It's because Open MPI uses a tree-based ssh startup pattern.
(amusingly enough, I'm literally half way through writing up a blog entry about
this exact same issue :-) )
That is, not only does Open MPI ssh from your mpirun-server to host1, Open MPI
may also ssh from host1 to host2 (or host1 to host3).
In short, if you're not using a resource manager (such as Torque or SLURM),
then you can't predict the ssh pattern, and you need
passwordless/passphraseless ssh logins from each server to each other server.
Make sense?
> On Jan 16, 2015, at 3:29 PM, Chan, Elbert wrote:
>
> Hi
>
> I'm hoping that someone will be able to help me figure out a problem with
> connecting to multiple nodes with v1.8.4.
>
> Currently, I'm running into this issue:
> $ mpirun --host host1 hostname
> host1
>
> $ mpirun --host host2,host3 hostname
> host2
> host3
>
> Running this command on 1 or 2 nodes generates the expected result. However:
> $ mpirun --host host1,host2,host3 hostname
> Permission denied, please try again.
> Permission denied, please try again.
> Permission denied (publickey,password,keyboard-interactive).
> --
> ORTE was unable to reliably start one or more daemons.
> This usually is caused by:
>
> * not finding the required libraries and/or binaries on
> one or more nodes. Please check your PATH and LD_LIBRARY_PATH
> settings, or configure OMPI with --enable-orterun-prefix-by-default
>
> * lack of authority to execute on one or more specified nodes.
> Please verify your allocation and authorities.
>
> * the inability to write startup files into /tmp (--tmpdir/orte_tmpdir_base).
> Please check with your sys admin to determine the correct location to use.
>
> * compilation of the orted with dynamic libraries when static are required
> (e.g., on Cray). Please check your configure cmd line and consider using
> one of the contrib/platform definitions for your system type.
>
> * an inability to create a connection back to mpirun due to a
> lack of common network interfaces and/or no route found between
> them. Please check network connectivity (including firewalls
> and network routing requirements).
> --
>
> This is set up with passwordless logins with passphrases/ssh-agent. When I
> run passphraseless, I get the expected result.
>
> What am I doing wrong? What can I look at to see where my problem could be?
>
> Elbert
>
> --
>
> Elbert Chan
> Operating Systems Analyst
> College of ECC
> CSU, Chico
> 530-898-6481
>
> ___
> users mailing list
> us...@open-mpi.org
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
> Link to this post:
> http://www.open-mpi.org/community/lists/users/2015/01/26207.php
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/