[mpich-discuss] FW: Error message with MPICH2-1.0.8

[Pfeiffer, Sharon]

UNRESTRICTED | ILLIMITÉ

 

Just an update.  I tested to see if it will run on the host/node if I specified it in my bsub command (-m) but it failed too.

 

 

Sharon (46654)

 

From: mpich-discuss-bounces at mcs.anl.gov [mailto:mpich-discuss-bounces at mcs.anl.gov] On Behalf Of Pfeiffer, Sharon
Sent: December 5, 2011 9:15 AM AECL
To: mpich-discuss at mcs.anl.gov
Subject: Re: [mpich-discuss] Error message with MPICH2-1.0.8

 

(1)   UNRESTRICTED | ILLIMITÉ

(2)    

(3)     You are right, I logged on to the two nodes that it was having problems with and did not find my home directory.

(4)    I'm trying to understand MPI and have one more question, if I statically assign the job to run on that node "ccs511", I do not get the error message.

Could you tell me why this is the case?

 

Thanks.

 

Sharon (46654)

 

From: mpich-discuss-bounces at mcs.anl.gov [mailto:mpich-discuss-bounces at mcs.anl.gov] On Behalf Of Andrus, Brian Contractor
Sent: December 2, 2011 4:36 PM AECL
To: mpich-discuss at mcs.anl.gov
Subject: Re: [mpich-discuss] Error message with MPICH2-1.0.8

 

Sharon,

 

I suspect your home directory does not exist on one of the nodes.

 

Log onto the nodes and verify that.

 

 

Brian Andrus

ITACS/Research Computing

Naval Postgraduate School

Monterey, California

voice: 831-656-6238

 

 

From: mpich-discuss-bounces at mcs.anl.gov [mailto:mpich-discuss-bounces at mcs.anl.gov] On Behalf Of Pfeiffer, Sharon
Sent: Friday, December 02, 2011 12:41 PM
To: mpich-discuss at mcs.anl.gov
Subject: [mpich-discuss] Error message with MPICH2-1.0.8

 

UNRESTRICTED | ILLIMITÉ

We are getting the following error message whenever a job is submitted to our compute cluster.  

I have provided information below, however, if you require any further information, please email me.

Thank you.

Sharon Pfeiffer 

________________________________________________________________________________________________

Computational Reactor Physics Branch - AECL Nuclear Laboratories, Ontario, K0J 1J0 - (613) 584-8811 ext. 46654 

________________________________________________________________________________________________

Version: MPICH2-1.0.8

OS: Red Hat Linux (64-bit) 

System : Linux cluster

Error message:

touch: cannot touch `/home/pfeiffes/.mpd.conf': No such file or directory

Cannot create MPD configuration file. Exiting ...

Job  /cluster/lsf8.0/8.0/linux2.6-glibc2.3-x86_64/bin/mpich2_wrapper /ASD-RH-64/AECL/CODES/MCNP5/bin/Linux/mcnp5V1.40.1mpich2-1.0.8.Intel.64bits.Nov042009.mpi name=fname xsdir=e70c.xsd eol

TID   HOST_NAME   COMMAND_LINE            STATUS            TERMINATION_TIME

===== ========== ================  =======================  ===================

00001 ccs512                       Undefined               

00002 ccs512                       Undefined               

00003 ccs512                       Undefined               

00004 ccs512                       Undefined               

00005 ccs511                       Undefined               

00006 ccs511                       Undefined               

00007 ccs511                       Undefined               

00008 ccs511                       Undefined               

00009 ccs511                       Undefined               

00010 ccs511                       Undefined               

00011 ccs511                       Undefined               

00012 ccs511                       Undefined               

00013 ccs511                       Undefined               

00014 ccs511                       Undefined               

00015 ccs511                       Undefined               

00016 ccs511                       Undefined               

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20111205/0b4a2ed9/attachment.htm>
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: ATT429549.txt
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20111205/0b4a2ed9/attachment.txt>