StarCD326 SuSE10.0_x86_64 LAM (rsh problem)
I have a problem with LAM MPI (which is from StarCD3.26 CDdisk) in SuSE10_x86_64. I have all needed permission with rsh and it steel doesn't work. At the same time local parallel run works fine.
There are 3 outputs from hboot command. First and second are correct, while third (from starcd run scrip) is wrong. Does anybody have any ideas or recommendations? -------------------------------------------------------------------------------------------------------- 1) starcd326@node1:~> hboot -t -c lam-conf.lamd -sessionsuffix node1.14210 -s -I "-H 192.168.2.1 -P 32844 -n 1 -o 0" starcd326@node1:~> 2) starcd326@node1:~> rsh node1 hboot -t -c lam-conf.lamd -sessionsuffix node1.14210 -s starcd326@node1:~> 3) starcd326@node1:~> rsh node1 hboot -t -c lam-conf.lamd -sessionsuffix node1.14210 -s -I "-H 192.168.2.1 -P 32844 -n 1 -o 0" ----------------------------------------------------------------------------- Synopsis: hboot [-dhnNstv] [-c <schema>] [-I <inet_topo>] [-R <rtr_topo>] Description: Start LAM on the local node Options: -c <conf> Use <conf> as the process schema -b <name> Use <name> for the unix socket names -d Print debug information (implies -v) -h Print this message -I <inet_topo> Set $inet_topo variable -N Pretend to hboot (used with recon(1)) -R <rtr_topo> Set $rtr_topo variable -s Close stdio of processes -t Kill existing session first -v Be verbose ----------------------------------------------------------------------------- starcd326@node1:~> |
Re: StarCD326 SuSE10.0_x86_64 LAM (rsh problem)
your script seems incorrect. Try to run star-cd the standard way without the script first
star -debug -mpi=lam -... |
All times are GMT -4. The time now is 01:00. |