[mpich-discuss] cpi

יוסף אלון yos104104 at gmail.com
Wed Mar 23 10:43:18 CDT 2016


what do you mean?


2016-03-23 17:42 GMT+02:00 Kenneth Raffenetti <raffenet at mcs.anl.gov>:

> cpi.c is a source file, not an executable.
>
> On 03/23/2016 10:41 AM, יוסף אלון wrote:
>
>> when i do this i reciev:
>>
>> cluster at elec-cluster-1 ~ $ *_mpiexec -n 5 -f machinefile
>> ./mpich2/mpich-3.1/examples/cpi.c_*
>> [proxy:0:0 at elec-cluster-1] HYDU_create_process
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>> execvp error on file ./mpich2/mpich-3.1/examples/cpi.c (Permission denied)
>>
>>
>> ===================================================================================
>> =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
>> =   PID 2895 RUNNING AT 147.161.4.200
>> =   EXIT CODE: 255
>> =   CLEANING UP REMAINING PROCESSES
>> =   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
>>
>> ===================================================================================
>> [proxy:0:1 at elec-cluster-2] HYDU_create_process
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>> execvp error on file ./mpich2/mpich-3.1/examples/cpi.c (Permission denied)
>> [proxy:0:4 at elec-cluster-5] HYDU_create_process
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>>
>> ===================================================================================
>> =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
>> =   PID 7382 RUNNING AT 147.161.4.201
>> =   EXIT CODE: 255
>> =   CLEANING UP REMAINING PROCESSES
>> =   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
>>
>> ===================================================================================
>>
>> 2016-03-23 17:34 GMT+02:00 Kenneth Raffenetti <raffenet at mcs.anl.gov
>> <mailto:raffenet at mcs.anl.gov>>:
>>
>>     The error in your first message was that mpiexec was unable to find
>>     the file "./examples/cpi".
>>
>>     The error in your second message is that mpiexec was unable to find
>>     your "machinefile".
>>
>>     Please make sure you are giving the correct paths to these files in
>>     your mpiexec command.
>>
>>     Ken
>>
>>     On 03/23/2016 10:20 AM, יוסף אלון wrote:
>>
>>         i am not using a share network and i have it on the place in all
>>         nodes.
>>         and thus file are located in same place on every node.
>>         i tried to run like this allso
>>         תמונה מוטבעת 1
>>
>>         2016-03-23 17:06 GMT+02:00 Kenneth Raffenetti
>>         <raffenet at mcs.anl.gov <mailto:raffenet at mcs.anl.gov>
>>         <mailto:raffenet at mcs.anl.gov <mailto:raffenet at mcs.anl.gov>>>:
>>
>>
>>
>>              Are you executing your commands from a shared network
>>         filesystem? If
>>              not, have you copied your MPI installation and cpi binaries
>>         into the
>>              same location on all the machines in your cluster?
>>
>>              Ken
>>
>>              On 03/23/2016 09:47 AM, יוסף אלון wrote:
>>
>>
>>                  hiii
>>
>>                  i am new here and i have a 18 node cluster that works
>>         pretty
>>                  good when i
>>                  execute the command:
>>
>>                  *mpiexec -f machinefile -n 18 hostname
>>                  * and the folowing output:
>>                  elec-cluster-1
>>                  elec-cluster-2
>>                  elec-cluster-3
>>                  elec-cluster-5
>>                  elec-cluster-4
>>                  elec-cluster-6
>>                  elec-cluster-7
>>                  elec-cluster-9
>>                  elec-cluster-8
>>                  elec-cluster-10
>>                  elec-cluster-11
>>                  elec-cluster-13
>>                  elec-cluster-14
>>                  elec-cluster-15
>>                  elec-cluster-16
>>                  elec-cluster-12
>>                  elec-cluster-18
>>                  elec-cluster-17
>>
>>                  when i execute the command:
>>                  *mpiexec -n 5 -f machinefile ./examples/cpi*
>>
>>                     nothing is seems to work and i receive:
>>
>>                  [proxy:0:0 at elec-cluster-1] HYDU_create_process
>>
>>
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>>                  execvp error on file ./examples/cpi (No such file or
>>         directory)
>>
>>
>>
>> ===================================================================================
>>                  =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
>>                  =   PID 2806 RUNNING AT 147.161.4.200
>>                  =   EXIT CODE: 255
>>                  =   CLEANING UP REMAINING PROCESSES
>>                  =   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
>>
>>
>> ===================================================================================
>>                  [proxy:0:2 at elec-cluster-3] HYDU_create_process
>>
>>
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>>                  execvp error on file ./examples/cpi (No such file or
>>         directory)
>>                  [proxy:0:3 at elec-cluster-4] HYDU_create_process
>>
>>
>> (/home/cluster/mpich2/mpich-3.1/src/pm/hydra/utils/launch/launch.c:75):
>>
>>
>> ===================================================================================
>>                  =   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
>>                  =   PID 6718 RUNNING AT 147.161.4.202
>>                  =   EXIT CODE: 255
>>                  =   CLEANING UP REMAINING PROCESSES
>>                  =   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
>>
>>
>> ===================================================================================
>>
>>                  i dont know what to do?
>>                  another think is how to run and compile a c program?
>>
>>                  --
>>                  בברכה, יוסף אלון
>>                  050-4916740
>>
>>
>>                  _______________________________________________
>>                  discuss mailing list discuss at mpich.org
>>         <mailto:discuss at mpich.org> <mailto:discuss at mpich.org
>>         <mailto:discuss at mpich.org>>
>>                  To manage subscription options or unsubscribe:
>>         https://lists.mpich.org/mailman/listinfo/discuss
>>
>>              _______________________________________________
>>              discuss mailing list discuss at mpich.org
>>         <mailto:discuss at mpich.org> <mailto:discuss at mpich.org
>>
>>         <mailto:discuss at mpich.org>>
>>              To manage subscription options or unsubscribe:
>>         https://lists.mpich.org/mailman/listinfo/discuss
>>
>>
>>
>>
>>         --
>>         בברכה, יוסף אלון
>>         050-4916740
>>
>>
>>         _______________________________________________
>>         discuss mailing list discuss at mpich.org <mailto:discuss at mpich.org>
>>         To manage subscription options or unsubscribe:
>>         https://lists.mpich.org/mailman/listinfo/discuss
>>
>>     _______________________________________________
>>     discuss mailing list discuss at mpich.org <mailto:discuss at mpich.org>
>>     To manage subscription options or unsubscribe:
>>     https://lists.mpich.org/mailman/listinfo/discuss
>>
>>
>>
>>
>> --
>> בברכה, יוסף אלון
>> 050-4916740
>>
>>
>> _______________________________________________
>> discuss mailing list     discuss at mpich.org
>> To manage subscription options or unsubscribe:
>> https://lists.mpich.org/mailman/listinfo/discuss
>>
>> _______________________________________________
> discuss mailing list     discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss
>



-- 
בברכה, יוסף אלון
050-4916740
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20160323/dc44e945/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss


More information about the discuss mailing list