HP XC System Software Administration Guide Version 3.1

.
Resource usage summary:
CPU time : 8252.65 sec.
Max Memory : 4 MB
Max Swap : 113 MB
.
.
.
The LSF bacct command provides accurate job accounting data on the following:
• Jobs submitted by all users
• Jobs accounted on all projects
• Jobs completed normally or exited
• Jobs executed on all hosts
• Jobs submitted to all queues
• Jobs accounted on all service classes
Consider using the -l of the bacct command to display the accounting data in its long format:
$ bacct -l job_number
For more information, see bacct(1).
15.10 LSF Daemon Log Maintenance
By default, the LSF daemon logs are stored in /var/lsf/log/ on the node on which LSF runs. There
are 6 daemon logs on HP XC:
• lim.log
• mbatchd.log
• mbschd.log
• res.log
• rla.log
• sbatchd.log
There is also a pim.log file, but it is typically empty.
These logs become large if debugging has been enabled.
To cache these logs without disrupting LSF operation, move these files to another location, as shown in
the following example:
# shownode servers lsf
n[15-16]
# pdsh -w n[15-16] "mkdir -p /var/lsf/log.old"
# pdsh -w n[15-16] "mv /var/lsf/log/* /var/lsf/log.old/"
LSF continues to write to the original log files. Now you can either archive the log.old directory or delete
them.
You can automate the procedure for caching LSF log files by using a cron job on the head node set for an
interval appropriate for your site.
15.11 Load Indexes and Resource Information
LSF-HPC with SLURM gathers limited resource information and load indexes from the LSF execution
host and from its integration with SLURM. Not all indexes are reported because SLURM does not provide
the same information that LSF-HPC with SLURM usually reports.
The LSF lshosts and lsload commands are two common commands for obtaining resource information
from LSF-HPC with SLURM.
15.10 LSF Daemon Log Maintenance 187