HP XC System Software Administration Guide Version 4.0

Table Of Contents
15.2.1 Configuring SLURM System Interconnect Support............................................................172
15.2.2 Configuring SLURM Servers...............................................................................................172
15.2.3 Configuring Nodes in SLURM............................................................................................172
15.2.4 Configuring SLURM Partitions...........................................................................................173
15.2.5 Configuring SLURM Features.............................................................................................175
15.2.6 Propagating Resource Limits...............................................................................................176
15.3 Restricting User Access to Nodes................................................................................................178
15.4 Job Accounting.............................................................................................................................178
15.4.1 Using the sacct Command...................................................................................................179
15.4.2 Disabling Job Accounting....................................................................................................180
15.4.3 Configuring Job Accounting................................................................................................180
15.5 Monitoring SLURM.....................................................................................................................182
15.6 Draining Nodes............................................................................................................................182
15.7 Configuring the SLURM Epilog Script........................................................................................184
15.8 Maintaining the SLURM Daemon Log........................................................................................185
15.9 Enabling SLURM to Recognize a New Node..............................................................................185
15.10 Removing SLURM.....................................................................................................................187
16 Managing LSF..........................................................................................................189
16.1 Standard LSF................................................................................................................................189
16.2 LSF with SLURM.........................................................................................................................190
16.2.1 Integration of LSF with SLURM..........................................................................................190
16.2.1.1 Job Starter Scripts.........................................................................................................192
16.2.1.2 SLURM External Scheduler.........................................................................................193
16.2.1.3 SLURM lsf Partition.....................................................................................................193
16.2.1.4 LSF with SLURM Failover...........................................................................................194
16.3 Switching the Type of LSF Installed............................................................................................194
16.4 LSF with SLURM Installation......................................................................................................195
16.5 LSF with SLURM Startup and Shutdown...................................................................................196
16.5.1 Starting Up LSF with SLURM.............................................................................................196
16.5.2 Shutting Down LSF with SLURM.......................................................................................197
16.6 Controlling the LSF with SLURM Service...................................................................................197
16.7 Launching Jobs with LSF with SLURM.......................................................................................197
16.8 Monitoring and Controlling LSF with SLURM Jobs...................................................................198
16.9 Maintaining Shell Prompts in LSF Interactive Shells..................................................................200
16.10 Job Accounting...........................................................................................................................201
16.11 LSF Daemon Log Maintenance..................................................................................................201
16.12 Load Indexes and Resource Information...................................................................................202
16.13 LSF with SLURM Monitoring....................................................................................................203
16.14 LSF with SLURM Failover.........................................................................................................203
16.14.1 Overview of LSF with SLURM Monitoring and Failover Support...................................204
16.14.2 Interplay of LSF with SLURM...........................................................................................204
16.14.3 Assigning the Resource Management Nodes....................................................................204
16.14.4 LSF with SLURM Failover and Running Jobs...................................................................205
16.14.5 Manual LSF with SLURM Failover....................................................................................206
16.15 Moving SLURM and LSF Daemons to Their Backup Nodes....................................................206
16.16 Enhancing LSF with SLURM.....................................................................................................207
16.16.1 LSF with SLURM Enhancement Settings..........................................................................207
16.16.2 Thresholds in LSF with SLURM and SLURM Interplay...................................................212
16.17 Configuring an External Virtual Host Name for LSF with SLURM on HP XC Systems..........212
8 Table of Contents