[OMPI devel] IPv6 support in OpenMPI?

Hello *, first I'd like to introduce myself. I'm Christian Kauhaus and I am currently working at the Department of Computer Architecture at the University of Jena (Germany). Our work group is digging into how to connect several clusters on a campus. As part of our research, we

Re: [OMPI devel] IPv6 support in OpenMPI?

, that will dictate starting with the tcp oob component. Since we are able to reach every node both on IPv4 and IPv6, we do not have the bootstrapping problem. It looks to me that ORTE/OOB would be the easier part to start with anyway. -Christian -- Dipl.-Inf. Christian Kauhaus

Re: [OMPI devel] IPv6 support in OpenMPI?

fore the actual coding... I agree. So here we go :-) Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Rechnerarchitektur und -kommunikation Institut fuer Informatik * Ernst-Abbe-Platz 1-2 * D-07743 Jena Tel: +49 3641 9 46376 * Fax: +49 3641 9 46372 * Raum 3217

Re: [OMPI devel] IPv6 support in OpenMPI?

ket for each IP version it returns (usually this means two sockets on IPv6-enabled hosts, but this may change in the future... who knows?) If the connection handling code already makes use of one big select loop, this should not be *too* hard... Christian -- Dipl.-Inf. Ch

Re: [OMPI devel] IPv6 support in OpenMPI?

df is fairly generic... Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Rechnerarchitektur und -kommunikation Institut fuer Informatik * Ernst-Abbe-Platz 1-2 * D-07743 Jena Tel: +49 3641 9 46376 * Fax: +49 3641 9 46372 * Raum 3217

Re: [OMPI devel] IPv6 support in OpenMPI?

;What do you mean by "IPv6-enabled rsh" ? Was it the daemon, client or >both ? We had both client and server IPv6-enabled and IPv6 addresses in the resolver, but the server did not listen on the IPv6 socket, resulting in a connection failure for IPv6. The subsequent connection

Re: [OMPI devel] IPv6 support in OpenMPI?

ocol. I see. Do you think that SUSv2[1] would be a good starting point? This means that we can rely on getaddrinfo() but not on sockaddr_in6 and friends. Is this ok? Christian [1] http://www.opengroup.org/onlinepubs/007908799/ -- Dipl.-Inf. Christian Kauhaus <&g

Re: [OMPI devel] IPv6 support in OpenMPI?

in both ways: either by putting numeric IPv4-addresses into the machinefile, or by specifying 'ssh -4'. Is this a solution? Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Rechnerarchitektur und -kommunikation Institut fuer Inform

Re: [OMPI devel] IPv6 support in OpenMPI?

remember that there is always the -4 switch in ssh. Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Rechnerarchitektur und -kommunikation Institut fuer Informatik * Ernst-Abbe-Platz 1-2 * D-07743 Jena Tel: +49 3641 9 46376 * Fax: +49 3641

Re: [OMPI devel] IPv6 in OpenRTE

e. What a pity. ;-) If someone could provide us an account on a non-IPv6-enabled Unix machine (like an old Solaris or HP-UX), this would be very helpful. This way we can be sure not to break the build with our patches. Christian -- Dipl.-Inf. Christia

Re: [OMPI devel] IPv6 in OpenRTE

m on a conference and then out for vacation for the next two weeks, so expect not too much until Easter. I enjoyed the IPv6 discussion in the last week, so I'm looking forward to see our first implementation results in the hopefully not-too-distant future. :-) Chri

Re: [OMPI devel] Building ompi occasionally touches the source files

setup like Adrian and during the build process opal/util/show_help_lex.c is *neither* touched nor modified. It is just compiled to build/ARCH/opal/util/show_help_lex.lo as it is supposed to be. -Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Re

Re: [OMPI devel] [IPv6] new component oob/tcp6

ially use an IPv4 transport and in case 2 we initially use an IPv6 transport for the oob. If neither case 1 or 2 are possible, we abort. I hope that all can agree that this is a good starting point. Regards Christian -- Dipl.-Inf. Christian Kauhaus <><

[OMPI devel] MPI::File::Create_errhandler() missing?

`MPI::File' | mpiiowriter.cc:29: warning: unused variable 'errhandler' After some source grepping, it seems that the function MPI::File::Create_errhandler() is not implemented, although the MPI2.0 standard requires it for MPI-IO. Should I file a ticket? Christian -- Dip

Re: [OMPI devel] ORTE scalability issues

ortunately, there's no easy way around this. Christian -- Dipl.-Inf. Christian Kauhaus <>< Lehrstuhl fuer Rechnerarchitektur und -kommunikation Institut fuer Informatik * Ernst-Abbe-Platz 1-2 * D-07743 Jena Tel: +49 3641 9 46376 * Fax: +49 3641 9 46372 * Raum 3217