Professional biography of Ben Clifford

Contact email: benc@ci.uchicago.edu.

Employment

University of Chicago Computation Institute, May 2006-present

I work on Swift, a programming language and execution environment for coarse grained distributed parallel data-centric computation. development of the system itself, work on underlying components (such as the Globus Toolkit), and support for applications built on top of the system (and its predecessor, the Griphyn Virtual Data System).

I am also involved in education, outreach and training activities for Globus and the Open Science Grid.

USC/Information Sciences Institute (ISI), Center for Grid Technologies, 2002-2005

Title: Programmer Analyst III / Programmer Analyst IV

My activities under Dr. Carl Kesselman in the Center for Grid Technologies were quite varied:

• Developer and a technical co-ordinator for MDS (the Monitoring and discovery (MDS) component of the Globus Toolkit) in a team of ~4 programmers
  Worked on three versions of MDS:
  • MDS2: OpenLDAP, multi-platform information gathering scripts (Linux, Solaris, IRIX, AIX) ; OpenLDAP database backends in C.
  • MDS3 and MDS4: Web-services (WSDL, SOAP, OGSI, WSRF) in a Java environment under Linux, with some C and shell script coding. XML was used heavily, with a focus on XSD and XPath.
• Creation and presentation of technical tutorial and demo material on MDS and the whole Globus Toolkit (notably a full day 'Build A Service' tutorial) at conferences and other events nationally and internationally
• Administered grid applications running on CGT's unix servers
• End-user support for the Globus Toolkit, online and in-person
• Participated in the Global Grid Forum, representing some of ISI and Globus' monitoring interests.

Custom Networks, 1997-2001

At Custom Networks, a small IT company in the Greater London area, I worked in several areas:

• Internet Service Provider (ISP) server deployment and management: Linux, sendmail, BIND, apache httpd.
• Design and implementation of business specific database applications: MS SQL Server, MS Access, Visual Basic for Applications
• Office IT system deployment and management for small businesses. Windows NT/2000; Microsoft BackOffice and Office suites

Education

Queen Mary, University of London, 1997-2001

M.Sci in Mathematics, Upper second class honours. In particular, I focused on discrete mathematics, whilst for my masters project I learned some Latin and translated part of Newton's Principia Mathematica.

EPCC, University of Edinburgh, Summer 2000

Summer Scholarship Programme, consisting first of introductory courses on high performance and parallel computing followed by an eight week individual project investigating the use of Jini in a grid environment. See report below.

University of California, Los Angeles, academic year 1998-1999

University of California's Education Abroad Program. GPA: 3.644. Twice on Provost's Honors List.

Publications, papers, articles, reports, tutorials, writing

Grid monitoring:

• Monitoring Clusters and Grids, Jennifer M. Schopf and Ben Clifford, ClusterWorld magazine, August 2004
• MDS: The Globus Monitoring and Discovery System, Ben Clifford, ClusterWorld magazine, Febuary 2005
• I have presented repeatedly on several generations of MDS, for example at GlobusWORLD events in 2003, 2004 and 2005

Replica location:

• Implementation and Evaluation of a ReplicaSet Grid Service Mary Manohar, Ann Chervenak, Ben Clifford, Carl Kesselman, presented at 5th IEEE/ACM International Workshop on Grid Computing (Grid 2004), Pittsburgh, PA, November 8, 2004.
• A Replica Location Grid Service Implementation Mary Manohar, Ann Chervenak, Ben Clifford, Carl Kesselman, Data Area Workshop, Global Grid Forum 10, March 2004.

Tutorials:

• I was one of the principal authors and presenters on several generations of the Globus "Build A (Grid) Service" tutorial, which has been presented in total to many hundreds of people around the globe. I was fortunate enough to be able to attend many of the sessions to present in person. Significant presentations include the double-sellout full-day sessions at Supercomputing 2003 and the very first GT4 WSRF core tutorial (half-day) which I authored specifically for the the 2nd GGF International Summer School on Grid Computing in 2004.
• In 2006, I was heavily involved in the preparation of materials and systems and presentation of sessions at the OSG Summer Grid Workshop on Padre Island, Texas.

I participated in the Grid2003 project which resulted in this paper:

• The Grid2003 Production Grid: Principles and Practice, The Grid2003 Project
  The Grid2003 Project has deployed a multi-virtual organization, application-driven grid laboratory (Grid3) that has sustained for several months the production-level services required by physics experiments of the Large Hadron Collider at CERN (ATLAS and CMS), the Sloan Digital Sky Survey project, the gravitational wave search experiment LIGO, the BTeV experiment at Fermilab, as well as applications in molecular structure analysis and genome analysis, and computer science research projects in such areas as job and data scheduling. The deployed infrastructure has been operating since November 2003 with 27 sites, a peak of 2800 processors, work loads from 10 different applications exceeding 1300 simultaneous jobs, and data transfers among sites of greater than 2 TB/day. We describe the principles that have guided the development of this unique infrastructure and the practical experiences that have resulted from its creation and use. We discuss application requirements for grid services deployment and configuration, monitoring infrastructure, application performance, metrics, and operational experiences. We also summarize lessons learned.

As a student, I worked on JiniGrid at EPCC in the University of Edinburgh, producing the following final report:

• JiniGrid: Specification and Implementation of a Task Farm Service for Jini.
  Edinburgh Parallel Computer Centre SSP Report, EPCC-SS-2000-02, September 2000.
  Download: [PDF 974k] [PS 2055k]; There is an also a poster: [PDF 612k] [PS 1244k] [CiteSeer]
  Jini is a technology that allows networks of heterogenous services to organise themselves with little human intervention. It provides for fault tolerance and for the automatic transfer of driver code, written in Java, when and where it is needed.
  These abilities will be extremely useful, if not essential, in a large scale environment such as the Grid.
  In this project, Jini technology is used to share compute servers using the task farm paradigm.
  A standard API that all compute servers must implement is defined. Four implementations with different capabilities are presented, as well as a selection of clients and helper classes.

For my M.Sci project, I was persuaded to refresh my Latin and read some of Newton's work under the watchful eye of Charles Leedham-Green.

• A translation of part of Newton's Principia
  M.Sci Project, Queen Mary and Westfield College, University of London, April 2001.
  (n.b. There are a number of cosmetic differences between this text and the text submitted for the degree)
  Download: [PDF 332k] [PS 353k] [DVI 139k]
  Newton's Principia provides the basis for modern Newtonian dynamics. Many of the results have survived the last three hundred years with little or no change. In this report, an English translation of a part of the text is presented, along with commentary.