Presentation is loading. Please wait.

Presentation is loading. Please wait.

Pierre Girard ATLAS Visit

Similar presentations


Presentation on theme: "Pierre Girard ATLAS Visit"— Presentation transcript:

1 Pierre Girard ATLAS Visit 2007-04-26
03/12/2018 2007/04/26 Grid at CCIN2P3 Pierre Girard ATLAS Visit

2 LCG/EGEE grid activities Grid integration at CC
03/12/2018 Content LCG/EGEE grid activities Grid integration at CC Grid team Grid site infrastructure Major concerns Global concerns Operational concerns Technical concerns Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

3 CCIN2P3 LCG/EGEE grid activities
03/12/2018 CCIN2P3 LCG/EGEE grid activities EGEE-SA1 Activity: European Grid Support, Operation Management LCG Tier-1 Activity: Data storage centre at both national and regional level, data reconstruction, data distribution over Tiers-2, etc. (EGEE) CIC: Core Infrastructure Centre (EGEE-II) ROC: Regional Operations Centre Global National Site Support Grid services Accounting CC IN2P3 Monitoring User Support (EGEE-II) ROC Storage (EGEE/EGEE-II/LCG) EGEE Resource Centre T1/T2 LCG-Site Computing Local Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

4 Grid integration at CC Grid team
03/12/2018 Grid integration at CC Grid team Grid Started using the « Cappuccino » strategy: put the cream on the top of the coffee, and let it be Grid team created over the production service infrastructure One member of each existing team appointed to follow up the grid deployment To accelerate the dissemination of grid technology within CCIN2P3 To ease the interfacing between grid middleware and CC-IN2P3 services/resources To provide expert advices (from both directions) Production Storage User Support Web / DB admin. Admin. System and Network Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

5 Grid integration at CC Grid site infrastructure (1)
03/12/2018 Grid integration at CC Grid site infrastructure (1) VO Box VO LHC Grid Information System VO Box VO LHC Top BDII VOMS 4 VOs MonBox 4 Sites V OBox VO LHC VO Box VO LHC Central LFC Biomed Local LFC 4 VOs LHC FTS 4 VOs LHC Local LFC 2 VOs LHC FTS 4 VOs LHC Site BDII Computing Element Computing Element SRM SRM Storage Element Storage Element Computing Element Computing Element Global service BQS HPSS DCACHE Regional service Anastasie Local Service WN Computing Storage Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

6 Grid integration at CC Grid site infrastructure (2)
03/12/2018 Grid integration at CC Grid site infrastructure (2) Several grid sites supply CCIN2P3 Ressources Pre-production grid Reconstr. Simulation Analysis PPS Site BDII T1 Site BDII T2 Site BDII ? SE SRM2.2 SE CE CE gCE CE CE CE CE BQS test WN Computing BQS Anastasie WN Computing ? WN Computing Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

7 Major concerns Global concerns (1)
03/12/2018 Major concerns Global concerns (1) VO Box VO LHC Grid Information System VO Box VO LHC ~20 machines Top BDII VOMS 4 VOs MonBox 4 Sites V OBox VO LHC VO Box VO LHC ~30 machines Central LFC Biomed Local LFC 4 VOs LHC FTS 4 VOs LHC Local LFC 2 VOs LHC FTS 4 VOs LHC ~4 node profiles ~20 node profiles Site BDII Computing Element Computing Element SRM SRM Storage Element Storage Element Computing Element Computing Element Storage Team Grid Team Grid Team Storage Team Grid Team Grid Team Global service BQS HPSS DCACHE Regional service Anastasie Local Service WN 2 FTEs ~2 FTEs Computing Storage Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

8 Major concerns Global concerns (2)
03/12/2018 Major concerns Global concerns (2) Our first major concerns Many service nodes Many different types of node Few people to administrate Few time before starting A production quality to be maintained So far as we can, we have… To reuse Our practical abilities Existing infrastructure when possible But, add nodes if that eases operations To avoid to introduce too much VO specificities Experience acquiring Operational procedures set up Monitoring/Administration tools adaptation Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

9 Major concerns Global concerns (3)
03/12/2018 Major concerns Global concerns (3) Improving grid communication will be THE challenge Mutliple information sources: LCG, EGEE, VOs, regional and internal site communication Too much information or knowledge are still coming from mails or from a mess of meetings A lot of progress has been achieved yet At CC, VO-Site communication improvement One VO support contact appointed by LHC VO Speak VO language with site Speak Site language with VO Shown to be a good point to improve the communication For ATLAS matters, grid site administrators systematically discuss with Ghita Rahal Ghita Rahal knows who is the best CC interlocutor for any ATLAS request Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

10 Major concerns Operational concerns
03/12/2018 Major concerns Operational concerns We set up operational procedures to suppress or, at least, to reduce grid service outage Ex.: CE update might be operated without any outage Set up a new CE and validate it works well out of production Close the old CE and replace it by the new one Take out the old CE when its jobs are ended But “bad” VO usage can interfer with that Ex.: Job submission explicitly refers to a CE by specifying its hostname It is time-consuming because you must inform the supported VOs before taking any action on the CE Job submission will failed if the CE is out of production Grid middleware theoretically enables those operations But problem certainly comes from the fact that M/W doesn’t enable to express requests like: “please submit my job to any allowed CE of site IN2P3-CC” Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

11 Major concerns Technical concerns (1)
03/12/2018 Major concerns Technical concerns (1) Dealing with VOMS information If I was a VO, I would be very enthousiastic about the new possibilities offered by VOMS But as site… I need to know what behavior is expected behind a VOMS role/group I must find a technical solution to translate it in terms of site policy I must possibly adapt the interface between grid frontend and local services to implement the behavior CE Jobmanager <-> BQS CE Information Provider <-> BQS LRMS-independent solution proposed by Jeff Templon for CE But, this solution raises some scalability problems with big sites ASAP we must identify together new requirements that will be introduced because of VOMS Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26

12 ATLAS is our most intensive grid user
03/12/2018 The end ATLAS is our most intensive grid user From grid team point of view (at least), we are working well with Atlas people French Atlas people are very present and responsive Atlas is also present and responsive at global operations level (ex.: grid operations meetings) Pierre Girard / ATLAS visit at CCIN2P3 2007/04/26


Download ppt "Pierre Girard ATLAS Visit"

Similar presentations


Ads by Google