ATLAS SCCS Planning June 25, 2008
----------------------------------
9am, SCCS Conf Rm A, to call in +1 510 665 5437, press 1, 3935#
Present: Chuck, Randy, Wei, Steffen, Booker, Peter
Agenda:
1. Production/Operation
- All GRID athena jobs are failing; US-wide Tier-2 problem that
has been going on over a week.
- No Production jobs running either, since there are no jobs
in the queue. New batch of MC production is expected soon.
- While idling, 50% CPUs in the general queue is used by one
person named fizisist... (from Chuck's pie chart)
2. FDR-2
- FDR Washup review on successes/failures can be found here:
http://indico.cern.ch/conferenceDisplay.py?confId=35770
- All AOD files SLAC signed up for have been delivered.
Anybody using them?
- Short FDR-3 runs (1-2 days) likely in the future, while
avoiding conflicts with detector commissioning and Cosmic runs.
3. Hardware
- The Thumper order by KIPAC has been delivered. They need to
swap the hard drives from the unit they borrowed (wain010) and
return it to ATLAS. We will then have the 5 new Thumpers complete
for ATLAS Tier-2 operation.
- Purchase order for a new ATLAS server for interactive usage,
and 1/2 Thumper (shared with BABAR) has PPA directorate approval.
Order to be placed with SUN this week, before June 30 when the
special pricing quote ends.
- The new interactive machine will have RHEL4 64-bit OS, as the
32-bit OS cannot address the 16 GB memory size.
4. AOB
- We will need to reconfigure xxlong queue when the GRID production
restarts, to accommodate very long Heavy Ion collision events.
Randy will look into raising the current quota (64 per user,
160 total) to higher values (256 per user, 512 total).
xxlong queue has a 1-week time limit.
|