LCG Management Board



Tuesday 13 December 2005 at 16:00




(Version 1 - 17.12.2005)


A.Aimar (notes), D.Barberis, L.Bauerdick, L.Betev, I.Bird (chair), T.Cass, C.Eck, T.Doyle, I.Fisk, D.Foster, B.Gibbard, H.Marten, G.Merino, B.Panzer, L.Robertson, J.Shiers

Action List

Next Meeting:

Tuesday 20 December 2005 at 1600

Minutes and Matters Arising

Minutes of Last Meeting ( minutes )


Minutes approved.


Action List Review (15') ( list of actions )


  • 06 Dec 2005 - CNAF should send milestones for Tier1-Tier1 and Tier1-Tier2 operations. For next MB meeting.


Still to do. No CNAF representative present at the meeting.


  • 06 Dec 2005 - ALICE, ATLAS and CMS should fill the VO boxes questionnaire on operations and send it to the GDB.

On the way. LHCb done.
ALICE, ATLAS and CMS said that they will send the questionnaires before Monday next week.

The latest information is maintained on the wiki page:


  • 06 Dec 2005 - J.Shiers - Confirm the reporting and tracking of operations problems deriving from the CMS data transfer service.

On the way.

Answer from J.Shiers to the MB mailing list:
We clearly need to improve / formalise the whole problem tracking / support / operations process. This is something that we are working on. At the Asia-Pacific T1-T2 workshop last week, it was proposed that we move the LCG 'SC' con-call to Monday to follow the existing operations call (with perhaps a 15' 'convenience' gap for people to disconnect / (re-)connect. A proposal for streamlining support has already been made at the recent GDB / LHCC review. So whilst it is correct that CMS and other experiments participating in the con-calls do bring up any on-going issues, this is not followed in a systematic or rigorous manner today.



Move the LCG SC weekly conference call to Monday, right after the EGEE. Attendance should become more formal, with minutes of the meetings and with regular participation by sites and experiments. An action list should be maintained.

  • 06 Dec 2005 - J.Shiers and K.Bos will distribute a proposal on how experiments plans can be made available to Tier1 sites.
    On the way.

A proposal will be mailed by J.Shiers.

The current understanding is that a weekly report, based on existing reports in IT, will be distributed to the MB list.
The weekly reports currently available within IT are: (1) a weekly report of the EIS team on experiments activities, (2) the weekly report on LCG operations and (3) the EGEE operations report.
A summary of those will be sent out to the MB list every Monday afternoon and should improve the situation for Tier-1 sites.

It is important that the report does not only summarize past activities but it should also include the experiments plans for the following week.

  • 6 Dec 05 - L.Robertson and A.Aimar will prepare the High Level Milestones for formal approval by the MB.

On the way.

The milestones will be distributed this week. The goal is to approve them at next MB, in order to start using the plans at start of Phase 2.


  • 6 Dec 05 - J.Shiers has initiated a team to define metrics to measure site reliability and availability, data transfer capability, and overall grid performance. He will distribute a proposal on this to the MB for input from the sites and services, before 6 December 2005.

On the way.

H.Renshall will produce the proposal.

The LHCC referees wanted something wider than the SFT and wanted also metrics about middleware reliability.


  • 10 Dec 05 - Tier-1 Sites (at GDB) should complete their plans following the guidelines of the presentation given at the GDB. (GDB presentation).

On the way.

Some sites said that they will send the updated plans when they have their 2006 plans discussed at the beginning of January.


  • 10 Dec 05 - People responsible for each area and service should also define some measurable metrics to follow during Phase 2.

To Do.


  • 12 Dec 05 - Sites should send updates to the capacity tables of the MoU.

A letter was sent to all centers asking for confirmation of: (1) the values in the MoU, (2) who will sign and (3) when they plan to sign the MoU.  Sites should urgently reply.

ATLAS TDAQ Large Scale Test in 2006 (20') ( document )


ATLAS TDAQ tests in Summer 2005 were very useful for the development of the TDAQ system. The summary of the tests and plans for the future is described in a document available upon request to ATLAS.


The ATLAS TDAQ team is asking to be able to run more advanced tests during end of 2006. The request is for availability of about 1200 nodes.

The tests will be important to verify:

- integration of the DAQ with the online software

- access to the condition database from a from large number of almost simultaneous read out processing tasks

- new versions of components, in particular for the control systems hierarchy and the distribution of the online parameters.

- fault tolerance and general stability of the DAQ system

CMS has a Level 1 milestone for the CPT project in October, when they will start their Data Challenge.
There should not be interference with other experiments’ needs. In September there must be sufficient capacity available to CMS in the Tier-0 resources. And CMS will probably not be able to reduce the nodes used in October.

In October/November 2006 there will be about 1800 nodes (+-10%) installed in total, for all experiments.
CMS will need about 600 nodes and, if the other experiments do not need them, ATLAS could use the other 1200 nodes.

The IT performance tests will continue in 2006 and will use 300-400 nodes that are outside the capacity provided to experiments.

A decision needs to be taken before March 2006 in order for ATLAS to study alternatives, if needed.

If the experiments agree on the principle a detail plan will be defined taking into account the ATLAS TDAQ request.


CMS agrees on the principle, but the schedule must be studied and arranged in detail as soon as possible.
ALICE agrees on the principle. ALICE will not have a lot of activity in October/November 2006: the ALICE Data Challenge is scheduled for earlier than Fall 2006.


Action: 15 Jan 06 - B.Panzer will discuss with the experiments and present to the MB a plan with possible dates and resources for the experiments and for IT activities (performance tests, etc). The plan will include a proposal for the ATLAS TDAQ large scale tests.


Draft report to the POB (20') ( tables )


The draft was distributed on Monday. The comments received will be taken into account in the report sent to the POB.

During the preparation of the report for the POB it was difficult to extract correct accounting figures. The quality of accounting is unclear and should be discussed at the MB. The proposal is to discuss “grid accounting” at the face to face MB meeting on the 10 January 2006, before the GDB.


There are several issues and open questions:

-          Experiments run some of their jobs locally and those jobs are not accounted by the LCG tools.

-          Some sites are not reporting regularly. And all accounting data should be reviewed.

-          The GOC accounting system reports different values than the local accounting systems. These differences should be clarified and reliable accounting data become available. 

-          Should the report to the POB include accounting of jobs executed locally and not only via the grid? Should the grid accounting system also count locally-submitted work to grid resources? Should the usage of the grid submission mechanisms be enforced on grid resources?

Apparently in Tier-1 sites about 50% of the resources are allocated to the grid, the other 50% is devoted to local analysis. And in Tier-2 sites 90% of the resources are assigned for local usage and 10% are being used via the grid.


Action: 10 Jan 06 - J.Gordon prepares a presentation on the situation of grid accounting, for the face to face MB meeting before the GDB (11 Jan 06). 




The WLCG high level milestones will be distributed to the MB for formal approval at next MB meeting. 



Summary of New Actions


Action: 10 Jan 06 - J.Gordon prepares a presentation on the situation of grid accounting, for the face to face MB meeting before the GDB (11 Jan 06).


Action: 15 Jan 06 - B.Panzer will discuss with the experiments and present to the MB a plan with possible dates and resources for the experiments and for IT activities (performance tests, etc). The plan will include a proposal for the ATLAS TDAQ large tests.


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