Overall smooth 2-week operation (until today)

  - new problem : 60% of pilots failing, but other 40% payload normal (2.4% failure)
  Being asked to check condor config, do not locally retry jobs that fail

  Also 2 events in BOINC queue, presumably unrelated
  - CERN operation error with DBRelease yesterday seemed to have caused job failures
  - monitoring: job count has jumped from ~2k to ~12k.  
  Presumed to be proper accounting of multicore payload.

Storage purchase

  - UM received 5x R740xd2 last week, installed, in production, adding 1180 TB usable
  Retired 2x older storage nodes (678 TB) with 4x MD3xxx shelves (including umfs11 which had the recent hardware problems)

  - MSU received 3x R740xd2 this week, racked, soon into production, adding 708 TB usable

  - net + 1210 TB