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/0122929
To dial in to the conference:
a. Dial +41 22 7676000
b. Enter access code 0165202
Production and PASTE Meeting, 21st July 2009, CERN
Chair: A.Tsaregorodtsev
Minutes: S. Paterson
CERN: J.Closier, S.Paterson, Z.Mathe, M.Rashid, V.Romanovsky, A.C.Smith, F.Stagni
Phone: R.Graciani, R.Nandakumar, A.Tsaregorodtsev, A.Zhelezov
Apologies: P.Charpentier, R.Santinelli, M.Sapunov
0. Ongoing Action List
(94) - 23/09/08 - Andrew,Marcos - Using SystemLogging service for dynamic services status monitoring (Andrew to provide FTS example)
(111) - 14/09/08 - Alexei,Andrei - Production request page, file merging and associated data distribution implementation
(116) - 18/11/08 - Ricardo - steer the CPU related activities in DIRAC, document procedures, move to the HEP CPU units
(122) - 13/01/09 - Ricardo,Vladimir - Develop specialized SAM Agent to track and report errors with regard to pilots
(133) - 03/03/09 - Matvey - Provide request DB interface page
(139) - 31/03/09 - Roberto,Stuart - Track and test glexec as it is deployed at the sites, put CE into production pending the official release
(140) - 31/03/09 - Andrew - Formulation of procedure for how to treat banning of sites based on job requirements e.g. input data / staging...
(146) - 21/04/09 - Vladimir,Joel - SAM SW installation logic by synchronizing shared areas with the CS SW specification. Should be complemented with the installed SW monitoring tools.
(151) - 26/05/09 - Andrew - Update central components with optimized BK methods using file time stamps
(156) - 02/06/09 - Ricardo,Joel - Refine VO-box setup to minimize impact of updates and maintenance procedures
(161) - 07/07/09 - Alexei - define Production Request for ongoing production to allow its monitoring
(162) - 07/07/09 - Ricardo,Andrei - document the TQ priorities algorithm
(163) - 07/07/09 - Joel - investigate possible use of CERN backup tools for log files archiving.
(164) - 16/07/09 - Matvey,Adri - Formalize and simplify the release procedure for new web portal pages (including regular DIRAC version updates)
(165) - 16/07/09 - Ricardo - Add WMS accounting for visualization of 'time to running' and other accounting metrics
(166) - 16/07/09 - Ricardo - Set up volhcb05 as the new certification machine
(167) - 16/07/09 - Philippe,Ricardo,Roberto - Ensure new middleware bindings are available and start SLC5 commissioning on volhcb12
Completed Actions:
Done - (160) - 07/07/09 - Ricardo - update the DIRAC hardware configuration paper with the current DIRAC server load plots
1. Action Updates
- Action(94) - SystemLoggingDB example
Ongoing.
- Action(111) - File merging productions & request page
Andrew was testing the production request page and this should be moved into production after new components are
committed. Stuart suggested that an organized half day to introduce the PPG and Core software people to production
requests. After some discussion it was agreed to wait until the final release is in production before involving the
PPG. A separate action is formulated for how to formalize and simplify the release procedure for the web portal. (
ACTION: Matvey,Adri )
- Action(116) - CPU studies
The HEP CPU factors published by the sites will be taken if present and Ricardo is investigating how to get this
information.
- Action(122) - Develop specialized SAM Agent to track and report errors with regard to pilots
Ongoing.
- Action(133) - RequestDB monitoring
Not yet ready after comments from Andrew.
- Action(139) - gLexec testing after deployment at new sites
Nothing to report.
- Action(140) - Banning faulty storage elements
Ongoing.
- Action(146) - SAM software distribution synchronization with the CS
Joel commented that a new module was added to the SAM suite to check the requested software is installed and
report whether orphan packages should be removed. A CS / LFC cross-check SAM test was added to the central SAM
tests.
- Action(151) - Update of central BK components with optimized methods
Ongoing.
- Action(156) - Refine VO-box setup to minimize impact of updates and maintenance procedures
Raja is preparing an agent to perform the updates and maintenance of the VO-boxes using a stored version parameter
in the CS (elsewhere from the production location).
- Action(160) - Update the DIRAC hardware configuration paper with the current DIRAC server load plots
Completed and passed to FIO.
- Action(161) - Define Production Request for ongoing production to allow its monitoring
Discussed above, this should be added before releasing in production.
- Action(162) - Document the TQ priorities algorithm
Ongoing.
- Action(163) - Investigate possible use of CERN backup tools for log files archiving.
Ongoing.
2. Production Status Report
- Report from the Production meeting
Recent CP WG requests created by Andrew are proceeding smoothly, no major problems. The last reprocessing
exercise showed many stalled jobs at CERN, this is under investigation but may be related to an announced
'transparent intervention'. With the current hardware it seems that the comfortable limit is 12k concurrent jobs with
50k jobs / day. More than 50k jobs / day could be achieved with shorter jobs however. There was some discussion
on the 'time to running' metric for user jobs. It was agreed to investigate the possibility of easily extracting this
information (e.g. WMSAccounting) and reporting it to the accounting for easy visualization. ( ACTION: Ricardo )
- Certification volhcb12 service
Joel reported that volhcb12 (SLC5) is available but the python GFAL bindings etc. are still not ready. A tarball of the
VOMS client for SLC5 is still not available. Unfortunately we have to wait until the candidate releases are available in
the AA for testing. We should ensure this point is raised at all appropriate meetings until solved. It was agreed to
separate the SLC5 commissioning from the issue of having a certification machine such that volhcb12 can be used for
that. volhcb05 can be used for certification in the meantime (SLC4) and Ricardo agreed to do that. ( ACTION: Ricardo )
3. DIRAC Tasks
Most components discussed above, only recent updates mentioned.
- Framework status
There were updates to the duration of the proxy problems that were recently discovered.
- WMS status
Andrei mentioned that CPU slots to which jobs are rounded up were different to before, it becomes more important to
accurately determine the CPU limit for productions such that filling mode can be exploited.
- DMS status
Ricardo commented that the DMS machine is at the limit (equivalent to volhcb09).
- Production Management status
The implications of running user code should be ironed out between Alexey, Adri and Matvey.
- Services deployment ( hardware, configuration )
Alexey reported that the head version of the web portal is not working. See Action (164).
4. AOB
None
There are minutes attached to this event.
Show them.