gwsubmit — job submission utility for the GridWay system
gwsubmit -t template [-n tasks] [-h] [-v] [-o] [-s start] [-i increment] [-d "id1 id2 ..."]
Submit a job or an array job (if the number of tasks is defined) to gwd
-h
Prints help.-t <template>
The template file describing 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.-d <id1 id2…>
Job dependencies. Submit the job on hold state, and release it once jobs with id1,id2,.. have successfully finished.-v
Print to stdout the job ids returned by gwd.-o
Hold job on submission.-p <priority>
Initial priority for the job.gwdag — dag job submission utility for the GridWay system
gwdag [-h] [-d] <DAG description file>
Submit a dag job to gwd
-h
Prints help.-d
Writes to STDOUT a DOT description for the specified DAG job.gwps — 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
prints 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 states matching that of job_state-o output_format
Formats output information, allowing the selection of which fields to display-c <delay>
This will cause gwps to print job information every <delay> seconds continuously (similar to top command).-n
Do not print the header-f
full format-x
xml formatjob_id
Only monitor this job_idTable 5. 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 (Globus 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 flag |
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 |
gwhistory — shows history of a job
gwhistory [-h] [-nx] <job_id>
Prints information about the execution history of a job
-h
prints this help.-n
do not print the header lines.-x
xml format.job_id
job identification as provided by gwps.Table 6. 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 of the host. |
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
prints help-c <delay>
This will cause gwhost to print job information every <delay> seconds continuously (similar to top command)-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, also prints queue information.Table 7. 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 8. 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
Prints help.-a
Asynchronous signal, only relevant for KILL and STOP.-k
Kill (default, if no signal specified).-t
Stop job.-r
Resume job.-o
Hold job.-l
Release job.-s
Re-schedule job.-9
Hard kill, removes the job from the system without synchronizing remote job execution or cleaning remote host.job_id [job_id2 …]
Job identification as provided by gwps. You can specify a blank space separated list of job ids.-A <array_id>
Array identification as provided by gwps.gwwait — synchronize a job
gwwait [-h] [-a] [-v] [-k] <job_id ...| -A array_id>
Waits for a job or array job
-h
help.-a
Any, returns 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.-A <array_id>
Array identification as provided by gwps.job_id
Job ids list (blank space separated).gwuser — monitors users in GridWay
gwuser [-h] [-nx]
Prints information about users in the GridWay system
-h
prints this help-n
do not print the header-x
xml formatTable 9. 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 usage statistics per user or resource. Note: accounting statistics are updated once a job is killed.
-h
Prints help.-n
Do not print the header.-x
xml output.< -d n | -w n | -m n | -t s>
Take into account jobs submitted after certain date, specified in number of days (-d), weeks (-w), months (-m) or an epoch (-t).-u user
Print usage statistics for user.-r hostname
Print usage statistics for host.Table 10. 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 | stop-resume |
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
Prints help.input_jsdl
Reads the jsdl document from the input_jsdloutput_gwjt
Stores the GridWay Job Template specification in the output_gwjt.jt file