Dear Brian,
Its my mistake. I just told you the output in my last email (as something I
forgot). It is
n0<17950> ssi:boot:base:linear_windowed: booting n0 (node18)
n0<17950> ssi:boot:base:linear_windowed: booting n1 (node17)
mpirun (locate_aschema): sysv: No such file or directory
so, for the sysv it is saying that it doesnot exist. However, it is there in
the system if I see through the 'locate' option as a 'directory' with
following files.
sysv> Makefile Makefile.am Makefile.in rpi_shm.c shm_low.c shm_sysv.c
If I make the Makefile (as a user not administrator) it gives
[mep04nid_at_bluegrid sysv]$ make
/bin/sh ../../../libtool --mode=compile gcc -DHAVE_CONFIG_H -I. -I.
-I../../../share/include -DLAM_BUILDING=1 -I../../../share/include -O2
-malign-double -funroll-loops -fomit-frame-pointer -c -o rpi_shm.lo `test -f
rpi_shm.c || echo './'`rpi_shm.c
gcc -DHAVE_CONFIG_H -I. -I. -I../../../share/include -DLAM_BUILDING=1
-I../../../share/include -O2 -malign-double -funroll-loops
-fomit-frame-pointer -c rpi_shm.c -o rpi_shm.o
rpi_shm.c: In function `proc_init':
rpi_shm.c:1174: structure has no member named `cp_locked'
make: *** [rpi_shm.lo] Error 1
Thanks,
ND
2008/7/5 Brian Barrett <brbarret_at_[hidden]>:
> I'm sorry, I should have been more clear. I was asking if you would run:
>
> mpirun -ssi rpi_verbose 1 -ssi rpi sysv -np 4 <your application>
>
> Brian
>
>
>
> On Jul 5, 2008, at 1:24 PM, Endee wrote:
>
> Sorry. Just forgot to mention that
>> 1. the output with adding '-ssi rpi_verbose 1' as suggested by you is as
>> following.
>> mpirun -ssi rpi_verbose 1 -np 4 bin/DG-DES-v1.0 <in_grid > output -->
>> works perfect { Please note that I did not use sysv}
>>
>> 2.mpirun -ssi rpi_verbose 1 sysv -np 4 bin/DG-DES-v1.0 <in_grid > output
>> --> gives following error
>>
>> n0<17950> ssi:boot:base:linear_windowed: booting n0 (node18)
>> n0<17950> ssi:boot:base:linear_windowed: booting n1 (node17)
>> mpirun (locate_aschema): sysv: No such file or directory
>> so, the sysv is no more there. I dont think there has been change in the
>> system files etc and I have been able to run sysv with it without any
>> trouble. I am reading further about sysv but will be grateful for your quick
>> help.
>> Best regards,
>> ND
>>
>>
>> 2008/7/5 Brian Barrett <brbarret_at_[hidden]>:
>> On Jul 5, 2008, at 11:03 AM, Endee wrote:
>>
>> Dear respected members,
>> Hi,
>> I am newb to LAM and mpi and am facing following problem. I request you to
>> guide me.
>> I have been using LAM without any trouble for my mpi code until recently.
>> My script uses PBS and is as follows:
>> #!/bin/sh
>> #PBS -l nodes=2:ppn=2
>> #PBS -l walltime=100:00:00
>> lamboot -v
>> cd /data/rundir
>> mpirun -ssi rpi sysv -np 4 program_exe <input > output
>>
>> Without actually changing anything, now I am getting a message with this
>> script :
>>
>> n0<17669> ssi:boot:base:linear_windowed: booting n0 (node18)
>> n0<17669> ssi:boot:base:linear_windowed: booting n1 (node17)
>>
>> -----------------------------------------------------------------------------
>> The selected RPI failed to initialize during MPI_INIT. This is a
>> fatal error; I must abort.
>> This occurred on host node18 (n0).
>> The PID of failed process was 17675 (MPI_COMM_WORLD rank: 0)
>>
>> -----------------------------------------------------------------------------
>>
>> It seems like you covered most of the initial issues. If you add the
>> argument
>>
>> -ssi rpi_verbose 1
>>
>> to the mpirun command line, you'll get a bunch of debugging information
>> from the rpi while it initializes. This might help lead us to the issue.
>>
>> Brian
>>
>>
>> --
>> Brian Barrett
>> LAM/MPI Developer
>> Make today a LAM/MPI day!
>>
>>
>> _______________________________________________
>> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>>
>> _______________________________________________
>> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>>
>
> --
> Brian Barrett
> LAM/MPI Developer
> Make today a LAM/MPI day!
>
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
|
