Minutes of the ITC-Research Computing Standing Committee

Meeting on November, 2003

 

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

 

Attending: Alice, Ed, Hamp, Kathy G., Katherine H., Mark S., Martha, Robin, Steve, Terry, Tim S., Tom S. – plus guests Bryan Wright and Joe Simard.

Chair:  Tim T.  Recorder:  Alice

Click here to see the agenda from this meeting.

 

I.    Corrections to minutes from the last meeting on October 31, 2003

            None.

 

II.   Ongoing Discussion Topics:

1.  SP retirement on 12/15/03

·     Letters emailed to the active users (19 since June, and 22 users from 9/02 – 9/03).  Have already seen some of their ids on the linux cluster.  The SP is going to surplus.

2.  VPN and IP filtering for FlexLM license daemons.  Several vendors are now requiring it, not just ESRI.  Can we implement on a separate license computer by mid-January?

·.Yes – it’s do-able by mid-January.  Involves new license files and fixing port addresses.  Does allow users to tunnel using ssh instead of having to use the VPN.  Will need to document.  Tim’s group will work on documentation

·  Also ongoing concern about what is the “UVA community”?  Would it include Mountain Lake? Blandy Farm, etc.?  What would happen to Continuing Education sites and students?  Only users in whois can get a certificate for the VPN.  Need to check with Jim on who can get blue.unix accounts.

3.  Clustering Unix Lab machines – Console logging turned on?

·   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.  So Unix Systems will get current version PBSPro on Orange & Teal.

4.  Aspen Cluster:  200GB disk on frontend, re-installation today.

·    Installation is progress – it’s been running fine with the new cable.

5.  Ganglia/Gmond usage page – Making “ganglia” graphics work for Unix Lab computers?

·    Steve has looked at this and it is difficult and a lot of work – whether this is worth it rather depends on the future direction of the Unix lab.  Decided to hold off on this for now.

6.  PBS Pro upgrade on Birch to get in version sync with Aspen over winter break?

·    Bill to look into how complicated this is – Hamp will check with Bill.

 

III.   New Topics:

7.  Transition from RedHat Linux to replacement.

·    Do we need separate CDP? Group thought no, not at this point.

·    What to go to, how to decide, how to support, rollout, etc.

·    Make sure we get LSP and current user-base input

The RedHat situation is changing with their decision to terminate support for “RedHat Linux”.  Possible licensing arrangements for Enterprise Linux are not clear – they are also making Enterprise Linux free and opensource – but that would put a lot of burden on systems staff.  Concluded that we do not have enough information to make a decision now – Hamp thinks they will end up at doing their own distribution if licensing and cost is reasonable. So we should monitor for the time being.

8.  Struggling with having enough space on holmes to install/upgrade ResComp software that is big enough and able to write as root

·    Hamp will see if he can make their partition bigger, around 20GB; also Robin says that Olaf is changing his backup protocol to work around the problem with /common.

9.  Two Charges from Dr. Reynolds:

·    “White paper” on next steps in ITC’s research computing infrastructure by mid-February.  Katherine and Ed already have a rudimentary start, so we’ll continue and pull together a draft to circulate, drawing from the RCTF and the three ad hoc faculty committees, two of which have final reports we can incorporate recommendations from.  Katherine and Ed will circulate a draft before Christmas for discussion at the 12/22 meeting.

·    Dean’s Technology Council on December 10:  mass storage/large storage needs.

o        Pick up on discussions from RCTF ad hoc committee, include key people from that and produce draft for December 10 DTC meeting – lay out what we have – who can use it – for what kind of needs – and where we see the “current holes”.

10.  Leo Zhiglei (lz2n) wants to buy a cluster – working with his students testing on our cluster.  He’s talking with his Dean and Mitch Rosen.  He’d like his housed in MEC so his students can have hands-on experience on setup, maintenance, and administration – they need current technology.

·    So how to steer or help them?  ITC could do support contracts for clusters.  Perhaps we should offer this as a service.

11.  ITC’s strategic planning:  do we have specific input we want to suggest?

·    None was suggested at the meeting.

 

 

Next meeting is Monday, December 22, at 10:30 AM.

<--- Go to: ITC Research Computing Standing Committee Home Page