EGEE Uo M kickoff Meeting Jun 2004 Uom

  • Slides: 22
Download presentation
EGEE - Uo. M kick-off Meeting, Jun, 2004 Uom Roles, Responsibilities and Tasks Vassilis

EGEE - Uo. M kick-off Meeting, Jun, 2004 Uom Roles, Responsibilities and Tasks Vassilis Stefanidis Source of slices + material: EC, EGEE, CERN, GRNET EGEE is a project funded by the European Union

Objectives of this session • Understand overall aim of EGEE activities • Present Uo.

Objectives of this session • Understand overall aim of EGEE activities • Present Uo. M roles, responsibilities and tasks / activity • Uo. M team Presentation Athens, 27 -28 th May - 2

SA 1 overall objective • Create, operate, support and manage a production quality infrastructure

SA 1 overall objective • Create, operate, support and manage a production quality infrastructure SEE - GRID Athens, 27 -28 th May - 3

Greece: GRID projected topology Xanthi Thessaloniki Ioannina Larissa Mytilini Athens Isabella – Δημόκριτος 10

Greece: GRID projected topology Xanthi Thessaloniki Ioannina Larissa Mytilini Athens Isabella – Δημόκριτος 10 TB Storage Area Samos Patra 32 Dual Xeon 1 GB RAM Chios Syros Grid Node 622 Mbps Po. S 1 Gbps Gig Ethernet Crete Rodos 2. 5 Gbps Po. S upgradable to 10 Gbps Athens, 27 -28 th May - 4

Sites + responsibilities Production site Responsible partner: operations HG 01 -GRNET ICCS HG 02

Sites + responsibilities Production site Responsible partner: operations HG 01 -GRNET ICCS HG 02 (Athens 2) + potential IASA cluster IASA HG 03 (Thessaloniki) + potential Auth cluster Auth+Uo. M HG 04 (Patras) CTI HG 05 (Crete) ICS-FORTH Pre-production site Pre 01 (Uo. M) Uo. M Pre 02 (Uo. Patras) Uo. Patras Pre 03 (Uo. A; certification site more likely) Uo. A + Support for key ROC services by specific partners (see SA 1 presentation) Athens, 27 -28 th May - 5

EGEE activities in Greece • SA 1: GRID Operations, Support and Management • NA

EGEE activities in Greece • SA 1: GRID Operations, Support and Management • NA 3: User Training and Induction • NA 5: Policy and International Cooperation Athens, 27 -28 th May - 6

Our collective aim • SA 1: build expertise and operational procedures that will allow

Our collective aim • SA 1: build expertise and operational procedures that will allow Greece to: • Integrate into European production-level infrastructure • Operate a self-standing coherent Grid infrastructure • Create teams of core experts for the future • NA 3: train and inform users, operators, etc. • NA 5: contribute to whitepapers, standards etc on the international stage • If we do this, EGEE-2 will follow! Athens, 27 -28 th May - 7

SA 1 objectives in Greece: detail • Pre-production infrastructure: smaller sites with next generation

SA 1 objectives in Greece: detail • Pre-production infrastructure: smaller sites with next generation m/w • 8/5 support, crucial as real-life testbeds, for m/w and application testing • Production infrastructure: only stable clusters with significant resources can be admitted to the EGEE production infrastructure • • • 24/7 operation, supported by RC, ROC and CICs Run a Regional Operations Centre One in each federation Provide front-line support to users and resource centers Support new resource centers joining EGEE in the regions Support deployment and operations in the resource centers • Key specific ROC services: security, helpdesk/TT, portal, monitoring, m/w certification, installation procedures, core Grid services, etc. Athens, 27 -28 th May - 8

NA 3 objectives: overall and GR • Train the GRID community and wider user

NA 3 objectives: overall and GR • Train the GRID community and wider user community • Establish a training center in each region • 5 regions Athens, 27 -28 th May - 9

NA 5 • General GRID and specific technical whitepapers • Aegean & AUEB 2

NA 5 • General GRID and specific technical whitepapers • Aegean & AUEB 2 Athens, 27 -28 th May - 10

Pre-production service • Smaller sites • New generation m/w (EGGE-1 or LCG-2) comming soon

Pre-production service • Smaller sites • New generation m/w (EGGE-1 or LCG-2) comming soon (15 Jun 2004 ? ? ) • Crucial for testing and experimentation • Activities similar to those for production service Athens, 27 -28 th May - 11

SA 1 objectives: detail • Core infrastructure services: • Operate essential grid services •

SA 1 objectives: detail • Core infrastructure services: • Operate essential grid services • Grid monitoring and control: • • Proactively monitor the operational state and performance, Initiate corrective action • Middleware deployment and resource induction: • • Validate and deploy middleware releases Set up operational procedures for new resources • Resource provider and user support: • • Coordinate the resolution of problems from both Resource Centres and users Filter and aggregate problems, providing or obtaining solutions • Grid management: • • Coordinate ROCs and CICs Manage the relationships with resource providers via service-level agreements. Athens, 27 -28 th May - 12

Operations centers: hierarchy Athens, 27 -28 th May - 13

Operations centers: hierarchy Athens, 27 -28 th May - 13

M/W: lifecycles • From 1 st April 2004 Production grid service based on the

M/W: lifecycles • From 1 st April 2004 Production grid service based on the LCG infrastructure running LCG-2 grid m/w • In parallel develop a “next generation” grid facility Produce a new set of grid services according to evolving standards (web services) Run a pre-production service providing early access for evaluation purposes Will replace LCG-2 on production facility in 2005 LCG-1 LCG-2 Globus 2 based EGEE-1 EGEE-2 Web services based VDT EDG . . . Ali. En LCG . . . EGEE Athens, 27 -28 th May - 14

Evolution of RCs Site Parallel (Gflops) Cluster (num. nodes) HG 01 (GRNET) N/A 64*2

Evolution of RCs Site Parallel (Gflops) Cluster (num. nodes) HG 01 (GRNET) N/A 64*2 HG 02 (Athens 2) N/A HG 03 (Saloniki) Disk (Tb) 10. 0 Automated Tape (Tb) Avg. LAN (Mbps) Avg. WAN (Mbps) Join VOs supported M 0; M 15 cms, alice, atlas, dteam, lhcb 10. 0 1000. 0 2500. 0 128 N/A 1000. 0 2500. 0 M 15 N/A 128 N/A 1000. 0 2500. 0 M 15 HG 04 (Patra) N/A 128 N/A 1000. 0 2500. 0 M 15 HG 05 (Crete) N/A 128 N/A 1000. 0 2500. 0 M 15 Athens, 27 -28 th May - 15

Specific responsibilities • Uo. A+IASA+GRNET-HQ: m/w certification; release documentation, etc. • • Certification testbed

Specific responsibilities • Uo. A+IASA+GRNET-HQ: m/w certification; release documentation, etc. • • Certification testbed by IASA/Uo. A+Demokritos: Guidelines for configuration and automatic installation tools. Run local installation testbed to verify installation procedures. CTI: helpdesk, knowledge database, coordination of the support procedures. Uo. C: EGEE-SEE website/portal. IASA, Uo. A, Auth, ICCS: host and co-manage necessary core GRID services, as agreed with GRNET-HQ. ICS-FORTH: Coordinate the monitoring service (Grid. Ice server + database). Auth and Aegean: security. Auth operates the CA; Aegean provides support and specific authorisation activities, site security guidelines, RA. Demokritos: certification/installation + application specific support Training: all operations people should support! • Specific responsibilities start ASAP Athens, 27 -28 th May - 16

Milestones & Deliverables Month Deliverable / Milestone Item Lead M 03 DSA 1. 1

Milestones & Deliverables Month Deliverable / Milestone Item Lead M 03 DSA 1. 1 Detailed execution plan for first 15 months of infrastructure operation M 06 MSA 1. 1 Initial pilot production grid operational (SEE RCs: GRNET, UCY, TAU) M 06 DSA 1. 2 Release notes corresponding to the initial pilot Grid infrastructure operational M 09 DSA 1. 3 Accounting and reporting web site publicly available M 12 MSA 1. 2 First review M 12 DSA 1. 4 Assessment of initial infrastructure operation and plan for next 12 months M 14 DSA 1. 5 First release of EGEE Infrastructure Planning Guide (“cook-book”) M 14 MSA 1. 3 Full production grid infrastructure operational (SEE: 9 RCs) M 14 DSA 1. 6 Release notes corresponding to the full production Grid infrastructure operational M 18 MSA 1. 4 Second review M 22 DSA 1. 7 Updated EGEE Infrastructure Planning Guide M 24 DSA 1. 8 Assessment of production infrastructure operation and outline of how sustained operation of EGEE might be addressed. M 24 MSA 1. 5 Third review and expanded production grid operational M 24 DSA 1. 9 Release notes corresponding to expanded production Grid infrastructure operational Athens, 27 -28 th May - 17

ROC organization: vertical ROC Manager (GRNET) ROC Technical manager (GRNET) Specific people RC Manager

ROC organization: vertical ROC Manager (GRNET) ROC Technical manager (GRNET) Specific people RC Manager HG 1 roles Fabric admin RC Manager HG 2 M/W admin RA manager RC Manager HG 3 Monitoring / User support RC Manager HG 4 System admin RC Manager HG 5 N/W admin Technician Athens, 27 -28 th May - 18

Uo. M: Identification of personnel & roles Uo. M Team Collaborator name Contact/email Institute

Uo. M: Identification of personnel & roles Uo. M Team Collaborator name Contact/email Institute Margaritis Konstantinos kmarg@uom. g r Uo. M Scientific Coordinator Stefanidis Vassilis bstefan@uom. gr Uo. M Technical Coordinator Uo. M Assistant Technical Coordinator - System Admin Uo. M System Administrator - HG 3 Node Manager Typou Theodoros typou@uom. gr Georgakopoulos Kostas kgeorga@uom. gr Role Fotis George fgeo@uom. gr Uo. M System Administrator - HG 3 Node Manager Michailidis Panagiotis panosm@uom. gr Uo. M Application Developer Digalakis Iasonas jason@uom. gr Uo. M Application Developer Kousourakis Anastasios akusur@uom. gr Uo. M Computer & Network Technician Athens, 27 -28 th May - 19

Uo. M: (Pre) Tasks Uo. M Team Tasks – 1 st phase (waiting funding,

Uo. M: (Pre) Tasks Uo. M Team Tasks – 1 st phase (waiting funding, final tasks and deliverables) Tasks Completed remarks Globus Installation Yes Ver 3 - CA installed Uo. M Official EU Grid Registration Request No From Greek CA (auth) Cluster preparation No PCs definition - preparation Globus Survey (Documentation Survey) No Globus Modules Definition No Globus Operation (Documentation Survey) No Cluster Interconnection with Grid Manager No Small Grid Implementation (over Globus) No Uo. M EGEE Overview - Web Site No What module do what Definition Organize our work Athens, 27 -28 th May - 20

Uo. M Team Responsibilities Uo. M Team Tasks – 1 st phase Responsibilities Tasks

Uo. M Team Responsibilities Uo. M Team Tasks – 1 st phase Responsibilities Tasks remarks Globus Installation Ver 3 – CA installed Uo. M Official EU Grid Registration Request From Greek CA (auth) Egee-team@uom. gr mail account Cluster preparation Persons Stefanidis PCs definirion – preparation Fotis + Kousourakis Globus Survey (Documentation Survey) Typou+Fotis + Georgak + Michailidis + Kousourakis Globus Modules Definition Typou+Fotis + Georgak + Michailidis + Kousourakis What module do what Globus Operation (Documentation Survey) Typou+Fotis + Georgak + Michailidis + Kousourakis Cluster Interconnection with Grid Manager (Def) Typou + Georgako + Fotis Definition Small Grid Implementation (over Globus) Uo. M EGEE Overview - Web Site All Team Organize our work Michailidis + Georgak ? Athens, 27 -28 th May - 21

Communications procedures • egee-sa 1@grnet. gr • CERN Document Server (CDS): http: //agenda. cern.

Communications procedures • egee-sa 1@grnet. gr • CERN Document Server (CDS): http: //agenda. cern. ch/display. Level. php? fid=41 • Main site http: //egee-intranet. web. cern. ch/egeeintranet/gateway. html • EDMS server (In OTHERS/EGEE/) https: //edms. cern. ch Athens, 27 -28 th May - 22