2012 Software Review Planning Meeting: Mar. 23, 2012

From GlueXWiki
Jump to: navigation, search

Main Hall-D Software Review Page


Connecting

Phone:

  • +1-866-740-1260 : US+Canada
  • +1-303-248-0285 : International
  • then enter participant code: 3421244# (remember the "#").
  • or www.readytalk.com (and code without the #)

Agenda

At CMU: These resources are split with our lattice QCD group with whom
we share operations of the cluster. All CPUs are roughly 2.4GhZ nodes and
all are under three years old at the moment.

32       dual-quad core AMD machines      ->  256 compute cores 1GB core per CPU
12       quad-eight-core AMD machines    ->   384 compute cores 2GB core per CPU
180TB of RAID storage spread across several servers
10Giga-bit backbone from the RAID servers to the switches and 2Giga-bit connections
to each compute node.


Over the next few years, we anticipate purchasing around 16 boxes of the next
generation of CPUs (quad-sixteen or thrirty-two core boxes). We also expect to
double our disk storage capability as we start to retire some of our very old few-TB
servers. 

At FSU: this is what we have at the moment:

4   AMD Opteron 48-core computing servers   -->  192 cores
20  Intel quad-core computing servers       -->    80 cores
300 GB of RAM
85 TB of storage accross 6 RAID servers
1 Giga-bit network connections between servers and 10 Giga-bit network backbone from campus.

Minutes

Attendees: David L., Mark I., Curtis M., Matt S.

There will be no meeting next week as Curtis and Matt will be unavailable and David and Mark were wanting to attend a seminar at JLab on PWA+GPUs.

Status of Review Organization

March 30-April 4

David showed a draft list of "tight spots" and "weaknesses" and we discussed every item. Several wording changes were suggested that David will implement. We also decided to reorder the list to have items that are "must-haves" at the top with an indication of the border with the "would like to haves" at the bottom.

An incomplete draft of the plan for the management structure was shown. Several suggestions were made to this. Some things were unclear what the best way to display them was. David will modify the figure into 2 or 3 possible drafts that we can then discuss which works best.


Cross-Hall Collaboration

David reported that Sergey has sent him the source for Mini-hbook. It is not a pressing issue so he will look at it as soon as time allows.

Organization of Hall-D preparations for Review

Software Manpower, Schedule, Milestones/Challenges, Calibration

No significant changes on these since last time.

Computing Resources in the Collaboration

Curtis has received only one response to his request for computing resources. He will follow up with institutions he believes have access to significant farms to complete the list.

Other

We discussed briefly that Rolf wants each hall to provide a Research Management Plan. We also need to start work on the software section of the new CDR document. The two may have some overlap.

At some point, we also need to start gathering information from the collaboration on what effort has already been made on calibration. (IU was mentioned as having already done an exercise.)

Action Items

  • Modify Tight spots/weaknesses list (David)
  • Modify Management structure diagram (David)
  • Start outline for the written material that will be used for the CDR and provided to the reviewers. (David)
  • Resend request for CPU resources (Curtis)
Retrieved from "https://halldweb.jlab.org/wiki/index.php?title=2012_Software_Review_Planning_Meeting:_Mar._23,_2012&oldid=80331"