• LSF d oes not support chunk jobs. If a job is submitted to chunk queue, S LURM will let
the job pend .
• LSF does not support topology-aware advanced reservation scheduling.
7.1.6 Notes About Using LSF in the HP XC Environment
This section provides some additional information that sh ould be noted abo ut using LSF in
the HP XC Env iro nment.
7.1.6.1 Job Startup and Job Control
When LSF starts a SLURM job, it sets SLURM_JOBID to associate the job with the SLURM
allocation. During job running, all LSF supported operating-system -enforced resource limits
are supported, including core limit, cputime limit, data limit, file si ze limit, memory limit, and
stack l imit. If the u ser kills a job, LSF propag ates signals to entire job, incl uding the job file
runningonthelocalnodeandalltasksrunningonremotenodes.
7.1.6.2 Preemption S upport
LSF uses the SLURM "node share" feature to sup port preemption. When a low-priority is job
preempted, job processes are suspended on allocated nodes, and LSF places the high-priority job
on the same n ode. After high-priority job completes, LSF resum es s usp ended low-priority jobs.
7.2 Determining Execution Host
The lsid command displays the name of the HP XC system, and the name of the LSF
execution host, along with some general LSF in formation.
$ lsid
Platform LSF HPC 6.0 for SLURM, Sep 23 2004
Copyright 1992-2004 Platform Computing Corporation
My cluster name is penguin
My master name is lsfhost.localdomain
In this example, penguin is the HP XC system name (where is user is logged in and which
contains the compute nodes), and lsfhost.localdomain is the node where LSF is
installed and runs (LSF execution host).
7.3 Determining Available System Resources
For best use of system resources when laun ching an application, it is useful to know beforehand
what system resources are available for your use. This section describes how to obtain
information about system resources such as the number of processors availab le, LSF execution
host node information, and L SF system queues.
7.3.1 Getting Status of LSF
The bhosts command displays LSF resource usage information. This c om m and is useful to
check the status of the system processors. The bhosts comm and provides a summary of the
jobs on the system and in fo rm ation about the current state of LSF. For example, it can be used
to determine if LSF is ready to start accepting batch jobs.
LSF daemons run on only one node in the HP X C system, so the bhosts command will
list one host, which represents all the resou rces of the HP XC system. The total number
of processors for that host should be equal to the total number of processors assigned to the
SLURM lsf partition.
By default , this command returns the host name, host statu s, and job state statistics.
Using LSF 7-7
Commentaires sur ces manuels