Name: 2016 WLCG Collaboration Workshop
Start: 2016-02-01T08:00:00+00:00
End: 2016-02-03T18:00:00+00:00
Location: ISCTE-IUL - University Institute of Lisbon

2016 WLCG Collaboration Workshop

from Monday 1 February 2016 (08:00) to Wednesday 3 February 2016 (18:00)

Monday 1 February 2016

08:00

08:00 - 09:00

09:00

09:00 - 09:20
09:20 Compute
Compute
09:20 - 10:40
Contributions

09:20 Introduction - Oxana Smirnova (Lund University (SE))

09:25 Exploiting HPC for HEP workloads - Rodney Walker (Ludwig-Maximilians-Univ. Muenchen (DE))

09:45 Plugging Cloud and VM-based resources into WLCG - Andrew McNab (University of Manchester)

10:05 Discussion
10:40 Coffee break
Coffee break
10:40 - 11:00
11:00 Security and Trust Model
Security and Trust Model
11:00 - 12:30
Contributions

11:00 Overview Medium-Term Issues in Security and Trust Model - Ian Peter Collier (STFC - Rutherford Appleton Lab. (GB))

11:10 Lightning: Trust Fabric Evolution - David Groep (Nikhef National institute for subatomic physics (NL))

11:20 Lightning: New paradigms for academic computing security - Romain Wartel (CERN)

11:30 Lightning: Security in evolving infrastructures - Sven Gabriel

11:40 Lightning: Trust model between experiments and sites - Alessandro Di Girolamo (CERN)

11:50 Discussion - Ian Neilson (STFC RAL (GB)) Ian Peter Collier (STFC - Rutherford Appleton Lab. (GB))
12:30 Lunch
Lunch
12:30 - 14:00
14:00 Data
Data
14:00 - 16:00
Contributions

14:00 Intro - Dirk Duellmann (CERN)

14:05 Summary of experiment medium term input - Simone Campana (CERN)

14:20 Site input on medium term storage evolution - Samuel Cadellin Skipsey

14:35 Storage systems - medium term opportunities - Andreas Joachim Peters (CERN)

14:50 Discussion
16:00 Coffee break
Coffee break
16:00 - 16:20
16:20 Information systems, accounting and benchmarking.
Information systems, accounting and benchmarking.
16:20 - 18:25
Contributions

16:20 Intro - Alessandra Forti (University of Manchester (GB))

16:25 Information System - Maria Alandes Pradillo (CERN)

16:35 Benchmarking - Helge Meinhard (CERN) Manfred Alef (Karlsruhe Institute of Technology (KIT))

16:55 Accounting - John Gordon (STFC - Rutherford Appleton Lab. (GB))

17:05 Discussion
18:00
18:00 - 19:00
Contributions

18:00 Request to endorse Tier 2 member of WLCG OB - Roger Jones (Lancaster University (GB))

18:05 Update on MoU signatures - Ian Bird (CERN)

18:10 Discussion of evolving Tier definitions - Ian Bird (CERN)

18:25 Update on EUT0 - Peter Clarke (University of Edinburgh (GB))
Tuesday 2 February 2016
09:00 Introduction & goals of the day - Ian Bird (CERN)
Introduction & goals of the day
- Ian Bird (CERN)
09:00 - 09:30
Focus on how to work towards a model for computing for the HL-LHC era. What are the areas where we need to invest R&D, how do we being to understand the likely costs?
09:30 Summary of top concerns of the experiments - Ian Bird (CERN) Daniele Bonacorsi (University of Bologna) Eric Christian Lancon (CEA/IRFU,Centre d'etude de Saclay Gif-sur-Yvette (FR)) Stefan Roiser (CERN) Predrag Buncic (CERN) Andrej Filipcic (Jozef Stefan Institute (SI))
Summary of top concerns of the experiments
- Ian Bird (CERN)
- Daniele Bonacorsi (University of Bologna)
- Eric Christian Lancon (CEA/IRFU,Centre d'etude de Saclay Gif-sur-Yvette (FR))
- Stefan Roiser (CERN)
- Predrag Buncic (CERN)
- Andrej Filipcic (Jozef Stefan Institute (SI))
09:30 - 10:30
10:30 Coffee
Coffee
10:30 - 11:00
11:00 Infrastructure models - Simone Campana (CERN)
Infrastructure models
- Simone Campana (CERN)
11:00 - 12:30
<ul> <li>How to reduce the overall cost of the infrastructure, e.g. by: <ul> <li>Reducing the amount of scattered storage <li>How to procure and incorporate large scale compute resources at scale <li>What is the networking model - OPN–style private? <li>The use of other resources: HPC, volunteer, etc. What is the model for distributed sites (Tier 2)? </ul> <li>The idea of setting up an early prototype of a data/cloud infrastructure to test ideas (a la “Zephyr” proposal) - suggestion already supported by several Tier 1s <li>What about specialist sites/resources (HPC, GPU etc) for specific workflows <li>Security considerations, especially access control and how that affects performance and cost </ul>
12:30 Lunch
Lunch
12:30 - 14:00
14:00 Experiment workflows & data management tools and infrastructure - Daniele Bonacorsi (University of Bologna)
Experiment workflows & data management tools and infrastructure
- Daniele Bonacorsi (University of Bologna)
14:00 - 15:00
<ul> <li>Can we think about common toolsets for all experiments, given 10 years until HL-LHC? <li>Input on data management convergence from previous day <li>What is realistic in terms of common infrastructure and services in order to achieve commonality? <li>More commonality is an expectation of funding agencies. <li>Political limitations? e.g. specific project funding? <li>Many sites (esp Tier 1s) have to support other sciences on the same infrastructure </ul>
15:00 Technology Evolution - Bernd Panzer-Steindel (CERN)
Technology Evolution
- Bernd Panzer-Steindel (CERN)
15:00 - 16:00
<ul><li>Should we set up a technology tracking activity (as Bernd has been doing), but perhaps now realised together with the concurrency forum and the tech lab activity – to provide a real testing and benchmarking environment (openlab here too). <li>Could be a distributed collaborative effort - in common with HSF/concurrency forum </ul>
16:00 Coffee
Coffee
16:00 - 16:30
16:30 Undesrtanding and modelling of the distributed infrastructure & computing models - Markus Schulz (CERN)
Undesrtanding and modelling of the distributed infrastructure & computing models
- Markus Schulz (CERN)
16:30 - 17:30
<ul> <li>How well do we understand our current workflows, their behaviour and resource needs? <ul> <li>with respect to storage, remote access, networks, CPU, memory <li>How well do we understand the behaviour of our current infrastructure? <li>What can we do to improve this understanding in an experiment independent way? <li>how independent can this be? </ul> <li>What has been done already in experiments? <li>What would be desirable? Ability to model ideas of infrastructure to understand performance, costs, etc. <li>What is potentially common across experiments? What is specific? <li><b>Can we derive a cost model for the infrastructure to explain the full costs of computing and the relative costs of each component?</b> </ul>
19:00

19:00 - 21:00
Wednesday 3 February 2016
09:00 Software topics - Benedikt Hegner (CERN)
Software topics
- Benedikt Hegner (CERN)
09:00 - 10:00
<ul> <li>What is actually useful to do in common? <li>Tools or support for common automated and intelligent build/test/validation services? <li>More ? Common libraries etc? Role of HSF <li>What is usefully shareable? <li>Detailed software performance analysis and tools for analysis <li>All this should be in the context of the HSF. Some activities towards common (lower-level) build tools was started already. Organise a dedicated HSF workshop on this?- <li>Do experiments actually want to commit to the HSF for common software interests? <li>Given today's (and expected evolution of) processor and machine architecture, is today's data architecture (i.e. ROOT) appropriate - do we need to re-think completely? </ul>
10:00 Coffee
Coffee
10:00 - 10:30

10:30

10:30 - 12:30

14:00

14:00 - 18:00

Choose timezone