Notes from the ITC-Research Computing Standing Committee Meeting
January 28, 2008 at 10:30 AM
2015 Ivy Road, 1st Floor Conference Room

Members: Alice, Hamp, Jim, Joe S., Mark, Mike, Robin, Terry, Tim S., Tom, Tim T. and members of Systems, Research Computing and ACHS as desired

Attending: Alice, Hamp, Jim, Sean for Joe S., Tim S., Tom, Tim T., Katherine, Kathy
Chair: Tom
Recorder: Alice

I. Corrections to minutes from last meeting on December 17, 2007?
(Click to review the agenda from this meeting)

II. Old Business:

• Update on CSAC, NSF PetaScale Track 2 meetings, and related.
• Computational Science center (UVACSE)? This was discussed at the January CSAC meeting. The essence of the discussion is to declare it exists – seed it with some existing resources (staff, cycles) – and create a faculty governance board responsible for allocating its resources. Many details remain to be worked through.
• The next "condo cluster" planning. Will there be a cluster? A condo?
  (Current (two-year-old) web site: http://itc.virginia.edu/research/itc-clusters/ ) We do not have enough money to replace Cedar – so we will extend both Cedar and Dogwood by a year. Matt Neurock may be interested in buying some Dogwood nodes – it would be easy to buy some new nodes and integrate them into the existing Dogwood cluster – wait and see.
• Public forum on queuing policies - in late January (unlikely) or early February. (Tim T.: "Is it moot?")
• Doing a public forum is probably moot for the moment – hold off for awhile and see how the faculty governance board evolves – but it would be good to have one queuing policy for everything.
• Ed & Katherine's review of other institutions queuing and cluster purchase programs.
• Katherine has gathered some information while at BioMed HPC Conference in Boston. Several had 3 queues (default, short, and dedicated queues for node purchasers).
• Katherine's 2006 proposal PBS Service Units Proposal (keep on the agenda?) We could pass on these materials and ideas to the faculty board and wait and see what that group wants to do.
• CSAC request to Tom for report on current cluster use vis-a-vis PBS queue use/analysis.
• Looking at what applications 8 possible TeraGrid candidates are using -- talking to one of Matt Neurock’s grad students.
• Linux Clusters: Cedar, Dogwood Elder
• Downtime for UPS switchover? Might be in March. Cedar is done. Dogwood and Elder remain – might be able to do as a rolling switchover.
• Summary of HPC Bootcamp January 7-11.
• Had 45 registrations with 32 showing up for the lectures, and 20 showing up for the hands-on sessions. It was well received – all who attended the hands-on sessions were new folks. The pre-Bootcamp Unix course was also well attended (~25 people) – and it did make a difference in their ability to move around in a file system and use an editor – most new-to-Unix folks are unfamiliar with command-line processing.
• Update on Computational Science Speaker Series? Next speaker is Jack Dongarra (Univ. of Tennessee, ORNL) on Feb. 11 at 3:30.
• Update on A-School (Earl Mark & Eric Field) possibly having HPC windows compute cluster and harvesting idle cycles from office PCs and labs & classrooms.
• Eric Field is getting the software working on their machines.
• Establish our Operating Agreements: Some possibilities:
• Discussion of purpose of group: is it a Big-picture & Policy group? A Nitty-Gritty operational group? Is this group doing what it should be doing (policy, Big-picture, nitty-gritty, etc)? Going forward we will want to communicate with the new faculty governance group and see how we want to work together.
• Use of systems and itc-rescomp mailing lists – will keep using these lists as we have been using them.
• Notification of attending or not? Will notify the whole group about meetings via email – and put the meetings on the “core group’s” Exchange calendars. Please send Tom email if not coming.
• Start and end on time? We will not build in travel time to the meeting schedule.
• Meeting day and time? (It's currently last Monday, not fourth Monday of the month.)
• End meetings with clear requests and promises for action.
• Don't leave meeting with unspoken issues or concerns.
• Others?

III. New Business:

• Any news, information from E-School? SURA? CSAC brownbags? UCIT? Other organizations?
• Biomolecular Research Facility purchasing high-throughput DNA sequencer that could generate up to 20 Terabytes per day; not clear presently how much can be discarded after screening.
• Any other Items?
• The Scholars Lab and Research Lab are sponsoring a Spring Speakers Series – the schedule is coming out soon.
• Completion and review promises and requests from this meeting.

IV. Adjourn by 11:45 and next meeting

• Next Scheduled Meeting of ITC ResComp Standing Committee: Monday, February 25th, 10:30 AM in ITC-2015 Ivy Road, Room #102 (First Floor Conference Room)! (Note: Tom can't make it – so Tim T. will chair it.)
  Please send suggestions, additions, corrections to: Tom or Alice

Go to: ITC Research Computing Committee Home Page