gwsubmit — job submission utility for the GridWay system
gwsubmit [-h] [-v] [-o] [-d "id1 id2 ..."] [-p priotity] [-n tasks [-s start] [-i increment]] <[-t] template>
Submits a job or an array job (if the number of tasks is defined) to gwd
-h
print this help-v
print to stdout the job ids returned by gwd-o
hold job on submission-d “id1 id2 …”
job dependencies. Submit the job on hold state, and release it once the jobs with id1, id2, … have finished-p priority
initial priority for the job-n tasks
submit an array job with the given number of tasks all the jobs in the array will use the same template-s start
start value for custom param in array jobs. Default 0-i increment
increment value for custom param in array jobs. Each task has associated the value. PARAM = start + increment * TASK_ID
, and MAX_PARM = start + increment * (tasks - 1)
. Default 1-t template
template file describing the jobgwps — report a snapshot of the current jobs
gwps [-h] [-u user] [-r host] [-A AID] [-s job_state] [-o output_format] [-c delay] [-nfx] [job_id]
Prints information about all the jobs in the GridWay system (default)
-h
print this help-u user
monitor only jobs owned by user-r host
monitor only jobs executed in host-A AID
monitor only jobs part of the array AID
-s job_state
monitor only jobs in state job_state
(see JOB STATES)-o output_format
define output information (see FIELD INFORMATION)-c delay
refresh job information every delay seconds-n
do not print the header-f
full format-x
xml formatjob_id
only monitor this job_idTable 1. Field options
FIELD NAME | FIELD OPTION | DESCRIPTION |
---|---|---|
USER | u | owner of this job |
JID | J | job unique identification assigned by the Gridway system |
AID | i | array unique identification, only relevant for array jobs |
TID | i | task identification, ranges from 0 to TOTAL_TASKS -1, only relevant for array jobs |
FP | p | fixed priority of the job |
TYPE | y | type of job (simple, multiple or mpi) |
NP | n | number of processors |
DM | s | Dispatch Manager state, one of: pend, hold, prol, prew, wrap, epil, canl, stop, migr, done, fail |
EM | e | Execution Manager state: pend, susp, actv, fail, done |
RWS | f | flags: R times this job has been restarted, W number of processes waiting for this job, S re-schedule |
START | t/T | the time the job entered the system |
END | t/T | the time the job reached a final state (fail or done) |
EXEC | t/T | total execution time, includes suspension time in the remote queue system |
XFER | t/T | total file transfer time, includes stage-in and stage-out phases |
EXIT | x | job exit code |
TEMPLATE | j | filename of the job template used for this job |
HOST | h | hostname where the job is being executed |
Note: t option only prints time and T also writes the date |
Table 2. Job states
JOB STATES | identifier |
---|---|
PENDING | (i) |
PROLOG | (p) |
HOLD | (h) |
WRAPPER | (w) |
EPILOG | (e) |
STOP | (s) |
KILL | (k) |
MIGRATE | (m) |
ZOMBIE | (z) |
FAILED | (f) |
gwhistory — shows history of a job
gwhistory [-h] [-nx] <job_id>
Prints information about the execution history of a job
-h
print this help-n
do not print the header lines-x
xml formatjob_id
job identification as provided by gwpsTable 3. Field information
NAME | DESCRIPTION |
---|---|
HID | host unique identification assigned by the GridWay system |
START | the time the job start its execution on this host |
END | the time the job left this host, because it finished or it was migrated |
PROLOG | total prolog (file stage-in phase) time |
WRAPPER | total wrapper (execution phase) time |
EPILOG | total epilog (file stage-out phase) time |
MIGR | total migration time |
REASON | the reason why the job left this host |
QUEUE | name of the queue |
HOST | FQDN/LRMS of the resource |
gwhost — shows hosts information
gwhost [-h] [-c delay] [-nfx] [-m job_id] [host_id]
Prints information about all the hosts in the GridWay system (default)
-h
print this help-c delay
refresh host information every delay
seconds-n
do not print the header-f
full format-x
xml format-m job_id
prints hosts matching the requirements of a given jobhost_id
only monitor this host_id
, printing also queue information.Table 4. Field information
FIELD | DESCRIPTION |
---|---|
HID | host unique identification assigned by the GridWay system |
PRIO | priority assigned to the host |
OS | operating system |
ARCH | architecture |
MHZ | CPU speed in MHZ |
%CPU | free CPU ratio |
MEM(F/T) | system memory: F = Free, T = Total |
DISK(F/T) | secondary storage: F = Free, T = Total |
N(U/F/T) | number of slots: U = used by GridWay, F = free, T = total |
LRMS | local resource management system, the jobmanager name |
HOSTNAME | FQDN of this host |
Table 5. Queue field information
FIELD | DESCRIPTION |
---|---|
QUEUENAME | name of this queue |
SL(F/T) | slots: F = Free, T = Total |
WALLT | queue wall time |
CPUT | queue cpu time |
COUNT | queue count number |
MAXR | max. running jobs |
MAXQ | max. queued jobs |
STATUS | queue status |
DISPATCH | queue dispatch type |
PRIORITY | queue priority |
gwkill — controls job execution
gwkill [-h] [-a] [-k|-t|-o|-s|-r|-l|-9] <job_id [job_id2 ...]|-A array_id>
Sends a signal to a job or array job
-h
print this help-a
asynchronous signal, only relevant for KILL and STOP-k
kill (default, if no signal specified)-t
stop-r
resume-o
hold-l
release-s
re-schedule-9
hard kill, removes the job from the system without synchronizing remote job execution or cleaning remote hostjob_id [job_id2 …]
job identification as provided by gwps-A <array_id>
array identification as provided by gwpsgwwait — synchronize a job
gwwait [-h] [-a] [-v] [-k] [-t timeout] <job_id [job_id2 ...]|-A array_id>
Waits for a job or array job
-h
help.-a
any. Return when the first job of the list or array finishes-v
prints job exit code-k
keep jobs. They remain in fail or done states in the GridWay system. By default, jobs are killed and their resources freed-t timeout
do not wait more than timeout seconds. A negative value means waiting for ever (default)job_id [job_id2 …]
job identification or list of jobs ids as provided by gwps.-A array_id
array identification as provided by gwpsgwuser — monitors users in GridWay
gwuser [-h] [-nx]
Prints information about users in the GridWay system
-h
print this help-n
do not print the header lines-x
xml formatTable 6. Field information
FIELD | DESCRIPTION |
---|---|
UID | user unique identification assigned by the GridWay system |
NAME | name of this user |
JOBS | number of Jobs in the GridWay system |
RUN | number of running jobs |
IDLE | idle time, (time with JOBS = 0) |
EM | Execution Manager drivers loaded for this user |
TM | Transfer Manager drivers loaded for this user |
PID | process identification of driver processes |
gwacct — prints accounting information
gwacct [-h] [-nx] [-d n|-w n|-m n|-t s] <-u user|-r host>
Prints accounting information about users or hosts in the GridWay system
-h
print this help-n
do not print the header lines-x
xml output-d n
print accounting information from n
days ago (ex: -d 1) -w n
print accounting information from n
weeks ago (ex: -w 1)-m n
print accounting information from n
months ago (ex: -m 1)-t s
print accounting information from s
seconds, where s is an epoch (i.e. -t 1159809792
)-u user
print accounting information for user-r hostname
print accounting information for hostTable 7. Field information
FIELD | DESCRIPTION |
---|---|
HOST/USER | host/user usage summary for this user/host |
XFR | total transfer time on this host (for this user) |
EXE | total execution time on this host (for this user), without suspension time |
SUSP | total suspension (queue) time on this host (for this user) |
TOTS | total executions on this host (for this user) |
Termination reasons: | |
SUCC | success |
ERR | error |
KILL | kill |
USER | user requested |
SUSP | suspension timeout |
DISC | discovery timeout |
SELF | self migration |
PERF | performance degradation |
S/R | <nowiki>stop/resume<nowiki> |
gwdagman — DAG job submission utility for the GridWay system
gwdagman [-h] [-d] <dagman file>
Submits a DAG job to gwd
-d
Generate DOT file. It is written to STDOUT-h
Print this help jsdl2gw — parser to translate JSDL file into GridWay Job Template file
jsdl2gw [-h] input_jsdl [output_gwjt]
Converts a JSDL document into a GridWay job template. If no output file is defined, it defaults to the standard output. This enables the use of pipes with gwsubmit in the following fashion:
jsdl2gw jsdl-job.xml | gwsubmit
-h
print this helpinput_jsdl
read the JSDL document from the input_jsdloutput_gwjt
store the GridWay Job Template specification in the output_gwjt.jt file