Choose timezone
Your profile timezone:
PASTE meeting
→
Europe/Zurich
2-R-014 (CERN)
2-R-014
CERN
Description
CERN, bat 2 R-014
To join the telephone conference, click here: https://audioconf.cern.ch/call/0165202
To dial in to the conference:
a. Dial +41 22 7676000
b. Enter access code 0165202
Production and PASTE Meeting, 3rd March 2010, CERN
Chair: A.Tsaregorodtsev
Minutes: S.Paterson
CERN: P.Charpentier, J.Closier, Z.Mathe, S.Paterson, V.Romanovski, R.Santinelli, A.C.Smith, F.Stagni
Phone: V.Fernandez, R.Graciani, E.Lanciotti, R.Nandakumar, M.Sapunov, A.Tsaregorodtsev, A.Zhelezov
Apologies:
0. Ongoing Action List
#10907 - Steer the CPU related activities in DIRAC, move to the HEP CPU units - Ricardo is pursuing the implementation of the new units.
#10912 - SAM installed SW monitoring tools - The SAM DB URL will be added to the Savannah action, Joel will debug the SoftwareReport module.
#11084 - Recover site mapping accounting plots and site actions - Adri is to confirm the status of this action.
#11163 - Site summary pages - Federico is collecting all relevant site related information. The format of the data is to be decided through coordination with Matvey.
#12383 - LHCb resources status monitoring as SAM sensor - Ongoing.
#12384 - Alarms set by the Resource Status System - too many notifications were being sent so this was reduced. Ongoing.
#13405 - Keeping Real Data on disk at CERN - Joel commented that the service class of the pool is still pending.
#13406 - Testing data access with xrootd protocol - Philippe mentioned that the name of the xroot protocol was not consistent between the sites but was not an issue for us.
1. Production Status Report
- Current productions
Over 20 productions for around 40M events were launched yesterday and are running smoothly so far. As soon as some real data becomes available the EXPRESS and FULL streams will be put in place, releases of Brunel and DaVinci are becoming available for this. The problem uncovered with the DataRecoveryAgent last week is due to incompatibilities after the upgrade and will be carefully debugged.
2. DIRAC Release Update
- DIRAC v5r1 prerelease
The v5r1 release is still being prepared. Since SVN branches will start to be utilised Andrei conveyed there were some teething problems with hidden differences between otherwise identical files.
3. DIRAC Tasks
- ResourceStatus System status
Roberto mentioned that the ROOT file access tests have been moved to 'critical'. There is a possible problem with file access at NIKHEF, the local dCache tunnel library was not installed, Roberto will update the test to reflect the same settings as the modules and will provide an additional test to confirm the site libraries are sane.
- Framework status
Andrei mentioned that the Administrator service is now quite stable and the associated web portal development has started.
- Bookkeeping status
Zoltan mentioned a few fixes had been implemented.
- DMS status
Minor bug fixes.
- Production Management status
Alexey reported the work is in progress on the production request page. Andrew added new plugins based on shares from the CS and distribution of RAW data.
- VO-boxes
Andrei asked Raja to send him the VO-box paper link in order to propagate changes, one more port must be opened for management of the installed components. Another of the requested improvements would be the use of SQUID caches to improve the latency of the software distribution. Elisa has a prototype for the software installation via SQUID.
- Web Portal
Philippe mentioned there are a few pending changes such as the menu reorganisation and the usage of the new graphics library. Andrei mentioned the new graphics libraries will be used in the upcoming release. The full split of LHCb and generic code has been performed but testing is ongoing, how to implement the configuration settings is the last major issue to be resolved.
- Services deployment ( hardware, configuration )
The retirement of some older machines will proceed at a slow pace.
4. AOB
Elisa asked whether the pace of data removal had significantly changed recently, Andrew confirmed nothing had been removed for some time. Philippe reported that the DC06 cleanup was announced without any complaints so should start after the LHCb week.
Philippe reminded that the LHC is starting and there should be more frequent production meetings with the onset of real data. A plugin for managing the runs by file type and size will be added by Andrew.
Andrei asked whether names should be assigned to the bullet points in the agenda for the Tier-1 jamboree, it was agreed to rediscuss this on the mailing lists. Roberto and Joel were asked to ensure the presence of a representative from Tier-0.
There are minutes attached to this event.
Show them.