Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

From: Jeff Squyres \(jsquyres\) (jsquyres_at_[hidden])
Date: 2006-03-31 09:36:31


> -----Original Message-----
> From: devel-bounces_at_[hidden]
> [mailto:devel-bounces_at_[hidden]] On Behalf Of Brian Barrett
> Sent: Friday, March 31, 2006 9:08 AM
> To: Open MPI Developers
> Subject: Re: [OMPI devel] IPv6 support in OpenMPI?
>
> From a practical standpoint, Open MPI has to support both IPv4 and
> IPv6 for the foreseeable future. We currently try to wire up one
> connection per "IP device", so it seems like we should be able to
> find some way to automatically switch between IPv6 or IPv4 based on
> what we determine is available on that host, right? I'll admit it
> has been a year or so since I've looked at this, so I could be
> completely off base there.

I'll echo Brian's sentiments (and excellent writeup): we'd *LOVE* to
have IPv6 support in Open MPI. So thanks! But we do need to be able to
support both v4 and v6, so converting the v4 code to do v6 isn't really
attractive.

Our philosophy in Open MPI is that the infrastructure should "do the
Right Thing whenever possible." Hence, in a best-case scenario, it
would be great if the two TCP components (oob and btl) can automatically
figure out whether they're supposed to use IPv4 or IPv6
addressing/sockets/whatever to reach their peers, and act accordingly.

I have no personal experience with IPv6, but one thought that strikes me
is that the components might be able to figure out what to do by looking
at/parsing either the hostnames or the results that come back from
resolving the hostname...?

-- 
Jeff Squyres
Server Virtualization Business Unit
Cisco Systems