mopdf.com

bacctThe specified file path can contain up to 4094 characters for UNIX, or up to512 characters for Windows.-Lp ls project name .Displays accounting statistics for jobs belonging to the specified LicenseScheduler projects. If a list of projects is specified, project names must beseparated by spaces and enclosed in quotation marks (") or (').-M host list fileDisplays accounting statistics for jobs dispatched to the hosts listed in a file(host list file) containing a list of hosts. The host list file has the followingformat:v Multiple lines are supportedv Each line includes a list of hosts separated by spacesv The length of each line must be less than 512 characters-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 andenclosed in quotation marks (") or ('), and maximum length cannot exceed 1024characters.-N host name -N host model -N cpu factorNormalizes CPU time by the CPU factor of the specified host or host model, orby the specified CPU factor.If you use bacct offline by indicating a job log file, you must specify a CPUfactor.-P project name .Displays accounting statistics for jobs belonging to the specified projects. If alist of projects is specified, project names must be separated by spaces andenclosed in quotation marks (") or ('). You cannot use one double quote andone single quote to enclose the list.-q queue name .Displays accounting statistics for jobs submitted to the specified queues.If a list of queues is specified, queue names must be separated by spaces andenclosed in quotation marks (") or (').-S time0,time1Displays accounting statistics for jobs submitted during the specified timeinterval. Reads lsb.acct and all archived log files (lsb.acct.n) unless -f isalso used.The time format is the same as in bhist.-sla service class nameDisplays accounting statistics for jobs that ran under the specified service class.If a default system service class is configured withENABLE DEFAULT EGO SLA in lsb.params but not explicitly configured inlsb.applications, bacct -sla service class name displays accountinginformation for the specified default service class.-U reservation id . -U allDisplays accounting statistics for the specified advance reservation IDs, or forall reservation IDs if the keyword all is specified.A list of reservation IDs must be separated by spaces and enclosed inquotation marks (") or (').Chapter 1. bacct3

bacctThe -U option also displays historical information about reservationmodifications.When combined with the -U option, -u is interpreted as the user name of thereservation creator. For example:bacct -U all -u user2shows all the advance reservations created by user user2.Without the -u option, bacct -U shows all advance reservation informationabout jobs submitted by the user.In a MultiCluster environment, advance reservation information is only loggedin the execution cluster, so bacct displays advance reservation information forlocal reservations only. You cannot see information about remote reservations.You cannot specify a remote reservation ID, and the keyword all only displaysinformation about reservations in the local cluster.-u user name . -u allDisplays accounting statistics for jobs submitted by the specified users, or byall users if the keyword all is specified.If a list of users is specified, user names must be separated by spaces andenclosed in quotation marks (") or ('). You can specify both user names anduser 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.In MultiCluster job forwarding mode, you can use the local job ID and clustername to retrieve the job details from the remote cluster. The query syntax is:The query syntax is:bacct submission job [email protected] cluster nameFor job arrays, the query syntax is:bacct "submission job id[index]"@submission cluster name"The advantage of using submission job [email protected] cluster name insteadof bacct -l job id is that you can usesubmission job [email protected] cluster name as an alias to query a local job inthe execution cluster without knowing the local job ID in the execution cluster.The bacct output is identical no matter which job ID you use (local job ID orsubmission job [email protected] cluster name).You can use bacct 0 to find all finished jobs in your local cluster, but [email protected] cluster name is not supported.-h Prints command usage to stderr and exits.-V Prints Platform LSF release version to stderr and exits.Default output format (SUMMARY)Statistics on jobs. The following fields are displayed:vvvv4Total number of done jobsTotal number of exited jobsTotal CPU time consumedAverage CPU time consumedPlatform LSF Command Reference

bacctvvvvvMaximum CPU time of a jobMinimum CPU time of a jobTotal wait time in queuesAverage wait time in queueMaximum wait time in queuevvvvvvvMinimum wait time in queueAverage turnaround time (seconds/job)Maximum turnaround timeMinimum turnaround timeAverage hog factor of a job (cpu time/turnaround time)Maximum hog factor of a jobMinimum hog factor of a jobv Total throughputv Beginning time: the completion or exit time of the first job selectedv Ending time: the completion or exit time of the last job selectedThe total, average, minimum, and maximum statistics are on all specified jobs.The wait time is the elapsed time from job submission to job dispatch.The turnaround time is the elapsed time from job submission to job completion.The hog factor is the amount of CPU time consumed by a job divided by itsturnaround time.The throughput is the number of completed jobs divided by the time period tofinish these jobs (jobs/hour).Output: Brief format (-b)In addition to the default format SUMMARY, displays the following fields:U/UIDName of the user who submitted the job. If LSF fails to get the user name bygetpwuid, the user ID is displayed.QUEUEQueue to which the job was submitted.SUBMIT TIMETime when the job was submitted.CPU TCPU time consumed by the job.WAITWait time of the job.TURNAROUNDTurnaround time of the job.FROMHost from which the job was submitted.EXEC ONHost or hosts to which the job was dispatched to run.Chapter 1. bacct5

bacctJOB NAMEThe job name assigned by the user, or the command string assigned by defaultat job submission with bsub. If the job name is too long to fit in this field, thenonly the latter part of the job name is displayed.The displayed job name or job command can contain up to 4094 characters.Output: Long format (-l)Also displays host-based accounting information (CPU T, MEM, and SWAP) forcompleted jobs when LSF HPC EXTENSIONS "HOST RUSAGE" in lsf.conf.In addition to the fields displayed by default in SUMMARY and by -b, displaysthe following fields:JOBIDIdentifier that LSF assigned to the job.PROJECT NAMEProject name assigned to the job.STATUSStatus that indicates the job was either successfully completed (DONE) orexited (EXIT).DISPATCH TIMETime when the job was dispatched to run on the execution hosts.COMPL TIMETime when the job exited or completed.HOG FACTORAverage hog factor, equal to "CPU time" / "turnaround time".MEMMaximum resident memory usage of all processes in a job. By default, memoryusage is shown in MB. Use LSF UNIT FOR LIMITS in lsf.conf to specify alarger unit for display (MB, GB, TB, PB, or EB).CWDFull path of the current working directory for the job.Specified CWDUser specified execution CWD.SWAPMaximum virtual memory usage of all processes in a job. By default, swapspace is shown in MB. Use LSF UNIT FOR LIMITS in lsf.conf to specify alarger unit for display (MB, GB, TB, PB, or EB).INPUT FILEFile from which the job reads its standard input (see bsub -i input file).OUTPUT FILEFile to which the job writes its standard output (see bsub -o output file).ERR FILEFile in which the job stores its standard error output (see bsub -e err file).EXCEPTION STATUSPossible values for the exception status of a job include:idleThe job is consuming less CPU time than expected. The job idle factor6Platform LSF Command Reference

bacct(CPU time/runtime) is less than the configured JOB IDLE threshold for thequeue and a job exception has been triggered.overrunThe job is running longer than the number of minutes specified by theJOB OVERRUN threshold for the queue and a job exception has beentriggered.underrunThe job finished sooner than the number of minutes specified by theJOB UNDERRUN threshold for the queue and a job exception has beentriggered.runtime est exceededThe job is running longer than the number of minutes specified by theruntime estimation and a job exception has been triggered.SYNCHRONOUS EXECUTIONJob was submitted with the -K option. LSF submits the job and waits for thejob to complete.JOB DESCRIPTIONThe job description assigned by the user at job submission with bsub. This fieldis omitted if no job description has been assigned.The displayed job description can contain up to 4094 characters. Dispatched number Task(s) on Host(s)The number of tasks in the job and the hosts to which those tasks were sentfor processing. Is displayed ifLSB ENABLE HPC ALLOCATION is set to Y or y inlsf.conf. Allocated number Slot(s) on Host(s)The number of slots that were allocated to the job based on the number oftasks, and the hosts on which the slots are allocated. Is displayedifLSB ENABLE HPC ALLOCATION is set to Y or y in lsf.conf.Effective RES REQDisplays a job's effective resource requirement as seen by the Scheduler afterresolving any OR constructs.PE Network IDDisplays network resource allocations for IBM Parallel Edition (PE) jobssubmitted with the bsub -network option, or to a queue (defined inlsb.queues) or an application profile (defined in lsb.applications) with theNETWORK REQ parameter defined.For example:bacct -l 210Job 210 , User user1 ;, Project default , Status DONE . Queue normal ,Command my pe job Tue Jul 17 06:10:28: Submitted from host hostA , CWD /home/pe jobs ;Tue Jul 17 06:10:31: Dispatched to hostA , Effective RES REQ select[type local] order[r15s:pg] rusage[mem 1.00] , PE NetworkID 1111111 2222222 used 1 window(s)per network per task;Tue Jul 17 06:11:31: Completed done .Output: Advance reservations (-U)Displays the following fields:Chapter 1. bacct7

bacctRSVIDAdvance reservation ID assigned by brsvadd commandTYPEType of reservation: user or systemCREATORUser name of the advance reservation creator, who submitted the brsvaddcommandUSERUser name of the advance reservation user, who submitted the job with bsub-UNCPUSNumber of CPUs reservedRSV HOSTSList of hosts for which processors are reserved, and the number of processorsreservedTIME WINDOWTime window for the reservation.v A one-time reservation displays fields separated by slashes(month/day/hour/minute). For example:11/12/14/0-11/12/18/0v A recurring reservation displays fields separated by colons(day:hour:minute). For example:5:18:0 5:20:0Output: Affinity resource requirements information (-l -aff)Use -l -aff to display accounting job information about CPU and memory affinityresource allocations for job tasks. A table with the heading AFFINITY is displayedcontaining the detailed affinity information for each task, one line for eachallocated processor unit. CPU binding and memory binding information are shownin separate columns in the display.HOSTThe host the task is running onTYPERequested processor unit type for CPU binding. One of numa, socket, core, orthread.LEVELRequested processor unit binding level for CPU binding. One of numa, socket,core, or thread. If no CPU binding level is requested, a dash (-) is displayed.EXCLRequested processor unit binding level for exclusive CPU binding. One ofnuma, socket, core, or thread. If no exclusive binding level is requested, a dash(-) is displayed.IDSList of physical or logical IDs of the CPU allocation for the task.The list consists of a set of paths, represented as a sequence integers separatedby slash characters (/), through the topology tree of the host. Each pathidentifies a unique processing unit allocated to the task. For example, a stringof the form 3/0/5/12 represents an allocation to thread 12 in core 5 of socket 08Platform LSF Command Reference

bacctin NUMA node 3. A string of the form 2/1/4represents an allocation to core 4of socket 1 in NUMA node 2. The integers correspond to the node ID numbersdisplayed in the topology tree from bhosts -aff.POLRequested memory binding policy. Eitherlocal or pref. If no memory bindingis requested, - is displayed.NUMAID of the NUMA node that the task memory is bound to. If no memorybinding is requested, a dash (-) is displayed.SIZEAmount of memory allocated for the task on the NUMA node.For example the following job starts 6 tasks with the following affinity resourcerequirements:bsub -n 6 -R"span[hosts 1] rusage[mem 100]affinity[core(1,same socket,exclusive (socket,injob)):cpubind socket:membind localonly:distribute pack]" myjobJob 6 is submitted to default queue normal . bacct -l -aff 6Accounting information about jobs that are:- submitted by all users.- accounted on all projects.- completed normally or exited- executed on all hosts.- submitted to all queues.- accounted on all service -----------------------------------Job 6 , User user1 , Project default , Status DONE , Queue normal , Command myjob Thu Feb 14 14:13:46: Submitted from host hostA , CWD HOME ;Thu Feb 14 14:15:07: Dispatched 6 Task(s) on Host(s) hostA hostA hostA hostA hostA hostA ; Allocated 6 Slot(s) on Host(s) hostA hostA hostA hostA hostA hostA ;Effective RES REQ select[type local] order[r15s:pg]rusage[mem 100.00] span[hosts 1] affinity[core(1,same socket,exclusive (socket,injob))*1:cpubind socket:membind localonly:distribute pack] ;Thu Feb 14 14:16:47: Completed done .AFFINITY:HOSThostAhostAhostAhostAhostAhostACPU BINDING-----------------------TYPELEVEL EXCLIDScoresocket socket /0/0/0coresocket socket /0/1/0coresocket socket /0/2/0coresocket socket /0/3/0coresocket socket /0/4/0coresocket socket /0/5/0MEMORY BINDING-------------------POLNUMA SIZElocal 016.7MBlocal 016.7MBlocal 016.7MBlocal 016.7MBlocal 016.7MBlocal 016.7MBAccounting information about this job:CPU TWAITTURNAROUNDSTATUSHOG ---------------SUMMARY:( time unit: second )Total number of done jobs:1Total CPU time consumed:0.0Maximum CPU time of a job:0.0Total wait time in queues:81.0Total number of exited jobs:Average CPU time consumed:Minimum CPU time of a job:00.00.0Chapter 1. bacct9

bacct AverageMaximumAverageMaximumAverageMaximumwait time in queue:wait time in queue:turnaround time:turnaround time:hog factor of a job:hog factor of a job:81.081.0Minimum wait time in queue:181 (seconds/job)181Minimum turnaround time:0.00 ( cpu time / turnaround time )0.00Minimum hog factor of a job:81.01810.00Termination reasons displayed by bacct When LSF detects that a job is terminated, bacct -l displays one of the followingtermination reasons. The corresponding integer value logged to the JOB FINISHrecord in lsb.acct is given in parentheses.vvvvvvvvvvvTERM ADMIN: Job killed by root or LSF administrator (15)TERM BUCKET KILL: Job killed with bkill -b (23)TERM CHKPNT: Job killed after checkpointing (13)TERM CWD NOTEXIST: current working directory is not accessible or does notexist on the execution host (25)TERM CPULIMIT: Job killed after reaching LSF CPU usage limit (12)TERM DEADLINE: Job killed after deadline expires (6)TERM EXTERNAL SIGNAL: Job killed by a signal external to LSF (17)TERM FORCE ADMIN: Job killed by root or LSF administrator without timefor 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)v TERM ORPHAN SYSTEM: The orphan job was automatically terminated byLSF (27)v TERM OWNER: Job killed by owner (14) v TERM PREEMPT: Job killed after preemption (1)v TERM PROCESSLIMIT: Job killed after reaching LSF process limit (7)v TERM REMOVE HUNG JOB: Job removed from LSF system after reaching ajob runtime limit (26)v TERM REQUEUE ADMIN: Job killed and requeued by root or LSFadministrator (11)vvvvvTERM REQUEUE OWNER: Job killed and requeued by owner (10)TERM RUNLIMIT: Job killed after reaching LSF run time limit (5)TERM SWAP: Job killed after reaching LSF swap usage limit (20)TERM THREADLIMIT: Job killed after reaching LSF thread limit (21)TERM UNKNOWN: LSF cannot determine a termination reason—0 is loggedbut TERM UNKNOWN is not displayed (0)v TERM WINDOW: Job killed after queue run window closed (2)v TERM ZOMBIE: Job exited while LSF is not available (19)Tip: The integer values logged to the JOB FINISH record in lsb.acct andtermination reason keywords are mapped in lsbatch.h.Example: Default formatbacctAccounting information about jobs that are:- submitted by users user1.- accounted on all projects.10Platform LSF Command Reference

bacct- completed normally or exited.- executed on all hosts.- submitted to all queues.- accounted on all service --------------- ----SUMMARY:( time unit: second )Total number of done jobs:60Total number of exited jobs:118Total CPU time consumed:1011.5Average CPU time consumed:5.7Maximum CPU time of a job:991.4Minimum CPU time of a job:0.0Total wait time in queues: 134598.0Average wait time in queue: 756.2Maximum wait time in queue: 7069.0Minimum wait time in queue:0.0Average turnaround time:3585 (seconds/job)Maximum turnaround time:77524Minimum turnaround time:6Average hog factor of a job: 0.00 ( cpu time / turnaround time )Maximum hog factor of a job: 0.56Minimum hog factor of a job: 0.00Total throughput:0.67 (jobs/hour) during 266.18 hoursBeginning time:Aug 8 15:48Ending time:Aug 19 17:59Example: Jobs that have triggered job exceptionsbacct -x -lAccounting 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 --------------Job 1743 , User user1 , Project default , Status DONE , Queue normal , Command sleep 30 Mon Aug 11 18:16:17 2009: Submitted from host hostB , CWD HOME/jobs , Output File /dev/null ;Mon Aug 11 18:17:22 2009: Dispatched to hostC ; Effective RES REQ select[(hname delgpu3 ) &&(type any)] order[r15s:pg] ;Mon Aug 11 18:18:54 2009: Completed done .EXCEPTION STATUS:underrunAccounting information about this job:CPU TWAITTURNAROUNDSTATUSHOG ------------------------------------- -------Job 1948 , User user1 , Project default , Status DONE , Queue normal ,Command sleep 550 ,Job Description This job is a test job. Tue Aug 12 14:15:03 2009: Submitted from host hostB , CWD HOME/jobs , Output File /dev/null ;Tue Aug 12 14:15:15 2009: Dispatched to hostC ; Effective RES REQ select[(hname delgpu3 ) &&(type any)] order[r15s:pg] ;Tue Aug 12 14:25:08 2009: Completed done .EXCEPTION STATUS:overrunidleAccounting information about this job:CPU TWAITTURNAROUNDSTATUSHOG ----------------------------------------------Job 1949 , User user1 , Project default , Status DONE , Queue normal ,Command sleep 400 Tue Aug 12 14:26:11 2009: Submit

This edition applies to version 9, release 1 of IBM Platform LSF (product numbers 5725G82 and 5725L25) and to all subsequent releases and modifications until otherwise indicated in new editions. Significant changes or additions to the text and illustrations are in