ATLAS SCCS Planning 26July2006
------------------------------
SCCS Conf Rm A, to call in +1 510 665 5437, press 1, 3935#
Present: Steffen, Randy, Stephen, Charlie, Len, JohnB, Chuck, Shirley, Wei
Agenda:
1. DQ2 Status/Web Proxy
There will be a meeting next week about the web server
approval. There are probably a long list of questions that are not
well defined. John will try to get a list prior to the meeting.
The typical clients are the SLAC batch system to get input data and
put output data. Other major clients are BNL to transfer the data
out and folk who run production to monitor it.
Who will complain if it doesn't work? At the moment suspect it will
be BNL folk.
Other questions, where does code come from, who updates it for
security updates? What data it is serving?
2. Trigger Farm Status
The power will not be available before September, probably more
like October. Will install in IR2 for now.
3. ATLAS Oracle Server
Steffen has suggested a name and that it is okay to put it in the
IFZ. Not sure where this falls in the priority list of John's
queues. Has power for 128 BaBar machines and after that 64. 24 of
those are for SSRL and 25 are GLAST, 8 for RD.
4. Slots for ATLAS Production jobs and other batch related stuff
Might be useful if we can increase the number of jobs. Perhaps
should make a dedicated queue for this. All production jobs run as
the same user so having a per-user limit isn't useful in
general. Will add it to the 45 queues we have...
Can we add more resources to the new queue? If we look at all the
public and BaBar jobs slots on 32% are used. Typically it has been
less than 50%. GLAST is getting ready for two data changes (dealing
with live data from the LAT) starting in August. Is there a forum
to discuss sharing resources? Neal and Randy are trying to set
something up.
Also need some ability to do other simulation for local
users. Should we continue to use the generic queues or create an
ATLAS specific queue? Would prefer to use the general queues with a
fair share list. Should ask for this to be created. Charlie will
request this (of Neal and unix-admin).
5. Panda use of /tmp
Panda jobs have been using /tmp. Some need up to 5GB per job. All
machines beyond the tori (perhaps not with HyperThreading turned
on) has enough space. Could think about adding a disk to some
nomas, not that we normally like to make machines different.
The ATLAS jobs currently have no way to request this but have asked
Wei to hack the request ('-R scratch > 5') into the lsf.pm module.
6. DQ2/Data Management Workshop 28/29th September 2006 @ BNL
SCCS and SLAC's travel are over committed already so need to get
this on the list as soon as possible.
Wei is the point person for ATLAS in SCCS. He will be spending most
of his time on ATLAS. Wei will hopefully go.
7. AOB
News: We're officially on ATLAS and the Tier-2 was approved. Wei is
the lead person for handling ATLAS. The majority of his time will
be worrying about and taking care of ATLAS.
Need to also get an idea of how much memory is needed for
jobs. Also want to know about what is required for local
storage. The latest production release has been delayed to allow
developers to reduce the memory usage.
Money for the Tier-2 meant to arrive around the 1st
September. Would like the hardware in production before the end of
November, so need to get the door out the door before the end of
September.
There is a chunk of the lab budget for air cooling but not for
water cooling. Which means that the visible cost would be a lot
larger for water cooling.
Action Items:
-------------
060726 Randy Talk to Richard about DQ2 Workshop
060726 Charlie Request ATLAS LSF priority group
060726 Stephen Find out about maximum memory and local storage per job
060628 Stephen Arrange phone conference for future 9am meetings
060704 Done for today, need to redo for future meetings.
060726 Done. Same number.
060412 Systems Provide Oracle service for ATLAS Trigger testing (RT
46089)
060419 No ticket yet, so nothing done.
060426 Now have ticket 46089.
060503 No news.
060524 Steffen has provided configuration information. Now in
Chuck's
hands.
060628 Randy will ask Chuck about status.
060726 First on list for V240 but not sure when it will
happen. Will put a T3a on it.
060224 Chuck Will check on web server request for DQ2 machine
060301 Waiting for web server request information from Stephen.
060308 Haven't checked yet; haven't received Stephen's request yet.
060315 Still not sent Chuck information.
060405 No update.
060412 No update.
060419 No update.
060426 Resubmitted request as it was lost before.
060503 Not heard anything for about two weeks.
060524 Stephen need to update ticket, moving from yakut to DQ2
machine.
060628 Request updated now running on atl-dq2, waiting for scan.
060726 Meeting on Monday about this.
060224 Richard Discuss ATLAS trigger machines with others in SCCS
060301 Only limited response from John W was resigned
acceptance... need to work on an actual deployment plan as
there are real issues to be solved.
060308 John aware and in plans as much as anything is. New
engineer will take over.
060315 No update.
060405 No update.
060412 No update.
060419 No update.
060426 No update.
060503 No update.
060524 RT 45823. Engineer looking at power availability. On track
for
August.
060628 Understand schedule, Randy will make sure John is aware.
060726 Need to nail down when power will be available. Steffen
things he can make it happen with existing equipment.
