LSF Version 7.3 - Using Platform LSF HPC
blaunch Distributed Application Framework
Most MPI implementations and many distributed applications use rsh and ssh as their
task launching mechanism. The
blaunch command provides a drop-in replacement for
rsh and ssh as a transparent method for launching parallel and distributed applications
within LSF.
The following figure illustrates
blaunch processing:
About the blaunch command
Similar to the LSF lsrun command, blaunch transparently connects directly to the
RES/SBD on the remote host, and subsequently creates and tracks the remote tasks,
and provides the connection back to LSF. There no need to insert
pam, taskstarter into
the
rsh or ssh calling sequence, or configure any wrapper scripts.
blaunch supports the following core command line options as rsh and ssh:
◆
rsh
host_name
command
◆
ssh
host_name
command
Whereas the host name value for rsh and ssh can only be a single host name, you can
use the
-z option to specify a space-delimited list of hosts where tasks are started in
parallel. All other
rsh and ssh options are silently ignored.
blaunch only works within an LSF job; it can only be used to launch tasks on remote
hosts that are part of a job allocation. On success,
blaunch exits with 0.
blaunch is not supported on Windows.
root
sbatchd
job
sbatchd
job
res
User job containing
blaunch
nios
root
res
task
res
task
request to spawn
task on remote host
validation
register to
be signal handler
report task PID,
resource usage
control
input/output
first execution host
remote execution host