Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] OpenMPI out of band TCP retry exceeded
From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2011-04-28 08:04:29


I do note that you are using an ancient version of Open MPI (1.2.8). Is there any way you can upgrade to a (much) later version, such as 1.4.3? That might improve your TCP connectivity -- we made improvements in those portions of the code over the years.

On Apr 27, 2011, at 8:09 PM, Ralph Castain wrote:

>
> On Apr 27, 2011, at 1:31 PM, Sindhi, Waris PW wrote:
>
>> No we do not have a firewall turned on. I can run smaller 96 slave cases
>> on ln10 and ln13 included on the slavelist.
>>
>> Could there be another reason for this to fail ?
>
> What is in "procgroup"? Is it a single application?
>
> Offhand, there is nothing in OMPI that would explain the problem. The only possibility I can think of would be if your "procgroup" file contains more than 128 applications in it.
>
>>
>>
>> Sincerely,
>>
>> Waris Sindhi
>> High Performance Computing, TechApps
>> Pratt & Whitney, UTC
>> (860)-565-8486
>>
>> -----Original Message-----
>> From: users-bounces_at_[hidden] [mailto:users-bounces_at_[hidden]] On
>> Behalf Of Ralph Castain
>> Sent: Wednesday, April 27, 2011 2:18 PM
>> To: Open MPI Users
>> Subject: Re: [OMPI users] OpenMPI out of band TCP retry exceeded
>>
>> Perhaps a firewall? All it is telling you is that mpirun couldn't
>> establish TCP communications with the daemon on ln10.
>>
>>
>> On Apr 27, 2011, at 11:58 AM, Sindhi, Waris PW wrote:
>>
>>> Hi,
>>> I am getting a "oob-tcp: Communication retries exceeded" error
>>> message when I run a 238 MPI slave code
>>>
>>>
>>> /opt/openmpi/i386/bin/mpirun -mca btl_openib_verbose 1 --mca btl ^tcp
>>> --mca pls_ssh_agent ssh -mca oob_tcp_peer_retries 1000 --prefix
>>> /usr/lib/openmpi/1.2.8-gcc/bin -np 239 --app procgroup
>>>
>> ------------------------------------------------------------------------
>>> --
>>> mpirun was unable to start the specified application as it encountered
>>> an error:
>>>
>>> Error name: Unknown error: 1
>>> Node: ln10
>>>
>>> when attempting to start process rank 234.
>>>
>> ------------------------------------------------------------------------
>>> --
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0] ORTE_ERROR_LOG: Unreachable in file
>>> orted/orted_comm.c at line 130
>>> [ln13:27867] [[61748,0],0] ORTE_ERROR_LOG: Unreachable in file
>>> orted/orted_comm.c at line 130
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>> [ln13:27867] [[61748,0],0]-[[61748,0],32] oob-tcp: Communication
>> retries
>>> exceeded. Can not communicate with peer
>>>
>>> Any help would be greatly appreciated.
>>>
>>> Sincerely,
>>>
>>> Waris Sindhi
>>> High Performance Computing, TechApps
>>> Pratt & Whitney, UTC
>>> (860)-565-8486
>>>
>>>
>>> _______________________________________________
>>> users mailing list
>>> users_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>>
>> _______________________________________________
>> users mailing list
>> users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users

-- 
Jeff Squyres
jsquyres_at_[hidden]
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/