Minutes of the ITC-Research Computing Standing Committee

Meeting on March 29, 2004

Members: Alice, Bill, Brian, Dawn, Ed, Hamp, Kathy G., Katherine H., Jim, Mark S., Martha, Michael, Robin, Sue Ellen, Steve, Terry, Tim S., Joe Simard, Tom S.

Attending: Alice, Bill, Ed, Hamp, Kathy G., Katherine H., Mark S., Martha, Robin, Tim S., Joe Simard, Tom S.

Chair: Tim T. Recorder: Alice

Click here to see the agenda from this meeting.

I. Corrections to minutes from the last meeting on February 23, 2004?

None.

II. Ongoing Discussion Topics:

1. VPN and IP filtering for FlexLM license daemons.

· Nearly done – just a few more packages to do – Matlab switches tomorrow.

2. UnixLab machines – Console logging turned on and can detect direct logins (which is sufficient). Notes:

· We need usage stats to make/justify choices about future uses for the room – so we want to see who is logging in and out of the console.

· The machines are aging – do we replace with workstations? Or PCs/linux? Or nodes? In any event we need to start publicizing that the SGIs will be going away as they fail – so need to generate a list of who is using what on the SGIs.

· Decided to put the clustering of the unix lab machines on a back burner – and instead work on making the orange and teal cluster ready as a compute cluster.

3. Update on Orange and Teal clusters to latest PBS Pro version; move crick.med behind firewall.

· Put crick behind ACHS firewall for HIPAA use -- this depends on solving the problems with watson (bad performance with database builds and bus errors) – do not want to do anything with crick until get the watson situation resolved –have been trying different hardware components on watson

· Teal Cluster: Dependent on sorting out the problems with Watson. Proposed: PBSPro upgrade. Put 2 processors removed from crick and put into one teal node; use Craylink to hook them together. If other 4 CPUs are compatible, link them as well. Define a “teal-login” machine – block interactive login on all but teal-login.

· Orange Cluster: PBSPro upgrade complete. Define “orange1” as the “orange-login” machine – block interactive login on all but orange-login.

· Long term goal is to have routing queues set up (or Condor-G) so that users can log into central system and submit to any PBS queue we have.

4. DNS allocations in 10.x.x.x range update:

· No meeting yet – still looking at some segment of this range as a free-for-all (and not routable at all) and another segment as restricted and routable within UVa; need to make and publish recommendations for how departments can use it and the limitations of this scenario.

· This needs to get nailed down – via email? Catalog what is being used – reserve some blocks – and then announce (especially need to announce to LSPs).

· Also need a guide for departments and our own ITC staff on using the 192.168.x.x space.

5. Update on SEAS SUR grant clusters – Mitch contacted Tim T.

· SEAS has had some testers, but wants us to do some general testing and then help with marketing to SEAS.

III. New Topics:

6. Timeline for installation and testing of Aspen & Birch clusters to 2.6 kernel?

· Lots of unknowns right now – dependent on ROCKS – could aim for last week in July.

· Think we should get a performance boost from 2.6 with respect to I/O scheduling.

· Hera @ RCSC could be upgraded to Fedora Core 2 when that is available and could serve as a test platform.

· Upgrade to the Intel compiler 8.0 will be done at the time of the OS upgrade.

· Next version of IMSL will be compiled with the Intel compiler, version 7.0 (maybe 7.1) rather than the PGI compiler. Therefore we have to be sure to retain the rpms even if Intel doesn’t keep them available at their Web site.

· We can retain the two 7.0 licenses as long as we wish and use them concurrently with our 8.0 licenses, since the compilers are purchased rather than “leased.” However, the Intel representative was not able to change our 7.0 licenses to work on aix.license. Therefore we will need to keep an Intel compiler license manager running on jeeves.

7. Cost and funding alternatives for a 64-bit frontend of the SMP?

· Hamp thinks we may be able to get one with older technology (an H70) from our old dump machine since we are getting a new dump machine from SEAS. Should be within the next month or so.

8. ITC’s research computing “whitepaper” draft:

· See Tim Sigmon’s recent email on this topic and send all comments to Tim – and then we can re-iterate. Tim S. is willing to do the re-write.

Next meeting is Monday, April 26, at 10:30 AM. (This meeting was cancelled; so next meeting was May 24, 2004)

Go to: ITC Research Computing Standing Committee Home Page