Some Thoughts on
Goals of Working Groups

D. Olson
30 June 1997

 

Reminder of Project Goals

  1. Produce 50 TB dataset of typical experiment. Should mock up 2-year running for STAR and PHENIX.
  2. Dataset should have "signals" which can be queried at least at every order of magnitude in density. Something every event (like STAR E-by-E characteristics), something every 10 events like cascade or D or low-Pt bubbles, something every 10**2, 10**3, 10**4, 10**5, 10**6, 10**7 events.
  3. Dataset should consist of DST, uDST and event-generator (final physics event) type data.
  4. Ability to analyze new queries.
  5. Ability to re-structure (reorganize) 50 TB in xx? hours.
  6. Ability to query 50 TB dataset (on tape) and select (move through analysis CPU's) 1 TB in 5 hours.

General Goals

  1. Define tests to do over the next several months in order to make the choices for the final implementation.
  2. Identify tasks & assignments.
  3. Identify specific requirements.
  4. Assign responsibility to write up sections for the project description document.
  5. Estimate manpower.

WG on Clustering and Object Store

  1. Consider implications with and without Objectivity / RD45.
  2. Consider relationship between storage objects (containers, clusters, files, tapes, ...) and physics objects (events, tracks, points, hits, vertices, particles, ...). How does this relationship get expressed in C++?

WG on Simulations and Data Generation

  1. Event format for generators.
  2. Matrix of number of events to produce vs. source (generator, geant, ...)
  3. Data volume and CPU time requirements.
  4. Determine amount of data to produce directly.
  5. Determine amount of data that can be "duplicated" by randomizing the original in some fashion.
  6. Determine signals to put into data.

WG on Object Model & Performance Monitoring

  1. What parameters of storage objects and physics objects need to be monitored?
  2. What parameters can be monitored (via HPSS, via Objectivity, via alternative)?
  3. What integration is required for prototype implementation and final implementation?

WG on Proto-type Implementation & Facilities

  1. Describe I/O in STAF.
  2. Identify prototype scope (see note from Soren).
  3. Identify required resources & facilities.
  4. Consider architecture of final implementation.
  5. Identify what is known about NERSC & RCF facilities.
  6. Consider SciTL - Scientific Template Library.