LCG Management Board

Date/Time:

Tuesday 25 July 2006 at 16:00

Agenda:

http://agenda.cern.ch/fullAgenda.php?ida=a063094

Members:

http://lcg.web.cern.ch/LCG/Boards/MB/mb-members.html

 

(Version 1 - 30.7.2006)

Participants:

A.Aimar (notes), D.Barberis, L.Bauerdick, S.Belforte, L.Betev, N.Brook, Ph.Charpentier, J.Gordon, F.Hernandez, M.Lamanna, E.Laure, H.Marten, G.Merino, Di Quing, H.Renshall, L.Robertson (chair), J.Shiers, O.Smirnova

Action List

https://twiki.cern.ch/twiki/bin/view/LCG/MbActionList

Next Meeting:

Tuesday 8 August from 16:00 to 1700

1.      Minutes and Matters arising (minutes)

 

1.1         Minutes of Previous Meeting

The minutes of the previous meeting were approved.

 

D.Barberis confirmed that ATLAS, as specified in the minutes of the 18 July, agrees that the process of providing new estimates is acceptable for them and mid-August is their deadline.

 

2.      Action List Review (list of actions)

Actions that are late are highlighted in RED.

 

  • 23 May 06 - Tier-1 sites should confirm via email to J.Shiers that they have set-up and tested their FTS channels configuration for transfers from all Tier-1 and to/from Tier-2 sites. * Is it not sufficient to set up the channel but the action requires confirmation via email that transfers from all Tier-1 and to/from the "known" Tier-2 has been tested.

 

To be done: BNL, FNAL, NDGF and TRIUMF.

 

These sites will be asked individually to complete this action.

 

  • 30 Jun 06 - J.Gordon reports on the defined use cases and policies for user-level accounting in agreement with the security policy working group, independently on the tools and technology used to implement it.

 

Not done.

Presented to the GDB in June and asked for feedback. Did not receive any.

Reminded it to the July GDB.

J.Gordon does not receive any use cases he will propose some use cases himself at the GDB in September.

 

  • 20 Jul 06 - Tier-1 sites should nominate one or two representatives to the TCG. Nomination should be sent to I.Bird before the 18 July 2006. The representative should represent the needs of the sites not his/her own site or personal views.

 

Done.

The sites representatives at the TCG are Daniele Cesini and Jeff Templon in addition to Alessandra Forti.

The MB approved the nominations.

 

3.       Draft Agenda for the LCG Comprehensive Review (agenda) - L.Robertson  

 

This second draft has small changes in timing and organisation requested by the referees.

 

Les Robertson gave an overview of the agenda as discussed and agreed with the reviewers.

 

For each presentation the discussion and the comments of the MB are inline in italic black.

Monday 25 September
09:00-10:00

  • Overview, global collaboration, master schedule - 30 mins                                      L.Robertson
  • Resource usage, site availability - 15 mins                                                            C.Eck
  • Implications of changes in LHC schedule, ramp-up - 15 mins                                 L.Robertson

------------------------------------------------Coffee-------------------------------------------------

10:30-13:00
Stream A

  • Application area -                        P.Mato should organize it, discussing with App.Area the projects
    • Overview - 30 mins 
    • Simulation - 20 mins
    • Core Libraries and Services - 20 mins
    • Persistency Framework Projects - 20 mins
  • Middleware (1) -
    • Critical components and services that have not yet been deployed - 20 mins 

      Somebody from Experiments should organize it. D.Barberis for ATLAS volunteered
      to collect the information and give the presentation.
      The talk will first be presented at the MB in BNL in order to agreed on the priorities and
      features (e.g. in SRM 2.2, in 3D services, etc.).


    • gLite 3.0 experience - reliability and performance - 40 mins -

      M.Schulz should organize it.
      Speakers: someone from distribution/operations and someone from a site collecting
      the experience from the other sites.
      J.Gordon suggested that experiments could also be talking on their usage of the middleware.
      D.Barberis suggested that the experiment could give some report on their experience at that moment.
      M.Lamanna pointed out that the reviewers probably expect performance and quantitative measures
      of the middleware. Needs to be clarified with the reviewers.


10:30-13:00
Stream B

  • CERN Fabric -
    • Tier-0 +CAF status, performance, reliability - 60 mins -                 Maybe too much on CERN?
  • Mass storage progress -                                                                         One hour for mass storage.
    • CASTOR - 20 mins -                                                                  Castor team
    • dCache - 20 mins -                                                                    dCache
    • DPM - 10 mins                                                                          The MB agreed to add a short talk on DPM
    • SRM v2.2 - 20 mins -                                                                 M.Litmaath
  • Networking including the LCG OPN - 30 mins -                                         D.Foster to organize. Reduce to 20 min to make
                                                                                                                time for DPM

--------------------------------------------------Lunch -----------------------------------------------

14:00-15:30 -

  • Distributed analysis -
    • Demonstrations of distributed analysis on the grid from experiments 60 mins

      Speaker: somebody using the grid, not developing software.
      Not someone from ARDA this time,  in order to see how the common users do analysis with the grid.

      ATLAS, CMS and LHCb agreed to provide a presentation. ALICE not present at that moment.

      L.Robertson and M.Lamanna will ask more information to the reviewers in order to
      better fulfill their expectations.

  • Tour of the CERN Computer Centre

--------------------------------------------------Coffee -----------------------------------------------


16:00-18:30
Stream A

  • Middleware (2) -
    • EGEE middleware planning - 20 mins -              C.Grandi's presentation on JRA1 plans.
    • OSG middleware planning - 20 mins -                 Activities linked to OSG and their work with
                                                                             the middleware providers (VDT development and support, etc).
    • Interoperability between OSG, EGEE, NDGF - 20 mins –              L.Field’s presentation to the internal review.
  • Grid deployment and operations
    • Middleware deployment - 40 mins -                       Presented already a few times. Reduce to 20-30 minutes.
    • Operations - EGEE and OSG - 30 mins -              Someone from OSG and from a ROC in EGEE. 
                                                                               Extend to 20 min each.
    • Organisational structure
    • Operations experience
    • User support model - 20 mins -                            Someone from GGUS to explain the support model and status.

16:00-18:00
Stream B

  • Tier-1 status
    • Summary of the Tier-1 status from the internal service review - 30 minutes –
      Summary from V.Guelzow, or J.Gordon, from the LCG internal review, plus update.

    • Progress and difficulties - report from a Tier-1 site - 30 minutes -
      Report from a T1 site. How they are progressing and the difficulties encountered.
      Andrew Sansum could do it, if J.Gordon does not do the previous talk.
  • Tier-2 status
    • Overview of Tier-2 readiness - 20 mins -
      M.Jouvin from GRIF. An updated follow-on of the talk at the Tier-2 workshop.

    • Report from a Tier-2 federation - 20 mins -
      Maybe from Italy, or Spain would be good.
      The UK also has good examples but not if RAL presents as Tier-1.
       G.Merino volunteered to present the situation in Spain where federated
      Tier-2 sites are active both for Atlas and CMS.

    • Report from a Tier-2 in a country without a Tier-1 - 20 mins -
      J.Shiers will find in the Workshop Tier-2 workshop in Munich.
      Could be someone from Prague.

      H.Marten proposed that a presentation on the Russias Tier-2 sites would be useful in a future MB.
  • 3D progress - 30 mins -                                      Dirk Duellmann  will organize it. Someone from outside would be better.
                                                                            Should present the status of the sites of the Phase 1 and 2.

    ---------------------

Tuesday 26 September
08:30-10:30

  • Service Challenges
    • Progress since last review - SC3, SC4 - 60 mins
    • Experiment status - experience with SC4
      • ALICE - 30 mins
      • ATLAS - 30 mins

No comment from the MB. Speakers will be defined in September.

-------------------------------Coffee -----------------------------------------------

11:00-13:00

  • Service Challenges (continued)
    • Experiment status - experience with SC4
      • CMS - 30 mins
      • LHCb - 30 mins

No comment from the MB. Speakers will be defined in September.

  • Management - 30 mins -                 L.Robertson will organize it.
    • Planning
    • Communications issues
  • Wrap-up

---------------------------------

 

 

4.      Capacity Available and Required in SC4 (tables) - H.Renshall  

Initial analysis

 

H.Renshall presented an initial attempt to compare the capacity available at the sites and what needs to be ready for end of Q3.

 

Many changes may occur, for instance:

-          Experiments dates could be shifting and

-          Sites will receive equipment during the quarter.

 

But this is a start and this “resources table” should become more accurate and be regularly updated and analysed.

 

Note on the “Max Req” column: In some cases there is no overlap in the resource usage so the maximum required is taking into account the non-overlaps and it is maximum resources needed in any given moment.

 

From a first analysis what sticks out is:

-          CERN: problem with CPU capacity.

Comment from CERN: In September new equipment will be available. But delivery must not slip.

-          FZK, SARA, TRIUMF, PIC: all with problems with CPU capacity.

Comment from FZK: The problem is due to a problem with the BIOS and the machines are being updated. Disks are also there and will be ready with the current time scale.

Comment from PIC: The number from CMS need to be verified off-line. A tender for 200 Kspecint2k is open and then should be deployed byt early October.

SARA and TRIUMF should comment off-line.

 

LHCb pointed out that they will reassess their needs in the next weeks.

Action:
Sites should check the values and confirm them to H.Renshall. Provide explanations when there are fewer resources available than required.

 

5.      Preparation of the MB in BNL (Sept 2006) - L.Robertson  

 

 

L.Robertson asked who from the experiments will go to the MB in BNL.

 

Actions:

Experiments should confirm their participation to the MB in BNL (in person or by phone).

 

The time proposed is from 9 AM to 11 AM local time. (3 PM to 5 PM CERN time).

 

Note: Starting at 830 AM was discussed, but further inquiry showed that will be too difficult to have access to BNL in time for 830.

 

 

6.      AOB  

 

 

NO AOB.

 

7.      Summary of New Actions  

 

 

 

Actions:

15 Aug 06 - Experiments should confirm their participation to the MB in BNL (in person or by phone).

 

 

Action:
15 Aug 06 - Sites should check the values of the resources availability and required and confirm them to H.Renshall. Provide explanations when there are fewer resources available than required.

 

 

The full Action List, current and past items, will be in this wiki page before next MB meeting.