[mpich-discuss] cannot run mpich on multiple hosts due toauthentication issues

Jayesh Krishna jayesh at mcs.anl.gov
Tue Oct 13 09:21:50 CDT 2009


 Hi,
  MPICH 1.2.5 is very old. Try using the latest stable version (1.2) of
MPICH2 (available at
http://www.mcs.anl.gov/research/projects/mpich2/downloads/index.php?s=down
loads) and let us know if you still have problems.
  Also make sure that you have upgraded WinXP to the latest service pack
(SP3).

(PS: Make sure that you have turned off the windows firewall on your
machines - or look at the windows developer's guide for details on how to
configure MPICH2 with the windows firewall.)

Regards,
Jayesh

-----Original Message-----
From: mpich-discuss-bounces at mcs.anl.gov
[mailto:mpich-discuss-bounces at mcs.anl.gov] On Behalf Of Jordan Atlas
Sent: Monday, October 12, 2009 10:52 AM
To: mpich-discuss at mcs.anl.gov
Subject: [mpich-discuss] cannot run mpich on multiple hosts due
toauthentication issues

Hello MPICH list,

I am having an issue similar to that described at
https://lists.mcs.anl.gov/mailman/htdig/mpich-discuss/2006-March/001207.ht
ml
, but I don't see any responses to this inquiry.

I am using MPICH 1.2.5 on Windows XP.

I can run the cpi.exe example for multiple processes on my host machine
(e.g. mpirun -np 4 cpi.exe).

I am trying to use 2 machines using the command:

C:\Temp>mpirun -np 4 -logon -machinefile machines.txt cpi.exe

When I do this, I get the output:

Mpd needs an account to launch processes with:
account (domain\user): Jordan
password:
easy_connect::WSAETIMEDOUT error, re-attempting
easy_connect(jca33-305-desktop-2)
easy_connect::WSAETIMEDOUT error, re-attempting
easy_connect(jca33-305-desktop-2)
Error: ConnectToMPD(jca33-305-desktop-2:8675): easy_connect failed: 
error 10060, A connection attempt failed because the connected party did
not properly respond after a period of time, or established connection
failed because connected host has failed to respond.

Error: ConnectToMPD(jca33-305-desktop-2:8675): easy_connect failed: 
error 10060, A connection attempt failed because the connected party did
not properly respond after a period of time, or established connection
failed because connected host has failed to respond.

MPIRunLaunchProcess: Connect to jca33-305-desktop-2 failed, error 10060
MPIRunLaunchProcess: Connect to jca33-305-desktop-2 failed, error 10060
aborting...
Error 10035, process 2:
   SendInitDataToRoot: recv ack failed
   A non-blocking socket operation could not be completed immediately.


If I do it without the -logon option I get the same results (without the
prompt for username and password).

I don't have access to a domain account, but both machines have the user
'Jordan' with the same password.  Also, both machine names are in the
machines.txt file.

Does anyone have any suggestions?

Thanks,

--Jordan Atlas

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20091013/648284b9/attachment.htm>


More information about the mpich-discuss mailing list