Choose timezone
Your profile timezone:
PASTE meeting
Description
CERN, bat 2 R-030
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, 17th June 2008, CERN
Chair: A.Tsaregorodtsev
Minutes: A.Tsaregorodtsev
CERN: J.Closier, P.Charpentier, A.C.Smith, A.Zhelezov
Phone: M.Sapunov, N.Brook, R.Nandakumar, A.Tsaregorodtsev
0. Ongoing Action List
(07) - 27/11/07 - Zoltan, Elisa - Ongoing new bookkeeping system development
(57) - 24/06/08 - Vladimir,Roberto - Automatic publishing of BDII / GOCDB information in the CS using
GOCDB site names and provide a summary of recent changes
(70) - 12/08/08 - Joel,Ricardo - Perform and document DIRAC3 installation in the LHCb release area
at CERN with accessible CS file (Ricardo to update the install script for LCG tag)
(79) - 26/08/08 - Vladimir - Update CS to use new host aliases
(82) - 01/09/08 - Ricardo/Adri - to provide information from accounting to allow GridMap for LHCb VO T1 activity
(83) - 01/09/08 - Stuart,Roberto - To perform glexec tests
(86) - 09/09/08 - Andrei - Document the job finalization output data upload policy
(90) - 09/09/08 - Joel - Use new ProductionOutputData JDL parameter in modules instead of creating LFNs
(92) - 16/09/08 - Ricardo - Add publishing of information to batch monitoring tool
(93) - 16/09/08 - Andrew - Improve RAW data monitoring tools
(94) - 23/09/08 - Roberto, Marcos - Using SystemLogging service for dynamic services status monitoring
(95) - 23/09/08 - Roberto - SLS and SAM sensors development
(96) - 23/09/08 - Roberto, Matvey - Dashboard SAM tests visualization, porting to DIRAC framework
(97) - 23/09/08 - Andrei - release and install DIRAC v2r21 with the new Stager code
(98) - 23/09/08 - Philippe - Check SE definitions in the DIRAC2 CS for conformance with SRM v2 end-points
(99) - 23/09/08 - Roberto - arrange for LFC entries change directly in the ORACLE back-end
(100) - 23/09/08 - Joel - ask to lower priorities of the LHCb LXBATCH non-grid queues
(101) - 23/09/08 - Zoltan - check memory consumption by the new BookkeepingManager processes.
(102) - 23/09/08 - Matvey, Adria - DIRAC Web portal installation on volhcb11, documenting the installation
procedure
(103) - 23/09/08 - Paul, Stuart - produce structured HTML version of the Shifter's guide
Update on ongoing actions:
(07) - A detailed list of tasks for the Bookkeeping migration to the new version will be provided
( Action: Zoltan, Philippe ). This will include ( to be better formulated ):
- accomplishing the BK schema (simulation conditions, processing paths, etc );
- migration of the ORACLE backend to a production service;
- check for all the occasions of using the old BK service in DIRAC3 and migrate to the new one;
- migrate complete user interfaces to the new BK service with no losses in functionality.
(09) - Action point split into (94-96)
(70) - The procedure of DIRAC installation in the LHCb release area should be smooth now.
Joel will reattempt it with v3r2.
(80) - Philippe has tested and committed the Stager code which should now be released in DIRAC2 (ACTION: Andrei);
This will be installed on volhcb04/05. Roberto will arrange for changing of about 1.4 M entries in the
LFC with the FIO people. Philippe will check the SE definitions in the DIRAC CS service to point
to v2 end-points. The action is closed and split into (97-99).
(85) - After discussions it was decided that all the LHCb users will use proxies to access BK service. The
corresponding mail was sent by Philippe to the Collaboration. Action closed.
(88) - Action done and closed
(92) - first tests are done, awaiting feedback from the LXBATCH responsible person
(93) - A detailed task description will be provided in Savannah (Andrei, Andrew)
1. Production (A.C.Smith)
Production 3035 & 3036 were affected by a faulty environment setup affecting submission and monitoring of
the corresponding pilots. This was corrected by Ricardo.
Low LHCb rank for CERN CEs was traced back to a user submitting jobs through GANGA interface with LCG
backend and consuming the LHCb quotas. It was decided to raise the question of lowering priorities of the
LHCb LXBATCH non-grid queues on the next meeting with IT support (Action: Joel, Philippe)
Many jobs were failing because of input data situated in the FAILOVER type storage due to a logical bug
in the JObWrapper (Action: Stuart). The fix to prevent job creation by the Transformation Agent for the
input data in the FAILOVER storage is put in place by Andrei.
CS was stuck again on Monday and restarted. Until the problem is fully understood and fixed in the DISET
framework, dayly restart of the CS master and slaves should be performed a la slave at PIC. (Action: Raja
for slaves at VO-boxes, Andrei for the master CS)
BookkeepingManager was stuck several time in the last week. Zoltan will upgrade the DIRAC3 installation
to the latest version on volhcb05. BookkeepingManager processes also consume a lot of memory resulting
in system swapping and degraded performance. This bahviour should be thoroughly checked (Action: Zoltan)
RequestDB has pending requests from over 11K jobs which starts to be worrying. This was mostly provoked
by stuck new BK service resulting in many failover BK requests. After restart of the service, the backlog
of requests gradually clears up. Andrew will watch thoroughly the state of the RequestDB service. The
summary of the RequestDB status will be published in the Request monitoring DIRAC web page (Task: Matvey)
2. DIRAC3 tasks
The DIRAC Web portal at lhcbweb(test).pic.es were rather slow on Tuesday morning. This stresses the
necessity to have one more DIRAC Web portal installation. It was decided to provide an instance on volhcb11
host at CERN. This should also provide a well defined and documented procedure for the web portal installation.
( Action: Matvey, Adri )
3. AOB
Philippe raised a question about the tools to be used for producing the Production and other documentation.
The LaTeX as the base tool is not easy to use. However, this is the only known, for the moment, tool capable
of producing both pdf output for printed docs and structed HTML pages for on-line browsing. The HTML pages
should now be generated and made available through the Production twiki page (Action: Paul, Stuart). Based
on this experience, we will decide if we continue with LaTeX as base tool for producing detailed stable
documentation
There are minutes attached to this event.
Show them.