Platform™ LSF™ Command Reference Version 7 Update 3 Release date: May 2008 Last modified: May 16, 2008 Comments to: doc@platform.com Support: support@platform.
Copyright © 1994-2008, Platform Computing Inc. Although the information in this document has been carefully reviewed, Platform Computing Inc. (“Platform”) does not warrant it to be free of errors or omissions. Platform reserves the right to make corrections, updates, revisions or changes to the information in this document.
Contents bacct . . . bapp . . . badmin . bbot . . . bchkpnt . bclusters bgadd . . bgdel . . bhist . . . bhosts . . bhpart . . bgmod . bjgroup . bjobs . . . bkill . . . . bladmin . blaunch . blcollect . blhosts . . blimits . . blinfo . . blkill . . . blparams blplugins blstat . . . bltasks . . blusers . . bmgroup bmig . . . bmod . . bparams . bpeek . . bpost . . . bqueues . bread . . brequeue bresources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
brestart . . bresume . . brlainfo . . brsvadd . . brsvdel . . brsvmod . brsvs . . . . brun . . . . bsla . . . . . bslots . . . bstatus . . bstop . . . . bsub . . . . bswitch . . btop . . . . bugroup . . busers . . . ch . . . . . . lsacct . . . . lsacctmrg . lsadmin . . lsclusters . lseligible . lsfinstall . . lsfmon . . . lsfrestart . . lsfshutdown lsfstartup . lsgrun . . . lshosts . . . lsid . . . . . lsinfo . . . . lsload . . . lsloadadj . lslogin . . . lsltasks . . . lsmon . . . lspasswd . lsplace . . .
pmcremoverc . . . . pmcsetrc . . . . . . . perfadmin . . . . . . perfremoverc . . . . perfsetrc . . . . . . . pversions (Windows) pversions (UNIX) . . ssacct . . . . . . . . . ssched . . . . . . . . . taskman . . . . . . . . tspeek . . . . . . . . . tssub . . . . . . . . . . wgpasswd . . . . . . wguser . . . . . . . . Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Platform LSF Command Reference
bacct Displays accounting statistics about finished jobs. Synopsis bacct [-b | -l] [-d] [-e] [-w] [-x] [-app application_profile_name] [-C time0,time1] [-D time0,time1] [-f logfile_name] [-Lp ls_project_name ...] [-m host_name ...|-M host_list_file] [-N host_name | -N host_model | -N cpu_factor] [-P project_name ...] [-q queue_name ...] [-sla service_class_name ...] [-S time0,time1] [-u user_name ... | -u all] bacct [-b | -l] [-f logfile_name] [job_ID ...] bacct [-U reservation_ID ...
Options The total throughput of the LSF system can be calculated by specifying -u all without any of the -m, -q, -S, -D or job_ID options. The throughput of certain hosts can be calculated by specifying -u all without the -q, -S, -D or job_ID options. The throughput of certain queues can be calculated by specifying -u all without the -m, -S, -D or job_ID options. bacct does not show local pending batch jobs killed using bkill -b.
-m host_name ... Displays accounting statistics for jobs dispatched to the specified hosts. If a list of hosts is specified, host names must be separated by spaces and enclosed in quotation marks (") or (’). -N host_name | -N host_model | -N cpu_factor Normalizes CPU time by the CPU factor of the specified host or host model, or by the specified CPU factor. If you use bacct offline by indicating a job log file, you must specify a CPU factor. -P project_name ...
Default output format (SUMMARY) If a list of users is specified, user names must be separated by spaces and enclosed in quotation marks (") or (’). You can specify both user names and user IDs in the list of users. job_ID ... Displays accounting statistics for jobs with the specified job IDs. If the reserved job ID 0 is used, it is ignored. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Default output format (SUMMARY) Statistics on jobs.
U/UID Name of the user who submitted the job. If LSF fails to get the user name by getpwuid(3), the user ID is displayed. QUEUE Queue to which the job was submitted. SUBMIT_TIME Time when the job was submitted. CPU_T CPU time consumed by the job. WAIT Wait time of the job. TURNAROUND Turnaround time of the job. FROM Host from which the job was submitted. EXEC_ON Host or hosts to which the job was dispatched to run.
Advance Reservations (-U) The job is consuming less CPU time than expected. The job idle factor (CPU time/runtime) is less than the configured JOB_IDLE threshold for the queue and a job exception has been triggered. overrun The job is running longer than the number of minutes specified by the JOB_OVERRUN threshold for the queue and a job exception has been triggered.
◆ TERM_FORCE_ADMIN: Job killed by root or LSF administrator without time for cleanup (9) ◆ TERM_FORCE_OWNER: Job killed by owner without time for cleanup (8) ◆ TERM_LOAD: Job killed after load exceeds threshold (3) ◆ TERM_MEMLIMIT: Job killed after reaching LSF memory usage limit (16) ◆ TERM_OWNER: Job killed by owner (14) ◆ TERM_PREEMPT: Job killed after preemption (1) ◆ TERM_PROCESSLIMIT: Job killed after reaching LSF process limit (7) ◆ TERM_REQUEUE_ADMIN: Job killed and requeued by root o
Example: Jobs that have triggered job exceptions Example: Jobs that have triggered job exceptions bacct -x -l Accounting information about jobs that are: - submitted by users user1, - accounted on all projects. - completed normally or exited - executed on all hosts. - submitted to all queues. - accounted on all service classes.
, Queue , Command Mon Aug 18 20:27:44: Submitted from host , CWD <$HOME/jobs>, Output File ; Mon Aug 18 20:31:16: [14] dispatched to ; Mon Aug 18 20:31:18: Completed . EXCEPTION STATUS: underrun Accounting information about this job: CPU_T WAIT TURNAROUND STATUS HOG_FACTOR MEM SWAP 0.19 212 214 exit 0.
Files - completed normally or exited - executed on all hosts. - submitted to all queues. - accounted on all service classes.
bapp Displays information about application profile configuration. Synopsis bapp [-l | -w] [application_profile_name ...] bapp [-h | -V] Description Displays information about application profiles configured in lsb.applications. Returns application name, job slot statistics, and job state statistics for all application profiles: In MultiCluster, returns the information about all application profiles in the local cluster. CPU time is normalized. Options -w Wide format.
Long output format(-l) Long output format(-l) In addition to the above fields, the -l option displays the following: Description A description of the typical use of the application profile. PARAMETERS/ SSUSP STATISTICS The number of job slots in the application profile allocated to jobs that are suspended by LSF because of load levels or run windows. USUSP The number of job slots in the application profile allocated to jobs that are suspended by the job submitter or by the LSF administrator.
Per-process resource usage limits The possible UNIX per-process resource limits are: CORELIMIT The maximum size of a core file. By default, the limit is shown in KB. Use LSF_UNIT_FOR_LIMITS in lsf.conf to specify a larger unit for display (MB, GB, TB, PB, or EB). DATALIMIT The maximum size of the data segment of a process, in KB. This restricts the amount of memory a process can allocate. FILELIMIT The maximum file size a process can create, in KB.
See also Timeout in minutes for job post-execution processing. If post-execution processing takes longer than the timeout, sbatchd reports that post-execution has failed (POST_ERR status), and kills the process group of the job’s post-execution processes. REQUEUE_EXIT_VALUES Jobs that exit with these values are automatically requeued. RES_REQ Resource requirements of the application profile. Only the hosts that satisfy these resource requirements can be used by the application profile.
badmin Administrative tool for LSF. Synopsis badmin subcommand badmin [-h | -V] Description IMPORTANT: This command can only be used by LSF administrators. badmin provides a set of subcommands to control and monitor LSF. If no subcommands are supplied for badmin, badmin prompts for a subcommand from standard input. Information about each subcommand is available through the help command. The badmin subcommands include privileged and non-privileged subcommands.
Subcommand synopsis Subcommand synopsis ckconfig [-v] diagnose [job_ID ... | "job_ID[index]" ...] reconfig [-v] [-f] mbdrestart [-C comment] [-v] [-f] qopen [-C comment] [queue_name ... | all] qclose [-C comment] [queue_name ... | all] qact [-C comment] [queue_name ... | all] qinact [-C comment] [queue_name ... | all] qhist [-t time0,time1] [-f logfile_name] [queue_name ...] hopen [-C comment] [host_name ... | host_group ... | all] hclose [-C comment] [host_name ... | host_group ...
Options subcommand Executes the specified subcommand. See Usage section. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Usage ckconfig [-v] Checks LSF configuration files located in the LSB_CONFDIR/cluster_name/configdir directory, and checks LSF_ENVDIR/lsf.licensescheduler. The LSB_CONFDIR variable is defined in lsf.conf (see lsf.conf(5)) which is in LSF_ENVDIR or /etc (if LSF_ENVDIR is not defined).
Usage Verbose mode. Displays detailed messages about the status of the configuration files. Without this option, the default is to display the results of configuration file checking. All messages from the configuration file check are printed to stderr. -f Disables interaction and proceeds with reconfiguration if configuration files contain no fatal errors. mbdrestart [-C comment] [-v] [-f] Dynamically reconfigures LSF and restarts mbatchd and mbschd.
Activates specified queues, or all queues if the reserved word all is specified. If no queue is specified, the system default queue is assumed. Jobs in a queue can be dispatched if the queue is activated. A queue inactivated by its run windows cannot be reactivated by this command. -C comment Logs the text of the comment as an administrator comment record to lsb.events. The maximum length of the comment string is 512 characters. qinact [-C comment] [queue_name ...
Usage Closes batch server hosts. Specify the names of any server hosts or host groups. All batch server hosts are closed if the reserved word all is specified. If no argument is specified, the local host is assumed. A closed host does not accept any new job, but jobs already dispatched to the host are not affected. Note that this is different from a host closed by a window; all jobs on it are suspended in that case. -C comment Logs the text as an administrator comment record to lsb.events.
Shuts down sbatchd on the specified hosts, or on all batch server hosts if the reserved word all is specified. If no host is specified, the local host is assumed. sbatchd exits upon receiving the request. -f Disables interaction and does not ask for confirmation for shutting down sbatchd. hstartup [-f] [host_name ... | all] Starts sbatchd on the specified hosts, or on all batch server hosts if the reserved word all is specified. Only root and users listed in the file lsf.
Usage -t time0,time1 Displays only those events that occurred during the period from time0 to time1. See bhist(1) for the time format. The default is to display all queue events in the event log file (see below). -f logfile_name Specify the file name of the event log file. Either an absolute or a relative path name may be specified. The default is to use the event log file currently used by the LSF system: LSB_SHAREDIR/cluster_name/logdir/lsb.events. Option -f is useful for offline analysis.
◆ LC_CHKPNT - Log checkpointing messages ◆ LC_COMM - Log communication messages ◆ LC_CONF - Print out all parameters in lsb.
Usage LOG_DEBUG3 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2, LOG_DEBUG1, and LOG_DEBUG levels. 3 Default: 0 (LOG_DEBUG level in parameter LSF_LOG_MASK) -f logfile_name Specify the name of the file into which debugging messages are to be logged. A file name with or without a full path may be specified. If a file name without a path is specified, the file is saved in the LSF system log directory.
The higher the number, the more functions in the software that are timed and whose execution time is logged. The lower numbers include more common software functions. Higher levels include all lower levels. Default: undefined (no timing information is logged) -f logfile_name Specify the name of the file into which timing messages are to be logged. A file name with or without a full path may be specified. If a file name without a path is specified, the file is saved in the LSF system log file directory.
Usage Running badmin showconf from a master candidate host reaches all server hosts in the cluster. Running badmin showconf from a slave-only host may not be able to reach other slave-only hosts. badmin showconf only displays the values used by LSF. For example, if you define LSF_MASTER_LIST in lsf.conf, and EGO_MASTER_LIST in ego.conf, badmin showconf displays the value of EGO_MASTER_LIST. badmin showconf displays the value of EGO_MASTER_LIST from wherever it is defined.
Set a new sampling period in seconds. See also bqueues, bhosts, lsb.params, lsb.queues, lsb.hosts, lsf.conf, lsf.
bbot bbot Moves a pending job relative to the last job in the queue. Synopsis bbot job_ID | "job_ID[index_list]" [position] bbot -h | -V Description Changes the queue position of a pending job or job array element, to affect the order in which jobs are considered for dispatch. By default, LSF dispatches jobs in a queue in the order of arrival (that is, first-come, first-served), subject to availability of suitable server hosts.
position Optional. The position argument can be specified to indicate where in the queue the job is to be placed. position is a positive number that indicates the target position of the job from the end of the queue. The positions are relative to only the applicable jobs in the queue, depending on whether the invoker is a regular user or the LSF administrator. The default value of 1 means the position is after all other jobs with the same priority. -h Prints command usage to stderr and exits.
bchkpnt bchkpnt checkpoints one or more checkpointable jobs Synopsis bchkpnt [-f] [-k] [-p minutes | -p 0] job_ID | "job_ID[index_list]" ... bchkpnt [-f] [-k] [-p minutes | -p 0] -J job_name |-m host_name | -m host_group |-q queue_name |-u "user_name" | -u all [0] bchkpnt -h | -V Description Checkpoints the most recently submitted running or suspended checkpointable job. LSF administrators and root can checkpoint jobs submitted by other users. Jobs continue to execute after they have been checkpointed.
Checkpoints only jobs submitted by the specified users. The keyword all specifies all users. Ignored if a job ID other than 0 (zero) is specified. To specify a Windows user account, include the domain name in uppercase letters and use a single backslash (DOMAIN_NAME\user_name) in a Windows command line or a double backslash (DOMAIN_NAME\\user_name) in a UNIX command line. job_ID | "job_ID[index_list]" Checkpoints only the specified jobs. -h Prints command usage to stderr and exits.
bclusters bclusters displays MultiCluster information Synopsis bclusters [-app] bclusters [-h | -V] Description For the job forwarding model, displays a list of MultiCluster queues together with their relationship with queues in remote clusters. For the resource leasing model, displays remote resource provider and consumer information, resource flow information, and connection status between the local and remote cluster. Options -app Displays available application profiles in remote clusters.
For receive-jobs queues, shows the name of the remote cluster that can send jobs to the local queue. STATUS Indicates the connection status between the local queue and remote queue. ok The two clusters can exchange information and the system is properly configured. disc Communication between the two clusters has not been established. This could occur because there are no jobs waiting to be dispatched, or because the remote master cannot be located.
Files Remote Cluster Application Information bcluster -app displays information related to application profile configuration under the heading Remote Cluster Application Information. Application profile information is only displayed for the job forwarding model. bclusters does not show local cluster application profile information. REMOTE_CLUSTER The name of the remote cluster. APP_NAME The name of the application profile available in the remote cluster.
bgadd creates job groups Synopsis bgadd [-L limit] [-sla service_class_name] job_group_name bgadd [-h | -V] Description Creates a job group with the job group name specified by job_group_name. You must provide full group path name for the new job group. The last component of the path is the name of the new group to be created. You do not need to create the parent job group before you create a sub-group under it.
See also ◆ Create a job group named portfolio1 under job group /risk_group: bgadd /risk_group/portfolio1 See also bgdel, bjgroup 42 Platform LSF Command Reference
bgdel deletes job groups Synopsis bgdel [-u user_name | -u all] job_group_name | 0 bgdel -c job_group_name bgdel [-h | -V] Description Deletes a job group with the job group name specified by job_group_name and all its subgroups. You must provide full group path name for the job group to be deleted. The job group cannot contain any jobs. Users can only delete their own job groups. LSF administrators can delete any job groups.
See also See also bgadd, bjgroup 44 Platform LSF Command Reference
bhist displays historical information about jobs Synopsis bhist [-a | -d | -e |-p | -r | -s] [-b | -w] [-l] [-C start_time,end_time] [-D start_time,end_time] [-f logfile_name | -n number_logfiles | -n 0] [-S start_time,end_time] [-J job_name] [-Lp ls_project_name] [-m host_name] [-N host_name | -N host_model | -N CPU_factor] [-P project_name] [-q queue_name] [-u user_name | -u all] bhist [-t] [-f logfile_name] [-T start_time,end_time] bhist [-J job_name] [-N host_name | -N host_model | -N cpu_factor] [job_
Options If you submitted a job with multiple resource requirement strings using the bsub -R option for the order, same, rusage, and select sections, bjobs -l displays a single, merged resource requirement string for those sections, as if they were submitted using a single -R. bhist -l can display job exit codes. A job with exit code 131 means that the job exceeded a configured resource usage limit and LSF killed the job with signal 3 (131-128=3).
Only displays information about jobs submitted during the specified time interval. Specify the span of time for which you want to display the history. If you do not specify a start time, the start time is assumed to be the time of the first occurrence. If you do not specify an end time, the end time is assumed to be now. Specify the times in the format "yyyy/mm/dd/HH:MM". Do not specify spaces in the time interval string. The time interval can be specified in many ways.
Output If you use bhist directly on an event log, you must specify a CPU factor. Use lsinfo to get host model and CPU factor information. -P project_name Only displays information about jobs belonging to the specified project. -q queue_name Only displays information about jobs submitted to the specified queue. -u user_name | -u all Displays information about jobs submitted by the specified user, or by all users if the keyword all is specified.
Detailed history includes job group modification, the date and time the job was forwarded and the name of the cluster to which the job was forwarded. The displayed job command can contain up to 4094 characters for UNIX, or up to 255 characters for Windows. Initial checkpoint period The initial checkpoint period specified at the job level, by bsub -k, or in an application profile with CHKPNT_INITPERIOD.
Time Interval Format Specifies both the start and end times of the interval. start_time, Specifies a start time, and lets the end time default to now. ,end_time Specifies to start with the first logged occurrence, and end at the time specified. start_time Starts at the beginning of the most specific time period specified, and ends at the maximum value of the time period specified. For example, 2/ specifies the month of February—start February 1 at 00:00 a.m.
bhosts displays hosts and their static and dynamic resources Synopsis bhosts [-e | -l | -w] [-x] [-X] [-R "res_req"] [host_name | host_group] ... bhosts [-e | -l | -w] [-X] [-R "res_req"] [cluster_name] bhosts [-e ] -s [resource_name ...] bhosts [-h | -V] Description By default, returns the following information about all hosts: host name, host status, job state statistics, and job slot limits. bhosts displays output for condensed host groups.
Options ◆ num_ok, num_unavail, num_unreach, and num_busy are the number of hosts that are ok, unavail, unreach, and busy, respectively.
For host groups, the names of the hosts belonging to the group are displayed instead of the name of the host group. Do not use quotes when specifying multiple host groups. cluster_name MultiCluster only. Displays information about hosts in the specified cluster. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Output Host-Based Default Displays the following fields: HOST_NAME The name of the host.
Output The host does not allocate more than JL/U job slots for one user at the same time. These job slots are used by running jobs, as well as by suspended or pending jobs that have slots reserved for them. For preemptive scheduling, the accounting is different. These job slots are used by running jobs and by pending jobs that have slots reserved for them (see the description of PREEMPTIVE in lsb.queues(5) and JL/U in lsb.hosts(5)). MAX The maximum number of job slots available.
The migration threshold is the time that a job dispatched to this host can remain suspended by the system before LSF attempts to migrate the job to another host. If the host’s operating system supports checkpoint copy, this is indicated here. With checkpoint copy, the operating system automatically copies all open files to the checkpoint directory when a process is checkpointed. Checkpoint copy is currently supported only on Cray systems.
Output CURRENT LOAD Displays the total and reserved host load. Reserved You specify reserved resources by using bsub -R. These resources are reserved by jobs running on the host. Total The total load has different meanings depending on whether the load index is increasing or decreasing. For increasing load indices, such as run queue lengths, CPU utilization, paging activity, logins, and disk I/O, the total load is the consumed plus the reserved amount.
Files Reads lsb.hosts. See also lsb.
bhpart bhpart displays information about host partitions Synopsis bhpart [-r] [host_partition_name ...] bhpart [-h | -V] Description By default, displays information about all host partitions. Host partitions are used to configure host-partition fairshare scheduling. Options -r Displays the entire information tree associated with the host partition recursively. host_partition_name ... Displays information about the specified host partitions only. -h Prints command usage to stderr and exits.
STARTED Number of job slots used by running or suspended jobs owned by users or user groups in the host partition. RESERVED Number of job slots reserved by the jobs owned by users or user groups in the host partition. CPU_TIME Cumulative CPU time used by jobs of users or user groups executed in the host partition. Measured in seconds, to one decimal place.
bgmod bgmod modifies job groups Synopsis bgmod [-L limit | -Ln] job_group_name bgmod [-h | -V] Description Modifies the job group with the job group name specified by job_group_name. Only root, LSF administrators, the job group creator, or the creator of the parent job groups can use bgmod to modify a job group limit. You must provide full group path name for the modified job group. The last component of the path is the name of the job group to be modified.
To modify limits of /canada or/canada/projects, you must specify the exact group name: bgmod -L 6 /canada or bgmod -L 6 /canada/projects See also bgadd, bgdel, bjgroup Platform LSF Command Reference 61
bjgroup bjgroup displays information about job groups Synopsis bjgroup [-N] [-s [group_name]] bjgroup [-h | -V] Description Displays job group information. Options -s Sorts job groups by group hierarchy.
-N Displays job group information by job slots instead of number of jobs.
Job slots (-N) output SLA The name of the service class that the job group is attached to with bgadd -sla service_class_name. If the job group is not attached to any service class, empty parentheses () are displayed in the SLA name column. JLIMIT The job group limit set by bgadd -L or bgmod -L. Job groups that have no configured limits or no limit usage are indicated by a dash (-). Job group limits are displayed in a USED/LIMIT format.
RSV The number of job slots in the job group that are reserved by LSF for pending jobs. SLA The name of the service class that the job group is attached to with bgadd -sla service_class_name. If the job group is not attached to any service class, empty parentheses () are displayed in the SLA name column. OWNER The job group owner.
bjobs bjobs displays information about LSF jobs Synopsis bjobs [-A] [-a] [-W] [-w | -l] [-X] [-x] [-app application_profile_name] [-g job_group_name] [-sla service_class_name] [-J job_name] [-Lp ls_project_name] [-m host_name | -m host_group | -m cluster_name] [-N host_name | -N host_model | -N cpu_factor] [-P project_name] [-q queue_name] [-u user_name | -u user_group | -u all | -G user_group] job_ID | "job_ID[index_list]" ...
Use -a with -x option to display all jobs that have triggered a job exception (overrun, underrun, idle). -aps Displays absolute priority scheduling (APS) information for pending jobs in a queue with APS_PRIORITY enabled. The APS value is calculated based on the current scheduling cycle, so jobs are not guaranteed to be dispatched in this order. Pending jobs are ordered by APS value. Jobs with system APS values are listed first, from highest to lowest APS value.
Options With MultiCluster, -l shows the names of hosts in the local cluster. Each pending reason is associated with one or more hosts and it states the cause why these hosts are not allocated to run the job. In situations where the job requests specific hosts (using bsub -m), users may see reasons for unrelated hosts also being displayed, together with the reasons associated with the requested hosts. The life cycle of a pending reason ends after the time indicated by PEND_REASON_UPDATE_INTERVAL in lsb.
Use -g with -sla to display job groups attached to a service class. Once a job group is attached to a service class, all jobs submitted to that group are subject to the SLA. bjobs -l with -g displays the full path to the group to which a job is attached.
Output Only displays jobs that have been submitted by the specified users or user groups. The keyword all specifies all users. To specify a Windows user account, include the domain name in uppercase letters and use a single backslash (DOMAIN_NAME\ user_name) in a Windows command line or a double backslash (DOMAIN_NAME\\user_name) in a UNIX command line. The -u option cannot be used with the -G option. job_ID | "job_ID[index]" Displays information about the specified jobs or job arrays.
EXEC_HOST The name of one or more hosts on which the job is executing (this field is empty if the job has not been dispatched). If the host on which the job is running has been removed from the configuration, the host name is displayed as lost_and_found. Use bhist to get the original host name. If the host is part of a condensed host group, the host name is displayed as the name of the condensed host group.
Output loadSched The load scheduling thresholds for the job. loadStop The load suspending thresholds for the job. JOB STATUS Possible values for the status of a job include: PEND The job is pending, that is, it has not yet been started. PSUSP The job has been suspended, either by its owner or the LSF administrator, while pending. RUN The job is currently running. USUSP The job has been suspended, either by its owner or the LSF administrator, while running. SSUSP The job has been suspended by LSF.
◆ The host on which a rerunnable job is running is unavailable and the job has been requeued by LSF with a new job ID, as if the job were submitted as a new job. ◆ After the execution host becomes available, LSF tries to kill the ZOMBI job. Upon successful termination of the ZOMBI job, the job’s status is changed to EXIT. With MultiCluster, when a job running on a remote execution cluster becomes a ZOMBI job, the execution cluster treats the job the same way as local ZOMBI jobs.
Output ◆ SWAPLIMIT ◆ PROCESSLIMIT ◆ THREADLIMIT ◆ OPENFILELIMIT The possible UNIX per-process resource usage limits are: ◆ RUNLIMIT ◆ FILELIMIT ◆ DATALIMIT ◆ STACKLIMIT ◆ CORELIMIT If a job submitted to the queue has any of these limits specified (see bsub(1)), then the lower of the corresponding job limits and queue limits are used for the job. If no resource limit is specified, the resource is assumed to be unlimited. User shell limits that are unlimited are not displayed.
EXIT Number of unsuccessfully completed jobs of the job array. SSUSP Number of LSF system suspended jobs of the job array. USUSP Number of user suspended jobs of the job array. PSUSP Number of held jobs of the job array. Examples bjobs -pl Displays detailed information about all pending jobs of the invoker. bjobs -ps Display only pending and suspended jobs. bjobs -u all -a Displays all jobs of all users.
bkill bkill sends signals to kill, suspend, or resume unfinished jobs Synopsis bkill [-l] [-app application_profile_name] [-g job_group_name] [-sla service_class_name] [-J job_name] [-m host_name | -m host_group] [-q queue_name] [-r | -s signal_value | signal_name] [-u user_name | -u user_group | -u all] [job_ID ... | 0 | "job_ID[index]" ...
USUSP Job finishes, next job in the chunk starts if one exists (NJOBS -1, PEND -1, SUSP -1, RUN +1) WAIT Job finishes (NJOBS-1, PEND -1) If the job cannot be killed, use bkill -r to remove the job from the LSF system without waiting for the job to terminate, and free the resources of the job. Options 0 Kills all the jobs that satisfy other options (-app. -g, -m, -q, -u, and -J). -b Kills large numbers of jobs as soon as possible.
Options Use -g with -sla to kill jobs in job groups attached to a service class. bkill does not kill jobs in lower level job groups in the path. For example, jobs are attached to job groups /risk_group and /risk_group/consolidate: bsub -g /risk_group myjob Job <115> is submitted to default queue . bsub -g /risk_group/consolidate myjob2 Job <116> is submitted to default queue .
Use -sla with -g to kill jobs in job groups attached to a service class. The -sla option is ignored if a job ID other than 0 is specified in the job_ID option. Use bsla to display the configuration properties of service classes configured in lsb.serviceclasses, the default SLA configured with ENABLE_DEFAULT_EGO_SLA in lsb.params, and dynamic information about the state of each service class.
See also Kills the most recently submitted job associated with the application profile fluent for the current user. bkill -app fluent 0 Kills all jobs associated with the application profile fluent for the current user. See also bsub(1), bjobs(1), bqueues(1), bhosts(1), bresume(1), bapp(1), bsla(1), bstop(1), bgadd(1), bgdel(1), bjgroup(1), bparams(5), lsb.
bladmin reconfigures the Platform LSF License Scheduler daemon (bld) Synopsis bladmin subcommand bladmin [-h | -V] Description Use this command to reconfigure the License Scheduler daemon (bld). You must be a License Scheduler administrator to use this command. Subcommand List ckconfig [-v] reconfig [host_name ... | all] shutdown [host_name ... | all] blddebug [-c class_name ...] [-l debug_level] [-f logfile_name] [-o] blcdebug [-l debug_level] [-f logfile_name] [-o] collector_name ...
Options Options ckconfig [-v] Checks LSF License Scheduler configuration in LSF_ENVDIR/lsf.licensescheduler and lsf.conf. By default, bladmin ckconfig displays only the result of the configuration file check. If warning errors are found, bladmin prompts you to use the -v option to display detailed messages. -v Verbose mode. Displays detailed messages about configuration file checking to stderr. reconfig [host_name ... | all] Reconfigures License Scheduler. shutdown [host_name ...
Possible values: 0 LOG_DEBUG level in parameter LS_LOG_MASK in lsf.conf. 1 LOG_DEBUG1 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2 LOG_DEBUG1, and LOG_DEBUG levels. 2 LOG_DEBUG2 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2 LOG_DEBUG1, and LOG_DEBUG levels. LOG_DEBUG3 level for extended logging. A higher level includes lower logging levels.
See also 1 LOG_DEBUG1 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2 LOG_DEBUG1, and LOG_DEBUG levels. 2 LOG_DEBUG2 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2 LOG_DEBUG1, and LOG_DEBUG levels. 3 LOG_DEBUG3 level for extended logging. A higher level includes lower logging levels. For example, LOG_DEBUG3 includes LOG_DEBUG2, LOG_DEBUG1, and LOG_DEBUG levels.
blaunch launches parallel tasks on a set of hosts Synopsis blaunch [-n] [-u host_file | -z host_name ... | host_name] command [argument ...] blaunch [-h | -V] Description IMPORTANT: You cannot run blaunch directly from the command line. RESTRICTION: The command blaunch does not work with user account mapping. Do not run blaunch on a user account mapping host. Most MPI implementations and many distributed applications use rsh and ssh as their task launching mechanism.
Diagnostics Whereas the host name value for rsh and ssh is a single host name, you can use the -z option to specify a space-delimited list of hosts where tasks are started in parallel. Specify a list of hosts on which to execute the task. If multiple host names are specified, the host names must be enclosed by quotation marks (" or ') and separated by white space. This option is exclusive of the -u option. command [argument ...] Specify the command to execute.
blcollect license information collection daemon that collects license usage information Synopsis blcollect -c collector_name -m host_name [...] -p license_scheduler_port [-i lmstat_interval | -D lmstat_path] blcollect [-h | -V] Description Periodically collects license usage information from Macrovision FLEXnet. It queries FLEXnet for license usage information from the FLEXnet lmstat command, and passes the information to the License Scheduler daemon (bld).
blhosts blhosts displays the names of all the hosts running the License Scheduler daemon (bld) Synopsis blhosts [-h | -V] Description Displays a list of hosts running the License Scheduler daemon. This includes the License Scheduler master host and all the candidate License Scheduler hosts running bld. Options -h Prints command usage to stderr and exits. -V Prints release version to stderr and exits. Output Prints out the names of all the hosts running the License Scheduler daemon (bld).
blimits displays information about resource allocation limits of running jobs Synopsis blimits [-w] [-n limit_name ...] [-m host_name | -m host_group | -m cluster_name ...] [-P project_name ...] [-q queue_name ...] [-u user_name | -u user_group ...] blimits -c blimits -h | -V Description Displays current usage of resource allocation limits configured in Limit sections in lsb.
Options PER_HOST slot limits are not displayed. The bhosts commands displays these as MXJ limits. In MultiCluster, blimits returns the information about all limits in the local cluster. Limit names and policies are set up by the LSF administrator. See lsb.resources(5) for more information. Options -c Displays all resource configurations in lsb.resources. This is the same as bresources with no options. -w Displays resource allocation limits information in a wide format.
If a user group is specified, displays the resource allocation limits that include that group in their configuration. For a list of user groups see bugroup(1)). -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits.
Example MEM Amount of memory currently used and maximum configured for the limit policy, as specified by the Limit section MEM parameter. TMP Amount of tmp space currently used and maximum amount of tmp space configured for the limit policy, as specified by the Limit section TMP parameter. SWP Amount of swap space currently used and maximum amount of swap space configured for the limit policy, as specified by the Limit section SWP parameter.
blinfo displays static License Scheduler configuration information Synopsis blinfo -Lp | -p | -D | -G | -P blinfo [-a [-t token_name | "token_name ..."]] [-o alpha | total] [-g "feature_group ..."] blinfo -A [-t token_name | "token_name ..."] [-o alpha | total ] [-g "feature_group ..."] blinfo -C [-t token_name | "token_name ..."] [-o alpha | total] [-g "feature_group ..."] blinfo [-t token_name | "token_name ..."] [-o alpha | total] [-g "feature_group ...
Output -g feature_group ... When FEATURE_GROUP is configured for a group of license features in lsf.licensescheduler, shows only information about the features configured in the FEATURE_LIST of specified feature groups. You can specify more than one feature group at one time. When you specify feature names with -t, features in the feature list defined by -t and feature groups are both displayed. Feature groups listed with -g but not defined in lsf.licensescheduler are ignored.
DISTRIBUTION The distribution of the licenses among license projects in the format [project_name, percentage[/number_licenses_owned]]. This determines how many licenses a project is entitled to use when there is competition for licenses. The percentage is calculated from the share specified in the configuration file. Allocation output (-A) FEATURE The license name. This becomes the license token name. When LOCAL_TO is configured for a feature in lsf.
Output LIC_SERVERS Names of FLEXnet license server hosts that belong the to service domain. Each host name is enclosed in parentheses, as shown: (port_number@host_name) Redundant hosts (that share the same FLEXnet license file) are grouped together as shown: (port_number@host_name port_number@host_name port_number@host_name) Hierarchical Output (-G) The following fields describe the values of their corresponding configuration fields in the ProjectGroup Section of lsf.licensescheduler.
◆ The directory path and command that License Scheduler runs when reporting a violation Defined in lsf.licensescheduler. EXT_FILTER_PORT TCP listening port used by all external plug-ins to communicate with License Scheduler hosts. Defined in lsf.licensescheduler. FLX_LICENSE_FILE Path to the file that contains the license keys FLEXnet.Ext.Filter and FLEXnet.Usage.Snapshot to enable the FLEXnet APIs. Defined in lsf.licensescheduler. HOSTS License Scheduler candidate hosts. Defined in lsf.
Examples Examples displays both NON_SHARED_DISTRIBUTION and WORKLOAD_DISTRIBUTION information: blinfo -a blinfo -a FEATURE g1 SERVICE_DOMAIN LS TOTAL 3 DISTRIBUTION [p1, 50.0%] [p2, 50.0% / 2] NON_SHARED_DISTRIBUTION [p2, 2] WORKLOAD_DISTRIBUTION [LSF 66.7%, NON_LSF 33.3%] blinfo -a does not display NON_SHARED_DISTRIBUTION, if the NON_SHARED_DISTRIBUTION is not defined: blinfo -a FEATURE g1 SERVICE_DOMAIN LS TOTAL 0 g2 g33 LS WS 0 0 DISTRIBUTION [p1, 50.0%] [p2, 50.
blkill terminates an interactive License Scheduler task Synopsis blkill [-t seconds] task_ID blkill [-h | -V] Description Terminates a running or waiting interactive task in License Scheduler. Users can kill their own tasks. You must be a License Scheduler administrator to terminate another user’s task. By default, blkill notifies the user and waits 30 seconds before killing the task. Options task_ID Task ID of the task you want to kill.
blparams blparams displays information about configurable License Scheduler parameters defined in the files lsf.licensescheduler and lsf.conf Synopsis blparams [-h | -V] Description Displays the following parameter values: ADMIN The License Scheduler administrator. Defined in lsf.licensescheduler.
Specifies the log class filtering to be applied to bld. Messages belonging to the specified log class are recorded. Not all debug message are controlled by log class. LS_DEBUG_BLD sets the log class and is used in combination with MASK, which sets the log level. For example: LS_LOG_MASK=LOG_DEBUG LS_DEBUG_BLD="LC_TRACE" You need to restart the bld daemon after setting LS_DEBUG_BLD for your changes to take effect.
Options LS_PREEMPT_PEER Enables bottom-up license token preemption in hierarchical project group configuration. License Scheduler attempts to preempt tokens from the closest projects in the hierarchy first. This balances token ownership from the bottom up. Defined in lsf.licensescheduler. LSF_LIC_SCHED_HOSTS List of hosts that are candidate LSF License Scheduler hosts. Defined in lsf.conf.
blplugins displays plug-in activity and the check-in, check-out, and deny counters as seen by the License Scheduler for each feature and service domain Synopsis blplugins [-h | -V] Description Displays the License Scheduler Vendor Plugin Status. Options -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Output IP The IP address for each external filter server plugin.
blstat blstat displays dynamic license information Synopsis blstat [-a] [-c token_name] [-G] [-s] [-S] [-D service_domain_name | "service_domain_name ..."] [-Lp ls_project_name | "ls_project_name ..."] [-P][-t token_name | "token_name ..."] [-o alpha | total | avail] [-g "feature_group ..."] blstat [ -h | -V] Description Displays license usage statistics. By default, shows information about all licenses and all clusters. Options -a Displays each project group’s accumulated value of licenses.
Feature groups listed with -g but not defined in lsf.licensescheduler are ignored. -Lp ls_project_name | "ls_project_name ..." Shows project description for specified projects (non-hierarchical). Use spaces to separate multiple names and enclose them in quotation marks. -o alpha | total | avail Sorts license feature information alphabetically, by total licenses, or by available licenses. ◆ alpha: Features are listed in descending alphabetical order.
Output TOTAL_FREE The number of free licenses that are available to License Scheduler projects. (Licenses that are not reserved or in use.) OTHERS The number of licenses checked out by users who are not submitting their jobs to License Scheduler projects. By default, these licenses are not being managed by License Scheduler policies. To enforce license distribution policies for these license features, configure ENABLE_DYNAMIC_RUSAGE=Y in the feature section for those features in lsf.licensescheduler.
FREE The number of licenses the license project has free. (The license tokens have been allocated to the license project by License Scheduler, but the licenses are not reserved and have not yet been checked out from the FLEXnet license manager.) DEMAND Numeric value indicating the number of tokens required by each project. NON_SHARED The number of non-shared licenses belonging to the license project.
See also SERVICE_DOMAIN: SD2 TOTAL_INUSE: 0 TOTAL_RESERVE: 0 TOTAL_FREE: 65 PROJECT SHARE Lp1 50.0 % 4 0 0 32 2 Lp2 50.
bltasks displays License Scheduler interactive task information Synopsis bltasks [-l] [task_ID] bltasks [-l] [-p | -r | -w] [-Lp “ls_project_name...”] [-m “host_name...”] [-t “terminal_name...”] [-u “user_name...”] bltasks [-h | -V] Description Displays current information about interactive tasks managed by License Scheduler (submitted using taskman). By default, displays information about all tasks. Options task_ID Only displays information about the specified task. -l Long format.
Output Output Default Output Displays the short format with the following information: TID Task ID that License Scheduler assigned to the task. USER The user who submitted the task. STAT The current status of the task. ◆ RUN: Task is running. ◆ WAIT: Task has not yet started. ◆ PREEMPT: Task has been preempted and currently has no license token. HOST The name of host from which the task was submitted. PROJECT The name of the project to which the task belongs.
blusers displays license usage information Synopsis blusers [-J | -l | -P -j job_ID -u user_name -m host_name | -P -c cluster_name -j job_ID -u user_name -m host_name] blusers [-h | -V] Description By default, displays summarized information about usage of licenses. Options -J Displays detailed license usage information about each job. -l Long format. Displays additional license usage information. See Output on page 111 for a description of information that is displayed.
Output -J Output Displays the following summary information for each job: JOBID The job ID assigned by LSF. USER The name of the user who submitted the job. HOST The name of the host where the job has been started. PROJECT The name of the license project that the job is associated with. CLUSTER The name of the LSF cluster that the job is associated with. Displays “-” for an interactive job. START_TIME The job start time.
Examples blusers -l FEATURE SERVICE_DOMAIN feat1 LanServer blusers -J JOBID USER 553 user1 RESOURCE p1_f1 HOST hostA RUSAGE 1 USER user1 HOST hostA NLICS 1 PROJECT p3 SERVICE_DOMAIN app_1 NTASKS OTHERS DISPLAYS PIDS 1 0 (/dev/tty) (16326) CLUSTER cluster1 START_TIME Oct 5 15:47:14 See also blhosts, blinfo, blstat Platform LSF Command Reference 113
bmgroup bmgroup displays information about host groups Synopsis bmgroup [-r] [-l] [-w] [host_group ...] bmgroup [-h | -V] Description Displays host groups and host names for each group. By default, displays information about all host groups including host groups created for EGO-enabled SLA scheduling. A host partition is also considered a host group. Host groups for EGO-enabled SLA When hosts are allocated to an EGO-enabled SLA, they are dynamically added to a host group created by the SLA.
See also lsb.
bmig bmig migrates checkpointable or rerunnable jobs Synopsis bmig [-f] [job_ID | "job_ID[index_list]"] ... bmig [-f] [-J job_name] [-m "host_name ..." | -m "host_group ..."] [-u user_name | -u user_group | -u all] [0] bmig [-h | -V] Description Migrates one or more of your checkpointable or rerunnable jobs to a different host. You can migrate only running or suspended jobs; you cannot migrate pending jobs.
configured in lsf.conf, the migrated jobs keep their APS information, and the migrated jobs compete with other pending jobs based on the APS value. If you want to reset the APS value, you must use brequeue instead of bmig. Options -f Forces a checkpointable job to be checkpointed and migrated, even if non-checkpointable conditions exist within the operating system environment. job_ID | "job_ID[index_list]" | 0 Migrates jobs with the specified job IDs. LSF ignores the -J and -u options.
bmod bmod modifies job submission options of a job Synopsis bmod [bsub_options] [job_ID | "job_ID[index]"] bmod [-g job_group_name | -gn] [job_ID] bmod [-sla service_class_name | -slan] [job_ID] bmod [-aps "system=value" | "admin=value" | -apsn] [job_ID] bmod [-h | -V] Option List [-B | -Bn] [-N | -Nn] [-r | -rn] [-ul | -uln] [-x | -xn] [-a esub_application] [-app application_profile_name | -appn] [-aps "system=value" | "admin=value" | -apsn] [-b begin_time | -bn] [-C core_limit | -Cn] [-c [hour:]min
[-M mem_limit | -Mn] [-m "host_name[@cluster_name][[!] | +[pref_level]] | host_group[[!] | +[pref_level]] ..." | -mn] [-mig migration_threshold | -mign] [-n num_processors | -nn ] [-o out_file | -on] [-oo out_file | -oon] [-P project_name | -Pn] [-p process_limit | -pn] [-Q "[exit_code …] [EXCLUDE(exit_code …)]" ] [-q "queue_name ...
Description Options related to file names and job spooling directories support paths that contain up to 4094 characters for UNIX and Linux, or up to 255 characters for Windows. Options related to command names and job names can contain up to 4094 characters for UNIX and Linux, or up to 255 characters for Windows. You can modify all options of a pending job, even if the corresponding bsub option was not specified.
◆ Standard output (stdout) file name up to 4094 characters for UNIX and Linux or 255 characters for Windows (-o output_file) ◆ Standard error (stderr) file name up to 4094 characters for UNIX and Linux or 255 characters for Windows (-e error_file) ◆ Overwrite standard output (stdout) file name up to 4094 characters for UNIX and Linux or 255 characters for Windows (-oo output_file) ◆ Overwrite standard error (stderr) file name up to 4094 characters for UNIX and Linux or 255 characters for Windows (-eo
Description bmod -g cannot be combined with other bmod options. It can only operate on pending jobs. It cannot operate on running or finished jobs. You can modify your own job groups and job groups that other users create under your job groups. LSF administrators can modify job groups of all users. You cannot move job array elements from one job group to another, only entire job arrays. If any job array elements in a job array are running, you cannot move the job array to another group.
Modifying absolute priority scheduling options Administrators can use bmod -aps to adjust the APS value for pending jobs. bmod -apsn cancels previous bmod -aps settings. You cannot combing bmod -aps with other bmod options. bmod -aps "system=value" job_ID Set a static non-zero APS value of a pending job. Setting a system APS value overrides any calculated APS value for the job. The system APS value cannot be applied to running jobs.
bparams bparams displays information about configurable system parameters in lsb.params Synopsis bparams [-a] [-l] bparams [-h | -V] Description Displays the following parameter values: ◆ Default Queues ◆ Job Dispatch Interval ◆ Job Checking Interval ◆ Job Accepting Interval Options -a All format. Displays all the configurable parameters set in lsb.params. -l Long format. Displays detailed information about all the configurable parameters in lsb.params.
bpeek displays the stdout and stderr output of an unfinished job Synopsis bpeek [-f] [-q queue_name | -m host_name | -J job_name | job_ID | "job_ID[index_list]"] bpeek [-h | -V] Description Displays the standard output and standard error output that have been produced by one of your unfinished jobs, up to the time that this command is invoked. By default, displays the output using the command cat. This command is useful for monitoring the progress of a job and identifying errors.
bpost bpost sends external status messages and attaches data files to a job Synopsis bpost [-i message_index] [-d "description"] [-a data_file] job_ID | "job_ID[index]" | -J job_name bpost [-h | -V] Description Provides external status information or sends data to a job in the system. Done or exited jobs cannot accept messages. By default, operates on the message index 0. By default, posts the message "no description". If a you specify a job ID: ◆ You can only send messages and data to your own jobs.
With MultiCluster, both clusters must run LSF Version 7 or later. You cannot post a message to a MultiCluster job if the clusters are disconnected. You cannot attach files to MultiCluster jobs. Options -a data_file Attaches the specified data file to the job external storage. This option is ignored for MultiCluster jobs; you can only attach a file if the job executes in the local cluster. Use the JOB_ATTA_DIR parameter in lsb.params(5) to specify the directory where attachment data files are saved.
bqueues bqueues displays information about queues Synopsis bqueues [-w | -l | -r] [-m host_name | -m host_group | -m cluster_name | -m all] [-u user_name | -u user_group | -u all] [queue_name ...] bqueues [-h | -V] Description Displays information about queues. By default, returns the following information about all queues: queue name, queue priority, queue status, job slot statistics, and job state statistics. In MultiCluster, returns the information about all queues in the local cluster.
Displays the queues that can accept jobs from the specified user. If the keyword all is specified, displays the queues that can accept jobs from all users. If a user group is specified, displays the queues that include that group in their configuration. For a list of user groups see bugroup(1)). queue_name ... Displays information about the specified queues. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits.
Output The queue is re-activated by LSF when one of its dispatch windows and one of its run windows are open again. The initial state of a queue at LSF boot time is set to open, and either active or inactive depending on its windows. MAX The maximum number of job slots that can be used by the jobs from the queue. These job slots are used by dispatched jobs which have not yet finished, and by pending jobs which have slots reserved for them.
The nice value at which jobs in the queue are run. This is the UNIX nice value for reducing the process priority (see nice(1)). STATUS Inactive The long format for the -l option gives the possible reasons for a queue to be inactive: Inact_Win The queue is out of its dispatch window or its run window. Inact_Adm The queue has been inactivated by the LSF administrator. SSUSP The number of job slots in the queue allocated to jobs that are suspended by LSF because of load levels or run windows.
Output The maximum CPU time a job can use, in minutes, relative to the CPU factor of the named host. CPULIMIT is scaled by the CPU factor of the execution host so that jobs are allowed more time on slower hosts. When the job-level CPULIMIT is reached, a SIGXCPU signal is sent to all processes belonging to the job. If the job has no signal handler for SIGXCPU, the job is killed immediately.
The maximum file size a process can create, in KB. This limit is enforced by the UNIX setrlimit system call if it supports the RLIMIT_FSIZE option, or the ulimit system call if it supports the UL_SETFSIZE option. DATALIMIT The maximum size of the data segment of a process, in KB. This restricts the amount of memory a process can allocate. DATALIMIT is enforced by the setrlimit system call if it supports the RLIMIT_DATA option, and unsupported otherwise.
Output The memory paging rate exponentially averaged over the last minute, in pages per second. io The disk I/O rate exponentially averaged over the last minute, in KB per second. ls The number of current login users. it On UNIX, the idle time of the host (keyboard not touched on all logged in sessions), in minutes. On Windows, the it index is based on the time a screen saver has been active on a particular host. tmp The amount of free space in /tmp, in MB.
overrun Configured threshold in minutes for overrun jobs, and the number of jobs in the queue that have triggered an overrun job exception by running longer than the overrun threshold underrun Configured threshold in minutes for underrun jobs, and the number of jobs in the queue that have triggered an underrun job exception by finishing sooner than the underrun threshold idle Configured threshold (CPU time/runtime) for idle jobs, and the number of jobs in the queue that have triggered an overrun job exce
Output This queue only accepts batch interactive jobs. Jobs must be submitted using the -I, -Is, and -Ip options of bsub(1). The default is to accept both interactive and non-interactive jobs. FAIRSHARE_QUEUES Lists queues participating in cross-queue fairshare. The first queue listed is the master queue—the queue in which fairshare is configured; all other queues listed inherit the fairshare policy from the master queue.
DISPATCH_WINDOWS Dispatch windows are the time windows in a week during which jobs in the queue may be dispatched. When a queue is out of its dispatch window or windows, no job in this queue is dispatched. Jobs already dispatched are not affected by the dispatch windows. The default is no restriction, or always open (that is, twenty-four hours a day, seven days a week). Note that such windows are only applicable to batch jobs.
Output PRE_EXEC The PRE_EXEC command runs on the execution host before the job associated with the queue is dispatched to the execution host (or to the first host selected for a parallel batch job). POST_EXEC The post-execution command for the queue. The POST_EXEC command runs on the execution host after the job finishes. REQUEUE_EXIT_VALUES Jobs that exit with these values are automatically requeued. See lsb.queues(5) for more information. RES_REQ Resource requirements of the queue.
RERUNNABLE If the RERUNNABLE field displays yes, jobs in the queue are rerunnable. That is, jobs in the queue are automatically restarted or rerun if the execution host becomes unavailable. However, a job in the queue is not restarted if you remove the rerunnable option from the job. CHECKPOINT If the CHKPNTDIR field is displayed, jobs in the queue are checkpointable. Jobs use the default checkpoint directory and period unless you specify other values.
See also See also bugroup(1), nice(1), getrlimit(2), lsb.
bread reads messages and attached data files from a job Synopsis bread [-i message_index] [-a file_name] job_ID | "job_ID[index]" | -J job_name bread [-h | -V] Description Reads messages and data posted to an unfinished job with bpost. By default, displays the message description text of the job. By default, operates on the message with index 0. You can read messages and data from a job until it is cleaned from the system. You cannot read messages and data from done or exited jobs.
Example By default, -a gets the attachment file from the directory specified by the JOB_ATTA_DIR parameter. If JOB_ATTA_DIR is not specified, job message attachments are saved in LSB_SHAREDIR/info/. -i message_index Specifies the message index to be retrieved. Default: 0 job_ID | "job_ID[index]" | -J job_name Required. Specify the job to operate on. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Example bpost -i 1 -d "step 1" -a step1.
brequeue kills and requeues a job Synopsis brequeue [-J job_name | -J "job_name[index_list]"] [ -u user_name | -u all ] [ job_ID | "job_ID[index_list]"] [-d] [-e] [-r] [-a] [-H] brequeue [-h | -V] Description You can only use brequeue on a job you own, unless you are root or the LSF administrator. Kills a running (RUN), user-suspended (USUSP), or system-suspended (SSUSP) job and returns it to the queue.
Limitations -J job_name | -J "job_name[index_list]" Operates on the specified job. Since job names are not unique, multiple job arrays may have the same name with a different or same set of indices. -u user_name | -u all Operates on the specified user’s jobs or all jobs. To specify a Windows user account, include the domain name in uppercase letters and use a single backslash (DOMAIN_NAME\user_name) in a Windows command line or a double backslash (DOMAIN_NAME\\user_name) in a UNIX command line.
bresources displays information about resource reservation and resource limits configuration Synopsis bresources [-s] [resource_name ...] bresources [-h | -V] Description By default, bresources displays all resource configurations in lsb.resources. This is the same as blimits -c. Options -s Displays per-resource reservation configurations from the ReservationUsage section of lsb.resources.
brestart brestart restarts checkpointed jobs Synopsis brestart [bsub_options] [-f] checkpoint_dir [job_ID | "job_ID[index]"] brestart [-h | -V] Option List -B -f -N -x -b begin_time -C core_limit -c [hour:]minute[/host_name | /host_model] -D data_limit -E "pre_exec_command [argument ...]" -F file_limit -m "host_name[+[pref_level]] | host_group[+[pref_level]] ..." -G user_group -M mem_limit -q "queue_name ...
To restart a job on another host, both hosts must be binary compatible, run the same OS version, have access to the executable, have access to all open files (LSF must locate them with an absolute path name), and have access to the checkpoint directory. The environment variable LSB_RESTART is set to Y when a job is restarted. LSF invokes the erestart(8) executable found in LSF_SERVERDIR to perform the restart. Only the bsub options listed here can be used with brestart.
bresume bresume resumes one or more suspended jobs Synopsis bresume [-app application_profile_name] [-g job_group_name] [-J job_name] [-m host_name] [-q queue_name] [-sla service_class_name] [-u user_name | -u user_group | -u all] [0] bresume [job_ID | "job_ID[index_list]"] ... bresume [-h | -V] Description Sends the SIGCONT signal to resume one or more of your suspended jobs. Only root and LSF administrators can operate on jobs submitted by other users. You cannot resume a job that is not suspended.
Use bsla to display the properties of service classes configured in LSB_CONFDIR/cluster_name/configdir/lsb.serviceclasses (see lsb.serviceclasses(5)) and dynamic information about the state of each configured service class. -u user_name | -u user_group | -u all Resumes only jobs owned by the specified user or group, or all users if the reserved user name all is specified.
brlainfo brlainfo displays host topology information Synopsis brlainfo [-l] [host_name ...] brlainfo [-h | -V] Description brlainfo contacts the Platform LSF HPC topology adapter (RLA) on the specified host and presents topology information to the user. By default, displays information about all hosts running RLA. Options -l Long format. Displays additional host topology information. See Output on page 150 for a description of information that is displayed. host_name ...
NFREECPUS ON EACH NODE Number of free CPUs on each node For example: 2/0,1/1 STATIC CPUSETS List of static cpuset names For example: NO STATIC CPUSETS CPU_RADIUS Available CPUs with a given radius. CPU radius is determined by the processor topology of the system and is expressed in terms of the number of router hops between CPUs.
brsvadd brsvadd adds an advance reservation Synopsis brsvadd [-o] [-d "description"] [-N reservation_name] {-s | -n job_slots {-u user_name | -g group_name}} {-m "host_name | host_group ..." [-R "res_req"] | [-m "host_name | host_group ..."] -R "res_req"} {-b begin_time -e end_time | -t time_window} brsvadd {-h | -V} Description CAUTION: By default, this command can only be used by LSF administrators or root.
◆ minute: 0-59 (mm) You must specify at least hour:minute. Year, month, and day are optional. Three fields are assumed to be day:hour:minute, four fields are assumed to be month:day:hour:minute, and five fields are year:month:day:hour:minute. If you do not specify a day, LSF assumes the current day. If you do not specify a month, LSF assumes the current month. If you specify a year, you must specify a month. The time value for -b must use the same syntax as the time value for -e.
Options For example: brsvadd -n 3 -M "hostA hostB" -u user2 -b 16:0 -e 17:0 -d "Production AR test" Reservation user2#0 (Production AR test) is created brsvadd -n 2 -N Production_AR -M hostA -u user2 -b 16:0 -e 17:0 -d "Production AR test" Reservation Production_AR (Production AR test) is created If a job already exists that references a reservation with the specified name, an error message is returned: The specified reservation name is referenced by a job. -n job_slots Number of job slots to reserve.
is correct, but timeWindow(8:00-14:00 11:00-15:00) is not valid. LSF administrators can prevent running jobs from being killed when the reservation expires by changing the termination time of the job using the reservation (bmod -t) before the reservation window closes. When the job starts running, the run limit of the reservation is set to the minimum of the job run limit (if specified), the queue run limit (if specified), or the duration of the time window.
brsvdel brsvdel deletes an advance reservation Synopsis brsvdel reservation_ID ... brsvdel {-h | -V} Description CAUTION: By default, this command can only be used by LSF administrators or root. Deletes advance reservations for the specified reservation IDs.
brsvmod modifies an advance reservation Synopsis brsvmod [-o | -on] [-d "description"] [-u user_name | -g group_name] [[-b begin_time | [+|-]minutes] [-e end_time | [+|-]minutes]] | [-t time_window] reservation_ID brsvmod disable {-td "begin_date-end_date" | -tn} [-f] reservation_ID brsvmod addhost {-n job_slots -R "res_req" [-m "host_name ... | host_group ..."]} | {[-n job_slots] -m "host_name ... | host_group ..."} reservation_ID brsvmod rmhost {-n job_slots [-m "host_name ... | host_group ...
Subcommands 3 slots are required. LSF tries to find as many slots as possible from host1. If 3 slots are not available on host1, then LSF tries to find the rest from host2. Hosts with no slots available are removed from the list when the request is handled. Subcommands addhost [-n job_slots [-R "res_req"]] [-m "host_name ... | host_group ..."] reservation_ID Adds hosts and slots on hosts into the original reservation allocation. The hosts can be local to the cluster or hosts leased from remote clusters.
Once a reservation is disabled for a period, it cannot be enabled; that is, the disabled periods remain fixed. Before a reservation is disabled, you are prompted to confirm whether to continue disabling the reservation. Use the -f option to silently force the command to run without prompting for confirmation; for example, to allow for automating disabling reservations from a script. rmhost [-n job_slots] [-m "host_name ... | host_group ...
Options You must specify at least hour:minute. Year, month, and day are optional. Three fields are assumed to be day:hour:minute, four fields are assumed to be month:day:hour:minute, and five fields are year:month:day:hour:minute. If you do not specify a day, LSF assumes the current day. If you do not specify a month, LSF assumes the current month. If you specify a year, you must specify a month. The offset is in minutes, an integer with a prefix+ or -.
-m "host_name | host_group ..." Changes the list of hosts for which job slots specified with -n are reserved. At job submission, LSF considers the hosts in the specified order. If you also specify a resource requirement string with the -R option, -m is optional. The hosts can be local to the cluster or hosts leased from remote clusters. -n job_slots Changes the number of job slots to reserve.
Examples is correct, but timeWindow(8:00-14:00 11:00-15:00) is not valid. LSF administrators can prevent running jobs from being killed when the reservation expires by changing the termination time of the job using the reservation (bmod -t) before the reservation window closes. When the job starts running, the run limit of the reservation is set to the minimum of the job run limit (if specified), the queue run limit (if specified), or the duration of the time window.
brsvs displays advance reservations Synopsis brsvs [-l | -w] [-p all | "host_name ..."] brsvs [-l | -w] [-z all | "host_name ..."] brsvs [-c all | "policy_name"] brsvs [-h | -V] Description By default, displays the current advance reservations for all hosts, users, and groups.
Example Example brsvs -c reservation1 Policy Name: reservation1 Users: ugroup1 ~user1 Hosts: hostA hostB Time Window: 8:00-13:00 See also brsvadd, brsvdel, brsvmod, lsb.
brun forces a job to run immediately Synopsis brun [-b] [-c] [-f] -m "host_name[#num_cpus] ... " job_ID brun [-b] [-c] [-f] -m "host_name[#num_cpus] ... " "job_ID[index_list]" brun [-h | -V] Description CAUTION: This command can only be used by LSF administrators. Forces a pending job to run immediately on specified hosts. A job which has been forced to run is counted as a running job, this may violate the user, queue, or host job limits, and fairshare priorities.
Limitations slots on hostA are used, the job remains pending. With -c, LSF takes into consideration that hostA has 2 slots in use and hostB is completely free, so LSF is able to dispatch the job using the 2 free slots on hostA and all 4 slots on hostB. -f Allows the job to run without being suspended due to run windows or suspending conditions. -m "host_name[#num_cpus] ... " Required. Specify one or more hosts on which to run the job.
bsla displays information about service class configuration for goal-oriented service-level agreement (SLA) scheduling Synopsis bsla [service_class_name] bsla [-h | -V] Description bsla displays the properties of service classes configured in lsb.serviceclasses and dynamic information about the state of each configured service class. If a default system service class is configured with ENABLE_DEFAULT_EGO_SLA in lsb.params but no other service classes are explicitly configured in lsb.
Output NUM_RECALLED_HOSTS For EGO-enabled SLA service classes, the number of hosts allocated to the SLA that EGO has reclaimed. RECALLED_HOSTS_TIMEOUT For EGO-enabled SLA service classes, the amount of time EGO gives to LSF to clean up its workload before EGO reclaims the host. USER GROUP User names or user groups who can submit jobs to the service class.
NJOBS The current number of job slots used by jobs in the specified service class. A parallel job is counted as 1 job, regardless of the number of job slots it uses. PEND The number of pending job slots used by jobs in the specified service class. RUN The number of job slots used by running jobs in the specified service class. SSUSP The number of job slots used by the system-suspended jobs in the service class. USUSP The number of job slots used by user-suspended jobs in the specified service class.
See also See also bsla(1), bhist(1), bjobs(1), bkill(1), bmod(1), bsub(1), lsb.acct(5), lsb.
bslots displays slots available and backfill windows available for backfill jobs Synopsis bslots [-l] [-n slots] [-R "res_req"] [-W [hour:]minutes] bslots [-h | -V] Description The available slots displayed by bslots are not currently used for running jobs and can be used for backfill jobs. bslots displays a snapshot of the slots currently not in use by parallel jobs or advance reservations. They are not guaranteed to be available at job submission.
Options -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits.
bstatus gets current external job status or sets new job status Synopsis bstatus [-d "description"] job_ID | "job_ID[index]" | -J job_name bstatus [-h | -V] Description Gets and displays the message description text of a job, or changes the contents of the message description text with the -d option. Always operates on the message with index 0. You can set the external status of a job until it completes. You cannot change the status of done or exited jobs.
See also See also bpost(1), bread(1) 174 Platform LSF Command Reference
bstop suspends unfinished jobs Synopsis bstop [-a] [-d] [-app application_profile_name] [-g job_group_name] [-sla service_class_name] [-J job_name] [-m host_name | -m host_group] [-q queue_name] [-u user_name | -u user_group | -u all] [0] [job_ID ... | "job_ID[index]"] ... bstop [-h | -V] Description Suspends unfinished jobs. Sends the SIGSTOP signal to sequential jobs and the SIGTSTP signal to parallel jobs to suspend them. You must specify a job ID or -g, -J, -m, -u, or -q.
Examples Use bsla to display the properties of service classes configured in LSB_CONFDIR/cluster_name/configdir/lsb.serviceclasses (see lsb.serviceclasses(5)) and dynamic information about the state of each configured service class. -u user_name | -u user_group | -u all Suspends only jobs owned by the specified user or user group, or all users if the keyword all is specified.
bsub submits a batch job to LSF Synopsis bsub [options] command [arguments] bsub [-h | -V] Option List -B -H -I | -Ip | -Is -K -N -r | -rn -ul -x -a esub_application -app application_profile_name -b [[month:]day:]hour:minute -C core_limit -c [hour:]minute[/host_name | /host_model] -cwd "current_working_directory" -D data_limit -E "pre_exec_command [arguments ...
Description -Lp -M ls_project_name mem_limit -m "host_name[@cluster_name][[!] | +[pref_level]] | host_group[[!] | +[pref_level]] ..." -mig migration_threshold -n min_proc[,max_proc] -o output_file -oo output_file -P project_name -p process_limit -Q "[exit_code …] [EXCLUDE(exit_code …)]" -q "queue_name ...
Sets the user’s execution environment for the job, including the current working directory, file creation mask, and all environment variables, and sets LSF environment variables before starting the job. When a job is run, the command line and stdout/stderr buffers are stored in the directory home_directory/.lsbatch on the execution host. If this directory is not accessible, /tmp/.lsbtmp user_ID is used as the job’s home directory.
Options Options related to command names and job names can contain up to 4094 characters for UNIX and Linux, or up to 255 characters for Windows. Options for the following resource usage limits are specified in KB: ◆ Core limit (-C) ◆ Memory limit (-M) ◆ Stack limit (-S) ◆ Swap limit (-v) Use LSF_UNIT_FOR_LIMITS in lsf.conf to specify a larger unit for the limit (MB, GB, TB, PB, or EB).
Terminal support is available for a batch interactive job. When you specify the -Ip option, submits a batch interactive job and creates a pseudo-terminal when the job starts. Some applications (for example, vi) require a pseudo-terminal in order to run correctly. When you specify the -Is option, submits a batch interactive job and creates a pseudo-terminal with shell mode support when the job starts.
Options -rn specifies that the job is never rerunnable. bsub –rn disables job rerun if the job was submitted to a rerunnable queue or application profile with job rerun configured. The command level job rerunnable setting overrides the application profile and queue level setting. bsub –rn is different from bmod -rn, which cannot override the application profile and queue level rerunnable job setting. Members of a chunk job can be rerunnable.
In exclusive execution mode, your job runs by itself on a host. It is dispatched only to a host with no other jobs running, and LSF does not send any other jobs to the host until the job completes. To submit a job in exclusive execution mode, the queue must be configured to allow exclusive jobs. When the job is dispatched, bhosts(1) reports the host status as closed_Excl, and lsload(1) reports the host status as lockU.
Options -b [[month:]day:]hour:minute Dispatches the job for execution on or after the specified date and time. The date and time are in the form of [[month:]day:]hour:minute where the number ranges are as follows: month 1-12, day 1-31, hour 0-23, minute 0-59. At least two fields must be specified. These fields are assumed to be hour:minute. If three fields are given, they are assumed to be day:hour:minute, and four fields are assumed to be month:day:hour:minute.
Specifies the current working directory for the job. By default, if the current working directory is not accessible on the execution host, the job runs in /tmp. If the environment variable LSB_EXIT_IF_CWD_NOTEXIST is set to Y and the current working directory is not accessible on the execution host, the job exits with the exit code 2. -D data_limit Sets a per-process (soft) data segment size limit for each of the processes that belong to the batch job (see getrlimit(2)). The limit is specified in KB.
Options If the parameter LSB_STDOUT_DIRECT in lsf.conf is set to Y or y, the standard error output of a job is written to the file you specify as the job runs. If LSB_STDOUT_DIRECT is not set, it is written to a temporary file and copied to the specified file after the job finishes. LSB_STDOUT_DIRECT is not supported on Windows. If you use the special character %J in the name of the error file, then %J is replaced by the job ID of the job.
The options set by -extsched can be combined with the queue-level MANDATORY_EXTSCHED or DEFAULT_EXTSCHED parameters. If -extsched and MANDATORY_EXTSCHED set the same option, the MANDATORY_EXTSCHED setting is used. If -extsched and DEFAULT_EXTSCHED set the same options, the -extsched setting is used. Use DEFAULT_EXTSCHED in lsb.queues to set default external scheduler options for a queue.
Options If you use the -o out_file,-e err_file, -oo out_file, or the -eo err_file option, and you want the specified file to be copied back to the submission host when the job completes, then you must use the -f option. If the submission and execution hosts have different directory structures, you must make sure that the directory where the remote file and local file are placed exists. If the local and remote hosts have different file name spaces, you must always specify relative path names.
Gets the standard input for the job from specified file. Specify an absolute or relative path. The input file can be any type of file, though it is typically a shell script text file. Unless you use -is, you can use the special characters %J and %I in the name of the input file. %J is replaced by the job ID. %I is replaced by the index of the job in the array, if the job is a member of an array, otherwise by 0 (zero). The special characters %J and %I are not valid with the -is option.
Options To change the maximum job array value, set MAX_JOB_ARRAY_SIZE in lsb.params to any positive integer between 1 and 2147483646. The maximum number of jobs in a job array cannot exceed the value set by MAX_JOB_ARRAY_SIZE. You may also use a positive integer to specify the system-wide job slot limit (the maximum number of jobs that can run at any given time) for this job array. All jobs in the array share the same job ID and parameters. Each element of the array is distinguished by its array index.
When a job is checkpointed, the checkpoint information is stored in checkpoint_dir/job_ID/file_name. Multiple jobs can checkpoint into the same directory. The system can create multiple files. The checkpoint directory is used for restarting the job (see brestart(1)). The checkpoint directory can be any valid path. Optionally, specifies a checkpoint period in minutes. Specify a positive integer. The running job is checkpointed automatically every checkpoint period.
Options If LSB_MEMLIMIT_ENFORCE or LSB_JOB_MEMLIMIT are set to y in lsf.conf, LSF kills the job when it exceeds the memory limit. Otherwise, LSF passes the memory limit to the operating system. UNIX operating systems that support RUSAGE_RSS for setrlimit() can apply the memory limit to each process. The following operating systems do not support the memory limit at the OS level: - Windows - Sun Solaris 2.x -m "host_name[@cluster_name][[!] | +[pref_level]] | host_group[[!] |+[pref_level]] ...
In the example, if host2 or a member of hostgroupA has two or more processors, the entire job runs on the first execution host. 3 If the first execution host does not have enough processors to run the entire job, LSF selects additional hosts that are not defined as first execution host candidates. Follow these guidelines when you specify first execution host candidates: ❖ If you specify a host group, you must first define the host group in the file lsb.hosts.
Options job slots, the maximum slots requested cannot be less than the minimum PROCLIMIT, and the minimum slots requested cannot be more than the maximum PROCLIMIT.
If you use the special character %J in the name of the output file, then %J is replaced by the job ID of the job. If you use the special character %I in the name of the output file, then %I is replaced by the index of the job in the array, if the job is a member of an array. Otherwise, %I is replaced by 0 (zero).
Options -P project_name Assigns the job to the specified project. On IRIX 6, you must be a member of the project as listed in /etc/project(4). If you are a member of the project, then /etc/projid(4) maps the project name to a numeric project ID. Before the submitted job executes, a new array session (newarraysess(2)) is created and the project ID is assigned to it using setprid(2). -p process_limit Sets the limit of the number of processes to process_limit for the whole job. The default is no limit.
◆ A resource usage section (rusage). The resource usage section specifies the expected resource consumption of the task. ◆ A job spanning section (span). The job spanning section indicates if a parallel batch job should span across multiple hosts. ◆ A same resource section (same). The same section indicates that all processes of a parallel job must run on the same type of host.
Options You configured a static shared resource for licenses for the Verilog application as a resource called verilog_lic.
Use -s to specify a signal number; when the run window closes, the job is signalled by this signal instead of being suspended. -sla service_class_name Specifies the service class where the job is to run. If the SLA does not exist or the user is not a member of the service class, the job is rejected. If EGO-enabled SLA scheduling is configured with ENABLE_DEFAULT_EGO_SLA in lsb.params, jobs submitted without -sla are attached to the configured default SLA. You can use -g with -sla.
Options -t [[month:]day:]hour:minute Specifies the job termination deadline. If a UNIX or Linux job is still running at the termination time, the job is sent a SIGUSR2 signal, and is killed if it does not terminate within ten minutes. If a Windows job is still running at the termination time, it is killed immediately. (For a detailed description of how these jobs are killed, see bkill.
To use an advance reservation on a remote host, submit the job and specify the remote advance reservation ID. For example: bsub -U user1#01@cluster1 In this example, we assume the default queue is configured to forward jobs to the remote cluster. -u mail_user Sends mail to the specified email destination.
Options If no host or host model is given, LSF uses the default runtime normalization host defined at the queue level (DEFAULT_HOST_SPEC in lsb.queues) if it has been configured; otherwise, LSF uses the default CPU time normalization host defined at the cluster level (DEFAULT_HOST_SPEC in lsb.params) if it has been configured; otherwise, LSF uses the submission host.
In dependency conditions, job names specify only your own jobs, unless you are the LSF administrator. By default, if you use the job name to specify a dependency condition, and more than one of your jobs has the same name, all of your jobs that have that name must satisfy the test. If JOB_DEP_LAST_SUB in lsb.params is set to 1, the test is done on the job submitted most recently. Use double quotes (") around job names that begin with a number.
Options If you specify the first word of the message description (no spaces), the text of the job’s status begins with the specified word. Only the first word is evaluated. job_ID | "job_name" If you specify a job without a dependency condition, the test is for the DONE state (LSF assumes the “done” dependency condition by default). numdone(job_ID, operator number | *) For a job array, the number of jobs in the DONE state satisfies the test. Use * (with no operator) to specify all the jobs in the array.
-wa 'signal' Specifies the job action to be taken before a job control action occurs. A job warning action must be specified with a job action warning time in order for job warning to take effect. If -wa is specified, LSF sends the warning action to the job before the actual control action is taken. This allows the job time to save its result before being terminated by the job control action. The warning action specified by -wa option overrides JOB_WARNING_ACTION in the queue.
Output command [argument] The job can be specified by a command line argument command, or through the standard input if the command is not present on the command line. The command can be anything that is provided to a UNIX Bourne shell (see sh(1)). command is assumed to begin with the first word that is not part of a bsub option. All arguments that follow command are provided as the arguments to the command.
Submit a batch interactive job that starts csh as an interactive shell. bsub -b 20:00 -J my_job_name my_program Submit my_program to run after 8 p.m. and assign it the job name my_job_name. bsub my_script Submit my_script as a batch job. Since my_script is specified as a command line argument, the my_script file is not spooled. Later changes to the my_script file before the job completes may affect this job. bsub < default_shell_script where default_shell_script contains: sim1.exe sim2.
Limitations Limitations When using account mapping, the command bpeek(1) does not work. File transfer via the -f option to bsub(1) requires rcp(1) to be working between the submission and execution hosts. Use the -N option to request mail, and/or the -o and -e options to specify an output file and error file, respectively. See also bjobs, bkill, bqueues, bhosts, bmgroup, bmod, bchkpnt, brestart, bgadd, bgdel, bjgroup, sh, getrlimit, sbrk, libckpt.a, lsb.users, lsbqueues, lsb.params, lsb.hosts, lsb.
bswitch switches unfinished jobs from one queue to another Synopsis bswitch [-J job_name] [-m host_name | -m host_group] [-q queue_name] [-u user_name | -u user_group | -u all] destination_queue [0] bswitch destination_queue [job_ID | "job_ID[index_list]"] ... bswitch [-h | -V] Description Switches one or more of your unfinished jobs to the specified queue. LSF administrators and root can switch jobs submitted by other users.
Limitations Only switches jobs submitted by the specified user, or all users if you specify the keyword all. To specify a Windows user account, include the domain name in uppercase letters and use a single backslash (DOMAIN_NAME\user_name) in a Windows command line or a double backslash (DOMAIN_NAME\\user_name) in a UNIX command line. If you specify a user group, switches jobs submitted by all users in the group. destination_queue Required. Specify the queue to which the job is to be moved. job_ID ...
btop moves a pending job relative to the first job in the queue Synopsis btop job_ID | "job_ID[index_list]" [position] btop [-h | -V] Description Changes the queue position of a pending job or a pending job array element, to affect the order in which jobs are considered for dispatch. By default, LSF dispatches jobs in a queue in the order of their arrival (that is, first come, first served), subject to availability of suitable server hosts.
See also step of one is assumed. The job array index starts at one. The maximum job array index is 1000. All jobs in the array share the same job_ID and parameters. Each element of the array is distinguished by its array index. position Optional. The position argument can be specified to indicate where in the queue the job is to be placed. position is a positive number that indicates the target position of the job from the beginning of the queue.
bugroup displays information about user groups Synopsis bugroup [-l] [-r] [-w] [user_group ...] bugroup [-h | -V] Description Displays user groups and user names for each group. The default is to display information about all user groups. Options -l Displays information in a long multi-line format. Also displays share distribution if shares are configured. -r Expands the user groups recursively. The expanded list contains only user names; it does not contain the names of subgroups.
busers busers displays information about users and user groups Synopsis busers [-w] [user_name ... | user_group ... | all] busers [-h | -V] Description Displays information about users and user groups. By default, displays information about the user who runs the command. Options user_name ... | user_group ... | all Displays information about the specified users or user groups, or about all users if you specify all.
pending jobs which have job slots reserved for them. (see the description of PREEMPTIVE in lsb.queues). If the character ‘–’ is displayed, there is no limit. MAX is defined by the MAX_JOBS parameter in the configuration file lsb.users(5). NJOBS The current number of job slots used by specified users’ jobs. A parallel job that is pending is counted as n job slots for it uses n job slots in the queue when it is dispatched. PEND The number of pending job slots used by jobs of the specified users.
ch ch changes the host on which subsequent commands are to be executed Synopsis ch [-S] [-t] [host_name] ch [-h | -V] Description Changes the host on which subsequent commands are to be executed. By default, if no arguments are specified, changes the current host to the home host, the host from which the ch command was issued. By default, executes commands on the home host. By default, shell mode support is not enabled. By default, does not display execution time of tasks.
-t Turns on the timing option. The amount of time each subsequent command takes to execute is displayed. host_name Executes subsequent commands on the specified host. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Usage The ch command interprets the following built-in commands: cd [directory_name] Changes the current working directory to the specified directory. If a directory is not specified, changes to the user’s home directory by default.
lsacct lsacct displays accounting statistics on finished RES tasks in the LSF system Synopsis lsacct [-l] [-C time0,time1] [-S time0,time1] [-f logfile_name] [-m host_name] [-u user_name ... | -u all] [pid ...] lsacct [-h | -V] Description Displays statistics on finished tasks run through RES. When a remote task completes, RES logs task statistics in the task log file. By default, displays accounting statistics for only tasks owned by the user who invoked the lsacct command.
-u user_name ... | -u all Displays accounting statistics for only tasks owned by the specified users, or by all users if the keyword all is specified. If a list of users is specified, user names must be separated by spaces and enclosed in quotation marks (") or (’). You can specify both user names and user IDs in the list of users.
Files Voluntary cont sw Number of voluntary context switches. Involuntary con sw Number of involuntary context switches. Turnaround Elapsed time from task execution to task completion. Per Task Statistics ( -l) In addition to the fields displayed by default in SUMMARY, displays the following fields for each task: Starting time Time the task started. User and host name User who submitted the task, host from which the task was submitted, in the format user_name@host.
lsacctmrg merges task log files Synopsis lsacctmrg [-f] logfile_name ... target_logfile_name lsacctmrg [-h | -V] Description Merges specified task log files into the specified target file in chronological order according to completion time. All files must be in the format specified in lsf.acct (see lsf.acct(5)). Options -f Overwrites the target file without prompting for confirmation. logfile_name ... Specify log files to be merged into the target file, separated by spaces.
lsadmin lsadmin administrative tool for LSF Synopsis lsadmin subcommand lsadmin [-h | -V] Description CAUTION: This command can only be used by LSF administrators. lsadmin is a tool that executes privileged commands to control LIM and RES operations in the LSF cluster. If no subcommands are supplied for lsadmin, lsadmin prompts for subcommands from the standard input. For subcommands for which multiple host names or host groups can be specified, do not enclose the multiple names in quotation marks.
-h -V Options subcommand Executes the specified subcommand. See Usage section. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Usage ckconfig [-v] Checks LSF configuration files. -v Displays detailed messages about configuration file checking. reconfig [-f] [-v] Restarts LIMs on all hosts in the cluster. You should use reconfig after changing configuration files. The configuration files are checked before all LIMs in the cluster are restarted.
Usage Disables interaction and does not ask for confirmation for shutting down LIMs. limrestart [-v] [-f] [host_name ... | all] Restarts LIM on the local host if no arguments are supplied. Restarts LIMs on the specified hosts or on all hosts in the cluster if the word all is specified. You are prompted to confirm LIM restart. limrestart should be used with care. Do not make any modifications until all the LIMs have completed the startup process. If you execute limrestart host_name...
Shuts down RESs on the specified hosts or on all hosts in the cluster if the word all is specified. You are prompted to confirm RES shutdown. If RES is running, it keeps running until all remote tasks exit. -f Disables interaction and does not ask for confirmation for shutting down RESs. resrestart [-f] [host_name ... | all] Restarts RES on the local host if no arguments are specified. Restarts RESs on the specified hosts or on all hosts in the cluster if the word all is specified.
Usage -c "class_name ..." Specify software classes for which debug messages are to be logged. If a list of classes is specified, they must be enclosed in quotation marks and separated by spaces. Possible classes: LC_AFS - Log AFS messages LC_AUTH - Log authentication messages LC_CHKPNT - log checkpointing messages LC_COMM - Log communication messages LC_CONF - Print out all parameters in lsf.conf (and ego.
If a file name without a path is specified, the file is saved in the LSF system log file directory. The name of the file created has the following format: logfile_name.daemon_name.log.host_name On UNIX, if the specified path is not valid, the log file is created in the /tmp directory. On Windows, no log file is created. Default: current LSF system log file in the LSF system log file directory, in the format daemon_name.log.host_name.
Usage Default: undefined (no timing information is logged) -f logfile_name Specify the name of the file into which timing messages are to be logged. A file name with or without a full path may be specified. If a file name without a path is specified, the file is saved in the LSF system log file directory. The name of the file created has the following format: logfile_name.daemon_name.log.host_name On UNIX, if the specified path is not valid, the log file is created in the /tmp directory.
LIM reads EGO_MASTER_LIST from wherever it is defined. You can define either LSF_MASTER_LIST in lsf.conf or EGO_MASTER_LIST in ego.conf. LIM reads lsf.conf first, and ego.conf if EGO is enabled in the LSF cluster. LIM only takes the value of LSF_MASTER_LIST if EGO_MASTER_LIST is not defined at all in ego.conf. For example, if EGO is enabled in the LSF cluster, and you define LSF_MASTER_LIST in lsf.conf, and EGO_MASTER_LIST in ego.conf, lsadmin showconf displays the value of EGO_MASTER_LIST in ego.conf.
lsclusters lsclusters displays configuration information about LSF clusters Synopsis lsclusters [-l] [cluster_name ...] lsclusters [-h | -V] Description Displays configuration information about LSF clusters. By default, returns information about the local cluster and all other clusters of which the local cluster is aware (all clusters defined in the RemoteClusters section of lsf.cluster.cluster_name if that section exists, otherwise all clusters defined in lsf.shared). Options -l Long format.
SERVERS Number of LSF server hosts in the cluster. Long Format (-l) If this option is specified, the command also lists available resource names, host types, host models and cluster administrator’s login names, and whether local cluster accepts or sends interactive jobs to this cluster. See also ls_info, ls_policy, ls_clusterinfo lsf.
lseligible lseligible displays whether a task is eligible for remote execution Synopsis lseligible [-r] [-q] [-s] task lseligible [-h | -V] Description Displays whether the specified task is eligible for remote execution. By default, only tasks in the remote task list are considered eligible for remote execution. Options -q Quiet mode. Displays only the resource requirement string defined for the task. The string ELIGIBLE or NON-ELIGIBLE is omitted. -r Remote mode.
lsfinstall runs lsfinstall, the Platform LSF installation and configuration script Synopsis lsfinstall -f install.config lsfinstall -s -f slave.config lsfinstall -h Description lsfinstall runs the LSF installation scripts and configuration utilities to install a new Platform LSF cluster or upgrade LSF from a previous release. To install a fully operational LSF cluster that all users can access, you should install as root. You can run lsfinstall as a non-root user, with limitations. Required install.
Description After installation, you should run hostsetup to set up each server host in the cluster. After setting up the server hosts, you should start your cluster and test the installation by running some basic commands. Where lsfinstall is located lsfinstall is included in the LSF installation script tar file lsf7Update3_lsfinstall.tar.Z and is located in the lsf7Update3_lsfinstall directory created when you uncompress and extract installation script tar file.
❖ Put the distribution files in the same directory as lsf7Update3_lsfinstall.tar.Z TIP: Do not uncompress and extract the distribution tar files. ❖ Get a valid license key and create a license file (license.dat) in the same directory as the distribution files and lsf7Update3_lsfinstall.tar.Z. CAUTION: If you do not specify a license file with LSF_LICENSE, or lsfinstall cannot find a license file in the default location, lsfinstall exits.
Description ◆ Multi-user—By default, only root can start the LSF daemons. Any user can submit jobs to your cluster. To make the cluster available to other users, you must manually change the ownership and setuid bit for lsadmin and badmin to root, and the file permission mode to -rwsr-xr-x (4755) so that the user ID bit for the owner is setuid.
hostsetup example The following example sets up a host to use the cluster installed in /usr/share/lsf. It also configures the LSF daemons to start automatically (--boot="y"): # hostsetup --top="/usr/share/lsf" --boot="y" Running host setup remotely (rhostsetup) Use the rhostsetup script to launch hostsetup on remote hosts. rhostsetup uses either ssh or rsh. It is included in the installation script tar file lsf7Update3_lsfinstall.tar.
See also Optional parameters: LSF_LIM_PORT=port_number If the master host does not use the default LSF_LIM_PORT, you must specify the same LSF_LIM_PORT defined in lsf.conf on the master host. LSF_LOCAL_RESOURCES="resource ..." Defines the local resources for a dynamic host.
lsfmon installs or uninstalls LSF Monitor Synopsis lsfmon -install lsfmon -remove Description Installs or uninstalls LSF Monitor in an existing cluster. LSF Monitor runs on Microsoft Windows and allows you to use Windows Performance Monitor to chart information about the LSF cluster. The LSF Monitor service runs under the account of an LSF cluster administrator. Options -install Installs LSF Monitor on the host. -remove Removes LSF Monitor from the host.
lsfrestart lsfrestart restarts LIM, RES, sbatchd and mbatchd on all hosts in the cluster Synopsis lsfrestart [-f | -h | -V] Description CAUTION: This command can only be used by root or users listed in lsf.sudoers. Restarts LIM, RES, sbatchd and mbatchd, in that order, on all hosts in the local cluster. By default, prompts for confirmation of the next operation if an error is encountered. In order to be able to control all daemons in the cluster: ◆ The file /etc/lsf.sudoers has to be set up properly.
lsfshutdown shuts down LIM, RES, sbatchd and mbatchd on all hosts in the cluster Synopsis lsfshutdown [-f | -h | -V] Description CAUTION: This command can only be used by root or users listed in lsf.sudoers. Shuts down sbatchd, RES, LIM, and mbatchd, in that order, on all hosts. By default, prompts for confirmation of the next operation if an error is encountered. In order to be able to control all daemons in the cluster: ◆ The file /etc/lsf.sudoers has to be set up properly.
lsfstartup lsfstartup starts LIM, RES, sbatchd, and mbatchd on all hosts in the cluster Synopsis lsfstartup [-f ] lsfstartup [-h | -V] Description CAUTION: This command can only be used by root or users listed in lsf.sudoers. Starts LIM, RES, sbatchd, and mbatchd, in that order, on all hosts. By default, prompts for confirmation of the next operation if an error is encountered.
lsgrun executes a task on a set of hosts Synopsis lsgrun [-i] [-p | -P | -S] [-v] -f host_file | -m host_name ... | -n num_hosts [-R "res_req"] [command [argument ...]] lsgrun [-h | -V] Description Executes a task on the specified hosts. lsgrun is useful for fast global operations such as starting daemons, replicating files to or from local disks, looking for processes running on all hosts, checking who is logged in on each host, and so on.
Options -S Creates a pseudo-terminal with shell mode support on UNIX hosts. Shell mode support is required for running interactive shells or applications which redefine the CTRL-C and CTRL-Z keys (such as jove). This option is not supported on Windows. -v Verbose mode. Displays the name of the host or hosts running the task. -f host_file Either -f host_file, -m host_name or -n num_processors is required. Executes the task on all hosts listed in the host_file.
Diagnostics Exit status is 0 if all commands are executed correctly. Otherwise, the exit status is the first non-zero status returned by a remotely executed task. lsgrun executes the task on all hosts even if some have non-zero exit status. Exit status is -10 if a problem is detected in LSF.
lshosts lshosts displays hosts and their static resource information Synopsis lshosts [-w | -l] [-R "res_req"] [host_name | cluster_name] ... lshosts -s [resource_name ...] lshosts [-h | -V] Description Displays static resource information about hosts. By default, returns the following information: host name, host type, host model, CPU factor, number of CPUs, total memory, total swap space, whether or not the host is a server host, and static resources.
For MultiCluster, displays information about hosts in the specified clusters. The names of the hosts belonging to the cluster are displayed instead of the name of the cluster. Do not use quotes when specifying multiple clusters. -s [resource_name ...] Displays information about the specified resources. The resources must be static resources (shared or host-based). If no resource is specified, then displays information about all resources.
Output ncores The number of cores per processor configured on a host. nthreads The number of threads per core configured on a host. maxmem The maximum amount of physical memory available for user processes. By default, the amount is displayed in KB. The amount may appear in MB depending on the actual system memory. Use LSF_UNIT_FOR_LIMITS in lsf.conf to specify a larger unit for the limit (GB, TB, PB, or EB). maxswp The total available swap space. By default, the amount is displayed in KB.
If LSF_ENABLE_DUALCORE=Y in lsf.conf for dual-core CPU hosts, lshosts -l also displays if dual-core CPU license is enabled for the hosts and the number of dual-core licenses needed. LOAD_THRESHOLDS The thresholds for scheduling interactive jobs. If a load index exceeds the load threshold (or falls below the load threshold, for decreasing load indices), the host status is changed to “busy.” If the threshold is displayed as a dash “-”, the value of that load index does not affect the host’s status.
lsid lsid displays the current LSF version number, the cluster name, and the master host name Synopsis lsid [-h | -V] Description Displays the current LSF version number, the cluster name, and the master host name. The master host is dynamically selected from all hosts in the cluster. In MultiCluster, the master host is dynamically selected from all hosts in the local cluster. Options -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits.
lsinfo displays load sharing configuration information Synopsis lsinfo [-l] [-m | -M] [-r] [-t] [resource_name ...] lsinfo [-h | -V] Description By default, displays all load sharing configuration information including resource names and their meanings, host types and models, and associated CPU factors known to the system. By default, displays information about all resources. Resource information includes resource name, resource type, description, and the default sort order for the resource.
See also ◆ Dec—If the numeric value decreases as the load increases. ◆ N/A—If the resource is not numeric. INTERVAL The number of seconds between updates of that index. Load indices are updated every INTERVAL seconds. A value of 0 means the value never changes. BUILTIN If BUILTIN is Yes, the resource name is defined internally by LIM. If BUILTIN is No, the resource name is site-specific defined externally by the LSF administrator.
lsload displays load information for hosts Synopsis lsload [-l] [-N | -E] [-I load_index[:load_index] ...] [-n num_hosts] [-R res_req] [host_name ... | cluster_name ...] lsload -s [resource_name ...] lsload [-h | -V] Description Displays load information for hosts. Load information can be displayed on a per-host basis, or on a per-resource basis. By default, displays load information for all hosts in the local cluster, per host.
Output If res_req contains special resource names, only load information for hosts that provide these resources is displayed (run lshosts to find out what resources are available on each host). If one or more host names are specified, only load information about the hosts that satisfy the resource requirements is displayed. With MultiCluster, when a cluster name is specified, displays load information of hosts in the specified cluster that satisfy the resource requirements. host_name ... | cluster_name ...
The host is locked by its run window. Run windows for a host are specified in the configuration file (see lsf.conf(5)) and can be displayed by lshosts. A locked host does not accept load shared jobs from other hosts. lockU The host is locked by the LSF administrator or root. unavail The host is down or the LIM on the host is not running. unlicensed The host does not have a valid LSF license. r15s The 15-second exponentially averaged CPU run queue length.
Examples If -I load_index is specified, only shows indices for specified non-shared (host-based) dynamic numeric custom resources. Resource-Based Output (lsload -s) Displays information about dynamic resources (shared or host-based). Each line gives the value and the associated hosts for an instance of the resource. See lim(8), and lsf.cluster(5) for information on configuring dynamic shared resources. The displayed information consists of the following fields: RESOURCE Name of the resource.
lsloadadj adjusts load indices on hosts Synopsis lsloadadj [-R res_req] [host_name[:num_task] ...] lsloadadj [-h | -V] Description Adjusts load indices on hosts. This is useful if a task placement decision is made outside LIM by another application. By default, assumes tasks are CPU-intensive and memory-intensive. This means the CPU and memory load indices are adjusted to a higher number than other load indices.
Examples Examples lsloadadj -R "rusage[swp=20:mem=10]" Adjusts the load indices swp and mem on the host from which the command was submitted. Diagnostics Returns -1 if a bad parameter is specified; otherwise returns 0.
lslogin remotely logs in to a lightly loaded host Synopsis lslogin [-v] [-m "host_name ..." | -m "cluster_name ..."] [-R "res_req"] [rlogin_options] lslogin [-h | -V] Description Remotely logs in to a lightly loaded host. By default, lslogin selects the least loaded host, with few users logged in, and remotely logs in to that host using the UNIX rlogin command. In a MultiCluster environment, the default is to select the least loaded host in the local cluster.
Diagnostics Diagnostics Because lslogin passes all unrecognized arguments to rlogin, incorrect options usually cause the rlogin usage message to be displayed rather than the lslogin usage message.
lsltasks displays or updates a local task list Synopsis lsltasks [+ task_name ... | – task_name ...] lsltasks [-h | -V] Description Displays or updates a user local task list in $HOME/.lsftask. When no options are specified, displays tasks listed in the system task file lsf.task and the user task file .lsftask. If there is a conflict between the system task file lsf.task and the user task file (.lsftask), the user task file overrides the system task file.
See also The system and user task files contain two sections, one for the remote task list, the other for the local task list. The local tasks section starts with Begin LocalTasks and ends with End LocalTasks. Each line in the section is an entry consisting of a task name. A plus sign (+) or a minus sign (–) can optionally precede each entry. If no + or – is specified, then + is assumed. See also lseligible, ls_task, lsrtasks, lsf.
lsmon displays load information for LSF hosts and periodically updates the display Synopsis lsmon [-N | -E] [-n num_hosts] [-R res_req] [-I index_list] [-i interval] [-L file_name] [host_name ...] lsmon [-h | -V] Description lsmon is a full-screen LSF monitoring utility that displays and updates load information for hosts in a cluster. By default, displays load information for all hosts in the cluster, up to the number of lines that fit on-screen. By default, displays raw load indices.
Usage If you do not want load information to be displayed on your screen at the same time, use lsmon -L file_name < /dev/null. The format of the file is described in lim.acct(5). host_name ... Displays only load information for the specified hosts. -h Prints command usage to stderr and exits. -V Prints LSF release version to stderr and exits. Usage You can use the following commands while lsmon is running: [^L | i | n | N | E | R | q] ^L Refreshes the screen. i Prompts you to input a new update interval.
The host is locked by its run window. Run windows for a host are specified in lsf.conf and can be displayed by lshosts. A locked host does not accept load shared jobs from other hosts. lockU The host is locked by the LSF administrator or root. unavail The host is down or the Load Information Manager (LIM) on the host is not running. unlicensed The host does not have a valid LSF license. r15s The 15-second exponentially averaged CPU run queue length.
Diagnostics Diagnostics Specifying an incorrect resource requirement string while lsmon is running (via the R option) causes lsmon to exit with an appropriate error message. lsmon exits if it does not receive a reply from LIM within the update interval. See also lshosts, lsinfo, lsload, lslockhost, lim.
lspasswd registers user passwords in LSF on Windows Synopsis lspasswd [-u user_name] [-p password] lspasswd [-r] [-u user_name] lspasswd [-c] [-u user_name] [-p password] lspassword [-h | -V] Description Registers user passwords in LSF on Windows. Passwords must be longer than 3 characters and 31 characters or less. By default, if no options are specified, the password applies to the user who issued the command.
lsplace lsplace displays hosts available to execute tasks Synopsis lsplace [-L] [-n minimum | -n 0] [-R res_req] [-w maximum | -w 0] [host_name ...] lsplace [-h | -V] Description Displays hosts available for the execution of tasks, and temporarily increases the load on these hosts (to avoid sending too many jobs to the same host in quick succession). The inflated load decays slowly over time before the real load produced by the dispatched task is reflected in the LIM’s load information.
In order for a job to land on a host with an exclusive resource, you need to explicitly specify that resource for the resource requirements. The following example issues a command to display the host with the bigmem exclusive resource for your program to run on: lsrun -m ‘lsplace -R "bigmem"‘ myprogram The -w and -n options can be combined to specify the upper and lower bounds in processors to be returned, respectively.
lsrcp lsrcp remotely copies files using LSF Synopsis lsrcp [-a] source_file target_file lsrcp [-h | -V] Description Remotely copies files using LSF. lsrcp is an LSF-enabled remote copy program that transfers a single file between hosts in an LSF cluster. lsrcp uses RES on an LSF host to transfer files. If LSF is not installed on a host or if RES is not running then lsrcp uses rcp to copy the file. To use lsrcp, you must have read access to the file being copied.
Always use "/" to transfer files from a UNIX host to a Windows host, or from a Windows host to a UNIX host. This is because the operating system interprets "\" and lsrcp opens the wrong files. For example, to transfer a file from UNIX to a Windows host: lsrcp file1 hostA:c:/temp/file2 To transfer a file from Windows to a UNIX host: c:\share>lsrcp file1 hostD:/home/usr2/test/file2 file_name Name of source file. File name expansion is not supported. -h Prints command usage to stderr and exits.
See also ◆ rcp on UNIX. If lsrcp cannot contact RES on the submission host, it attempts to use rcp to copy the file. You must set up the /etc/hosts.equiv or HOME/.rhosts file in order to use rcp. See the rcp(1), rsh(1), ssh(1) manual pages for more information on using the rcp, rsh, and ssh commands. ◆ You can replace lsrcp with your own file transfer mechanism as long as it supports the same syntax as lsrcp.
lsrtasks displays or updates a remote task list Synopsis lsrtasks [+ task_name[/res_req] ... | – task_name[/res_req] ...] lsrtasks [-h | -V] Description Displays or updates a user’s remote task list in $HOME/.lsftask. When no options are specified, displays tasks listed in the system task file lsf.task and the user’s task file (.lsftask). If there is a conflict between the system task file lsf.task and the user task file, the user task file overrides the system task file.
Examples Prints LSF release version to stderr and exits. Examples % lsrtasks + task1 task2/"select[cpu && mem]" - task3 or in restricted form: % lsrtasks + task1 task2/cpu:mem - task3 Adds the command task1 to the remote task list with no resource requirements, adds task2 with the resource requirement cpu:mem, and removes task3 from the remote task list. % lsrtasks + myjob/swap>=100 && cpu Adds myjob to the remote tasks list with its resource requirements.
lsrun runs an interactive task through LSF Synopsis lsrun [-l] [-L] [-P] [-S] [-v] [-m "host_name ..." | -m "cluster_name ..."] [-R "res_req"] command [argument ...] lsrun [-h | -V] Description Submits a task to LSF for execution. With MultiCluster job forwarding model, the default is to run the task on a host in the local cluster. By default, lsrun first tries to obtain resource requirement information from the remote task list to find an eligible host. (See lseligible(1) and ls_task(3).
Usage With MultiCluster job forwarding model, the execution host can be a host in one of the specified clusters, if the remote cluster accepts tasks from the local cluster. (See RemoteClusters section in lsf.cluster(5).) -R "res_req" Runs the task on a host that meets the specified resource requirement. The size of the resource requirement string is limited to 512 bytes. For a complete explanation of resource requirement expressions, see Administering Platform LSF.
lstcsh load sharing tcsh for LSF Synopsis lstcsh [tcsh_options] [-L] [argument ...] Description lstcsh is an enhanced version of tcsh. lstcsh behaves exactly like tcsh, except that it includes a load sharing capability with transparent remote job execution for LSF. By default, a lstcsh script is executed as a normal tcsh script with load sharing disabled.
Usage There are three ways to run a lstcsh script with load sharing enabled: - Execute the script with the -L option - Use the built-in command source to execute the script - Insert "#!/local/bin/lstcsh -L" as the first line of the script (assuming you install lstcsh in /local/bin). Using @ or lsmode in a script does not enable load sharing if the script has not been executed using one of these three ways.
@ : Specify @ followed by nothing to indicate the command line is eligible for remote execution. @ host_name : Specify @ followed by a host name to force the command line to be executed on that host. Host names and the reserved word local following @ can all be abbreviated as long as they do not cause ambiguity. @ local : Specify @ followed by the reserved word local to force the command line to executed on the local host.
Files This command has the same function as the external command lsrtasks, except that the modified remote task list takes effect immediately for the current lstcsh session. See lsrtasks(1) for more details. lsltasks [+ task_name ... | - task_name ...] Displays or update a user’s local task list in the user’s task list $HOME/.lsftask. This command has the same function as the external command lsltasks, except that the modified local task list takes effect immediately for the current lstcsh session.
Limitations Type-ahead for the next command is discarded when a job is executing in the foreground on a remote host. It is not possible to provide input data to load sharing shell scripts (that is, shell scripts whose content is load shared). The lstcsh is fully compatible with tcsh 6.03 7-bit mode. Any feature that is not included in tcsh 6.03 is not supported.
pam pam Parallel Application Manager – job starter for MPI applications Synopsis HP-UX vendor MPI syntax bsub pam -mpi mpirun [mpirun_options ] mpi_app [argument ...] SGI vendor MPI syntax bsub pam [-n num_tasks ] -mpi -auto_place mpi_app [argument ...] Generic PJL framework syntax bsub pam [-t] [-v] [-n num_tasks ] -g [num_args] pjl_wrapper [pjl_options] mpi_app [argument ...] pam [-h] [-V] Description The Parallel Application Manager (PAM) is the point of control for Platform LSF.
Task startup for LSF HPC generic PJL jobs For parallel jobs submitted with bsub: ◆ PAM invokes the PJL, which in turn invokes the TaskStarter (TS). ◆ TS starts the tasks on each execution host, reports the process ID to PAM, and waits for the task to finish. Options Options for vendor MPI jobs -auto_place The -auto_place option on the pam command line tells the SGI IRIX mpirun library to launch the MPI application according to the resources allocated by LSF.
Exit Status Options for LSF HPC generic PJL jobs -t This option tells pam not to print out the MPI job tasks summary report to the standard output. By default, the summary report prints out the task ID, the host on which it was executed, the command that was executed, the exit status, and the termination time. -v Verbose mode. Displays the name of the execution host or hosts. -g [num_args] pjl_wrapper [pjl_options] The -g option is required to use the LSF generic PJL framework.
patchinstall UNIX only. Manage patches in a licensed Platform cluster. Synopsis patchinstall [-f env_file] [--silent] package... patchinstall -c [-f env_file] [--silent] package...
Output Checks that your user account has permission to write to the installation directory, backup directory, and history directory. Lists existing files that will be overwritten by the patch. Lists files that to be added by the patch. -f env_file This option should only be used if you cannot set your environment (for example, you cannot source cshrc.lsf or profile.lsf). Specify the full path and file name of a file (such as your LSF install.config file) that properly defines the parameter LSF_TOP.
pmcadmin Administer the Platform Management Console (PMC). Synopsis pmcadmin [start | stop | list | addrtm URL | -h ] Description CAUTION: This command can only be used by LSF administrators. Always run this command on the host that runs PMC. This command is used to administer the PMC. Options start Starts the Platform Management Console on the local host. stop Stops the Platform Management Console on the local host. list Status of the PMC service on the local host. addrtm URL RTM only.
pmcremoverc pmcremoverc Prevents automatic startup of the Platform Management Console (PMC) on a UNIX host. Synopsis pmcremoverc Description This is an administrative command. You must be logged on as root to issue this command. Prevents automatic startup of PMC on a UNIX host when a system reboot command is issued. After this command is issued, PMC no longer starts automatically if the host gets rebooted. In such a case, you must manually start PMC after the host has started up.
pmcsetrc Configures automatic startup of the Platform Management Console (PMC) on a UNIX host. Synopsis pmcsetrc Description Configures a UNIX host to allow automatic startup of PMC on the machine when a system reboot command is issued. Creates the file pmc under the system startup directory. This is an administrative command. You must be logged on as root to issue this command. For ease of administration, you should enable automatic startup. This starts PMC automatically when the host restarts.
perfadmin perfadmin Administer the LSF Reports (PERF) services. Synopsis perfadmin start service_name | all perfadmin stop service_name | all perfadmin [list | -h] Description CAUTION: This command can only be used by LSF administrators. Starts or stops the PERF services, or shows status. Run the command on the PERF host to control the following PERF services: loader controller (plc), job data transformer (jobdt), and data purger (purger).
Service status is unknown. The local host may not be the PERF host or Derby database host. HOSTNAME Name of the host. WSM_PID Process ID of the running service.
perfremoverc perfremoverc Prevents automatic startup of the LSF Reporting (PERF) daemons on a UNIX host. Synopsis perfremoverc Description This is an administrative command. You must be logged on as root to issue this command. Prevents automatic startup of PERF daemons on a UNIX host when a system reboot command is issued. After this script/command is issued, PERF daemons no longer start automatically if the host gets rebooted.
perfsetrc Configures automatic startup of the LSF Reporting (PERF) daemons on a UNIX host. Synopsis perfsetrc Description This is an administrative command. You must be logged on as root to issue this command. Configures a UNIX host to allow automatic startup of PERF daemons on the machine when a system reboot command is issued. Creates the file perf under the system startup directory. For ease of administration, you should enable automatic startup.
pversions (Windows) pversions (Windows) Windows version of the command: displays the version information for Platform products installed on a Windows host. Synopsis pversions [product_name] pversions -h pversions -V Description Displays the version and patch level of a Platform product installed on a Windows host, and the list of patches installed. Options product_name Specify the Platform product for which you want version information.
pversions (UNIX) UNIX version of the command: displays the version information for Platform products installed on UNIX hosts. Synopsis pversions [-f env_file] [-p product_name] pversions [-f env_file] -b build_number pversions [-f env_file] -q file_name pversions -c package_name pversions -h Description By default, displays the version and patch level of Platform products.
Output -q file_name Specify the file name of one installed file. For each binary type, displays basic version information and file location. If the binary has been updated after the most recent full installation, displays additional information about the most recent patch that updated the file (build number, fixes, notes, date installed) -h Outputs command usage and exits. Output Information is displayed in your command console.
last patched For the last patch to update the file after the most recent full installation, displays build number and date patch was installed. last patch notes Optional. Some information provided by Platform for the last patch that updated the file. last patch fixes Fixes included in the last patch that updated the file. Build Version Information (-b) With -b, displays information for patches with the specified build number only.
ssacct ssacct displays accounting statistics about finished Session Scheduler jobs Synopsis ssacct [-l] job_ID | [task_ID | "task_ID[index]"] ssacct [-l] "job_ID [index]"] [task_ID | "task_ID[index]"] ssacct [-l] -f log_file [job_ID | [task_ID | "task_ID[index]"]] ssacct [-l] -f log_file ["job_ID [index]"] [task_ID | "task_ID[index]"]] ssacct -h | -V Description By default, displays accounting statistics for all finished jobs submitted by the user who invoked the command. Options -l Long format.
Output Summary (default format) Statistics on all tasks in the session.
Examples Examples Default format ssacct 108 1[1] Accounting information about tasks that are: - submitted by all users. - completed normally or exited. - executed on all hosts. -----------------------------------------------------------------------------SUMMARY: ( time unit: second ) Total number of done tasks: Total CPU time consumed: 1 0.0 Maximum CPU time of a task: Total wait time: Total number of exited tasks: Average CPU time consumed: 0 0.0 Minimum CPU time of a task: 0.0 0.0 2.
Maximum CPU time of a task: Total wait time: 0.0 Minimum CPU time of a task: 0.0 2.0 Average wait time: 2.0 Maximum wait time: 2.0 Minimum wait time: Average turnaround time: 3 (seconds/task) Maximum turnaround time: 3 Average hog factor of a task: Maximum hog factor of a task : 2.0 Minimum turnaround time: 3 0.01 ( cpu time / turnaround time ) 0.01 Minimum hog factor of a task: 0.01 Files Reads job_ID.ssched.acct See also ssched, lsb.
ssched ssched submit tasks through Platform LSF Session Scheduler Synopsis ssched [options] command ssched [options] -tasks task_definition_file ssched [options] -tasks task_definition_file command ssched [-h | -V] Description Options can be specified on the ssched command line or on a line in a task definition file. If specified on the command line, the option applies to all tasks, whether specified on the command line or in a file. Options specified in a file apply only to the command on that line.
-i input_file -J task_name[index_list] -j "starter [starter] [%USRCMD] [starter]" -M mem_limit -o out_file -Q "exit_code ..." -W [minutes:]seconds -h -V Option Descriptions Command options -1 | -2 | -3 Enables increasing amounts of debug output -C Sanity check all parameters and the task definition file. Exit immediately after the check is complete. An exit code of 0 indicates no errors were found. Any non-zero exit code indicates an error. ssched -C can be run outside of LSF.
Option Descriptions If the parameter LSB_STDOUT_DIRECT in lsf.conf is set to Y or y, the standard error output of a task is written to the file you specify as the job runs. If LSB_STDOUT_DIRECT is not set, standard error output of a task is written to a temporary file and copied to the specified file after the task finishes. You can use the special characters %J, %I, %T, %X in the name of the input file. %J is replaced by the job ID.
If only a file name is specified, LSF writes the output file to the current working directory. If the current working directory is not accessible on the execution host after the task starts, LSF writes the standard output file to /tmp/. If the parameter LSB_STDOUT_DIRECT in lsf.conf is set to Y or y, the standard output of a task is written to the file you specify as the task runs. If LSB_STDOUT_DIRECT is not set, it is written to a temporary file and copied to the specified file after the task finishes.
See also See also ssacct, lsb.
taskman checks out a license token and manages interactive UNIX applications Synopsis taskman -Lp project -R “rusage[token=number[:duration=minutes | hoursh] [:token=number[:duration=minutes | hoursh]]...] [-N n_retries] [-v] command taskman [-h | -V] Description Runs the interactive UNIX application on behalf of the user. When it starts, the task manager connects to License Scheduler to request the application license tokens.
tspeek tspeek displays the stdout and stderr output of an unfinished Terminal Services job Synopsis tspeek job_ID tspeek [-h | -V] Description Displays the standard output and standard error output that have been produced by one of your unfinished Terminal Services jobs, up to the time that this command is invoked. This command is useful for monitoring the progress of a job and identifying errors.
tssub submits a Terminal Services job to LSF Synopsis tssub [bsub_options] command [arguments] tssub [-h | -V] Description Submits a Terminal Services job for batch execution and assigns it a unique numerical job ID. tssub is a wrapper around the bsub command which only submits jobs to hosts that have Microsoft Terminal Services installed. For bsub options, see the bsub command. You submit Terminal Services job with tssub instead of bsub. If the terminal window is closed, the job remains running.
Options Limitations ◆ You cannot use bmod to modify a job submitted as a Terminal Services job to become a non-Terminal Services job ◆ The bsub option -o out_file is not supported for tssub ◆ Only Windows bsub options are supported for tssub. For example, you cannot use the options -Ip, -Is, -L login_shell of bsub with tssub.
wgpasswd changes a user’s password for an entire Microsoft Windows workgroup Synopsis wgpasswd [user_name] wgpasswd [-h] Description You must run this command on a host in a Windows workgroup. You must have administrative privileges to change another user’s password. Prompts for old and new passwords, then changes the password on every host in the workgroup. By default, modifies your own user account. Options user_name Specifies the account to modify.
wguser wguser modifies user accounts for an entire Microsoft Windows workgroup Synopsis wguser [-r] user_name ... wguser [-h] Description CAUTION: You must run this command on a host in a Microsoft Windows workgroup. You should have administrative privileges on every host in the workgroup. Modifies accounts on every host in the workgroup that you have administrative privileges on.
Index A ABS_RUNLIMIT, lsb.
Index bacct -b 11 ssacct -l 299 CPU_TIME, bhpart 59 CPUF, bhosts -l 55 cpuf, lshosts 247 CPULIMIT bapp -l 18 bqueues -l 132 CPUSET_OS, brlainfo 150 CREATOR, bacct -U 12 CURRENT LOAD, bhosts -l 56 CWD bacct -l 11 bjobs -l 71 lsacct -l 220 D DATALIMIT bapp -l 19 bqueues -l 133 DEFAULT HOST SPECIFICATION, bqueues -l 136 Default queue indication, bqueues -l 130 DEFAULT_EXTSCHED, lsb.queues file, bsub -ext 187 DEFAULT_HOST_SPEC lsb.params file, bsub -c 184 lsb.queues file, bsub -c 184 DEFAULT_QUEUE, lsb.
Index bacct -l 11 ssacct -l 299 HOST, blusers output 111, 112 HOST_NAME bhosts 53 lshosts 247 lsload 254 lsmon 264 HOST_PARTITION_NAME, bhpart 58 HOSTNAME, brlainfo 150 HOSTS bhpart 58 blimits 91 blinfo output 97 blparams output 100 bqueues -l 137 lsclusters 230 hosts lost_and_found 53, 71 lsfinstall command 234 hostsetup command, example 237 hostsetup script, lsfinstall command 236 I idle job exception bacct -l -x 12 bjobs -l 74 bqueues -l 135 IDLE_FACTOR, bjobs -l 73 IGNORE_DEADLINE bqueues -l 135 lsb.
Index LOAD THRESHOLD, bhosts -l 56 LOAD_THRESHOLDS, lshosts -l 249 loadSched bhosts -l 54 bjobs -l 72 loadStop bhosts -l 54 bjobs -l 72 LOCAL_QUEUE, bclusters 38 LOCATION bhosts -s 56 lshosts -s 249 lsload -s 256 lost_and_found host 53, 71 lost_and_found queue 91 bqueues 70 lost_and_found queue name, bqueues 129 ls bqueues -l 134 lsload 255 lsmon 265 LS_MAX_TASKMAN_SESSIONS blinfo output 97 blparams output 101 LSF administrator, lsfinstall command 234 LSF_DESERVE, blstat output 106 LSF_ENABLE_EXTSCHEDULER,
Index bsla 169 busers 215 NJOBS bhosts 54 NLICS, blusers output 111 NNODES, brlainfo 150 NO_INTERACTIVE, bqueues -l 135 NON_LSF_DESERVE, blstat output 106 NON_LSF_FREE, blstat output 106 NON_LSF_USE, blstat output 106 NON_SHARED blinfo output 96 blstat output 107 NON-SHARED_DISTRIBUTION, blinfo output 95 nprocs lshosts 247 lshosts -l 248 NQS DESTINATION QUEUES, bqueues -l 137 NSTATIC_CPUSETS, brlainfo 150 NTASKS, blusers output 111 NTHREAD, bjobs -l 73 nthreads lshosts 248 lshosts -l 248 NUM_RECALLED_HOSTS,
Index PROJECT blinfo output 95 blstat output 106 blusers output 112 Project bhist -l 48 bjobs -l 71 PROJECT/GROUP, blstat output 107 PROJECT_NAME, bacct -l 11 PROJECTS, blimits 91 PSUSP bhist 48 bjobs -A 75 bjobs -l 72 Q QUEUE bacct -b 11 bjobs 70 QUEUE_NAME, bqueues 129 QUEUES, blimits 91 queues, lost_and_found 70, 91 R r15m bqueues -l 133 lsload 255 lsmon 265 r15s bqueues -l 133 lsload 255 lsmon 265 r1m bqueues -l 133 lsload 255 lsmon 265 RECALLED_HOSTS_TIMEOUT, bsla 168 RECEIVE_JOBS_FROM, bqueues -l 13
Index S Schedule delay for a new job, bqueues -l 131 SCHEDULING PARAMETERS, bqueues -l 133 SCHEDULING POLICIES bqueues -l 135 bqueues -r 139 secure shell 271 SEND_JOBS_TO, bqueues -l 138 server, lshosts 248 server hosts, lsfinstall command 234 SERVERS, lsclusters 231 SERVICE CLASS NAME, bsla 167 SERVICE_DOMAIN blinfo output 94, 95 blstat output 105 blusers output 111, 112 SHARE, blstat output 106 SHARE_INFO_FOR, blstat output 107 SHARES bhpart 58 blinfo output 96 SLA bjgroup default output 64 job slots (-N
Index top-level installation directory (LSF_TOP) 234 TOTAL bhist 48 bhosts -s 56 blinfo output 94 Total number of tasks, lsacct 219 TOTAL_FREE, blstat output 106 TOTAL_INUSE, blstat output 105 TOTAL_RESERVE, blstat output 105 TURNAROUND bacct -b 11 ssacct -l 299 Turnaround, lsacct 220 TYPE bacct -U 12 lsinfo -l 251 type, lshosts 247 U U/UID, bacct -b 11 underrun job exception bacct -l -x 12 bjobs -l 74 bqueues -l 135 UNKNOWN, blusers output 112 UNKWN bhist 48 bjobs -l 72 USER bacct -U 12 bjobs 70 blusers o