Package condor

HTCondor: High Throughput Computing

http://research.cs.wisc.edu/htcondor/

HTCondor is a workload management system for high-throughput and
high-performance jobs. Like other full-featured batch systems, HTCondor
provides a job queuing mechanism, scheduling policy, priority scheme,
resource monitoring, and resource management. Users submit their
serial or parallel jobs to HTCondor, HTCondor places them into a queue,
chooses when and where to run the jobs based upon a policy, carefully
monitors their progress, and ultimately informs the user upon
completion.

Version: 8.8.15

See also: condor-procd.

General Commands

condor_advertise condor_advertise sends one or more ClassAds to the condor_collector daemon on the central manager machine.
condor_annex condor_annex adds clouds resources to the pool. (“The pool” is determined in the usual manner for HTCondor daemons and tools.)
condor_check_userlogs condor_check_userlogs is a program for checking a job event log or a set of job event logs for errors.
condor_chirp condor_chirp is not intended for use as a command-line tool. It is most often invoked by an HTCondor job, while the job is executing.
condor_cod condor_cod issues commands that manage and use COD claims on machines, given proper authorization.
condor_config_val condor_config_val can be used to quickly see what the current HTCondor configuration is on any given machine.
condor_continue condor_continue continues one or more suspended jobs from the HTCondor job queue.
condor_convert_history As of Condor version 6.7.19, the Condor history file has a new format to allow fast searches backwards through the file.
condor_dagman condor_dagman is a meta scheduler for the HTCondor jobs within a DAG (directed acyclic graph) (or multiple DAGs).
condor_dagman_metrics_reporter
condor_drain condor_drain is an administrative command used to control the draining of all slots on an execute machine.
condor_fetchlog condor_fetchlog contacts HTCondor running on the machine specified by machine-name, and asks it to return a log file from that machine.
condor_findhost
condor_gather_info
condor_gpu_discovery condor_gpu_discovery outputs ClassAd attributes corresponding to a host's GPU capabilities.
condor_history condor_history displays a summary of all HTCondor jobs listed in the specified history files.
condor_hold condor_hold places jobs from the HTCondor job queue in the hold state. If the -name option is specified, the named condor_schedd is targeted for processing.
condor_install condor_configure and condor_install refer to a single script that installs and/or configures HTCondor on Unix machines.
condor_job_router_info condor_job_router_info displays information about job routing. The information will be either the available, configured routes or the routes for specified jobs.
condor_master This daemon is responsible for keeping all the rest of the HTCondor daemons running on each machine in your pool.
condor_now
condor_off condor_off shuts down a set of the HTCondor daemons running on a set of one or more machines.
condor_on condor_on starts up a set of the HTCondor daemons on a set of machines. This command assumes that the condor_master is already running on the machine.
condor_ping condor_ping attempts a security negotiation to discover whether the configuration is set such that the negotiation succeeds.
condor_pool_job_report condor_pool_job_report is a Linux-only tool that is designed to be run nightly using cron.
condor_power condor_power sends one UDP Wake on LAN (WOL) packet to a machine specified either by command line arguments or by the contents of a machine ClassAd.
condor_preen
condor_prio condor_prio changes the priority of one or more jobs in the HTCondor queue.
condor_q condor_q displays information about jobs in the HTCondor job queue.
condor_qedit condor_qedit modifies job ClassAd attributes of queued HTCondor jobs.
condor_qsub condor_qsub submits an HTCondor job. This job is specified in a PBS/Torque style or an SGE style.
condor_reconfig condor_reconfig reconfigures all of the HTCondor daemons in accordance with the current status of the HTCondor configuration file(s).
condor_release condor_release releases jobs from the HTCondor job queue that were previously placed in hold state.
condor_reschedule condor_reschedule updates the information about a set of machines' resources and jobs to the central manager.
condor_restart condor_restart restarts a set of HTCondor daemons on a set of machines. The daemons will be put into a consistent state, killed, and then invoked anew.
condor_rm condor_rm removes one or more jobs from the HTCondor job queue. If the -name option is specified, the named condor_schedd is targeted for processing.
condor_rmdir
condor_router_history condor_router_history summarizes statistics for routed jobs over the previous 24 hours.
condor_router_q condor_router_q displays information about jobs managed by the condor_job_router that are in the HTCondor job queue.
condor_router_rm condor_router_rm is a script that provides additional features above those offered by condor_rm, for removing jobs being managed by the HTCondor Job Router.
condor_run condor_run bundles a shell command line into an HTCondor job and submits the job.
condor_set_shutdown condor_set_shutdown sets a program (typically a script) to execute when the condor_master daemon shuts down.
condor_sos condor_sos sends the condor_command in such a way that the command is serviced ahead of other waiting commands.
condor_ssh_to_job condor_ssh_to_job creates an ssh session to a running job. The job is specified with the argument.
condor_stats condor_stats displays historic information about an HTCondor pool.
condor_status condor_status is a versatile tool that may be used to monitor and query the HTCondor pool.
condor_store_cred condor_store_cred stores passwords in a secure manner.
condor_submit condor_submit is the program for submitting jobs for execution under HTCondor.
condor_submit_dag condor_submit_dag is the program for submitting a DAG (directed acyclic graph) of jobs for execution under HTCondor.
condor_suspend condor_suspend suspends one or more jobs from the HTCondor job queue.
condor_tail condor_tail displays the last bytes of a file in the sandbox of a running job identified by the command line argument job-ID. stdout is tailed by default.
condor_top
condor_transfer_data condor_transfer_data causes HTCondor to transfer spooled data.
condor_transform_ads
condor_update_machine_ad condor_update_machine_ad modifies the specified condor_startd daemon's machine ClassAd.
condor_updates_stats condor_updates_stats parses the output from condor_status, and it displays the information relating to update statistics in a useful format.
condor_urlfetch
condor_userlog condor_userlog parses the information in job log files and displays summaries for each workstation allocation and for each job.
condor_userprio condor_userprio either modifies priority-related information or displays priority-related information.
condor_vacate condor_vacate causes HTCondor to checkpoint any running jobs on a set of machines and force the jobs to vacate the machine.
condor_vacate_job condor_vacate_job finds one or more jobs from the HTCondor job queue and vacates them from the host(s) where they are currently running.
condor_version With no arguments, condor_version prints the currently installed HTCondor version number and platform information.
condor_wait
condor_who condor_who queries and displays information about the user that owns the jobs running on a machine. It is intended to be run on an execute machine.