User Tools

Site Tools


Globus Endpoints

We currently support transfers to and from out clusters using Globus. If your cluster isn't listed below send a request to to have it added. So far the current endpoints are:

  • → ucdhpc#farm
  • → ucdhpc#hpc1
  • → ucdhpc#crick

Just login to to start transfers to or from any endpoint.

How a job manager is created

  • User submits a job
  • Globus gatekeeper handles the authentication and authorization of the user.
  • One gatekeeper is started for each connection.
  • As soon as the gatekeeper has authorized the user successfully, the gatekeeper starts a new process which becomes the job manager.
  • Gatekeeper exits when job manager is started

GRAM Commands

  • globusrun - Execute and manage jobs via GRAM
  • globus-job-cancel - Cancel a GRAM batch job
  • globus-job-clean - Cancel and clean up a GRAM batch job
  • globus-job-get-output - Retrieve the output and error streams from a GRAM job
  • globus-job-run - Execute a job using GRAM
  • globus-job-status - Check the status of a GRAM5 job
  • globus-job-submit - Submit a batch job using GRAM
  • globus-personal-gatekeeper - Manage a user's personal gatekeeper daemon
  • globus-gram-audit - Load GRAM4 and GRAM5 audit records into a database
  • globus-gatekeeper - Authorize and execute a grid service on behalf of a user
  • globus-job-manager - Execute and monitor jobs
  • globus-job-manager-event-generator - Create LRM-independent SEG files for the job manager to use
  • globus-fork-starter - Start and monitor a fork job
tier3/globus.txt · Last modified: 2015/05/20 23:41 by bill