vine_submit_workers(1)

vine_submit_workers1

Submit vine_worker to the condor, slurm, or uge batch systems.

Usage

FCvine_submit_workers [batch options] [worker options] [batch specific options] <servername> <port> <num-workers>FT

or

FCvine_submit_workers [batch options] [worker options] --manager-name <name> [batch specific options] <num-workers>FT

Overview

FCvine_submit_workersFT schedules the execution of vine_worker(1) on Condor, Slurm, or UGE through their respective job submission interfaces. The number of vine_worker scheduled and run is given by the num-workers argument.

The servername and port arguments specify the hostname and port number of the manager for the vine_worker to connect. Alternatively, this information can be obtained from the catalog server by specifying the name of the TaskVine manager using the --manager-name parameter.

Options

-T,--batch-type=<batch>

Name of the batch system to submit workers. Out of (condor, slurm, uge).

Options

-M,--manager-name=<name>

Name of the preferred manager for worker.

-N,--name=<name>

Same as -M (backwards compatibility).

-C,--catalog=<catalog>

Set catalog server to <catalog>. <catalog> format: HOSTNAME:PORT.

-t,--timeout=<time>

Abort after this amount of idle time (default=900s).

-d,--debug=<subsystem>

Enable debugging on worker for this subsystem (try -d all to start).

-w,--tcp-window-size=<size>

Set TCP window size

-i,--min-backoff=<time>

Set initial value for backoff interval when worker fails to connect to a manager. (default=1s)

-b,--max-backoff=<time>

Set maxmimum value for backoff interval when worker fails to connect to a manager. (default=60s)

-z,--disk-threshold=<size>

Set available disk space threshold (in MB). When exceeded worker will clean up and reconnect. (default=100MB)

-A,--arch=<arch>

Set architecture string for the worker to report to manager instead of the value in uname.

-O,--os=<os>

Set operating system string for the worker to report to manager instead of the value in uname.

-s,--workdir=<path>

Set the location for creating the working directory of the worker.

-P,--password=<pwfile>

Password file to authenticate workers to manager.

-ssl,--=<>

Use ssl to communicate with manager.

--cores=<cores>

Set the number of cores each worker should use (0=auto). (default=1)

--memory=<size>

Manually set the amonut of memory (in MB) reported by this worker.

--disk=<size>

Manually set the amount of disk (in MB) reported by this worker.

--scratch-dir=<path>

Set the scratch directory location created on the local machine. (default=/tmp/${USER}-workers)

-E,--worker-options=<str>

Extra options passed to vine_worker

-h,--help

Show help message.

Options

Condor

-r,--requirements=<reqs>

Condor requirements expression.

--class-ad=<ad>

Extra condor class ad. May be specified multiple times.

--autosize

Condor will automatically size the worker to the slot.

--docker-universe=<image>

Run worker inside <image> using condor's docker universe

Slurm

-j,--=<>

Use job array to submit workers.

-p,--parameters=<>

SLURM sbatch parameters.

Uge

-j,--=<>

Use job array to submit workers.

-p,--parameters=<>

UGE qsub parameters.

Exit status

On success, returns zero. On failure, returns non-zero.

Examples

Submit 10 worker instances to run on Condor and connect to a specific manager:


    

    
        

vine_submit_workers -T condor manager.somewhere.edu 9123 10

Submit 10 vine_worker instances to run on Condor in auto mode with their preferred project name set to Project_A and abort timeout set to 3600 seconds:


    

    
        

vine_submit_workers -T condor -a -t 3600 -M Project_A 10

From coop-computing-tools 1:7.14.5-1+b2 in Debian 13 (Trixie). Parsed by carta from the page's man source.