Task 10: Confirm Compute Resources

Follow this procedure to verify that compute resources are functioning properly:

Begin this procedure as the root user on the head node.
Set up the LSF environment by sourcing the LSF profile file:
# . /opt/hptc/lsf/top/conf/profile.lsf

Verify that the LSF profile file has been sourced by finding an LSF command:

# which lsid
/opt/hptc/lsf/top/6.1/linux2.6-glibc2.3-amd64-slurm/bin/lsid




	Note: This sample output was obtained from an Opteron-based system. Thus, the directory name `linux2.6-glibc2.3-amd64-slurm` is included in the path (the string `amd64` signifies an Opteron-based architecture). When an Itanium-based system is configured, the string `ia64` is included in the directory name. The string `slurm` exists in the path only if LSF-HPC with SLURM is configured.

If SLURM is configured, verify that the lsf partition exists:

# sinfo
PARTITION AVAIL TIMELIMIT NODES  STATE NODELIST
lsf          up  infinite     3   idle n[14-16]

Wait a few seconds for the LSF daemons to stabilize, then run the following commands to confirm that licensing is correct, the correct number of available processors are listed (it should match the number of processors in the lsf partition), and that the status of the system is shown as ok. Command output looks different depending upon which type of LSF is installed and configured:

LSF-HPC with SLURM:

Verify that LSF-HPC with SLURM is running:

# lsid
Platform LSF HPC 6.1 for SLURM, LSF_build_date
Copyright 1992-2005 Platform Computing Corporation

My cluster name is hptclsf
My master name is lsfhost.localdomain

Verify the static resource information:

# lshosts
HOST_NAME      type    model  cpuf ncpus maxmem maxswp server RESOURCES
lsfhost.loc SLINUX6 Opteron8  60.0     6     1M      -    Yes (slurm)

Verify the dynamic resource information:
# bhosts HOST_NAME STATUS JL/U MAX NJOBS RUN SSUSP USUSP RSV lsfhost.localdomai ok - 6 0 0 0 0 0
See the troubleshooting information in the HP XC System Software Administration Guide if you do not receive a status of ok from the bhosts command.

Standard LSF:

Verify that standard standard LSF is running:

# lsid
Platform LSF 6.1, LSF_build_date
Copyright 1992-2005 Platform Computing Corporation

My cluster name is hptclsf
My master name is  n13
[root@xc5n16 ~]# lshosts
HOST_NAME      type    model  cpuf ncpus maxmem maxswp server RESOURCES
n13      LINUX64 Itanium2  16.0     2  4036M  6144M    Yes ()
n16      LINUX64 Itanium2  16.0     2  4036M  6143M    Yes ()
n1       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n2       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n3       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n4       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n5       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n6       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n7       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n8       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n9       LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n10      LINUX64 Itanium2  16.0     2   977M  6144M    Yes ()
n11      LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()
n12      LINUX64 Itanium2  16.0     2  3012M  6144M    Yes ()

Verify the dynamic resource information:

# bhosts
HOST_NAME          STATUS       JL/U    MAX  NJOBS    RUN  SSUSP  USUSP RSV
n1              ok              -      2      0      0      0      0     0
n10             ok              -      2      0      0      0      0     0
n11             ok              -      2      0      0      0      0     0
n12             ok              -      2      0      0      0      0     0
n13             ok              -      2      0      0      0      0     0
n16             ok              -      2      0      0      0      0     0
n2              ok              -      2      0      0      0      0     0
n3              ok              -      2      0      0      0      0     0
n4              ok              -      2      0      0      0      0     0
n5              ok              -      2      0      0      0      0     0
n6              ok              -      2      0      0      0      0     0
n7              ok              -      2      0      0      0      0     0
n8              ok              -      2      0      0      0      0     0
n9              ok              -      2      0      0      0      0     0

Note:

Output from the bhosts command looks like this for nodes that do not have the compute role assigned:

n16         closed              -      2      0      0      0      0     0

See the troubleshooting information in the HP XC System Software Administration Guide if you do not receive a status of ok from the bhosts command.

For more information about where to find LSF-HPC with SLURM or standard LSF documentation, see the Preface at the beginning of this document .

Task 10: Confirm Compute Resources

Technical documentation

» Table of Contents

» Glossary

» Index