p20 repro:

Amount of data to be reprocessed:(info from Mike D)
currently we have 300M events on tape and with current rate of data
taking, we will have about 400M events by the end of October.
Each day of delayed reprocessing gives another 3M events.

Status of basic tools:
d0repro tools - ready (Daniel)
samgrid       - ready to test, minor upgrades may be needed
d0reco        - waiting for final version and calorimeter calibration
d0db-proxy servers - should work, but tests needed!

v7 deployment:
    Big SAMGrid site particpating in reprocessing will be CCIN2P3 Lyon.
    Completely new SAM station is being installed, then first tests
    and certification will be done.
Data distribuion/prestaging:
  - worries about ability to feed ~2000 CPUs with data
  - importance of early datasets definition and their prestaging
    on the processing sites stressed
  - for OSG sites multiple cashes close to CPUs could be a solution
     this needs more detailed investigation and a knowledge of CPU
     resources location (Gabriele)