ATLAS SCCS Planning 19Apr2006
-----------------------------
Present: Steffen, Chuck, Randy, Len, Wei, Gary, Stephen
Agenda:
1. DQ2 Status
No change. Setup a web proxy for the ATLAS jobs to use. Xin Zhao
has an account here now to help test it. There were a lot of
criticism about using the Pilot way of doing production at the
HEPiX meeting.
DQ2 machine ticket is 43380.
2. mysql replica Status
Will try to allocate a machine today (43381)
Seems it is out of date. Wei will see if he can update it.
3. Trigger Farm Status
Waiting to hear from Steffen on when to expect it. John has been
warned about it coming. Best bet for it coming up to SCCS in
early-mid August.
These machines will be 50 Dell 1650s. While they are no longer
appropriate for production use they will make a perfect test stand
for ATLAS trigger. (Steffen will talk to Randy after the meeting
about the replacements).
Steffen will create a ticket if there isn't one (Chuck created one
during the meeting, which is 45823). Will try to specify if they
need shelves, they could come with them.
4. ATLAS Oracle Server
Steffen is trying to determine the minimum configuration for this
machine still.
5. AOB
- Tier-2 Proposal
Richard was going to organise a phone meeting about it. Nothing
has happened recently. There have been phone meetings about the
DoE about what is likely to be a successful proposal. DoE is Saul
Gonzales and others. It may be difficult to avoid the SLAC
proposal being trumped by a University proposal that brings
matching proposal. We think Michigan will be putting in a
proposal, but they thought we'd have the edge. There is another
meeting on the phone tomorrow with DoE. Are exploring possible
university partnerships but not too likely. Currently have all
the correct content but needs to be reformatted to the form
requested. It is due in 15th May but also want to have a review
of it before submitting it. Therefore need to have it by around
the end of the month. Would circulate it by email and have a
phone meeting to discuss it. Richard and Chuck will discuss it
and move it forward.
- Long path
There was feedback on ATLAS using long paths. ATLAS are aware of
it and are working on it.
- Memory use of jobs
Not sure who to believe, the system admins watching jobs or the
job creators. One says 2GB and one 1GB per job.
Perhaps we can have a queue that does ATLAS jobs so that we only
run one of those per machine if it is 2GB. Or can have all jobs
specify their memory requirements so the batch system can use
that information to make sure machines do not get over
committed. Not clear how this will interact with the Pilot
system. "Selfish Scheduling Always Wins".
Action Items:
-------------
060412 Steffen Email unix-admin about Oracle requirements
060419 Determining requirements
060412 Systems Provide Oracle service for ATLAS Trigger testing
060419 No ticket yet, so nothing done.
060308 Stephen Check with ATLAS if there is an update mechanism
060315 No mechanism yet except for reinstall. Could ask some BaBar
folk about how we do this to see if it is applicable.
060405 No update.
060412 No update.
060419 No update.
060224 Stephen Enquire with ATLAS about certificates for DQ2 machine
060301 Not heard back from ATLAS folk, Wei pointed out a DoE
place to get service certificates.
060308 No update.
060315 No update.
060405 No update.
060412 No update.
060419 No update.
060224 Systems Provide DQ2 machine
060301 In the queue.
060308 Not done yet.
060315 Not done yet.
060405 No update.
060412 No update.
060417 Will try to allocation machine today.
060224 Systems Provide mysql replica
060301 In the queue.
060308 Not done yet.
060315 Not done yet.
060405 No update.
060412 No update.
060417 Will try to allocation machine today.
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.
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.
--
/------------------------------------+-------------------------\
|Stephen J. Gowdy | SLAC, MailStop 34, |
|http://www.slac.stanford.edu/~gowdy/ | 2575 Sand Hill Road, |
|http://calendar.yahoo.com/gowdy | Menlo Park CA 94025, USA |
|EMail: [log in to unmask] | Tel: +1 650 926 3144 |
\------------------------------------+-------------------------/
|