bjobs.1
NAME
bjobs - get information about batch jobs in the LSF system
SYNOPSIS
bjobs [ -h ] [ -V ] [ -w | -l ] [ -a ] [ -d ] [ -p ]
[ -s ] [ -r ] [-A]
[-q queue_name ] [ -m host_name | -m cluster_name ] [
-u user_name | -u all ] [ -J job_name_spec ] [ -P
project_name ] [ -N host_spec ]
[ jobId | "jobId[index_list]" ... ]
DESCRIPTION
Display the status and other information about the batch
jobs that are specified by the options. If no option is
specified, then the default is to display information about
all the unfinished (that is, pending, running and suspended)
jobs, of the user who invoked this command.
To display finished jobs, option -d or -a must be used when
jobId is not specified. Note that only the jobs that have
finished within the last CLEAN_PERIOD seconds can be
displayed (see lsb.params(5)). For jobs finished more than
CLEAN_PERIOD seconds ago, the bhist command can be used to
display their information.
Pending jobs are displayed in the order in which they will
be considered for dispatch. Jobs in higher priority queues
are displayed before those in lower priority queues. Pend-
ing jobs in the same priority queue(s) are displayed in the
order in which they were submitted but this order can be
changed by using the commands btop or bbot (see btop(1)).
If more than one job is dispatched to a host, the jobs on
that host are listed in the order in which they will be con-
sidered for scheduling on this host by their queue priori-
ties and dispatch times. Finished jobs are displayed in the
order in which they were completed.
A listing of jobs is displayed with the following fields:
JOBID
the job ID that LSF assigned to the job.
USER the user who submitted the job.
STAT The current status of the job (see JOB STATUS below).
QUEUE
The name of the job queue to which the job belongs. If
the queue to which the job belongs has been removed
from the configuration, the queue name will be
displayed as "lost_and_found". You may use bhist com-
mand to get the original queue name. The job in the
"lost_and_found" queue will remain pending until it is
switched by bswitch command into another queue.
FROM_HOST
The name of the host from which the job was submitted.
EXEC_HOST
The name of one or more hosts on which the job is exe-
cuting (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
will be displayed as "lost_and_found". You may use
bhist command to get the original host name.
JOB_NAME
The job name assigned by the user, or the command
string assigned by default (see bsub (1)). If the job
name is too long to fit in this field, then only the
latter part of the job name is displayed.
SUBMIT_TIME
The submission time of the job.
If the -l option is given, the resulting long format listing
includes the following additional fields:
Project
The project the job was submitted from.
Command
The job command.
CWD The current working directory on the submission host.
PENDING REASONS
The reason the job is in the PEND or PSUSP state. The
names of the hosts associated with each reason will be
displayed when both -p and -l options are specified.
SUSPENDING REASONS
The reason the job is in the USUSP or SSUSP state.
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 due to either of the
following two causes: 1) The load conditions on the
execution host or hosts have exceeded a threshold
according to the loadStop vector defined for the host
or queue or 2) the run window of the job's queue is
closed.
(See bqueues(1), bhosts(1), and lsb.queues(5).)
DONE The job has terminated with status of 0.
EXIT The job has terminated with a non-zero status - it may
have been aborted due to an error in its execution, or
killed by its owner or the LSF administrator.
UNKWN
The master batch daemon (mbatchd) has lost contact with
the slave batch daemon (sbatchd) on the host on which
the job runs.
ZOMBI
A job will become ZOMBI if:
1) the job is killed by bkill command while the sbatchd
on the execution host is unreachable and the job is
shown as UNKWN,
2) 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 will
try to kill the ZOMBI job. Upon successful termination
of the ZOMBI job, the job's status will be changed to
EXIT.
In an LSF MultiCluster environment, when a job running
on a remote execution cluster becomes a ZOMBIE job,
the execution cluster will treat the job the same way
as local ZOMBIE jobs. In addition, it notifies the
submission cluster that the job is in ZOMBIE state and
the submission cluster requeues the job.
RESOURCE USAGE
The values for the current usage of a job include:
CPU time
Cumulative total CPU time in seconds of all processes
in a job.
MEM Total resident memory usage in KBytes of all processes
in a job.
SWAP Total virtual memory usage in KBytes of all processes
in a job.
PGID Currently active process group ID in a job.
PIDs Currently active processes in a job.
OPTIONS
-h Print command usage to stderr and exit.
-V Print LSF release version to stderr and exit.
-w Display job information in a wide format. Fields are
displayed without truncation.
-l Display detailed information for each job in a (long)
multi-line format. See also bhist(1).
-a Display information about all jobs, including unfin-
ished jobs (pending, running or suspended) and recently
finished jobs. LSF remembers jobs that have finished
within a period up to now (the default period is 1
hour). This time parameter is configurable (see
lsb.params(5) for CLEAN_PERIOD). If neither -a, nor
-d, nor jobId is present, then finished jobs are not
displayed.
-d Display only the recently finished jobs. For the
default, see -a.
-p Display only the pending jobs, together with the pend-
ing reasons that causes each job not to be dispatched
during the last dispatch turn. Each pending reason is
associated with one or a number of host(s) and it
states the cause why these host(s) are not allocated to
run the job. In situations where the job requests
specific hosts (using -m switch of bsub(1)), 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 a
new dispatch turn starts. Thus a reason could last as
long as MBD_SLEEP_TIME (configurable) seconds (see
lsb.params(5)) and may not reflect the current load
situation.
-s Display only the suspended jobs, together with the
suspending reason that causes each job to become
suspended. The suspending reason not stay the same
while the job stays suspended. For example, a job may
have been suspended due to the paging rate, but after
the paging rate dropped another load index could
prevent the job from being resumed. The suspending
reason will be updated corresponding to the load index
The reasons could be as old as SBD_SLEEP_TIME (see
lsb.params(5)) seconds. So the reasons shown may not
reflect the current load situation.
-r Display only the running jobs.
-q queue_name
Display jobs that are in the queue queue_name. The
command bqueues returns a list of queues configured in
the system and information about the configurations of
these queues.
-m host_name | cluster_name
If a host or a host group name is specified, the com-
mand displays jobs that have been dispatched to the
host or host group specified by host_name. To deter-
mine the available batch server hosts and host groups,
use the commands bhosts and bmgroup, respectively. If
a cluster name is specified in an LSF MultiCluster
environment, the command displays jobs that are in the
cluster specified by cluster_name. To determine the
available clusters that interact with the local clus-
ter, use the command bclusters.
-u user_name | -u all
Display jobs that have been submitted by the user or
the user group (see bugroup(1)) specified by user_name,
or by all users (if the reserved user name all is
specified). The default is to display the jobs submit-
ted by the invoker.
-J job_name_spec
Display the jobs specified by job_name_spec.
job_name_spec is either a job name, or a job array
specification. (see bsub(1) -J option ).
-P project_name
Display jobs that have been submitted from the project
project_name. The default is to display jobs submitted
from all projects.
-N host_spec
Display CPU time consumed by the job, using a normal-
ized value. host_spec is either a host name, or a host
model name defined in LSF, or a CPU factor (use
lsinfo(1) to get host model and CPU factor informa-
tion). The appropriate CPU scaling factor for the
specified host_spec is used to normalize the actual CPU
time consumed by the job.
-A Display summarized information about job arrays. This
option only takes job IDs that correspond to job arrays
and not the job array index. The following fields are
displayed:
JOBID
Job Id of the job array
ARRAY_SPEC
Array specification in the format of name[index].
The array specification may be truncated, use -w
option together with -A to show the full array
specification.
OWNER
Owner of the job array
NJOBS
Number of jobs the job array has.
PEND Number of pending jobs of the job array
RUN Number of running jobs of the job array
DONE Number of successfully completed jobs of the job
array
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.
jobId | jobId[index_list] ...
Display the job or jobs with the specified
jobId or "jobId[index_list]", where
"jobId[index_list]" specifies selected job array ele-
ments. The index_list is an index list which defines a
set of element jobs with the form of [region, ...].
Each region has one of the the following forms:
index
This specifies the array element job whose index
value is index.
low_index-high_index [:step]
This specifies the array element jobs whose index
values are between low_index and high_index
inclusively. step is optinal, and specifies the
increment between low_index and high_index. E.g.,
1-5:2 specifies elements 1, 3, and 5.
low_index- [:step]
This specifies elements from low_index to the
upper bound of the job array.
-high_index[:step]
This specifies elements from the job element with
the lowest index value to the job element whose
index value is high_index.
The value of 0 for jobId is ignored.
EXAMPLES
% bjobs -pl
Display detailed information of all pending jobs of the
invoker.
% bjobs -ps
Display only pending and suspended jobs.
% bjobs -u all -a
Display all jobs of all users.
% bjobs -d -q short -m apple -u john
Display all the recently finished jobs submitted by
john to the queue short, and executed on the host
apple.
% bjobs 101 102 203 509
Display jobs with jobID 101, 102, 203, and 509.
SEE ALSO
bsub(1), bhosts(1), bmgroup(1), bclusters(1), bqueues(1)
bhist(1), lsb.params(5), mbatchd(8)