Transfer-queue Over Globus (TOG) - Going Global with Globus and Grid Engine

Introduction

The Transfer-queue Over Globus (TOG) software allows an enterprise to access remote compute resources via their existing local Grid Engine installation. The TOG software integrates Grid Engine V5.3 and Globus Toolkit V2.2.4 to provide this access to remote resources. The TOG software has been built as part of the EPCC Sun Data and Computer Grids project. This project aims to develop an industry-strength, fully Globus-enabled compute and data scheduler based around Grid Engine, Globus plus a wide variety of data technologies. The project started in February 2002 and will run until January 2004. The partners are the National e-Science Centre, represented in this project by EPCC, and Sun Microsystems.

Background

Grid Engine allows the efficient use of compute resources within an organisation. However there is some desirable Grid functionality that Grid Engine does not provide.

Grids can be classified at three different levels.

The Globus Toolkit is essentially a Grid API for connecting distributed compute and instrument resources. Integration with Globus allows Grid Engine to meet this third level. That is, it allows collaboration amongst enterprises. The TOG software integrates Grid Engine V5.3 and Globus Toolkit V2.2.4 to provide a user with this access to remote resources. This allows user jobs to be scheduled across a global grid.

Download

The How-To document describes the installation of TOG, its usage and a trouble-shooting guide.

TOG can be downloaded either as a binary or source archive:

The binary archive contains the TOG binaries, API documentation and the How-To document.

The source archive contains the TOG source, system tests that integrate with the Grid Engine testsuite, developer documents (design and testplan), and the How-To document.

Projects using TOG

The TOG software has been used to create a compute grid between the universities of Glasgow and Edinburgh in the UK. Researchers at the Glasgow site of the National e-Science Centre have been able to access compute resources at EPCC using a Grid Engine installation configured with the TOG software. TOG is also being used to set up a biomedical e-Science demonstration using the new SRIF network linking three sites within the University of Edinburgh - EPCC, the Scottish Centre for Genomic Technology and Informatics (GTI) at the New Royal Infirmary of Edinburgh and the MRC Human Genetics Unit (HGU) at the Western General Hospital.

Future Delevopments

Following the development of the TOG software, the project has investigated the integration of access to data sources via data grid technologies such as OGSA-DAI, GridFTP and SRB. The next step for the project team is to develop a hierarchical scheduler that scales better in a grid environment and enables access to remote data sources via data grid technologies. This will use an OGSA-compliant Grid Service interface to Grid Engine. The hierarchical scheduler will query child Grid Engine installations at collaborating sites to determine if they are able to run a user's job. The scheduler will then place the user's job at the site that best matches the following criteria.

  1. It is capable of running the job.
  2. It has the lowest load of the available sites.
  3. It has the best access to the required data sources.

For those user jobs that are not data grid aware, a data component will handle the transfer of data between sites. The hierarchical scheduler (JOSH) has been released, more information can be found here.

For more information on the project and its deliverables please access the EPCC Sun Data and Compute Grids project home page or contact the SunDCG project team.