wiki:InfrastructureWGMeetingD20091109
Last modified 10 years ago Last modified on 11/10/2009 11:18:06 AM

We will be having our regular bi-weekly Infrastructure WG telecon on Monday, November 9, at 12 Noon CT.

Agenda

  • TG Allocation Update
    • Current Allocation
      • 30K SUs on abe
      • 30K SUs on lincoln (nVidia Tesla GPUs)
      • Available now for immediate use
      • How to get access: contact MikeF
    • Next TG Allocation Cycle
      • Proposals due Jan15 for Apr1 allocations
  • InfraWG Ticket System Update
    • InfraWG tickets moving to secure ticket system
      • Migration of existing tickets is currently underway
    • http://jira.ncsa.uiuc.edu
    • How to get access:
      1. Go to http://jira.ncsa.uiuc.edu and self-register
        • Very easy: Only your name and email address is needed
      2. Contact MikeF to get authorization to the LSST tickets
  • Cost Sheet Update
    • Current version now v63
    • Summary of Changes
      • LSST-1 Rename labels from "Operations" to "Operating Costs" (no cost change)
      • LSST-2 Rename labels from "DAQ" to "DAC" (no cost change)
      • LSST-22 Delete the WBS SUMMARY tabs (no cost change)
      • LSST-8 Remove all references to the Stand-Alone DAC (no cost change)
      • LSST-21 Include all (Non-Labor) Infrastructure Costs in Cost Sheet
        • Changed the "apparent baseline" and the total cost estimate equally, so the actual cost estimate did not change.
        • Now much easier and simpler to compare the cost sheet with the PMCS baseline.
    • Upcoming Changes
      • LSST-24 Arch DPS and Base DPS: Fast Storage: Do not assume 500GB per drive as a constant into the future
      • LSST-23 ArchAOS and BaseAOS: Slow Disk: Do not assume 1000GB per drive as a constant into the future
      • LSST-10 Update Power & Cooling at Base Site (info already received from RonL)
      • #947 Tech Predictions tab: Should the model of capacity be 3 year step functions?
      • #973 Update Power & Cooling at ArchSite
    • Next steps with cost sheet
      • Full review each of the elements of the cost sheet (boxes of the mapping document)
        • More readable description of the formulas being used
        • Identification and documentation of assumptions
        • Identification and documentation of external data input
      • Serves two significant purposes
        • Allows for better internal reviews (validation of models and information used)
        • Provides justifications for external reviews
      • Results in an updated (or replacement of) Document-1684 and related documents ("Explanation of Cost Estimates")
  • Cost Estimate for ForcedSources
  • Storage Model Costs for Maintaining CSS Database Performance
    • See my analysis document attached to the email announcing this meeting
    • i.e. the cost of going to min. # spindles for CSS database storage to meet performance requirements
    • Summary of current estimates
    • Large costs associated with this - need validation from group - error in sheet? revise model? change performance requirements? alternative technologies?

Notes

Attendees: K-T, Jacek, JeffK, RayP, GDF, Daniel, MikeF

  • MikeF will include a reference to the baseline version of the cost sheet when reviewing changes
  • During the next baseline revision, we will make the the cost sheet and cost summary sheets "change controlled" in Docushare
  • LSST-9 Estimate Cost of Forcedsources
    • Pending update to diskIO sheet Doc 1990 [Jacek]
    • MikeF will update cost estimate when Doc 1990 is available
    • Note: The cost analysis document is attached to the JIRA issue (no more email attachments)
  • RayP is drafting a document that will outline how to think about alternative architectures such as GPUs, Solid State Storage, etc. This will include the attributes and characteristics to consider when discussing these technologies.
  • LSST-27 MikeF will review HW model tab in diskIO sheet Doc1990
  • LSST-28 Mikef will estimate Cost Difference (esp. P&C) of a 3yr CPU Replacement Policy vs 5yrs
  • LSST-29 Storage Costs for Maintaining CSS Database Performance was also discussed during the call. See ticket for details.
    • Note: The analysis document is attached to the JIRA issue (no more email attachments)