Ritesh --
So far the errors as such are not something because of LAM/MPI or BLCR.
They have been because of your environment/permissions.
The LD_LIBRARY_PATH is not being propagated properly in your case.
Two things --
- You would need to set the LD_LIBRARY_PATH in your ".bashrc" file. When
bash is invoked via rsh/ssh daemon, it attempts to source the .bashrc
file. This is an excerpt from the manpage of bash
---------------------------------------------------------------------
Bash attempts to determine when it is being run by the remote shell
daemon, usually rshd. If bash determines it is being run by rshd, it
reads and executes commands from ~/.bashrc, if that file exists and is
readable. It will not do this if invoked as sh. The --norc option may be
used to inhibit this behavior, and the --rcfile option may be used to
force another file to be read, but rshd does not generally invoke the
shell with those options or allow them to be specified.
-------------------------------------------------------------------
- Make sure you have the LD_LIBRARY_PATH all set before lamboot (putting
it in .bashrc of all nodes in the cluster should take care of this)
Alternatively, you can export environment variable during mpirun using the
"-x" option of mpirun. Check "mpirun --help".
Hope this help!
-Vishal
On Fri, 12 Mar 2004, Ritesh Tiwari wrote:
#
# Hi all,
# This is my fourth mail regarding the "installing lam with blcr". Except
# the first one nobody has replied the mails. I hope this time somebody will
# reply me soon.
#
# Now LAM/BLCR is working fine in single node. But in cluster when i try to
# run the sample programme hello.c following error comes, after compiling
# the hello.c
#
# $mpirun N hello
#
# hello: error while loading shared libraries: libcr.so.0: cannot open
# shared object file: No such file or directory
# -----------------------------------------------------------------------------
# It seems that [at least] one of the processes that was started with
# mpirun did not invoke MPI_INIT before quitting (it is possible that
# more than one process did not invoke MPI_INIT -- mpirun was only
# notified of the first one, which was on node n0).
#
# mpirun can *only* be used with MPI programs (i.e., programs that
# invoke MPI_INIT and MPI_FINALIZE). You can use the "lamexec" program
# to run non-MPI programs over the lambooted nodes.
# -----------------------------------------------------------------------------
#
# Although as i told earlier program runs with no error in a single node
# cluster, i have checked it individually with all nodes.I have checked the
# lam/mpi mailing-list but i am not able to find out the problem.
#
# For your information, previously when i installed BLCR i gave following
# command to confiure the blcr
#
# $ ./configure --with-linux=/usr/src/linux-2.4.20-8/
# --with-system-map=/boot/System.map --prefix=/home/BLCR
#
# BLCR directory contains lib subdir* which further contains blcr subdir*
# and all lib.* files.
#
# Now i configure lam/mpi with the following command
# $ ./configure --with-blcr=/home/BLCR --with-rpi=crtcp --with-rsh="ssh -x"
#
# then..
# $ make
# $ make all install
#
# I have added following lines in .bash_profile
# LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/BLCR/lib
# export LD_LIBRARY_PATH
#
# and output of
# $laminfo
# LAM/MPI: 7.0.4
# Prefix: /usr
# Architecture: i686-pc-linux-gnu
# Configured by: root
# Configured on: Wed Mar 10 12:58:41 IST 2004
# Configure host: wt68
# C bindings: yes
# C++ bindings: yes
# Fortran bindings: yes
# C profiling: yes
# C++ profiling: yes
# Fortran profiling: yes
# ROMIO support: yes
# IMPI support: no
# Debug support: no
# Purify clean: no
# SSI boot: globus (Module v0.5)
# SSI boot: rsh (Module v1.0)
# SSI coll: lam_basic (Module v7.0)
# SSI coll: smp (Module v1.0)
# SSI rpi: crtcp (Module v1.0.1)
# SSI rpi: lamd (Module v7.0)
# SSI rpi: sysv (Module v7.0)
# SSI rpi: tcp (Module v7.0)
# SSI rpi: usysv (Module v7.0)
# SSI cr: blcr (Module v1.0.1)
#
#
# please help me out !!
#
# Thanks
# Ritesh
#
# _______________________________________________
# This list is archived at http://www.lam-mpi.org/MailArchives/lam/
#
|
