 23: 34, Raymond, Michael wrote: > The NIC symmetry test is specific to HPE Cray MPICH. Cheers for that, Raymond: always good to know the provenance of things. Presumably, it's not needed in "upcoming" HPE Cray MPICH-s, where
ZjQcmQRYFpfptBannerStart
This Message Is From an External Sender
This message came from outside your organization.
 
ZjQcmQRYFpfptBannerEnd
On 2026/03/10 23:34, Raymond, Michael wrote:
>    The NIC symmetry test is specific to HPE Cray MPICH.

Cheers for that, Raymond: always good to know the provenance
of things.
  
Presumably, it's not needed in "upcoming" HPE Cray MPICH-s,
where later, underlying MPICH-s do the "pick a nic" thing?

Any ideas on a timeline for that?

>    As a workaround, try setting MPICH_OFI_NUM_NICS=1.

Had already found, and have since been using, it during our
testing, although the idea that we would need to workaround
a disabled-at-boot NIC has come as a bit of a surprise to us.

FWIW, up until now, some folk in our user community have been
getting confused when their jobs fail and they get a message
about setting something to make the warning, and failure, go
away, and, of course, many blindly follow the advice, without
considerating what the implications might be.

Up until now, we have provided documentation, with yet another
workaround, but, as with taking horses to water, we can't make
every user drink from that fountain of knowledge!


Kevin M. Buckley
--
Supercomputing Systems Administrator
Pawsey Supercomputing Centre
PERTH
Australia