EGI Technical Forum

Europe/Amsterdam
Lyon Conference Centre

Lyon Conference Centre

Lyon Conference Centre, Lyon, France
Steven Newhouse (EGI.EU)
Description
The EGI Technical Forum 2011 in Lyon provided an overview of the EGI community and reviewed the community's plans and progress towards the adoption of a federated virtualised infrastructure for the European user community. The TF was co-located with the Open Grid Forum (http://www.ogf.org) and Grid 2011 (http://www.gridcomputing.org/. The next large event is EGI Community Forum in Munich, will be held between 26-30 March, 2012.
    • 09:00 10:30
      EGI CSIRT Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The EGI CSIRT team will meet again to review and discuss
      various security issues. Discussion and update from following activities will be given:

      • Incident Response Task Force
      • Security Monitoring Group
      • Security Drill Grop
      • Security Training and Dissemination Group

      Agenda: https://www.egi.eu/indico/conferenceDisplay.py?confId=611

      Convener: Mingchao Ma (STFC)
      EGI CSIRT Monthly meeting agenda
      • 09:00
        Welcome and Introduction 30m
        Detail agenda: https://www.egi.eu/indico/conferenceDisplay.py?confId=611
        Speaker: Mingchao Ma (STFC)
        EGI CSIRT Monthly meeting agenda
      • 09:30
        IRTF update 30m
        Speaker: Leif Nixon (LIU)
        Slides
      • 10:00
        Security monitoring group update 30m
        Speaker: Daniel Kouril (CESNET)
        Slides
    • 09:00 10:30
      EMPTY Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

    • 09:00 10:30
      Globus EUROPE Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      For detailed agenda please refer to:
      http://www.globuseurope.org/agenda

      • 09:00
        Globus EUROPE 1h 30m
    • 09:00 10:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 09:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 09:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 09:00
        OGF 1h 30m St Clair 3b

        St Clair 3b

        Lyon Conference Centre

      • 09:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 09:00
        OGF OCCI WG F2F 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 09:00 10:30
      OGF Rhone 1 (75)

      Rhone 1 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 09:00
        OGF 1h 30m
    • 09:00 10:30
      Training: Tutorial on Secure Programming St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 09:00
        Tutorial on Secure Programming 1h 30m
        The security of software is becoming increasingly important to anyone who uses or develops it. This tutorial will teach developers how to proactively reduce the number of vulnerabilities in their software. This tutorial examines coding practices to prevent vulnerabilities by describing more than many types of vulnerabilities with examples of how they commonly arise, and techniques to prevent them. Most examples are in C, C++, Java and scripting languages.
        Speakers: Prof. Barton Miller (University of Wisconsin-Madison), Dr Elisa Heymann (Universitat Autonoma de Barcelona)
        Slides
    • 10:30 11:00
      Coffee break 30m
    • 10:30 20:30
      Posters and Demonstrations
    • 11:00 12:30
      Data Management Workshop Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Identifying, implementing and operating efficient and scalable data management and processing structures is one of the biggest problems one has to face when using a distributed computing infrastructure. These structures require robust software services with flexible integration and customisation facilities for both system administrators and end users.
      The middleware software stacks hosted on the European Grid Infrastructure provide several services for the management og data and metadata. The largest user groups of the European Grid Infrastructure have long-running experience of using these services and extending, integrating, customising them for community-specific use cases.

      This workshop provides a forum for EGI data service developers and operators, as well as for existing and emerging users of these service to exchange experiences, requirements and best practices concerning data management and processing. The workshop is coordinated by the User Community Support Team (UCST) of EGI.eu, the team that is responsible for the gathering and analysis of user requirements in EGI. By bringing the main stakeholders of data-related services together, UCST aims to facilitate information exchange and capture new requirements that can be fed into the next generation of software services of EGI.

      The aim of the workshop is to capture reusable best practices and solutions togehter with data-related requirements that are not yet addressed by any community or technology provider.

      If you would like to propose topic for discussion, please email it to ucst@egi.eu.

      Context
      Workshop_notes
      • 11:00
        EMI data services - the second year 15m
        The European Middleware Initiative is now rapidly approaching its projects half-value period. Nearly all objectives of the first year of EMI-Data have been achieved. Internet standards, like WebDAV and NFS4.1/pNFS have been integrated into the EMI set of storage elements, the already existing accounting record has been extended to cover storage and the synchronization of catalogues and storage elements has been designed and implemented within gLite. Furthermore, the close collaboration between EMI and EGI resulted in a very positive feedback from EGI and the subsequent creation of a set of new objectives focusing on the EGI acceptance of the EMI software distribution. This presentation will briefly described the achieved goals of the first year but will primarily focus on the work EMI Data is facing for the rest of its projects lifetime, including the design of the common EMI data client libraries and the new gLite File Transfer Service (FTS3).
        Speaker: Patrick Fuhrmann (DESY)
        Slides
      • 11:15
        EMI_datalib - consolidating ARC and gLite data libraries 15m
        EMI is a collaboration between the European middleware providers aiming to take the best out of each middleware to create one consolidated, all-purpose grid middleware. When EMI started there were two main tools for accessing data - gLite had lfc_util and the GFAL library, ARC had the ARC data tools and libarcdata2. While different in design and purpose, they both have the same goal; to move data in the grid. This presentation will explain the current plans, roadmap and status for EMI_datalib, the consolidated data transfer library.
        Speaker: Jon Kerr Nilsen (UIO)
        Slides
      • 11:30
        dCache, the evolving storage technology 15m
        For more than a decade, dCache now accompanies high energy physics and other communities in their needs of storing, transferring and accessing their ever increasing amount of data. Having started with the focus on large tape archives in front of relatively small disk caches (hence the name) the computing models, the required access protocols as well as the underlying storage and hardware technologies have permanently changed and have been adopted by dCache when needed. Only recently dCache introduced WebDAV as well as the NFS 4.1/pNFS protocols to stay competitive with industry standards and solutions allowing dCache to grow into young scientific communities. But the process continues. dCache is now planing to take advantage of the improved speed of solid state disks, however at the same time realizing that spinning disks will be around for a significant number of years from now, so that both technologies need to coexist in a single storage element with all necessary file movements on demand. Furthermore, with Hadoop FS, easy to maintain backend storage becomes available, which doesn't offer the well known file system semantics, so that the integration into dCache will become a challenge, the dCache developers are currently facing when adding HFS into the dCache supported set of backend storage technologies. This presentation will give a short summary of what dCache is offering in the recently published 1.9.12 Golden Release and what our milestones are for the next 12 months.
        Speaker: Paul Miller (dCache.org/DESY)
        Slides
      • 11:45
        DPM/LFC: Standards, Status and Plans 15m
        The Disk Pool Manager (DPM) is a lightweight solution for disk storage management. It provides an easy way to manage and configure disk pools, and exposes multiple interfaces for data access and control. It is used in production in more than 200 sites, serving communities like HEP and Biomed, among many others. In the last months we have made a big effort to provide standards compliant data access, with the goal of simplifying both the client and server side setups - no clients, simpler firewall settings, much simpler library dependencies. For POSIX access we have chosen NFS 4.1/pNFS, a very significant improvement over previous versions of the NFS protocol. It adds sessions and bulk operations for scalable access over the WAN, strong security, distributed data access, among many other new features. For download/upload style access, we have developed a new HTTP/WebDAV frontend. With it we get DPM data available in virtually any platform or setup - via web browsers, graphical filesystem browsers or command line tools like wget or curl - in a very high performance setup. +C3In this talk we will summarize the status of these components, the benefits for both clients and system administrators, and early performance measurements with comparison to existing protocols. We will describe how this work also benefits the LCG File Catalog (LFC), which now also exposes a HTTP/WebDAV frontend. Finally, we will also talk about other improvements we have done to the core of the DPM system, like filesystem weights, improved drain performance or third party copies.
        Speakers: Ricardo Rocha, Ricardo Rocha (CERN)
        Slides
      • 12:00
        SYNCAT - Storage Catalogue Consistency 15m
        This talk describes the current status of the Catalogue Consistency activity, which aims at giving to Grid Storage Elements, Central Catalogues and other external systems ways to interact in order to keep their metadata synchronized. The previous milestone produced a prototype system, built on standard messaging tools and a set of new core libraries/tools called SEMsg, that was successfully integrated with LFC and DPM. This was also used to show that the objective can be achieved also connecting it with the LHCb frameworks. We are also considering its usage in the context of ATLAS. Now the activity is going to head towards operating with the other EMI Storage elements. Aspects related to its deployment are now being consolidated and the components are available for evaluation in the software repositories, together with the technical documentation.
        Speaker: Fabrizio Furano
        Slides
      • 12:15
        File Transfer Service (FTS3): redesign for file transfer optimization and reliability 15m
        Speakers: Michail Salichos (CERN), Michail Salichos
        Slides
    • 11:00 12:30
      EGI CSIRT Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The EGI CSIRT team will meet again to review and discuss
      various security issues. Discussion and update from following activities will be given:

      • Incident Response Task Force
      • Security Monitoring Group
      • Security Drill Grop
      • Security Training and Dissemination Group

      Agenda: https://www.egi.eu/indico/conferenceDisplay.py?confId=611

      EGI CSIRT Monthly meeting agenda
      • 11:00
        Security training and dissemination group update 30m
        Speaker: Dorine Fouossong (CNRS)
        Slides
      • 11:30
        Security drill group update 30m
        Speaker: Dr Sven Gabriel (Nikhef)
      • 12:00
        Discussion 30m
        Possible topics as follow: - Security dashboard - SSC for NGI run
    • 11:00 12:30
      Globus EUROPE Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      For detailed agenda please refer to:
      http://www.globuseurope.org/agenda

      • 11:00
        Globus EUROPE 1h 30m
    • 11:00 12:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 3b

        St Clair 3b

        Lyon Conference Centre

      • 11:00
        OGF OCCI WG F2F 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 11:00 12:30
      Operations: Network support and monitoring Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session will cover topics related to partners and workflows for network support in EGI and provide an update on the status of tool for network monitoring.

      Convener: Dr Mario Reale (GARR)
      • 11:00
        Welcome, on-going activities, goals for the meeting 5m
        Speaker: Dr Mario Reale (GARR)
        Slides
      • 11:05
        HINTS status and Demo 25m
        Speaker: Dr Olivier Lenormand (CNRS)
        Slides
      • 11:30
        NetJobs overview and Demo 10m
        Speaker: Dr Mario Reale (GARR)
        Slides
      • 11:40
        PerfSONAR overview and update 20m
        Speaker: Domenico Vicinanza (DANTE)
        Slides
      • 12:00
        IPv6 survey and wrap up 5m
        In this short session we will wrap up the status of the IPv6 survey and the current outcome; we will report about the HEPiX IPv6 meeting at CERN and we will mention the option facing us w.r.t. IPv6
        Speaker: Dr Mario Reale (GARR)
        Slides
      • 12:05
        General Discussion on next steps for Monitoring and for IPv6 25m
        Speaker: All
    • 11:00 12:30
      Training: Tutorial on Secure Programming St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 11:00
        Tutorial on Secure Programming 1h 30m
        The security of software is becoming increasingly important to anyone who uses or develops it. This tutorial will teach developers how to proactively reduce the number of vulnerabilities in their software. This tutorial examines coding practices to prevent vulnerabilities by describing more than many types of vulnerabilities with examples of how they commonly arise, and techniques to prevent them. Most examples are in C, C++, Java and scripting languages.
        Speakers: Prof. Barton Miller (University of Wisconsin-Madison), Elisa Heymann
        Slides
    • 12:30 14:00
      Lunch break 1h 30m
    • 14:00 15:30
      Data Management Workshop Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Identifying, implementing and operating efficient and scalable data management and processing structures is one of the biggest problems one has to face when using a distributed computing infrastructure. These structures require robust software services with flexible integration and customisation facilities for both system administrators and end users.
      The middleware software stacks hosted on the European Grid Infrastructure provide several services for the management og data and metadata. The largest user groups of the European Grid Infrastructure have long-running experience of using these services and extending, integrating, customising them for community-specific use cases.

      This workshop provides a forum for EGI data service developers and operators, as well as for existing and emerging users of these service to exchange experiences, requirements and best practices concerning data management and processing. The workshop is coordinated by the User Community Support Team (UCST) of EGI.eu, the team that is responsible for the gathering and analysis of user requirements in EGI. By bringing the main stakeholders of data-related services together, UCST aims to facilitate information exchange and capture new requirements that can be fed into the next generation of software services of EGI.

      The aim of the workshop is to capture reusable best practices and solutions togehter with data-related requirements that are not yet addressed by any community or technology provider.

      If you would like to propose topic for discussion, please email it to ucst@egi.eu.

      Context
      Workshop_notes
      • 14:00
        Data Management - a Grid enablers perspective 13m
        The e-BioInfra platform provides grid workflow management and monitoring services for biomedical researchers that use the Grid for data analysis. As Grid enablers we have assisted users with both day-to-day and long time data management for their experiments. In this presentation we will give an overview of our experiences, solutions and remaining challenges.
        Speaker: Mark Santcroos (Academic Medical Center Amsterdam)
        Slides
      • 14:14
        LifeWatch NL 13m
        LifeWatch will construct and bring into operation the facilities, hardware, software and governance structures for all aspects of biodiversity research. It will provide a technical infrastructure with data at its core. In this talk we focus on short-term priorities of LifeWatch dealing with the most basic services needed for data access and integration. What virtual labs have already been built, what are the next steps and in what way do we envisage these and future labs to develop into a coherent infrastructure? What challenges will this pose for existing and new data and computing infrastructures?
        Speaker: Evert Lammerts
        Slides
      • 14:27
        Dutch bioinformatics data management 13m
        Speaker: Jan Bot
        Slides
      • 14:40
        Earth System Grid (ESG) and EGI interoperability 13m
        The work of the Earth Science activity in EGI-InSPIRE SA3 is devoted to Earth Science data access. The data from observations as well as simulations are often organized in geographically distributed databases. The data centers have developed service tools for basic research activities like searching, browsing and downloading of datasets; but those facilities are not directly available by ES applications running on EGI infrastructure. The goal of the “Earth Science service” in EGI-InSPIRE is to investigate and follow the development of specialized data access and management methods in the area of Earth Science such as satellite data via GENESI.DR or climate data via Earth System Grid federation (ESGF). ESGF is an international collaboration providing access to state of the art CMIP5 climate data (Coupled Model Inter-comparison Project 5). The CMIP5 data stored in ESGF will permit to evaluate the impact of climate change in various environmental and societal areas, such as regional climate, extreme events, agriculture, insurance… The ESGF software stack has been deployed at a number of sites around the world and a number of projects are exploiting and building on this infrastructure. ESGF uses a federated identity management system which is based on OpenID and PKI (supports X.509 certificates), but is not directly interoperable with the one of EGI. It means that to exploit CMIP5 data within EGI, users need authentication and authorization (AA) to both federations (IGTF & ESGF). This complex problem prevents the exploitation of ESGF resources within EGI. To analyze this situation and find solutions for the problems, a testbed is being deployed on EGI, consisting of a climate application that needs to access ESGF CMIP5 data to study extreme events. Different AA solutions will be discussed, of which one is based on Security Token Service (STS). Solutions will be available in the future by EGI-InSPIRE-SA3 and ESGF communities. We will present this ongoing work between the ES VRC in EGI-Inspire and ESGF. Many European teams are working on the impact of climate change and face the problem of a lack of compute resources in connection with large data sets. This work will be important to facilitate the exploitation of the CMIP5 data on EGI. ESGF is looking for a long term solution, based on ongoing developments of the ESG community, who are developing mechanisms to manage automatic mapping of credentials. The different interoperability solutions will be presented and have to be discussed between both trust federations (IGTF and ESGF).
        Speaker: Jan Raciazek
        Slides
      • 14:53
        Delivering a Collaborative Data Infrastructure - the EUDAT project 13m
        Europe’s science and research communities from a wide range of scientific fields are faced with increasingly large amounts of valuable data that stem from new sources such as powerful new sensors and scientific instruments used in analyses, experiments and observations as well as growing volumes of data from simulations and from the digitization of library resources. In order to make the most of the new opportunities emerging from this “explosion” of data, a group of European stakeholders has formed a consortium to build a sustainable pan-European infrastructure for scientific data. EUDAT is a new European initiative that will deliver a Collaborative Data Infrastructure (CDI) with the capacity and capability for meeting future researchers’ needs and enabling cross-disciplinary science in a sustainable way. Its design will reflect a comprehensive picture of the data service requirements of the research communities in Europe, and beyond. This will become increasingly important over the next decade as we face the challenges of massive expansion in the volume of data being generated and preserved (the so called ‘data tsunami’) and in the complexity of that data and the systems required to provide access to it.
        Speaker: Mark van den Sanden
        Slides
      • 15:06
        Grid Data Access: Proxy caches and User views 13m
        A new grid data access model has been developed at Nikhef, based on a caching mechanism and WebDAV access. This grid proxy cache can be added independently ""in front of"" existing LFC and SRM implementations, without having to make any modifications to the LFC or SRM servers. It provides a caching mechanism to speed up access to frequently requested files, as well as a transparent platform-independent access protocol. A secure WebDAV interface is offered, so that no grid-specific client software is needed to access the grid proxy cache. The WebDAV interface is accessible using username and passwords from Windows XP/Vista/7 and Mac OS X clients , and using grid certificates or proxies from Linux worker nodes. The grid proxy cache also includes load balancing and redundancy.
        Speaker: Jan Just Keijser
        Slides
      • 15:19
        Simplifying Large Scale Data Movement with Globus 11m
        Data movement is both a critical and frustrating aspect of computational research. For a relatively mundane task, moving terabytes of data reliably and efficiently can be surprisingly complicated, with many time-consuming manual activities required; automating these can help increase researchers' throughput. In this presentation we will provide an overview of the Globus suite of data movement technologies. We will introduce Globus Toolkit and GridFTP, the trusted workhorses for large-scale data movement, and will discuss the latest enhancements to these tools. We will then introduce Globus Online: a fast, reliable data movement service that simplifies large-scale file transfer using GridFTP without construction of custom end-to-end systems. Globus Online makes high-performance data movement capabilities available to any researcher anywhere, without the complexity of a full Globus install. We will demonstrate the process of signing up to Globus Online and using both GUI and CLI interfaces to move data between remote endpoints. We will also cover use of the Globus Connect feature, which allows users to move data between computing facilities and their local servers or laptops, even if behind a firewall. We will also cover highlights from several user case studies.
        Speaker: Mr Steve Tuecke (University of Chicago / Argonne National Laboratory)
        Slides
    • 14:00 15:30
      Globus EUROPE Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      For detailed agenda please refer to:
      http://www.globuseurope.org/agenda

      • 14:00
        Globus EUROPE 1h 30m
    • 14:00 15:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 3b

        St Clair 3b

        Lyon Conference Centre

      • 14:00
        OGF OCCI WG F2F 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 14:00 15:30
      OGF Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      • 14:00
        OGF 1h 30m
    • 14:00 15:30
      OSIRIS (Closed) Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Steven Newhouse (EGI.EU)
      • 14:00
        OSIRIS 1h 30m
    • 14:00 15:30
      Operations: EGI Operations Management Board (closed) Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Monthly meeting of the EGI Operations Management Board

      Conveners: Peter Solagna (EGI.EU), Dr Tiziana Ferrari (EGI.EU)
      Go to the OMB agenda
    • 14:00 15:30
      Training: Towards Making Metadata Handling Much Easier with AMGA in EGI St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 14:00
        Towards Making Metadata Handling Much Easier with AMGA in EGI 1h 30m
        AMGA has been around for more than 5 years as a gLite service to handle metadata on the Grid, and now become part of the EMI distribution intended to continue to support the metadata service requirements of the EGI user community. AMGA in the first place was designed and implemented to have in mind targeting the performance needs of the HEP community and the strict security requirements of the biomedical communities. AMGA has been used as a metadata service in many applications from different user communities. Among these applications are the Medical Data Manager (MDM) biomedical application developed by CNRS, the gLibrary (Digital Asset Management System for the Grid) developed by INFN, the GAP (Grid Application Platform) developed by ASGC and recently the data handling framework for Belle II experiment developed by KISTI. The latest AMGA developments support some new features like metadata federation and easy-to-use GUI client. The federation support allows AMGA users to populate metadata instances belonging to the same collection across multiple AMGA servers in cases where the metadata instances to be put in the same collection is too big to put in one AMGA server. The AMGA manager, an easy-to-use AMGA GUI client, aims at providing easier and more intuitive ways to have access to the AMGA metadata service than the traditional AMGA Command Line Interface (CLI) approach. The AMGA tutorial is dedicated to AMGA users who do not bother to put their hands a bit into the mud and would like to learn more about some easy-to-use features in metadata handling with the AMGA Manager. With both the AMGA CLI and the AMGA Manager, users will be instructed how to connect and interact with an AMGA server, define their own metadata collection and its schema, browse the collections and schemas, populate the collection with some entries and then make queries and browse the query results. Users will see how much easier and more convenient to handle and access metadata through the AMGA GUI client.
        Speakers: Mr Geun Chul Park (KISTI), Dr Soonwook Hwang (KISTI), Mr Taesang Huh (KISTI)
    • 15:30 16:00
      Coffee break 30m
    • 16:00 17:30
      Data Management Workshop Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Identifying, implementing and operating efficient and scalable data management and processing structures is one of the biggest problems one has to face when using a distributed computing infrastructure. These structures require robust software services with flexible integration and customisation facilities for both system administrators and end users.
      The middleware software stacks hosted on the European Grid Infrastructure provide several services for the management og data and metadata. The largest user groups of the European Grid Infrastructure have long-running experience of using these services and extending, integrating, customising them for community-specific use cases.

      This workshop provides a forum for EGI data service developers and operators, as well as for existing and emerging users of these service to exchange experiences, requirements and best practices concerning data management and processing. The workshop is coordinated by the User Community Support Team (UCST) of EGI.eu, the team that is responsible for the gathering and analysis of user requirements in EGI. By bringing the main stakeholders of data-related services together, UCST aims to facilitate information exchange and capture new requirements that can be fed into the next generation of software services of EGI.

      The aim of the workshop is to capture reusable best practices and solutions togehter with data-related requirements that are not yet addressed by any community or technology provider.

      If you would like to propose topic for discussion, please email it to ucst@egi.eu.

      Context
      Workshop_notes
      • 16:00
        The Cluster of Research Infrastructures for Synergies in Physics (CRISP) project 13m
        The Cluster of Research Infrastructures for Synergies in Physics (CRISP) project aims to build collaborations between the eleven Research Infrastructures (RIs) participating in the project. It focuses on four R&D tasks that are of utmost importance for these RIs: Accelerators, Instruments & Experiments, Detectors & Data Acquisition, and Information Technology (IT) & Data Management. This presentation gives a short introduction to the CRISP project and focuses on the aims and objectives with respect to Data Management.
        Speaker: Laurence Field (CERN)
        Slides
      • 16:13
        Questions, answers and discussion 1h 17m
        EGI_Data_Management_Services
    • 16:00 17:30
      Globus EUROPE Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      For detailed agenda please refer to:
      http://www.globuseurope.org/agenda

      • 16:00
        Globus EUROPE 1h 30m
    • 16:00 17:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 3b

        St Clair 3b

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 16:00
        OGF OCCI WG F2F 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 16:00 17:30
      OGF Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      • 16:00
        OGF 1h 30m
    • 16:00 17:30
      Operations: EGI Operations Management Board (closed) Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Monthly meeting of the EGI Operations Management Board

      Conveners: Peter Solagna (EGI.EU), Dr Tiziana Ferrari (EGI.EU)
      Go to the OMB agenda
    • 16:00 17:30
      Training: Towards Making Metadata Handling Much Easier with AMGA in EGI St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 16:00
        Towards Making Metadata Handling Much Easier with AMGA in EGI 1h 30m
        AMGA has been around for more than 5 years as a gLite service to handle metadata on the Grid, and now become part of the EMI distribution intended to continue to support the metadata service requirements of the EGI user community. AMGA in the first place was designed and implemented to have in mind targeting the performance needs of the HEP community and the strict security requirements of the biomedical communities. AMGA has been used as a metadata service in many applications from different user communities. Among these applications are the Medical Data Manager (MDM) biomedical application developed by CNRS, the gLibrary (Digital Asset Management System for the Grid) developed by INFN, the GAP (Grid Application Platform) developed by ASGC and recently the data handling framework for Belle II experiment developed by KISTI. The latest AMGA developments support some new features like metadata federation and easy-to-use GUI client. The federation support allows AMGA users to populate metadata instances belonging to the same collection across multiple AMGA servers in cases where the metadata instances to be put in the same collection is too big to put in one AMGA server. The AMGA manager, an easy-to-use AMGA GUI client, aims at providing easier and more intuitive ways to have access to the AMGA metadata service than the traditional AMGA Command Line Interface (CLI) approach. The AMGA tutorial is dedicated to AMGA users who do not bother to put their hands a bit into the mud and would like to learn more about some easy-to-use features in metadata handling with the AMGA Manager. With both the AMGA CLI and the AMGA Manager, users will be instructed how to connect and interact with an AMGA server, define their own metadata collection and its schema, browse the collections and schemas, populate the collection with some entries and then make queries and browse the query results. Users will see how much easier and more convenient to handle and access metadata through the AMGA GUI client.
        Speaker: Soonwook Hwang (EGI.EU)
    • 17:30 19:00
      Welcome cocktail 1h 30m
    • 09:00 10:30
      Plenary
      • 09:00
        Welcome and Opening 10m
        Speaker: Vincent Breton (CNRS)
      • 09:10
        Grid activity in France 20m
        Speaker: Dominique Boutigny
        Slides
      • 09:30
        An overview of the current policy developments at EU-level and the role of e-infrastructures in this evolving context 30m
        Kostas Glinos will present an overview of the current policy developments at EU-level and the role of e-Infrastructures in this evolving context. He will focus on two Europe 2020 flagship initiatives, the Digital Agenda for Europe and the Innovation Union, and on the steps towards the construction of the European Research Area. He will also refer to the ongoing consultation on the successor of the current Framework Programme for Research.
        Speaker: Kostas Glinos (Head of the European Commission’s GÉANT & e-Infrastructures unit of the Directorate General for Information Society)
        Slides
      • 10:00
        EGI-InSPIRE: Current status and future plans 30m
        EGI-InSPIRE is now a third of the way through the 4 year project and is making progress against its ambitious goals of providing a general purpose e-infrastructure for different science communities around Europe. This talk will highlight the successes of the first year, some of the highlights taking place during this weeks technical forum, and how these discussions will refine the plans that are being developed for the years ahead.
        Speaker: Steven Newhouse (EGI.EU)
        Slides
    • 09:00 19:00
      Posters and Demonstrations
    • 10:30 11:00
      Coffee break 30m
    • 11:00 12:30
      CHAIN F2F (Closed) Rhone 5

      Rhone 5

      Lyon Conference Centre

      Convener: Federico Ruggieri (INFN - Roma Tre)
      • 11:00
        CHAIN F2F 1h 30m
    • 11:00 12:30
      EGI Policy Development Workshop Rhone 2

      Rhone 2

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Are you interested in knowing more about the opportunity to access EU Structural Funds for e-Infrastructure? Do you want fresh insights on the next framework programme and related funding schemes after 2013 (Horizon 2020)? Then, join this session.

      The 2nd EGI Policy Workshop is the next step forward in facilitating and reinforcing the EGI-to-NGI and NGI-to-NGI policy development interactions and offer an opportunity to exchange best practices. This workshop leverages the first EGI Policy Workshop organised at the EGI User Forum in April 2011 to continue the flow of ideas on key policy issues, obtain updates from the NGIs on sustainability and agree on the main policy priorities in the short- and medium-term future.

      Overall, this session is to directly engage the community to ensure that EGI collectively evolves in the right direction regarding national and transnational policy matters underlining the importance of these activities and why it is essential for community involvement in this area. The target audience is policy makers from EGI participants and external partners; nevertheless, anyone with genuine interest in policy matters for e-Infrastructures is welcome.

      Convener: Sergio Andreozzi (EGI.EU)
      • 11:00
        Summary on the EGI Policy achievements 25m
        Speaker: Sergio Andreozzi (EGI.EU)
        Slides
      • 11:25
        Digital Agenda going Local, Horizon 2020, Structural Funds 20m
        Speaker: Damir Marinovic (EGI.EU)
        Slides
      • 11:45
        Discussion 45m
    • 11:00 12:30
      EGI SVG F2F (Closed) 1h 30m St Clair 5 (12M)

      St Clair 5 (12M)

      Lyon Conference Centre

      The EGI SVG members would like to take the opportunity to have a Face to Face meeting, as many will be attending the conference. This is primarily an internal meeting, where we discuss what we do and plans. A detailed agenda will be provided nearer the time.
      Speaker: Dr Linda Cornwall (STFC)
    • 11:00 12:30
      Globusonline.org -- Reliable File Transfer, No IT Required 1h 30m St Clair 3a

      St Clair 3a

      Lyon Conference Centre

      Science has become increasingly computation and data intensive. The ability to locate suitable resources, access resources reliably and securely, create and manage virtual organizations spanning multiple administrative domains, and transport large quantities of data, has emerged as fundamental requirement for progress. Globus software is established as a major source of middleware delivering these capabilities. We recently reengineered certain Globus components, improving usability and manageability in order to decrease the cost and complexity of deploying, operating, and using Globus infrastructure. However, we see lower rates of adoption among smaller scientific teams. To meet the needs of these communities, we are developing a new online, hosted service, globusonline.org, that provides a more integrated end-user solution for researchers. The initial goal of globusonline.org is to provide robust file transfer capabilities. Scientists often need to move data while pursuing their domain-specific goals (e.g., transferring simulation results from HPC facilities to their home institutions in accordance with purge policies, disseminating data to colleagues for further analyses, pipelining data to/from specialized machinery, etc.) Yet moving high-volume data across wide area networks is no easy task. Infrastructure failures are common, and tracking which transfers succeeded and which ones failed can be quite time-consuming. globusonline.org addresses these issues by delivering high-performance, reliable data movement services to end-users without requiring construction of custom, end-to-end systems. In this session, we will provide an update on recent developments in Globus and discuss future plans. We will also provide a brief introduction to globusonline.org, demonstrate current capabilities, and describe how they map to some current use cases.
      Speaker: Mr Steve Tuecke (University of Chicago / Argonne National Laboratory)
      Slides
    • 11:00 12:30
      HUC Sustainability Workshop 1h 30m Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      This session address sustainability in the context of the so-called Heavy User Communities (HUCs) of EGI-InSPIRE that are supported by SA3. For each of the communities involved, a senior user will briefly present their vision of the issues, after which we will hold a panel discussion. The main themes to be addressed include:
      • Sustainability of the discipline
      • Sustainability of the associated grid / DCI community
      • Sustainability of support for the specific tools and services currently provided / assisted by SA3
      The main HUCs (in terms of dedicated tasks) are:
      • High Energy Physics (HEP)
      • Life Sciences (LS)
      • Earth Sciences (ES)
      • Astronomy and Astrophysics (A&A)
      • Others - supported by the Shared Tools and Services task
      As time is tight, ONE slide per each question is all that can be accommodated (to leave plenty of time for discussion).
      Speakers: Claudio Vuerli (INAF), Horst Schwichtenberg (FRAUNHOFER), Jamie Shiers (CERN), Mr Johan Montagnat (CNRS), Laura Perini (INFN - IGI)
      • Sustainability from Life Sciences perspective 15m
      • Sustainability from Earth Sciences perspective 15m
      • Sustainability from Astronomy & Astrophysics perspective 15m
      • Sustainability from High Energy Physics perspective 15m
      • Additional viewpoints - other communities supported by SA3 10m
      • Discussion and conclusions 20m
    • 11:00 12:30
      Individual Presentations: Science Gateways & Portals St Clair 3b (90)

      St Clair 3b (90)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 11:00
        Adopting SAGA standard in Science Gateways 20m
        Science Gateways are considered as valid and innovative tools to increase Grid adoption and usage. Hiding the complexity of the Grid environment could indeed allow an easy access to e-Infrastructures to large Virtual Research Communities reducing the skills needed today to fully exploit them. In the Scientific Gateway design, the adoption of international standards should be considered as a mandatory practice in order to protect the investments in the creation of these high level user interfaces from middleware changes and lack of interoperability. In this way, Scientific Gateways can become “doors” to huge e-Infrastructures made of resources coming from different kind of grid infrastructures and connected via standard interfaces. For the above considerations we have decided to integrate in a series of Scientific Gateways we are developing, referring to different initiatives and scientific domains, the Simple API for Grid Applications (SAGA) Core API, a high level, application-oriented, software library for Grid application development specified by the Open Grid Forum. SAGA allows to create a unique interface towards different middleware stacks and makes Scientific Gateways able to exploit resources coming from different Grid worlds. Since our main requirement was to create generic modules allowing us to quickly develop new Scientific Gateways, we have decided to design and develop a software module able to interconnect the Scientific Gateway presentation layer and the underlying Grid infrastructures. In this way, creating a new Scientific Gateway can be reduced to the development of the presentation layer. This core module of our Gateways provides an interface towards the presentation layer and an interface, based on SAGA, towards the Grid Infrastructures. As SAGA implementation, we have adopted JSAGA (http://grid.in2p3.fr/jsaga/). The architecture of the portlets developed will be presented as well as some use cases.
        Speaker: Diego Scardaci (INFN)
        Slides
      • 11:20
        Supporting Identity Federations in Science Gateways 20m
        Science Gateways are cutting edge tools in the Grid computing world and are playing a key role in spreading the adoption and usage of this paradigm by large Virtual Research Communities mostly made by non IT-experts. Researchers require steadily increasing computational power and data storage that are currently provided by Grid infrastructures. However, the access procedure to these geographically distributed resources represents a barrier for non-expert users. Science Gateways try to fill the gap between the users and the resources with intuitive and easy to use interfaces. This work presents the Authentication and Authorisation Infrastructure (AAI) implemented for several Science Gateways developed in the context of some EU projects (e.g., DECIDE, EUMEDGRID-Support, GISELA, INDICATE, and others). The main design requirements were to simplify the access to Science Gateways, to allow the federation with other web facilities, and to create a smooth environment for users, hiding the complexities of the PKI but still providing the same level of security. In order to meet the above requirements, an LDAP server, linked with a Liferay-based multi-host web service, has been created to manage user authorisations. The authentication mechanism has been based on Shibboleth which implements a SAML2.0-based SSO across identity federations. A Liferay plug-in has been developed to integrate Shibboleth with Liferay and the support has been enabled for different identity federations. Among them, IDEM (www.idem.garr.it), managed by GARR, which counts more than 2,700,000 users.
        Speakers: Dr Marco Fargetta (Consorzio COMETA and INFN), Mr Riccardo Rotondo (INFN)
        Slides
      • 11:40
        Web interface for generic grid jobs, Web4Grid 20m
        For a long time grid has been used practically only by large projects which can afford to have fine-tuned sophisticated interfaces for the researchers involved on these projects. Without these interfaces the access to grid using shell commands is quite cumbersome for nowadays point and click standards. There are many research areas in which small teams or even individual researchers may need to run many jobs in an efficient manner. While most high throughput computational needs are very much suitable for what grid was intended for, very few users take advantage of it because the access is cumbersome and requires a learning period that many researchers, mainly in small groups, can not afford. To facilitate the use, some user-friendly web applications have been developed for single applications. An example could be e-NMR interface for biomolecular nuclear magnetic resonance and structural biology. Other graphical environments that allow users to run their own applications such as Migrating Desktop, Ganga or P-GRADE Portal are too complex to be used without prior training. To popularize grid it is required to have user friendly interfaces where simple programs can be easily uploaded and executed. Those interfaces should not aim at replacing sophisticated interfaces developed for specific applications. Neither it is required they allow all the options in submitting a job or in monitoring the grid system. On the contrary they should cover the most basic aspects and include suitable default options for the others. Web4Grid interface is intended to be a user-friendly web where grid users can submit their jobs and recover the results on an automatic way. Besides, the interface provides the capability to monitor the existing jobs and to check the (local) grid status (load, number of free cores available, ...). Web4Grid interface does not require specific grid usage training nor any knowledge about the middleware behind it.
        Speaker: Ms Antonia Tugores (CSIC)
        Slides
      • 12:00
        Experiences and Design of the New EGI Metrics Portal 20m
        The EGI Metrics Portal is an important tool for project management that aggregates a large number of quality and health metrics from all tasks within EGI. These metrics measure not only the status of the infrastructure, but also the activity of all people involved on the project. Some of these metrics are conflated from many sources, and some are manual and updated by activity and task leaders. Initially, a PHP portal was spawned from the Accounting Portal existing codebase, but its non-optimal MVC separation, the overhead of PHP development and a perceived complexity on requirement capture and evolution was viewed as an obstacle. Thus, a new Python and Django-based solution was postulated. The Django framework adds a well documented, community-supported and solid base for developing web applications that makes possible rapid prototyping and shorter development cycles, which reduce development risk considerably. It also is based on the DRY (Don't Repeat Yourself) tenet, which avoids code and model duplication. In this sense, many aspects of the new Metrics Portal are model-derived, and, using appropriate tools, model changes can be made in mere minutes. After each model change, conforming SQL tables and Python objects are created, and views are designed to instantiate forms on the fly based on the new model. This allowed to accelerate the development of the Portal so that all manual metrics were introduced in one step, instead of in several development cycles. The support of manual metrics mandated the implementation of an authorization model. Since much of EGI's user auth is based on certificates, the portal first checks for user certification. Since there are users without one, though, authentication for the LDAP-based SSO (Single Sign On) EGI login is automatically used if the user does not provide a certificate. Finally, the resulting portal is modular and layered, and all this layers can be separated into several machines and distributed for redundancy and availability.
        Speaker: Dr Ivan Diaz (FCTSG)
        Slides
    • 11:00 12:30
      NGI Helpdesk Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This workshop will address the status of NGI helpdesk integration into GGUS, and will be an opportunity to discuss technical issues and a future work plan.

      Convener: Dr Torsten Antoni (Karlsruhe Institute of Technology)
      • 11:00
        Introduction 10m
        Speaker: Dr Torsten Antoni (Karlsruhe Institute of Technology)
        Slides
      • 11:10
        The EGI Helpdesk 20m
        Speakers: Guenter Grein (KIT - Karlsruhe Institute of Technology), Dr Torsten Antoni (Karlsruhe Institute of Technology)
        Slides
      • 11:30
        Regional Helpdesk - GRNET Example 15m
        Speaker: Vassilis Gkamas
        Slides
      • 11:45
        Regional Helpdesk - Czech Example 15m
        Speaker: Mr Miroslav Ruda (Cesnet)
        Slides
      • 12:00
        xGUS - the EGI Helpdesk Template 15m
        Speakers: Guenter Grein (KIT - Karlsruhe Institute of Technology), Dr Torsten Antoni (Karlsruhe Institute of Technology)
        Slides
      • 12:15
        Discussion 15m
    • 11:00 12:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 4

        St Clair 4

        Lyon Conference Centre

    • 11:00 12:30
      Operations: Operational Level Agreement Workshop Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      During the workshop we will assess the current status of the EGI OLA framework and we will discuss future enhancements.

      Conveners: Christos Triantafyllidis (GRNET), Dimitris Zilaskos (Technical staff)
      • 11:00
        RP OLA and VO SLA status 30m
        Paper
        Slides
      • 11:30
        Critical Services Availability trends 1h
        Slides
    • 11:00 12:30
      Virtualisation and Cloud Computing: EGI Virtualisation Roadmap Pasteur (300)

      Pasteur (300)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session provides an opportunity for EGI and collaborating NGIs, EIROs, DCI projects and others to present their latest research, developments, findings, visions in the virtualization and cloud computing area.

      This would be an opportunity to set out the EGI federated virtualized infrastructure vision to a wider technical audience, and for technology providers to indicate how they are addressing the challenges.

      Themes:
      * Scientific Cloud Computing Infrastructure
      * Federated Virtualized Infrastructure
      * Cloud operations including experiences operating grid sites
      * DCI project technology updates
      * Scientific use of cloud resources

      Convener: Steven Newhouse (EGI.EU)
      • 11:00
        EGI Virtualisation Roadmap 1h 30m
        Slides
    • 12:30 14:00
      Lunch break 1h 30m
    • 14:00 15:30
      EGI SPG F2F (Closed) St Clair 5

      St Clair 5

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      A (closed) face to face meeting of EGI SPG to make progress on its normal business of producing and revising policy documents.

      Convener: David Kelsey (STFC)
      • 14:00
        Agree Agenda and appoint note taker 5m
      • 14:05
        Minutes of last meeting, review work plan and open actions 15m
        Minutes
      • 14:20
        Revision of Terms of Reference 10m
        Document
      • 14:30
        Service Operations Security Policy 15m
        Document
      • 14:45
        Revision of top-level Security Policy 40m
        Document
      • 15:25
        AOB and future meetings 5m
    • 14:00 15:30
      EGI Sustainability and Business Models Rhone 2

      Rhone 2

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Early this year, EGI.eu produced an EGI Sustainability Plan providing a comprehensive list of the wide range of services that EGI provides and outlined a taxonomy of potential revenue streams in order to sustain these services for future discussion and exploration. As a preliminary assessment, the identified revenue streams started to be matched to the services provided.

      This workshop represents a step forward in the preparation of the next iteration of the EGI sustainability plan. In preparation for this event, a survey was circulated among NGIs/EIROs and a report has been produced (https://documents.egi.eu/document/797).

      During the first part of this session, the general challenge of EGI sustainability as dependent to the sustainability of its ecosystem entities (e.g., NGIs/EIROs, User Communities, Technology Providers, EGI.eu) will be depicted and the results of the survey will be presented. Furthermore, a representative of an NGI, a User Community and a Technology Provider will provide its view on the matter. A panel discussion will serve to better explore the value proposition of each participating entities.

      The second session is more educational and is targeted at explaining what a business model is and details about what are they key components to describe it. Furthermore, insights on value proposition, service portfolio and revenue streams for EGI will be depicted. A real example for a possible EGI business model will be provided. A panel discussion will close the session.

      The target audience is all representatives from NGIs/EIROs, user communities and technology providers that are involved in exploring and defining the sustainability plan of their own organizations. Experts in the area of business models are also welcome to contribute to the discussion.

      The expected outcomes from the session are:
      - All participants will learn about the results of the preparatory survey circulated amongst EGI (associated) participants (NGIs/EIROs)
      - All participants will have a more clear understanding of the EGI eco-system sustainability challenge and its dependency to its components’ sustainability
      - All participants will gain a common understanding on business models and its related building blocks are so to establish a common ground to develop them for the various actors in the EGI eco-system
      - All participants will contribute in refining the value proposition for NGI to its resource centres, EGI to its end-users, EGI.eu to its NGIs/EIROs, Technology Providers to resource centres, Technology Providers to end-users
      - NGIs/EIROs/user community representatives will become more engaged on developing their business models and sustainability strategy in connection with EGI.eu/EGI
      - All participants will contribute to the drafting of business models for NGIs and EGI.eu

      Conveners: Sergio Andreozzi (EGI.EU), Steven Newhouse (EGI.EU)
      paper
      • 14:00
        Welcome and General Introduction 10m
        Speaker: Steven Newhouse (EGI.EU)
        Slides
      • 14:10
        NGIs/EIROs Sustainability Survey Report 15m
        Speaker: Sergio Andreozzi (EGI.EU)
        Paper
        Slides
      • 14:25
        Grid Computing in Germany and the Quest for Sustainability 15m
        Speaker: Dr Torsten Antoni (Karlsruhe Institute of Technology)
        Slides
      • 14:40
        The long-term future for WLCG and the role of EGI 15m
        Speaker: Dr Bob Jones (CERN)
        Slides
      • 14:55
        EMI Sustainability Plans 15m
        Speaker: Mr MORRIS RIEDEL (JUELICH SUPERCOMPUTING CENTRE)
        Slides
      • 15:10
        Panel Discussion 20m
    • 14:00 15:30
      EMI: Directions St Clair 3a

      St Clair 3a

      Lyon Conference Centre

      The European Middleware Initiative (EMI) project aims to deliver a consolidated set of middleware components based on the four major middleware providers in Europe - ARC, dCache, gLite and UNICORE. EMI 1 (Kebnekaise) is the first step towards a stable integrated distribution of compute and data management services that will deliver a broad suite of technologies for deployment in distributed computing infrastructures in Europe and beyond.
      The first EMI release is focused primarily on laying the foundations for the distribution, increasing the level of integration among the original middleware stacks, improving the compatibility with mainstream operating systems' guidelines and extending the compliance with existing standards.
      EMI 1 components follow more closely packaging guidelines and policies defined by Fedora, introduce widespread compliance with the File Hierarchy Standard (FHS), make extensive use of off-the-shelf packages from the OS distribution or major downstream repositories like EPEL, reduce the dependency on less standard technologies and protocols.
      EMI 1 introduced a number of changes and new functionality in response to existing user requirements in the areas of Security, Compute, Data, Information Systems.

      This session will present the major highlights of EMI 1 (Kebnekaise) and current implementations towards EMI 2 (Matterhorn).

      14:00 - 14:30 - "EMI 1 (Kebnekaise) Highlights, status and plans" - C. Aiftimiei
      14:30 - 15:00 - "EMI 2 (Materhorn) Roadmap" - Balazs Konya
      15:00 - 15:30 - "EMI Virtualization and Cloud Strategy" - Shahbaz Memon

      Convener: Florida Estrella (CERN)
      • 14:00
        EMI 1 (Kebnekaise) Highlights, status and plans 30m
        Speaker: Cristina Aiftimiei (INFN)
        Slides
      • 14:30
        EMI 2 (Matterhorn) Roadmap 30m
        Speaker: Balazs Konya (EMI project)
        Slides
      • 15:00
        EMI and Cloud Association Models 30m
        Speaker: Shahbaz memon
        Slides
    • 14:00 15:30
      Individual Presentations: Security St Clair 3b (90)

      St Clair 3b (90)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 14:00
        Argus policies in action 20m
        Authorization across the EMI middleware stacks (gLite, ARC and UNICORE) is currently not homogeneous, and components often have their own mechanisms of handling it. To address this inconsistency and to unify the authorization process, the Argus Authorization Service was chosen as the EMI solution. The Argus Authorization Service renders consistent authorization decisions for distributed services (e.g., user interfaces, portals, computing elements, storage elements). The service is based on the XACML standard, and uses authorization policies to determine if a user is allowed or denied to perform a certain action on a particular service. Authoring XACML policies in XACML itself is not straightforward: XML per se is perceived by many users as difficult to read, and editing can be prone to error. Argus solution to this issue is the Simplified Policy Language (SPL), which facilitates the authoring of policies. Site administrators can write policies in the SPL and import them in the PAP. Policies are then transparently converted in XACML and stored in the local repository. This presentation introduces the Argus SPL in detail and the tools that are used daily by administrators to manage authorization policies. Examples of commonly used policies and typical service operation are discussed. A demo showing the integration of Argus with the CREAM CE and gLexec WN will also be given.
        Speakers: Andrea Ceccanti (INFN), Valery Tschopp (Switch)
        Slides
      • 14:20
        CertWizard: a New Certificate Tool for the UK NGI User Community 20m
        Users find applying for and renewing of their certificates hard. In fact one third of the tickets on the UK NGI Helpdesk in the last year were related to certificates: a common theme being browser issues. STFC staff have produced a browser-independent tool for managing the certificates of the UK NGI user community. This tool, combined with other service improvments, provides a simpler-to-use interface which is more efficient and fully integrated with our already established certificate tools. The NGS runs the world's 2nd largest Grid Certification Authority: the IGTF-accredited UK e-Science CA. It is trialing several innovations for x509 authentication including alternatives to year-long user certificates, but their use will be needed for some time. The CA certificate itself is due for renewal in 2011 and so the opportunity is being taken to make changes at all levels of the service. Up until now, users have used their browser to apply for and renew their certificates. As browsers have evolved there have been a variety of incompatibilities in the way they handle certificates and our list of unsupported browsers has grown. The solution was to write a stand-alone tool to manage these certificate requests without involving a browser. The tool also adds the facility to renew a recently expired certificate and change details such as the user's email address without having to revoke it and apply for a new one like now. It has also been merged with our existing VOMS-enabled MyProxy Upload Tool so that a single tool can be used to manage all the user's certificate interactions. Further work is already underway to add interfaces to provide analogous support for host certificates and for RA Operators to approve both user and host certificate requests. Although the CA part of our tool is tied in to the UK eScience CA, the interface provided is well-defined and would not take too much effort to generalise for other community CAs so we are keen to demonstrate its functionality at the User Forum in Lyon.
        Speaker: John Kewley (STFC)
        Slides
      • 14:40
        Moonshot in Grids - one year after 20m
        Grids have traditionally used certificates which have scaled well globally and given a high level of assurance, but grids would become more useful if they could consume authentication tokens from other authentication infrastructures, also with different levels of assurance. Expected benefits include widening the user base, by making use of existing authentication infrastructure, and improved single sign-on for users. Moreover, central attribute authorities like VOMS have worked well for grids, but being able to make use of institutional attributes will be useful also for new data and services sustainability models, e.g. to support institutional subscriptions. In this presentation we will focus on the Moonshot project that brings the functionality of SAML-based identity federations to the world of non-web applications. Using Moonshot it is possible to rely on home identity providers to perform authentication and issue additional attributes about the users. The user experience from the SAML-based federations suggests that such an arrangement is well perceived. The Moonshot project has been presented already at previous EGI events and elsewhere and elicited an interest from various parties, including large user communities. Therefore, we will present a short introduction of the project and update of its current status, which will be followed by a live demonstration of the technology. In particular we will show how an MyProxy-based online CA can be established, which will issue certificates based on the same authentication and attributes as are utilizied by the Terena Certification Service. We will also describe current status of deployment and present requirements necessary to install the Moonshot technology. Given the interest from the Grid community and an already organized workshop on Moonshot usage in Grids and HPCs, we expect more discussions in this area over the next months, whose outcomes will also be presented in the talk.
        Speaker: Daniel Kouril (CESNET)
      • 15:00
        Securing the network 20m
        This presentation will cover the work conducted within the ScotGrid Glasgow Tier-2 site. It will focus on the multi-tiered network security architecture developed on the site to augment Grid site server security and will discuss the variety of techniques used including the utilisation of Intrusion Detection systems, logging and optimising network connectivity within the infrastructure. Also the analysis of the limitations of this approach and the potential for future research in this area will be investigated and discussed
        Speaker: Dr David Crooks (UG)
        Slides
    • 14:00 15:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 4

        St Clair 4

        Lyon Conference Centre

    • 14:00 15:30
      OGF Rhone 4

      Rhone 4

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 14:00
        OGF 1h 30m
    • 14:00 15:30
      Operations Tools and Availability Calculation Rhone 1 (75)

      Rhone 1 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session will cover the following topics:
      - status of deployment (regionalization, failvoer configuration) and future plans for all central operational tools (Operations portal, SAM, GOCDB, Metrics portal, broker network)
      - external tools (gstat, ace)
      - Availability calculation updates
      . new site availability algorithms
      . core services availability
      . operational tools availability

      Convener: Mr Emir Imamagic (SRCE)
      • 14:00
        GSTAT 10m
        Speaker: Eric Yen (ASGC)
      • 14:10
        SAM Status Update 20m
        Speaker: Marian Babik (CERN)
        Slides
      • 14:30
        ACE Status Update 10m
        Speaker: Pedro Andrade (CERN)
        Slides
      • 14:40
        New Availability Requirements 20m
        Speaker: Christos Kanellopoulos (GRNET)
        Documentation
        Slides
      • 15:00
        Operational Tools Monitoring 10m
        Speaker: Mr Emir Imamagic (SRCE)
        Slides
      • 15:10
        UNKNOWN Status in A/R Reports 10m
        Speaker: Malgorzata Krakowian (CYFRONET)
        Slides
      • 15:20
        Discussion 10m
    • 14:00 15:30
      Portal technologies for EGI communities Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Portals, portlets and science gateways provide simple mechanisms for users to interact with grid and cloud computing services and with the community-related functions offered within the European Grid Infrastructure. Portal frameworks, portlet repositories, “iframe” encapsulation of content enables EGI user support teams to customise and integrate third party services according to their customers’ needs.

      EGI aims to support development effort from the area for the benefit of EGI Virtual Research Communities through the sharing of beast practices. The workshop aims to bring together three groups from EGI – portal technology providers, NGI support teams, VRCs – to discuss and answer the following series of questions:

      • What kind of portal-related technologies and best practices are the most widely used and are emerging within the EGI community? How many and which VRCs and NGIs are supporting these?

      • What requirements do the user and operation communities have concerning the usage, operation, integration and further-development of portals, portlets and iframes?

      • How could a wider and harmonised adoption of these technologies be facilitated within EGI? What role should EGI.eu and the NGIs play in this process?

      The workshop consists of 2 x 90 minutes long sessions. The first slot includes presentations given by the most active and experienced portal provider and user communities from the NGIs and VRCs. The second slot is allocated to discussion where requirements and issues can be analysed and where an action plan concerning the wider adoption of EGI portal technologies can be drafted.

      Convener: Gergely Sipos (EGI.EU)
      Introduction
      Notes
      • 14:00
        The DECIDE project Science Gateway 15m
        The EU FP7 DECIDE (www.eu-decide.eu) project is focused on supporting neurologists and physicians involved in the assessment of neurodegenerative diseases in the diagnosis and prognosis and aims at enhancing user confidence by improving the reliability of the required analysis and by integrating different clinical approaches. It has been conceived to target a non-technical medical audience and tries to support the daily needs of neurologists while dealing with their patients, going well beyond the world of research. The aim of the project is to design, implement, and validate a dedicated e-Infrastructure based on the neuGRID outcomes and relying on the GEANT backbone and its supporting NRENs, on EGI and some of the European NGIs. Over this e-Infrastructure, a production quality service will be provided around the clock for the computer-aided extraction from medical images of diagnostic disease markers for Alzheimer’s and schizophrenia. The service that will be realized in the course of the DECIDE project will be exposed to end users as a Science Gateway based on the Liferay portlet container and the gLite middleware and makes use of a sophisticated authentication and authorization mechanism supporting Federations of Identity Providers based on Shibboleth and SAML 2.0. This work reports on the architecture and the present implementation of the Science Gateway developed and describes the various functional aspects of the portal like the AAI, the interface to Grid services, medical data encryption, metadata management and training service. The motivation of the work is to enable e-Health for European citizens providing the largest possible number of them with access to a high-quality early diagnostic and prognostic service for the Alzheimer Disease and other forms of dementia.,On this purpose, the DECIDE Science Gateway has been configured as a Service Provider of the IDEM (www.idem.garr.it) Identity Federation which counts, as of today, more than 2,700,000 members in Italy and abroad.
        Speaker: Dr Valeria Ardizzone (COMETA and INFN)
        Slides
      • 14:15
        The INDICATE project e-Culture Science Gateway 15m
        INDICATE (www.indicate-project.eu) is a European Union FP7 project which aims to establish a network of common interest made up of experts and researchers in the field of e-Infrastructures and Digital Cultural Heritage. Through the network, the participants can share experience, promote standards and guidelines, and seek harmonisation of best practices and policies. In this contribution we will present the INDICATE e-Culture Science Gateway that provides users with an easy-to-use web interface and a single sign-on beyond the home institute mechanism to access digital archives of Cultural Heritage data coming from Italy and China. The Gateway is based on Liferay for which a JSR 286 compliant portlet has been developed to interface the well known gLibrary framework developed by INFN and COMETA to create and manage digital repositories on the Grid. The AAI put in place is compliant with SAML 2.0 based Federations of Identity Providers enabled by Shibboleth. The INDICATE e-Culture Science Gateway has been configured as a Service Provider of the IDEM (www.idem.garr.it) Identity Federation which counts, as of today, more than 2,700,000 end users in Italy. What has been done is a major step forward towards an easier and wider use of e-Infrastructures by non-expert users who do not want to deal with personal digital certificates and the complex Grid Security Infrastructure. Opening the Grid to the Identity Federations will allow a tighter coupling of e-Infrastructures with Digital Libraries and already existing Cultural Heritage repositories.
        Speaker: Roberto Barbera (University of Catania and INFN and COMETA)
        Slides
      • 14:30
        Portals for the WeNMR Community 15m
        The WeNMR (http://www.wenmr.eu) project is an EU-funded international effort to streamline and automate structure determination from Nuclear Magnetic Resonance (NMR) and small angle X-ray scattering (SAXS) data. Conventionally calculation of structure requires the use of various software, considerable user expertise and vast computational resources. To facilitate the use of NMR spectroscopy in life sciences the eNMR/WeNMR consortium has set out to provide protocolized services through easy-to-use web interfaces, while still retaining sufficient flexibility to handle more specific requests. Thus far, a number of programs often used in Structural Biology have been made available through portals, including HADDOCK, XPLOR-NIH, CYANA, CS-ROSETTA, MARS, MDDNMR and now AMBER and GROMACS. We will present a few of the web-portals and demonstrate that the designed interfaces are as easy as possible for new users who often have limited computational experience, while still providing advanced users with more control over the calculation parameters. The implementation of these services, in particular the distribution of calculations to the Grid, involves a novel mechanism for submission and job handling that is independent of the type of job being run. With currently 330 registered users from all over the world, WeNMR has become the largest Virtual Organization (VO) in life sciences.
        Speaker: Schmitz Christophe
        Slides
      • 14:45
        SCI-BUS: building e-Science gateways in Europe 15m
        The success of the open-source P-GRADE and gUSE/WS-PGRADE portal technologies have shown us that there is a big need for a generic, customizable and powerful portal solution in e-Science. In order to satisfy this demand, we aim the followings in the forthcoming EU FP7 SCI-BUS project starting in 1st of October 2011: first, the project will create and disseminate a generic distributed computing infrastructure portal solution for e-Scientists based on gUSE/WS-PGRADE. Second, the project will create a customized science gateway building methodology using different APIs of the generic portal solution. Third, a number of customized science gateway portlets or services will be created based on this methodology and 11 customized science gateways will be established for the following communities: a. International seismology community b. Helio-physics community c. Swiss systems biology community of the SystemsX.ch project d. German MoSGrid computational chemistry and bioinformatics community e. Biomedical researchers community of the Academic Medical Centre of the University of Amsterdam f. Astrophysics community g. PireGrid SMEs community h. Business process modelling community involving a wide range of areas such as finance, healthcare, government, production, robotics and emergency i. Blender rendering community j. Citizen web-2 community k. Public application developer community Finally, these customized portlets will be made available in a portlet repository for external deployment where applicable. Within our talk we will present the SCI-BUS project, and technologies used within the project in a nutshell.
        Speakers: Prof. Peter Kacsuk (MTA SZTAKI), Mr Zoltan Farkas (MTA SZTAKI)
        Slides
      • 15:00
        LGI Pilot Job Portal 15m
        The LGI Pilot Job portal is developed by BiG Grid, the Dutch NGI. This portal framework is based on the Leiden Grid Initiative framework, which offers a uniform access model to multiple heterogenenous resources, such as clusters, clouds, supercomputers and now also gLite based grid infrastructure. The LGI Pilot Job framework is a single-user pilot job framework, in which grid authentication is done using a robot hardware token. User authentication on the portal itself is done using plain (i.e. non-grid) X509 certificates or using username/password authentication. An extension to support TERENA using SimpleSAML is currently being developed. Several client interfaces are available, including command-line clients written in C++ and Python, as well as PHP and Java clients. An R-interface to the LGI Pilot Job framework is currently being tested.
        Speaker: Jan Keijser (FOM)
        Slides
      • 15:15
        Gridcertlib - From Shibboleth authentication to X.509 certificates 15m
        GridCertLib is a Java library providing services to create a SLCS/X.509 certificate and a Grid proxy (optionally VOMS-enabled), given the SAML2 assertion resulting from a Shibboleth2 authentication. The library comes with some example servlets (cf. package.swing.gridcertlib.servlet) that provide sample code to use the GridCertLib features in a Java web services environment. The main use case envisioned for GridCertLib is to provide seamless and secure access to Grid/X.509 certificates and proxies in web portals: when a user logs in to the portal using the regular SWITCHaai Shibboleth authentication, GridCertLib can automatically obtain a Grid X.509 certificate from the SLCS service and generate a VOMS proxy from it. What is more, all of this can happen without further interaction with the user.
        Speaker: sergio maffioletti (UZH)
        Slides
    • 14:00 15:30
      UNICORE integration 1h 30m Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      This session will tackle the open issues related to the integration of UNICORE Resource Centres into EGI. It can be viewed as an extended UNICORE integration task force meeting but giving some more background for the benefit of occasional participant.

      Agenda:

      • Welcome and introduction
      • Status reports
      • Report by Marcin Radecki, ICM, Poland
      • Report by Rebecca Breu, Jülich, Germany
      • Management interface GOCDB
      • Monitoring interface SAM
      • Accounting interface
      • EGI Accounting Plans, John Gordon, STFC
      • User Membership Management
      • Argus Overview, Oscar Koeroo, Nikhef
      • Unicore and Argus Integration, Krzysztof Benedyczak, ICM (slides shown by Gert Svensson)
      • Next meeting

      Speaker: Gert Svensson (KTH)
    • 14:00 15:30
      Virtualisation and Cloud Computing: Technology Pasteur (300)

      Pasteur (300)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session provides an opportunity for EGI and collaborating NGIs, EIROs, DCI projects and others to present their latest research, developments, findings, visions in the virtualization and cloud computing area.

      This would be an opportunity to set out the EGI federated virtualized infrastructure vision to a wider technical audience, and for technology providers to indicate how they are addressing the challenges.

      Themes:
      * Scientific Cloud Computing Infrastructure
      * Federated Virtualized Infrastructure
      * Cloud operations including experiences operating grid sites
      * DCI project technology updates
      * Scientific use of cloud resources

      Convener: David O'Callaghan (TCD)
      • 14:00
        Virtualisation & Cloud Computing Technology 1h 30m
        Technology providers present their latest developments of cloud infrastructures and grid / cloud integration.
        Slides
        • FermiCloud: Enabling Scientific Computing with Integrated Private Cloud Infrastructure 20m
          FermiCloud is a private cloud Infrastructure-as-a-Service facility for scientific computing at Fermilab. Users can create virtual machines on demand with full access to the site network and mass storage systems. We use grid-based authentication systems to instantiate virtual machines, and are currently designing a grid-based authorization system as well based on authorization interoperability profiles. The virtualization of small experiment-specific servers and integration machines has already enabled significant savings in facilities cost. Potential future applications include preserving archival software setups for decommissioned experiments and virtualization for compartmentalization of job execution on multicore machines.
          Speakers: Keith Chadwick (Fermi National Accelerator Laboratory), Dr Steven Timm (Fermi National Accelerator Laboratory)
          Slides
        • StratusLab: status update and elastic deployment of services 20m
          Speaker: Vangelis Floros (GRNET)
          Slides
        • Clouds in grids using CLEVER 20m
          During the last few years, interest has gradually shifted from Grid Computing to an independent and complementary paradigm: the Cloud Computing. Both Grids and Clouds provide access to large, distributed, computing and storage resources but Clouds massively exploit virtualization to provide uniform interface to the underlying re source, thus hiding physical heterogeneity, geographical distribution and faults. While there are many similarities between the two computing models, the differences are those that matter most. Grid computing is better suited for organizations with large amounts of data being analysed by a small number of users, whereas Cloud computing is better suited to environments where there is a large number of users requesting small amounts of data, or many but small allocation requests. Although Grid technology continues to dominate public sector and scientific computing environments, new interests have raised in deploying cloud technology on grid-enabled resources to improve the management and reliability of those resources via the virtualization layer. The aim of this contribution is to present an integration example of both technologies where Grid resources are used to easily deploy on-demand Clouds using the CLEVER innovative Cloud middleware. CLEVER simplifies the access management of private/hybrid Clouds and provides simple and easily accessible interfaces to interact with different interconnected Clouds, deploy Virtual Machines and perform load balancing through migration. Designing a solution for on-demand private clouds rather than deploying individual products to address each user challenge leverages Grid computing in ways that extend control and flexibility, enabling the infrastructure required to fully take advantage of a dynamic computing resource model. Moreover, integrating a Cloud in a Grid adopts the Cloud paradigm to strengthen its security with the robust federated identity and access management architecture of Grids.
          Speaker: Dr Massimo Villari (University of Messina)
          Slides
        • WnoDeS – a Grid/Cloud Integration Framework 20m
          WNoDeS is a software framework developed at INFN CNAF to integrate Grid and Cloud provisioning. It is deployed on the INFN Tier-1 (CNAF) and Tier-2 (LNL and Bari) production infrastructures. WNoDeS is a solution to virtualize computing resources and to make them available through local and Grid access interfaces in case batch jobs are submitted, through a Virtual Interactive Pools to support the local instantiation of customized resources, and through the OGF OCCI standard or a Cloud Web portal to support users requiring generic virtualized computing resources. The WNoDeS key advantages are: the use of a common pool of resources due to the unnecessary to dedicate resources to user interfaces, Grid computing, Cloud computing and local users; the reuse of 10 years of worldwide development, expertise and resources brought by Grid computing in the key areas of Authentication, Authorization, Accounting, Information System, Brokering, Data transfer; the flexibility and scalability of the service due to the use of a standard batch system for resource provisioning and policing. WNoDeS adopts a distributed FS to share virtual images. To avoid the issue that any CPU core may become a distributed FS client, FUSE-based and GPFS-to-NFS export solutions have been investigated. Recently, WNoDeS has been modified to exploit open source software: now WNoDeS could support Cloud Services by also using the specific features of Torque and Maui. Moreover, the image distribution using Lustre as shared FS has been tested. Those changes will allow small farms to adopt WNoDES without using proprietary software. Furthermore, to optimize the use of computing resources WNoDeS is considering to adopt the same resource for virtual and real jobs. IGI, through a solution based on the WNoDeS framework, plans to offer an integrated computing infrastructure providing Grid computing services, Cloud computing services and interconnection of cloud computing resource centers for the Italian and research community.
          Speaker: Elisabetta Ronchieri (INFN CNAF)
          Slides
    • 15:30 16:00
      Coffee break 30m
    • 16:00 17:30
      EGI Sustainability and Business Models Rhone 2

      Rhone 2

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Early this year, EGI.eu produced an EGI Sustainability Plan providing a comprehensive list of the wide range of services that EGI provides and outlined a taxonomy of potential revenue streams in order to sustain these services for future discussion and exploration. As a preliminary assessment, the identified revenue streams started to be matched to the services provided.

      This workshop represents a step forward in the preparation of the next iteration of the EGI sustainability plan. In preparation for this event, a survey was circulated among NGIs/EIROs and a report has been produced (https://documents.egi.eu/document/797).

      During the first part of this session, the general challenge of EGI sustainability as dependent to the sustainability of its ecosystem entities (e.g., NGIs/EIROs, User Communities, Technology Providers, EGI.eu) will be depicted and the results of the survey will be presented. Furthermore, a representative of an NGI, a User Community and a Technology Provider will provide its view on the matter. A panel discussion will serve to better explore the value proposition of each participating entities.

      The second session is more educational and is targeted at explaining what a business model is and details about what are they key components to describe it. Furthermore, insights on value proposition, service portfolio and revenue streams for EGI will be depicted. A real example for a possible EGI business model will be provided. A panel discussion will close the session.

      The target audience is all representatives from NGIs/EIROs, user communities and technology providers that are involved in exploring and defining the sustainability plan of their own organizations. Experts in the area of business models are also welcome to contribute to the discussion.

      The expected outcomes from the session are:
      - All participants will learn about the results of the preparatory survey circulated amongst EGI (associated) participants (NGIs/EIROs)
      - All participants will have a more clear understanding of the EGI eco-system sustainability challenge and its dependency to its components’ sustainability
      - All participants will gain a common understanding on business models and its related building blocks are so to establish a common ground to develop them for the various actors in the EGI eco-system
      - All participants will contribute in refining the value proposition for NGI to its resource centres, EGI to its end-users, EGI.eu to its NGIs/EIROs, Technology Providers to resource centres, Technology Providers to end-users
      - NGIs/EIROs/user community representatives will become more engaged on developing their business models and sustainability strategy in connection with EGI.eu/EGI
      - All participants will contribute to the drafting of business models for NGIs and EGI.eu

      Conveners: Sergio Andreozzi (EGI.EU), Steven Newhouse (EGI.EU)
      paper
      • 16:00
        Introduction to Business Models 35m
        Speaker: Sy Holsinger (EGI.EU)
        Slides
      • 16:35
        Business Models: A Concrete Example for EGI 25m
        Speaker: Zeev Vaxman Fisher (IUCC)
        Slides
      • 17:00
        Panel Discussion 30m
    • 16:00 17:30
      GLOBUS integration 1h 30m Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      This session will tackle open issues related to the integration of GLOBUS Resource Centres into EGI. It can be viewed as an extended GLOBUS integration task force meeting but giving some more background for the benefit of occasional participant.

      Agenda:

      Welcome and introduction
      Status reports
      Globus in UMD
      - Report from Early Adaptor, Matteo Lanati, LRZ
      Management interface GOCDB
      Monitoring interface SAM
      Accounting interface
      - Grid-SAFE overview and status, Stephen Crouch, SSI
      - UK experiment with Grid-SAFE, John Gordon, STFC
      User Membership Management
      - Argus and Globus, Oscar Koeroo, Nikhef
      Next meetings
      AOB

      Speakers: Gert Svensson (KTH), Michaela Lechner (KTH)
    • 16:00 17:30
      NGI Operational Tools Marketplace Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Many NGIs use operational tools that are developed locally and not within any international projects. These include accounting and monitoring tools, helpdesks systems, factory management systems and maybe many others. Such tools are not well known to other NGIs, this session should be an occasion to advertise such NGI internal products that can be useful to the entire operations community.

      Convener: Daniele Cesini (INFN)
      • 16:00
        Introduction 5m
        Speaker: Daniele Cesini (INFN)
        Slides
      • 16:05
        NGI_AEGIS: WatG Browser, gFinger, DWARF 20m
        Speaker: Vladimir Slavnic (IPB)
        Slides
      • 16:25
        NGI_IT: HLRMon, WMSMonitor 20m
        Speakers: Danilo Dongiovanni (INFN), Enrico Fattibene (INFN)
        Slides
      • 16:45
        NGI_CH: national infrastructure operation tools 15m
        Speakers: Andres Aeschlimann (SWITCH), sergio maffioletti (UZH)
        Slides
      • 17:00
        CESNET: Improved x509 credential management 15m
        Speaker: Daniel Kouril (CESNET)
        Slides
      • 17:15
        NGI_PL: Bazaar 15m
        Speaker: Marcin Radecki (CYFRONET)
        Slides
    • 16:00 17:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 4

        St Clair 4

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

    • 16:00 17:30
      Portal technologies for EGI communities Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Portals, portlets and science gateways provide simple mechanisms for users to interact with grid and cloud computing services and with the community-related functions offered within the European Grid Infrastructure. Portal frameworks, portlet repositories, “iframe” encapsulation of content enables EGI user support teams to customise and integrate third party services according to their customers’ needs.

      EGI aims to support development effort from the area for the benefit of EGI Virtual Research Communities through the sharing of beast practices. The workshop aims to bring together three groups from EGI – portal technology providers, NGI support teams, VRCs – to discuss and answer the following series of questions:

      • What kind of portal-related technologies and best practices are the most widely used and are emerging within the EGI community? How many and which VRCs and NGIs are supporting these?

      • What requirements do the user and operation communities have concerning the usage, operation, integration and further-development of portals, portlets and iframes?

      • How could a wider and harmonised adoption of these technologies be facilitated within EGI? What role should EGI.eu and the NGIs play in this process?

      The workshop consists of 2 x 90 minutes long sessions. The first slot includes presentations given by the most active and experienced portal provider and user communities from the NGIs and VRCs. The second slot is allocated to discussion where requirements and issues can be analysed and where an action plan concerning the wider adoption of EGI portal technologies can be drafted.

      Introduction
      Notes
      • 16:00
        Discussions 1h 30m
        Slides
    • 16:00 17:30
      Service Management in the EGI/NGI ecosystem 1h 30m Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      This session has two core purposes: to collect feedback and experiences from EGI and NGI representatives in how they manage their Grid-based services, and to provide a vision of the emerging challenge of Grid service management and how it can be faced. Effective service level management is critical in production Grids, as their increasing maturity means that users are demanding a greater quality of service than seen in the development phase of the infrastructure. To compete with commercial services that aim for and often achieve ‘five nines’ levels of reliability, the Grid community needs to learn from industry’s experience in the area. This session provides a platform for members of the community to discuss service level management as a process by which grid infrastructure providers identify and agree on the level of IT service needed to satisfy their current level of maturity. It will also discuss best practices in delivering the utility and warranty users need (or expect), and pave the way to more advanced and effective service level agreements in grids. The session will be organised by the gSLM project, which is funded by the EC to bring experience from the commercial IT Service Management community to the Grid. It is also connected to two recently organized international workshops: BDIM2011 (held in conjunction with the 12th IFIP/IEEE International Symposium on Integrated Network Management) and the MDGS2011 (held in conjunction 17th International European Conference on Parallel and Distributed Computing Euro-Par 2011). It will build upon the discussions about the Service level management in Grids, which takes place at both workshops, The session will have presentations by both IT Management and Grid researchers as well as an in-depth panel discussion.
      Speakers: Owen Appleton (Emergence Tech Limited), Dr Thomas Schaaf (LMU), Mr Tomasz Szepieniec (Cyfronet)
      • Introduction to the workshop and gSLM 20m
        Dr Thomas Schaaf, gSLM Project Director will introduce the session. He will explain the background of the gSLM project and its mission to bring service level management to Grids.
      • Bringing SLM to Grids - panel discusison. 40m
        This session comprises an introduction by Owen Appleton of the gSLM project on the workshop series on service level management in Grids. This will be followed by a Panel discussion on the topic including: - Tomasz Szepieniec - PLGrid (Polish NGI) and Cyfronet - Helene Cordier - Frances Grilles (French NGI) and IN2P3 - Franck Michel - LSGC Technical Director (Life science user community) - Thomas Schaaf of gSLM and LMU/LRZ (SLM expert and resource centre for HPC/Grid)
        Slides
      • EGI view on service management 15m
        Tiziana Ferrari, EGI operations manager will discuss EGIs approach to servove management and OLAs as well as mentioning the status fo related work in business models.
        Slides
      • Conclusions and next steps 15m
        Dr Thomas Schaaf will conclude the session and introduce the Service Management tutorial session on Thursday.
    • 16:00 17:30
      Using Agile in Academic, national and European projects 1h 30m St Clair 3a (90) (Lyon Confernce Centre)

      St Clair 3a (90)

      Lyon Confernce Centre

      Several institutions and organisations are experimenting with agile methodologies, such as Scrum, Kanban and engineering practices from XP (e.g. TDD, continuous integration), or even Lean (e.g. stop the line culture). This session proposes a set of short experience reports, followed by a round table, perhaps in the form of an open fishbowl, where several people/projects could share their experience regarding their experimentation, focusing on which aspects were explored, what worked and what didn't. StratusLab for example is using most Scrum practices with a significant gain in performance (e.g. 4 public releases in its first year) and a great ability to adapt to our fast changing world. Introducing these methods in the grid world offers challenges and agile implementations must take into account its specificity (e.g. shared resources, distributed teams, highly specialised teams and individuals, operations vs development/integration). New tools and technologies also bring challenges, but also solutions. For example, releasing more often requires a higher level of process automation, which can be complex when dealing with testing services sensitive to security. For people unaware of agile methods, a short introduction to the agile eco-system should provide enough background such that this session is interesting to all.
      Speakers: Marc-Elian Begin (SixSq), Pau Minoves (i2CAT Foundation)
      Slides
      • Agile in a nutshell 20m
        Introduction to agile methodologies, including Scrum and engineering practices such as TDD, continuous integration and emerging designs.
        Speaker: Marc-Elian Begin (SixSq)
        Slides
      • Agile in Mantychore 20m
        Experience report on applying agile methodologies in the Mantychore project
        Speaker: Pau Minoves (i2CAT Foundation)
      • Agile in StratusLab 20m
        Experience report on applying agile methodologies in the StratusLab project
        Speaker: Marc-Elian Begin (SixSq)
        Slides
      • Open fishbowl discussion 30m
        Open discussion, using the Open Fishbowl format. Come and join the discussion or simple listen and learn.
    • 16:00 17:30
      Virtualisation and Cloud Computing: Users and Experience Pasteur (300)

      Pasteur (300)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session provides an opportunity for EGI and collaborating NGIs, EIROs, DCI projects and others to present their latest research, developments, findings, visions in the virtualization and cloud computing area.

      This would be an opportunity to set out the EGI federated virtualized infrastructure vision to a wider technical audience, and for technology providers to indicate how they are addressing the challenges.

      Themes:
      * Scientific Cloud Computing Infrastructure
      * Federated Virtualized Infrastructure
      * Cloud operations including experiences operating grid sites
      * DCI project technology updates
      * Scientific use of cloud resources

      Convener: David O'Callaghan (TCD)
      • 16:00
        Virtualisation & Cloud Computing Users and Experience 1h 30m
        User communities present their experiences and plans.
        • Research community utilisation of hybrid IaaS 15m
          Speaker: Dr David Wallom (Oxford e-Research Centre)
          Slides
        • StratusLab, Bioinformatics and the cloud 15m
          Speaker: Christophe Blanchet (IDB IBCP FR3302)
          Slides
        • Experiences on Hungarian Cloud Infrastructure Cloud Initiatives 15m
          Setting up an IaaS cloud is a tedious task even if the necessary components are available. In the presentation we would like to show an infrastructure cloud solution that offers users virtual machines and interconnected sets of virtual machines. We would like to show the purpose of our cloud, its user scope, the main features by highlighting some of the innovative tricks that we applied to provide a complete solution. Some future steps will also be highlighted.
          Speaker: Peter Stefan (NIIFI)
          Slides
        • HEPiX virtualization WG 15m
          Speaker: Owen Synge (DESY (HH))
          Slides
        • SARA BiGGrid HPC Cloud project 15m
          Speaker: Floris Sluiter (SARA)
          Slides
    • 17:30 19:00
      Welcome Cocktail 1h 30m
    • 09:00 10:30
      Plenary
      • 09:00
        Extreme Data Intensive Computing in Science 45m
        Scientific computing is increasingly revolving around massive amounts of data. From physical sciences to numerical simulations to high throughput genomics and homeland security, we are soon dealing with Petabytes if not Exabytes of data. This new, data-centric computing requires a new look at computing architectures and strategies. We will revisit Amdahl's Law establishing the relation between CPU and I/O in a balanced computer system, and use this to analyze current computing architectures and workloads. We will discuss how existing hardware can be used to build systems that are much closer to an ideal Amdahl machine. Scaling existing architectures to the yearly doubling of data will soon require excessive amounts of electrical power. We will explore how low-power processors combined with GPGPUs might provide an ideal, low-power platform with both excellent IO and computational performance. We have deployed various scientific test cases, mostly drawn from astronomy, over different architectures and compare performance and scaling laws. We discuss a hypothetical cheap, yet high performance multi-petabyte system currently under consideration at JHU. We will also explore strategies of interacting with very large amounts of data, and compare various large scale data analysis platforms.
        Speaker: Alex Szalay (Professor of Astronomy and Computer Science, Johns Hopkins University)
        Slides
      • 09:45
        The Digital Agenda for Europe 45m
        The talk will present the Digital Agenda for Europe, the EU's vision and action plan for bringing the benefits of the Digital Age to everybody. From among the many elements of the Digital Agenda the actions related to European e-Infrastructures and Cloud Computing will be explained in more detail.
        Speaker: Carl-Christian Buhr (Member of the Cabinet of Neelie Kroes)
        Slides
    • 09:00 19:00
      Posters and Demonstrations
    • 10:30 11:00
      Coffe break 30m
    • 11:00 12:30
      EGI Task Force: Quality Assurance (Closed) 1h 30m Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      Review of Quality Assurance processes and documents. Intended outcome: List of actions assigned to EGI, and all Technology Providers that are engaged with EGI with an SLA.
      Speakers: Alvaro Simon (FCTSG), Enol Fernandez del Castillo (CSIC), Ivan Diaz Alvarez (FCTSG), Michel Drescher (EGI.EU)
      Minutes
      Slides
      • Quality Criteria Definition Process Review 20m
        Speaker: Enol Fernandez del Castillo (CSIC)
        Slides
      • Review of the Verification Process for UMD 1.0, UMD 1.1 and UMD 1.2 30m
        Speaker: Ivan Diaz Alvarez (FCTSG)
        Slides
      • IGE feedback 10m
      • Next Steps and discussion 30m
    • 11:00 12:30
      EGI-InSPIRE St Clair 5 (15M)

      St Clair 5 (15M)

      Lyon Conference Centre

      • 11:00
        EGI InSPIRE PAC (closed) 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 11:00 12:30
      EGI/NGI Roadshows Rhone 2

      Rhone 2

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      EGI is a partnership between National Grid Initiatives (NGIs) and a coordinating body, named EGI.eu to operate a sustainable, pan-European Grid infrastructure for international scientific communities. NGIs are national legal entities charged with taking care of grid infrastructure related matters in their own countries. One of the objectives of EGI and particularly of members of the EGI-InSPIRE project is to expand access to the services of the European Grid Infrastructure to new user communities including new potential heavy users of the infrastructure from the ESFRI projects.

      EGI.eu aims to facilitate this process by developing an “EGI-NGI Roadshow” event model for NGIs. An EGI Roadshow event consists of presentations and optional demos or hands on sessions. The presentations introduce the goals, structure and services of EGI, while the demos and hands-on sessions demonstrate some of these services in practice for the sudience. The EGI Roadshow model not only provides ready-to-use content for NGI dissemination and training teams, but also includes instructions and best practices on how and which communities should NGIs invite for roadshow events. The model is customisable for local needs of the NGI and the audience.

      The session will present the roadshow model for NGIs and NGI representatives who attend the session are expected to organise and deliver events within their own countries from October.

      The Roadshow model is currently under development by the User Community Support Team of EGI.eu. During the 90 minutes long session the elements of the model will be presented. The session aims to be a “Training the trainers” type of event, where representatives from NGIs can learn how to organise and run EGI information events within their countries/regions. Attendees will also have the opportunity to provide feedback on the roadshow model itself.

      Convener: Gergely Sipos (EGI.EU)
      • 11:00
        Introduction to the EGI/NGI Roadshow Model 15m
        Speaker: Stephen Brewer (EGI.EU)
      • 11:15
        Elements of the model 30m
        Speaker: Richard McLennan (EGI.EU)
        Slides
      • 11:45
        The NGS roadshows 15m
        "The NGS (UK National Grid Service; www.ngs.ac.uk) has been running roadshow events for more than 2 years with 13 events having taken place. The main aims of the roadshows are to raise awareness of the NGS amongst researchers, post docs and PhD students as well as IT staff and to provide “hands on” training in using NGS resources. The roadshows are mainly held at NGS member sites of which there are currently 24. Roadshow events are also held at institutions that are interested in becoming NGS members or where there is a demand e.g. from a large research group. The roadshows follow a format which can be tailored to each institutions requirements but usually include an introduction to the NGS, presentations from current NGS users and presentations on how to get started using NGS resources. The afternoon session is a “hands on” training session to allow delegates to gain real experience of submitting jobs to the NGS. Feedback on the roadshows has been very positive with 80% of attendees likely to apply for a grid certificate and NGS account. We also carry out follow up feedback approximately 3 months after the roadshow. We are currently planning a large number of roadshow events. The NGS has recently had funding confirmed until the end of July 2012 and we are currently ensuring that all member sites host a roadshow event in the next 11 months if they have not already hosted an event."
        Speaker: Gillian Sinclair
        Slides
      • 12:00
        Discussion 30m
    • 11:00 12:30
      EMI Security Directions Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The EMI Security Infrastructure and strategy has been defined and deployed in the first year of the project. As the second year continues there will be additions made and strategy refinements.

      This can be a 90min session devoted to the Security directions that are/will be taken in the EMI project. Contributions can include the current and Security infrastructure (Architecture).
      Integration of common components inside the EMI stack, AAI services and possibilities for secured usage of EMI services through pseudo-anonymous identities and encrypted data storage.

      Convener: John White (University of Helsinki, Finland)
      • 11:00
        EMI Security Overview 15m
        Slides
      • 11:15
        Upcoming Use Cases for Initializing Grid Identity 30m
        Speaker: Henri Mikkonen (Helsinki Institute of Physics)
        Slides
      • 11:45
        LCG and the HEP Community 25m
        Speaker: Dr Maarten Litmaath (CERN)
        Slides
      • 12:10
        Webstart tool for Encrypted Data 20m
        Slides
    • 11:00 12:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 11:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 11:00
        PGI: BES/JSDL/GLUE Discussions 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

    • 11:00 12:30
      Operations:OTAG (Closed) St Clair 3b

      St Clair 3b

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      EGI OTAG-10

      Convener: Daniele Cesini (INFN)
      • 11:00
        Introduction 5m
        Speaker: Daniele Cesini (INFN)
      • 11:05
        GGUS report generator 20m
        Speaker: Guenter Grein (KIT - Karlsruhe Institute of Technology)
        Slides
      • 11:25
        Operations Portal Status and VO Dashboard Roadmap 25m
        Speaker: Cyril Lorphelin (CNRS)
        Slides
      • 11:50
        SAM: EMI UI and NRPE Support 15m
        Speakers: David Collados (CERN), Marian Babik (CERN)
        Slides
      • 12:05
        Enabling ACLs on Message Broker Network 10m
        Speaker: Christos Triantafyllidis (GRNET)
        Slides
      • 12:15
        Deployment of package building infrastructure for JRA1 15m
        Speaker: Christos Triantafyllidis (GRNET)
        Slides
    • 11:00 12:30
      SIENA Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      About SIENA
      SIENA, the Standards and Interoperability for eInfrastructure Implementation Initiative (2010-2012), is focused on delivering a Roadmap creating a common vision for the future evolution of European Research and an integrated standards-based, interoperable European e-Infrastructure. This builds upon the knowledge, assets, best practices, policies and capabilities of the six European Distributed Computing Infrastructures (DCI) to provide value to all stakeholders in Research, Government and Industry.

      The main goal of the workshop is to focus on DCI assets for the purpose of serving the eScience community and identifying standards required to make these assets interoperable. The workshop features a presentation from Carl Christian Buhr, Member of the Cabinet of Neelie Kroes European Commission Vice-President for the Digital Agenda, as well as insights into the various assets that the EC-funded DCI and ESFRI projects can offer in the areas of eScience, Industry and eGovernment. Effective dialogue between stakeholder participants will be ensured through an Open Discussion on technical challenges, eGovernment, industry uptake, and call to action.

      • 11:00
        SIENA 1h 30m
    • 11:00 12:30
      Virtualisation and Cloud Computing: Collaborating Projects St Clair 4 (45)

      St Clair 4 (45)

      Lyon Conference Centre

      This session provides an opportunity for EGI and collaborating NGIs, EIROs, DCI projects and others to present their latest research, developments, findings, visions in the virtualization and cloud computing area.

      This would be an opportunity to set out the EGI federated virtualized infrastructure vision to a wider technical audience, and for technology providers to indicate how they are addressing the challenges.

      Themes:
      * Scientific Cloud Computing Infrastructure
      * Federated Virtualized Infrastructure
      * Cloud operations including experiences operating grid sites
      * DCI project technology updates
      * Scientific use of cloud resources

      Convener: Michel Drescher (EGI.EU)
      • 11:00
        Virtualisation & Cloud Computing Collaborating Projects 1h 30m
        Collaborating projects present their latest developments in in the virtualisation and cloud area.
        Slides
        • Strategic Plan for a European Cloud Computing Infrastructure 20m
          Speaker: Dr Bob Jones (CERN)
          Paper
          Slides
        • IGE, Globus Toolkit appliances for the cloud 15m
          Speaker: Dr Ioan Lucian Muntean (UTC)
        • The EDGI cloud solution 15m
          Speaker: Jozsef Kovacs (MTA SZTAKI)
        • Mantychore 15m
          Speaker: Pau Minoves (i2CAT Foundation)
    • 11:00 12:30
      e-FISCAL project workshop 1h 30m Pasteur (300)

      Pasteur (300)

      Lyon Conference Centre

      Description:

      The goal of the e-FISCAL project is to analyse the costs of the current European dedicated HTC and HPC computing e-Infrastructures for research, compare them with equivalent commercial leased or on-demand offerings and provide an evaluation report. The cost of the national computing e-Infrastructures will be analysed in relation to its components that correspond to the recurring operating costs (Opex – Operating expenditures) that will include the operation of the hardware and the human support necessary to successfully exploit the hardware (system administrators, user support, training, application porting, managers, etc.) and the cost related to the investments in infrastructure (Capex – Capital Expenditures). Other methods will complement this approach. Information will be collected mainly through questionnaires and interviews triggered by the e-FISCAL project workshop.

      The e-FISCAL workshop aims to provide an introduction to the project and stimulate an initial discussion and feedback with regard to e-Fiscal draft questionnaire that will made available to the participants before the session. The session will start with a brief introduction from the Project director outlining the goals and the work-plan of the e-Fiscal project. The second presentation will review the state-of-the-art on costs and business models for e-Infrastructures. Finally, the third presentation will show a draft of the e-FISCAL questionnaire, followed by open discussion and feedback from the participants.

      The target audience is EGI/NGI representatives, PRACE and HPC centers representatives and related financial experts including industrial representatives and financial experts from Cloud computing; nevertheless, anyone with genuine interest in financial matters for e-Infrastructures is welcome to participate in the session.

      For the e-FISCAL representatives the workshop serves as an opportunity to directly engage with the community ensuring active participation from related stakeholders. For the participants – the workshop offers an opportunity to understand the scope of the project and the requirements needed to complete the e-Fiscal questionnaire in order to obtain quality data that will be used in further cost estimation and analysis. Participants will also have the chance to engage in a focused discussion in order to better evaluate the importance of the e-Fiscal project for improving the decision-making process in the expansion and changes in operations and technology application, evolution and sustainability planning of e-Infrastructures, introduction of business models and energy saving through green computing.

      Agenda:

      - Introduction to e-Fiscal Project (15')
      - Setting the Scene for e-Infrastructures Cost Analysis and Sustainability Plans (15')
      - Presenting the e-Fiscal Methodology and Draft Questionnaire (15')
      - Open discussion stimulated by the methodology and questionnaire supported by a panel (45')

      Speaker: Fotis Karayannis (AUEB-RC)
      Draft Questionnaire
      e-FISCAL project factsheet
      Invitation
      Minutes
      Poster
      Questionnaire_process_flow_chart
      Slides
    • 12:30 14:00
      Lunch break 1h 30m
    • 14:00 15:30
      CHAIN Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      The CHAIN project, in cooperation with EUIndiaGrid2, EUMEDGRID-Support and GISELA, organises a workshop that is a follow-up of the Workshops organised at ISGC 2011 in Taipei and at the EGI UF in Vilnius. The former was focused on interoperation and interoperability between EU and Asia, while the latter was mainly concentrated on the matching of the VRC requirements with the services offered by the eInfrastructure providers.
      This workshop proposes to make a step forward investigating the needs of VRC regarding interoperations and interoperability, possibly demonstrating the existing solutions developed until now and discussing the standards that are ready to be adopted.
      At the date of the EGI TF, CHAIN will have signed MoUs with some VRCs and can thus show the preliminary results of these collaborations.
      The interoperations among regional infrastructures both at the operational and organizational levels is one of the CHAIN's major goals.

      GISELA (www.gisela-grid.eu), which started on 1st September 2010, aims at
      • Ensuring the long-term sustainability of its e-Infrastructure in Latin American and the Caribbean by implementing the NGI / LGI sustainability model proposed by EELA-2 (www.eu-eela.eu), in association with CLARA and collaborating with EGI.
      • Providing full support to the EELA-2 User Communities whose research investigations are carried out at the institution level or in small collaborations, and to the larger VRCs spanning Latin America and Europe and using this Infrastructure.

      The workshop is expected to analyse the progress made since the Vilnius User Forum in the matching of User Communities’ requirements and Resource Providers’ plans. Hopefully it will help to pinpoint the remaining critical issues and the necessary technical developments, if any, that still need to be addressed in order to fulfil the requirements of the VRCs.
      EGI, CHAIN, GISELA, EUIndiaGRid2 and EUMEDGRID-Support will make use of the outcomes of the workshop to better solve the issues related to the involvement of Virtual Research Communities in the usage of Grid infrastructures.

      CHAIN Web: www.chain-project.eu
      GISELA Web: www.gisela-grid.eu
      EUMEDGRID-Support: www.eumedgrid.eu
      EUIndiaGrid2: www.euindiagrid.eu

      • 14:00
        Climate Change: WRF4G & CAM4G 15m
        Speaker: Valvanuz Fernandez Quiruelas (University of Cantabria, Spain)
        Slides
      • 14:15
        eInfrastructures for Agricultural Research (agINFRA) 15m
        Speaker: Miguel-Angel Sicilia (University of Alcala)
      • 14:30
        Applications in South Africa 15m
        Speaker: Bruce Becker (Meraka Institute)
        Slides
      • 14:45
        Short reports from WeNMR and HealthGrid 20m
        Speaker: Dr Marco Verlato (INFN)
        Slides
      • 15:05
        Results from CHAIN 15m
        Speaker: Ales Krenek (CESNET)
        Slides
      • 15:20
        Discussion 10m
    • 14:00 15:30
      EGI-InSPIRE St Clair 5 (15M)

      St Clair 5 (15M)

      Lyon Conference Centre

      • 14:00
        EGI-InSPIRE PMB (closed) 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 14:00 15:30
      Individual Presentations: Software Environments St Clair 3b

      St Clair 3b

      Lyon Conference Centre

      • 14:00
        GC3Pie: A Python framework for high-throughput computing 20m
        GC3Pie is a suite of Python classes (and command-line tools built upon them) to aid in submitting and controlling batch jobs to clusters and grid resources seamlessly. GC3Pie aims at providing the building blocks by which Python scripts that combine several applications in a dynamic workflow can be quickly developed. GC3Libs, the main component of the GC3Pie framework, provides services for submitting computational jobs to Grids and batch systems and controlling their execution, persisting job information, and retrieving the final output. GC3Libs takes an application-oriented approach to batch computing. A generic Application class provides the basic operations for controlling remote computations, but different Application subclasses can expose adapted interfaces, focusing on the most relevant aspects of the application being represented. GC3Libs can run applications in parallel, or sequentially, or any combination of the two, and do arbitrary processing of data in the middle. It provides a programing model to dynamically create workflow-like execution logic.
        Speaker: Sergio Maffioletti (UZH/GC3)
        Slides
      • 14:20
        Managing deployment and activation of Web Applications in a distributed e-Infrastructure 20m
        The gCube framework is a flexible tool for managing e-Infrastructures. Its enabling technology, i.e. the lower layer gluing together the e-Infrastructure resources, has been recently extended to feature the management of Web Applications. This work was stimulated by a use case expressed by the FAO community calling for the design and implementation of a solution to inject Web Applications (by means of WAR archives) into the existing gCube-enabled infrastructure, namely D4Science. Initially designed to remotely instantiate/remove Web Services and Java Libraries on a single and specific remote hosting environment, the gCore container, the gCube deployment technology has been largely empowered to manage virtual platforms. The virtual platform is an extendible model for transparently interfacing a potentially unlimited number of hosting environments. The resulting gCube enabling technology is capable of dynamically instantiating platforms (along with their resources) compliant to such a model. When new software designed to run on a specific platform is detected, a virtual image of the target platform is created, then the software is moved to the remote server and deployed and activated there. Following their activation, newly running units (what they really are depends on the concrete hosting environment) and their entry points are published in the gCube Information system. In such a way, they are discoverable both by humans and interested clients. Importantly, from being part of the gCube Deployment Model, Web Applications can be uploaded once and deployed many times, shared across multiple Virtual Organizations and Virtual Research Environments. The first implementation of virtual platform targets the Apache Tomcat container by building on top of its Client Deployer library and interfacing the Tomcat Manager service.
        Speaker: Mr Andrea Manzi (CERN)
        Slides
      • 14:40
        User Defined Runtime Environments in UNICORE 20m
        Users of computational resources come with a multitude of different application scenarios. It is difficult if not impossible to cater for all user requirements of a computing center at the same time and in a timely manner. Therefore, it would be beneficial if the user could provide the runtime environment and thus pose less complex requirements for the computing center. The computing center can then focus on the provision and maintenance of physical machines and the virtualization infrastructure. The central concept behind user defined execution environments is the availability of software in a well-defined environment. Particular versions of libraries, file system layout etc. are such that the application in question can directly execute without further configuration. Thus, not all software that users may want to run needs to be available in and maintained by computing centres. Software maintenance and updates are done in the virtual machine images, e. g. at the virtual organization~(VO) or research community level. In order to take much of the burden of deploying virtual machines from the user, current developments in UNICORE are targeting a seamless integration of this scenario. In the simplest case, users would select virtual machine images from image repositories and deploy them in a virtualized environment. In doing so, they would still be following the original UNICORE pattern, but providing additional information about the desired environment. The actual job submission already known from current UNICORE will remain the same. At a higher level, the selection of the concrete execution environment could even be automatically done by a service, such that the user would only have to send a request for the execution of a particular application with given input data. Our presentation will give a status report and outlook of the ongoing developments. Furthermore, we will discuss the applicability of the UNICORE model to the above scenario.
        Speaker: Bjoern Hagemeier (JUELICH)
        Slides
      • 15:00
        apppot - Generic application deployment on a computational Grid 20m
        AppPot is a way to implement generic application deployment on a computational Grid, and especially to enable users to provide their own software to the computing cluster. AppPot uses User Mode Linux to provide users with a development and running environment they have full control over. User Mode Linux provides a virtualized environment in which users can build and run their own computational applications. AppPot augments this with scripts that can take a copy of the UserModeLinux system image and submit it as a regular computational job using the ARC middleware. Apppot is already used in production within the Swiss National Grid Infrastructure (SMSCG) to support applications from several scientific domains like meteorology and computational chemistry.
        Speaker: Riccardo Murri (UZH/GC3)
        Slides
    • 14:00 15:30
      New Security Policies for EGI Rhone 4

      Rhone 4

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      This session will present the new and/or revised security policies that the EGI Security Policy Group has been working on during the last 12 months. This is aimed at an audience of operations staff, CSIRTs, NGIs, VO managers, other Infrastructures and indeed anyone interested in learning about the new work in the area of security policy. Feedback and comments will be very welcome.

      Convener: David Kelsey (STFC)
      • 14:00
        Overview of EGI SPG and work plans for 2011 20m
        Speaker: David Kelsey (STFC)
        Slides
      • 14:20
        Draft Service Operations Security Policy 20m
        Speaker: David Groep (FOM)
        Document
        Slides
      • 14:40
        Draft Security Policy for the Endorsement and Operation of Virtual Machine Images 20m
        Speaker: David Kelsey (STFC)
        Document
        Slides
      • 15:00
        Future Security Policy work and collaboration with other infrastructures 15m
        Speaker: David Kelsey (STFC)
        Slides
      • 15:15
        Discussion 15m
    • 14:00 15:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 14:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 14:00
        PGI: BES/JSDL/GLUE Discussions 1h 30m St Clair 1

        St Clair 1

        Lyon Conference Centre

    • 14:00 15:30
      Resource Centre Forum Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The Resource Centres are at the heart of the EGI High Throughput Computing infrastructure: they contribute resources, requirements and expertise, and have the potential to extend the EGI service offer and the current user base by supporting a wider group of disciplines and user communities who need high capacity for their data-intensive computing needs. The extension of the current user base is essential for the consolidation and long-term sustainability of EGI, of the NGIs and the Centres themselves.

      The Resource Centre Forum is an opportunity to contribute to the evolution of the EGI Ecosystem, and to share expertise and plans with other computing centres. The Resource Centre Forum will address the following areas:

      • support of diverse user communities, and plans to extend to new communities and projects;
      • the technical challenges faced to support multiple disciplines in various areas (operations, deployed middleware, existing capabilities and services, etc.);
      • requirements of better Reliability, Availability, Serviceability, and Usability of the Grid middleware to support multiple disciplines within the constraints of the existing manpower;
      • new services, long-term sustainability, business models and cloud computing;
      • interest in a coordinated action of large Resource Centres at the European level.

      Resource Centre and NGI representatives are invited to participate.

      Proposal
      • 14:00
        Role and Challenges of the Resource Centre in the EGI Ecosystem 15m
        Speaker: Dr Tiziana Ferrari (EGI.EU)
        Slides
      • 14:15
        KIT: experience and plans 15m
        Speaker: Andreas Heiss (KIT)
        Slides
      • 14:30
        PIC: experience and plans 15m
        Speaker: Gonzalo Merino (Port d'Informació Científica)
        Slides
      • 14:45
        INFN-CNAF: experience and plans 15m
        Speaker: Mauro Morandin (INFN)
        Slides
      • 15:00
        NDGF:experience and plans 15m
        Speaker: Oxana Smirnova (NDGF)
        Slides
      • 15:15
        SARA/NIKHEF: experience and plans 15m
        Speaker: Ron Trompert (SARA)
        Slides
    • 14:00 15:30
      SIENA Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      About SIENA
      SIENA, the Standards and Interoperability for eInfrastructure Implementation Initiative (2010-2012), is focused on delivering a Roadmap creating a common vision for the future evolution of European Research and an integrated standards-based, interoperable European e-Infrastructure. This builds upon the knowledge, assets, best practices, policies and capabilities of the six European Distributed Computing Infrastructures (DCI) to provide value to all stakeholders in Research, Government and Industry.

      The main goal of the workshop is to focus on DCI assets for the purpose of serving the eScience community and identifying standards required to make these assets interoperable. The workshop features a presentation from Carl Christian Buhr, Member of the Cabinet of Neelie Kroes European Commission Vice-President for the Digital Agenda, as well as insights into the various assets that the EC-funded DCI and ESFRI projects can offer in the areas of eScience, Industry and eGovernment. Effective dialogue between stakeholder participants will be ensured through an Open Discussion on technical challenges, eGovernment, industry uptake, and call to action.

      • 14:00
        SIENA 1h 30m
    • 14:00 15:30
      Towards an effective e-Infrastructures impact assessment St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 14:00
        Towards an effective e-Infrastructures impact assessment 1h 30m
        Impact assessment is the hot-topic in these months among every research initiative. Several support actions or studies, including the ERINA+, eNventory and – recently - RI-Impact, are working toward the development of an effective process allowing a sound assessment exercise and, at the same time, able to be easily adopted by projects partners as part of their day-by-day activities. One of the challenges related to impact assessment is how to link the performance of a single project to that of the related e-Infrastructure initiatives as a whole. How is the e-Infrastructures domain supporting the fulfilment of the knowledge society? What are the benefits of e-Infrastructures for researchers worldwide? How to evaluate the economic and social sustainability of e-Infrastructures projects? Answering these questions is the goal of the ERINA+ work during the next months and the initial results will be discussed publicly in the session proposed. As a virtual continuation of the session held during the Vilnius EGI User Forum in April 2011, this session is a step forward through which the ERINA+ team will show the improvements of the proposed impact assessment approach, its methodology, and the overall process. During the session the ERINA+ team will present the preliminary results of the domain mapping (e-Infrastructures vs projects), an analysis of e-Infrastructures specificities and the self-assessment methodology for e-Infrastructures projects which will be performed through the adoption of a web tool. The initial design of such web tool and the expected interaction model will be presented together with its main features. The session will be organised in two different moments: during the first one the ERINA+ project partners will give presentations on the topics described above, the second part will be dedicated to the gathering of the e-Infrastructures projects expectations towards the self-assessment web tool. This second session will be conducted using moderation techniques.
        Speakers: Mr Andrea Manieri (Engineering), Dr Fabiana Monacciani (Eurokleis), Dr antonella Passani (T6 ecosystems)
    • 14:00 15:30
      Virtual Research Communities Pasteur 300

      Pasteur 300

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Within EGI the model for scalable user support is the Virtual Research Community (VRC). This model serves both large and small communities by offering structured research communities a sustainable mechanism with which to interact with EGI. VRCs are groups of researchers, possibly widely dispersed, working together effectively through the use of information and communications technology (ICT). With the help of EGI the VRC researchers can collaborate, communicate, share resources, access remote computers or equipment and produce results as effectively as if they, and the resources they require, were physically co-located. EGI through its partners provides a set of services for VRCs, which includes the following:

      • Computing, data storage and other types of resource made available by EGI stakeholders through open source middleware software solutions.
      • A requirement gathering process and tracking system run by the User Community Support Team of EGI.eu to capture, detail and investigate communities’ requirements and to provide solutions directly or through third parties.
      • Assistance and training to become routine user of the infrastructure, to adapt of VRC-specific applications and data to EGI technologies.

      While VRCs benefit from these existing services they also develop and operate services that would be in the interest of other VRCs.

      The 2 x 90 minutes long session provides opportunity for VRCs and user communities to present their experiences and plans of being part of the EGI community and about the services they (will) use and offer within the European Grid Infrastructure.

      The representatives of the EGI User Community Support activity will introduce the services provided by EGI for VRCs, including the Application Database, the Training Marketplace and the Services for Virtual Organisations.

      Convener: Gergely Sipos (EGI.EU)
      • 14:00
        Services for EGI VRCs 20m
        Speaker: Stephen Brewer (EGI.EU)
      • 14:20
        WeNMR: the tale of Virtual Research Community in NMR and structural biology 15m
        WeNMR (www.wenmr.eu) has established itself as a lively and growing Virtual Research Community in the life sciences and structural biology area, with a focus on NMR. It currently represents the largest Virtual Research Organization (VO) in the life science area and was the first VRC officially recognized by the EGI. Its user community involves researchers from around the world and is covering more than 30 countries, including South Africa and Latin and North America and Asia Pacific. In my presentation I will highlight what WeNMR offers to its users and how it has grown into a successful VRC over the last few years and describe its relationship with EGI and other related projects.
        Speaker: Alexandre Bonvin (eNMR/WeNMR (via Dutch NGI))
      • 14:35
        The Life-Science Grid Community VRC in EGI 10m
        The Life-Science Grid Community is an open Virtual Research Community federating Virtual Organizations (VOs) related to the Life-Science field. It gathers five VOs representing around 500 users world-wide. Its main missions are to represent the Life-Science grid users, coordinate technical and non-technical actions, provide technical services, organize community-specific training events and help transferring knowledge among the VOs. The Life-Science Grid Community initiative started in June 2010 and signed a memorandum of understanding with EGI in June 2011. This presentation will summarize the achievements of the last year and highlight our current actions and challenges.
        Speaker: Tristan Glatard (CNRS)
        Slides
      • 14:45
        Technical Support Teams in the Life-Science Grid Community 10m
        Speaker: Franck MICHEL (CNRS)
        Slides
      • 14:55
        Towards a Molecular Science VRC 15m
        "To progress towards a Virtual Research Community (VRC) of Molecular Science (MS) we are designing a roadmap for gathering together the members of the COMPCHEM, GAUSSIAN and MoSGrid Virtual Organizations (VO)s as well as other individuals and user clusters. The users involved mainly belong to the following MS areas: electronic structure, dynamics and statistics, Materials by in silico design and structure-property relationships, Molecular virtual reality and ab initio Simulations, Learning object repositories, training and dissemination. To this end emphasis is being given to the grid porting of popular packages, to the development of tools and frameworks facilitating the use of the grid, to the design and the implementation of gateways and workflows with the intention of fostering the forming of a cooperative environment for MS scientists. For the same purpose de facto standards for electronic structure and quantum dynamics are being adopted and improved. This has the twofold motivation of pushing to much higher level the complexity of the accurate and realistic multiscale applications affordable by the members of the community and of fostering a Service oriented approach and economy in MS research and innovation. Typical applications belonging to this endeavour are the modelling of renewable energy technologies, the atmospheric secondary pollutants production, the labelling of new families of chemicals and to the assemblage of MS virtual campus learning objects. A difficulty in assembling the mentioned VRC is the inadequate structuring of the MS community. To better find a viable solution to this problem we are trying: - designing and developing new tools for evaluating the quality of the work done by the members of the partner organizations - basing on the mentioned tools a grid economy rewarding proactive behaviours in the members of the partner organizations - establishing connections with user clusters developing an maintaining innovative MS packages, databases of chemical relevance and educational & training services - fostering the adoption of middleware solution combining high performance with high throughput computing "
        Speaker: Alessandro Constantini
        Slides
      • 15:10
        Activities of the EGI Fusion Community 20m
        "Fusion community usage of grid resources has grown in the last years. This usage has been reinforced by the use of different tools allowing the use of different infrastructures and the creation and management of complex workflows. These tools hide the complexity of the platforms being used and ensure the results of the different tasks submitted are retrieved in a transparent manner. Several articles and conference papers have been published in recent years showing how these tools and the grid can be helpful not only for the Fusion community, but for any other VRC. In this presentation we want to show how using Kepler we can run complex use cases able to submit jobs to the grid and HPC resources, also including the visualization of the final results. Several use cases are shown, including single grid job - single hpc job; parametric grid - single grid; parametric grid - parametric HPC."
        Speaker: Antonio Gomez
        Slides
    • 14:00 15:30
      e-FISCAL project (closed meeting) 1h 30m Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      This is an internal meeting for the e-Fiscal project.
      Speaker: Fotis Karagiannis (AUEB-RC)
    • 15:30 16:00
      Coffee break 30m
    • 16:00 17:30
      CHAIN Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      The CHAIN project, in cooperation with EUIndiaGrid2, EUMEDGRID-Support and GISELA, organises a workshop that is a follow-up of the Workshops organised at ISGC 2011 in Taipei and at the EGI UF in Vilnius. The former was focused on interoperation and interoperability between EU and Asia, while the latter was mainly concentrated on the matching of the VRC requirements with the services offered by the eInfrastructure providers.
      This workshop proposes to make a step forward investigating the needs of VRC regarding interoperations and interoperability, possibly demonstrating the existing solutions developed until now and discussing the standards that are ready to be adopted.
      At the date of the EGI TF, CHAIN will have signed MoUs with some VRCs and can thus show the preliminary results of these collaborations.
      The interoperations among regional infrastructures both at the operational and organizational levels is one of the CHAIN's major goals.

      GISELA (www.gisela-grid.eu), which started on 1st September 2010, aims at
      • Ensuring the long-term sustainability of its e-Infrastructure in Latin American and the Caribbean by implementing the NGI / LGI sustainability model proposed by EELA-2 (www.eu-eela.eu), in association with CLARA and collaborating with EGI.
      • Providing full support to the EELA-2 User Communities whose research investigations are carried out at the institution level or in small collaborations, and to the larger VRCs spanning Latin America and Europe and using this Infrastructure.

      The workshop is expected to analyse the progress made since the Vilnius User Forum in the matching of User Communities’ requirements and Resource Providers’ plans. Hopefully it will help to pinpoint the remaining critical issues and the necessary technical developments, if any, that still need to be addressed in order to fulfil the requirements of the VRCs.
      EGI, CHAIN, GISELA, EUIndiaGRid2 and EUMEDGRID-Support will make use of the outcomes of the workshop to better solve the issues related to the involvement of Virtual Research Communities in the usage of Grid infrastructures.

      CHAIN Web: www.chain-project.eu
      GISELA Web: www.gisela-grid.eu
      EUMEDGRID-Support: www.eumedgrid.eu
      EUIndiaGrid2: www.euindiagrid.eu

      • 16:00
        GISELA 15m
        Speaker: Philippe Gavillet (CIEMAT)
      • 16:15
        EUIndiaGrid2 15m
        Speaker: Alberto Masoni (EU-IndiaGrid2)
      • 16:30
        EMI 15m
        Speaker: Alberto Di Meglio (EMI)
        Slides
      • 16:45
        Interoperabilty and Standards 15m
        Speaker: Giuseppe Andronico (INFN)
      • 17:00
        Discussion and Conclusions 30m
    • 16:00 17:30
      EGI Software Vulnerability Group 1h 30m Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      The purpose of the EGI Software Vulnerability Group (SVG) is to eliminate existing software vulnerabilities from the EGI infrastructure and prevent the introduction of new ones. Thus reducing the likelihood of Security Incidents. This session will inform attendees of the activities of the SVG, and plans for the future. This will include a summary of the Vulnerability issue handling process, how the group interacts with various parties including software providers, and what has been learnt over the last year. It will also include a summary of the vulnerability assessement activities which have taken place and plans for the coming year. Plans for how to take the activity forward in the future will be presented and discussed.
      Speakers: Prof. Elisa Heymann (Universitat Autònoma de Barcelona), Dr Linda Cornwall (STFC)
      Slides
      • The Software Vulnerability Issue handling process 30m
        This summarizes the software vulnerability issue handling process in EGI. It includes how the SVG interacts with the various parties, and what has changed over the last year.
      • Vulnerability Assessment 30m
    • 16:00 17:30
      EGI Task Force: Repositories and Automation 1h 30m Rhone 5 (12M)

      Rhone 5 (12M)

      Lyon Conference Centre

      Review of Provisioning UMD 1.0, and UMD 1.1. Review of current software provisioning processes. Intended outcome: List of actions assigned to EGI, and all Technology Providers that are engaged with EGI with an SLA.
      Speakers: Kostas Koumantaros (GRNET), Michel Drescher (EGI.EU)
      Minutes
      • Review the Provisioning process for UMD 1.0, UMD 1.1 and UMD 1.2 15m
        Speaker: Kostas Koumantaros (GRNET)
        Slides
      • Next steps & Feedback from EMI 15m
      • Next steps& Feedback from IGE 15m
      • Next steps & Feedback from SAGA 15m
      • Discussion 30m
    • 16:00 17:30
      EGI-InSPIRE St Clair 5 (15M)

      St Clair 5 (15M)

      Lyon Conference Centre

      • 16:00
        EGI-InSPIRE PMB (closed) 1h 30m St Clair 5

        St Clair 5

        Lyon Conference Centre

    • 16:00 17:30
      OGF St Clairs

      St Clairs

      Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 3a

        St Clair 3a

        Lyon Conference Centre

      • 16:00
        OGF 1h 30m St Clair 2

        St Clair 2

        Lyon Conference Centre

      • 16:00
        PGI: BES/JSDL/GLUE Discussions 1h 30m St Clair1

        St Clair1

        Lyon Conference Centre

    • 16:00 17:30
      Resource Centre Forum Rhone 1

      Rhone 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The Resource Centres are at the heart of the EGI High Throughput Computing infrastructure: they contribute resources, requirements and expertise, and have the potential to extend the EGI service offer and the current user base by supporting a wider group of disciplines and user communities who need high capacity for their data-intensive computing needs. The extension of the current user base is essential for the consolidation and long-term sustainability of EGI, of the NGIs and the Centres themselves.

      The Resource Centre Forum is an opportunity to contribute to the evolution of the EGI Ecosystem, and to share expertise and plans with other computing centres. The Resource Centre Forum will address the following areas:

      • support of diverse user communities, and plans to extend to new communities and projects;
      • the technical challenges faced to support multiple disciplines in various areas (operations, deployed middleware, existing capabilities and services, etc.);
      • requirements of better Reliability, Availability, Serviceability, and Usability of the Grid middleware to support multiple disciplines within the constraints of the existing manpower;
      • new services, long-term sustainability, business models and cloud computing;
      • interest in a coordinated action of large Resource Centres at the European level.

      Resource Centre and NGI representatives are invited to participate.

      Proposal
      • 16:15
        CYFRONET: experience and plans 15m
        Speaker: Mr T. Szepieniec (CYFRONET)
        Slides
      • 16:30
        RAL: experience and plans 15m
        Speaker: Prof David Britton (UG)
        Slides
      • 16:45
        UMD distribution: feedback from sites 15m
        Speaker: Mario David (LIP Lisbon)
        Slides
      • 17:00
        Discussion 30m
    • 16:00 17:30
      SIENA Rhone 3 (175)

      Rhone 3 (175)

      Lyon Conference Centre

      About SIENA
      SIENA, the Standards and Interoperability for eInfrastructure Implementation Initiative (2010-2012), is focused on delivering a Roadmap creating a common vision for the future evolution of European Research and an integrated standards-based, interoperable European e-Infrastructure. This builds upon the knowledge, assets, best practices, policies and capabilities of the six European Distributed Computing Infrastructures (DCI) to provide value to all stakeholders in Research, Government and Industry.

      The main goal of the workshop is to focus on DCI assets for the purpose of serving the eScience community and identifying standards required to make these assets interoperable. The workshop features a presentation from Carl Christian Buhr, Member of the Cabinet of Neelie Kroes European Commission Vice-President for the Digital Agenda, as well as insights into the various assets that the EC-funded DCI and ESFRI projects can offer in the areas of eScience, Industry and eGovernment. Effective dialogue between stakeholder participants will be ensured through an Open Discussion on technical challenges, eGovernment, industry uptake, and call to action.

      • 16:00
        SIENA 1h 30m
    • 16:00 17:30
      Towards an effective e-Infrastructures impact assessment St Clair 4

      St Clair 4

      Lyon Conference Centre

      • 16:00
        Towards an effective e-Infrastructures impact assessment 1h 30m
    • 16:00 17:30
      Virtual Research Communities Pasteur 300

      Pasteur 300

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Within EGI the model for scalable user support is the Virtual Research Community (VRC). This model serves both large and small communities by offering structured research communities a sustainable mechanism with which to interact with EGI. VRCs are groups of researchers, possibly widely dispersed, working together effectively through the use of information and communications technology (ICT). With the help of EGI the VRC researchers can collaborate, communicate, share resources, access remote computers or equipment and produce results as effectively as if they, and the resources they require, were physically co-located. EGI through its partners provides a set of services for VRCs, which includes the following:

      • Computing, data storage and other types of resource made available by EGI stakeholders through open source middleware software solutions.
      • A requirement gathering process and tracking system run by the User Community Support Team of EGI.eu to capture, detail and investigate communities’ requirements and to provide solutions directly or through third parties.
      • Assistance and training to become routine user of the infrastructure, to adapt of VRC-specific applications and data to EGI technologies.

      While VRCs benefit from these existing services they also develop and operate services that would be in the interest of other VRCs.

      The 2 x 90 minutes long session provides opportunity for VRCs and user communities to present their experiences and plans of being part of the EGI community and about the services they (will) use and offer within the European Grid Infrastructure.

      The representatives of the EGI User Community Support activity will introduce the services provided by EGI for VRCs, including the Application Database, the Training Marketplace and the Services for Virtual Organisations.

      Convener: Gergely Sipos (EGI.EU)
      • 16:00
        Earth Science HUC and the ES GRID Community 15m
        The ES Grid Community (ES VRC) will present an overview about the current activities and future plans. The Earth Science Grid community is following its strategy of propagating Grid technology to the ES disciplines, setting up collaboration among the members of the community and stimulating the interest of stakeholders on the political level since ten years already. This strategy is based on a roadmap published by the community in the Earth Science Informatics journal 3/2010. It was based on different European Grid projects and led to a Grid Earth Science VRC that covers a variety of ES disciplines; all of them in the end facing the same kind of ICT problems. National funding plays an essential role for dissemination activities through presentations and publishing papers. The major event for the VRC is the European Geosciences Union general assembly that gathers around 10 000 participants, mostly European. The community has been organizing a grid session at the EGU for the last 4 years. The penetration of Grid in the ES community is indicated by the variety of applications, the number of countries in which ES applications are ported, the number of papers in international journals and the number of related PhDs. Users of among six virtual organisations (VO) belong to ES Grid VRC. The ES HUC is operating a catch-all VO (ESR) to also attract ES researchers that are not organized in groups yet. The lack of networking and development funding has decreased the global impact of this community as the expertise is geographically dispersed. Due to the present technological evolution in the ES community, this funding situation implies a large risk on the sustainability of the ES VRC as a whole, even if new applications have been deployed. Common activities are requests like a COST Action that aims to establish cross-disciplinary, holistic Earth System Science by enabling ES stakeholders, scientists and their applications to better exploit the multitude of resources provided by current DCIs (Grid, Cloud and HPC/GPU). Partners of the ES Grid community are active in different European projects. The services for the ES task in EGI-Inspire concerns the data that are a key part of any ES application. The ES community requires several interfaces to access data and metadata outside of the EGI infrastructure, e.g. by using grid-enabled database interfaces. The data centres have also developed service tools for basic research activities such as searching, browsing and downloading these datasets, but these are not accessible from applications executed on the Grid. The ES HUC task in EGI-Inspire aims to enable these tools to be accessed from the Grid. In collaboration with GENESI-DR (Ground European Network for Earth Science Interoperations - Digital Repositories) this task is maintaining and evolving an interface in response to new requirements that will allow data in the GENESI-DR infrastructure to be comfortably used in EGI applications. A new activity of the ES HUC together with the international climate community for IPCC is to couple the data oriented Earth System Grid (ESG) with computing resources of the EGI infrastructure. The first technical difficulty to solve is the different security mechanism.
        Speaker: Andre Gemünd (SCAI)
        Slides
      • 16:15
        Astronomy & Astrophysics community: Status, Activities, and Evolution 15m
        Speaker: Claudio Vuerli (INAF)
        Slides
      • 16:30
        Towards an Auger VRC 15m
        The Pierre Auger Observatory studies the highest energy cosmic air showers. International collaboration of about 500 people from 111 institutes from 18 countries operates large detector systems to detect rare events of ultra high energy cosmic ray showers. Monte Carlo simulations of showers require large computing and storage capacity. The EGI Grid is the way to access several computing centers using the same interface. We describe the organization of shower production on the EGI Grid. We will mention the current main issues with the massive production. We will also show the organization of the VO, problems with frequent updates of the middleware and how users manage to access resources.
        Speaker: Jiri Chudoba (CESNET)
      • 16:45
        The Digital Cultural Heritage community 15m
        The amount of digited content from the cultural heritage sector is growing very rapidly, due to the establishment of national and regional digitisation programmes. The generation of digital cultural heritage is accelerated also by the impulse given by Europeana, the flagship initiative of the European Commission referenced in the Digital Agenda. The resulting data need high quality infromation technology management, access facilities, interoperation with non-cultural heritage and research in general and, above all, preservation of data. The e-infrastructures can play a very important role in this scenario of growth.
        Speaker: Antonella Fresa
        Slides
      • 17:00
        Discussion 30m
    • 18:30 19:30
      Travel to the dinner venue 1h
    • 19:30 23:00
      GALA DINNER 3h 30m
    • 09:00 10:30
      Plenary Pasteur (300) (Universe)

      Pasteur (300)

      Universe

      • 09:00
        The XSEDE Architecture – The Importance of Interoperability and the Role of Standards 45m Pasteur (300)

        Pasteur (300)

        Universe

        XSEDE introduces a new approach—one that combines an emphasis on standards as well as quality attributes such as ease-of-use, reliability, extensibility, and interoperability—to satisfying user needs. Standards, a key feature of the architecture, reduce risk, exploit a diversity of software source, and extend the set of accessible resources to include other national infrastructures. This talk presents a high-level view of the XSEDE architecture and its realization. We begin with a discussion of the goals and design principles that drove the XSEDE architecture design process with a particular focus on addressing the question, “why standards?”. Next, we examine the architecture in more detail through the lens of the capabilities delivered to users and the standards used to deliver them. We then discuss possibilities for standards-based interoperation with European infrastructures, as well as some known gaps in the standards space that need to be filled. We conclude with a discussion of the deployment plan and status.
        Speaker: Andrew Grimshaw (Professor of Computer Science, University of Virginia)
        Slides
      • 09:45
        Life Sciences computing needs and the GRID 45m Pasteur (Lyon Conference Centre)

        Pasteur

        Lyon Conference Centre

        The technology of Next Generation Sequencing represents a new dimension for research in the Life Sciences field. The new technologies allow the sequencing of genomes and transcriptomes faster and at a much lower budget than in previous genome sequencing projects. In Europe more than 70 institutions host more than 200 of those NGS systems with a capacity to sequence about one Tera bp per day, that is the equivalent of more than 330 human genomes. This number will be increased dramatically during the next few years on one side by the increasing number of NGS systems but also by the fast developing NGS technology providing increasing sequence capacity and sequence length. The vast amount of sequence data arriving daily at the computation centers creates challenges in the informatics and bioinformatics field. In my talk I will try to describe the computational needs of the Life Science community and discuss how the use of GRID infrastructures could help in this process.
        Speaker: Erik Boncam-Rudloff (Chairman of the European COST Action: SeqAhead, Next Generation Sequencing Data Analysis Network)
        Slides
    • 10:30 11:00
      Coffee break 30m
    • 10:30 13:00
      eConcertation Meeting (By Invitation Only) Rhone 3

      Rhone 3

      Lyon Conference Centre

      • 10:30
        Riding the wave: One year later 10m
        Speakers: Dr Carlos Morais Pires (European Commission), Dr Krystyna Marek (European Commission)
        Slides
      • 10:40
        The global scene 20m
        Speaker: Dr Wouter Los (LIFEWATCH)
        Slides
      • 11:00
        Digital object identifiers: Presentation of the study 20m
        Speaker: Dr Paolo Bouquet
        Slides
      • 11:20
        Panel: Towards a data access interoperability task force 1h 20m
        Speaker: Dr Herbert Van de Sompel
    • 11:00 12:30
      Accounting Tutorial Rhone 1 (Universe)

      Rhone 1

      Universe

      Everyone welcome but probably only of use to those who already have their own accounting systems which publish data to APEL or who plan to soon.

      Minutes
      • 11:00
        Introduction 10m
        Speaker: Dr John Gordon (STFC)
        Minutes
      • 11:10
        The APEL Architecture 15m
        Speaker: Ms Alison Packer (STFC)
        Slides
      • 11:25
        Messaging 15m
        Speaker: William Rogers
        Slides
      • 11:40
        Experiences 40m
        • Gratia 10m
          Slides
        • DGAS 10m
          Slides
        • SGAS 10m
        • Others 10m
      • 12:20
        Discussion 10m
    • 11:00 12:30
      EGI-InSPIRE St Clair 2 (Universe)

      St Clair 2

      Universe

      • 11:00
        EGI InSPIRE Collaboration Board (closed) 1h 30m
    • 11:00 12:30
      EMI: User Tutorial St Clair 4

      St Clair 4

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The European Middleware Initiative (EMI)
      aims to deliver a consolidated set of middleware components
      for deployment in Distributed Computing Infrastructures, extending the
      interoperability between grids and other computing
      infrastructures, strengthening the reliability of the services, and
      establish a sustainable model to maintain and
      evolve the middleware, fulfilling the requirements of user
      communities.

      EMI middleware is not build from ground up, but rather,
      delivers a consolidated and streamlined set of services and
      components from existing middleware projects ARC, gLite, UNICORE and dCache by
      re-factoring existing components, defining and implementing standards
      and phasing out duplicate or obsolete
      components from the original middleware stacks. The middleware
      components are divided in four areas (Compute, Data, Security,
      Infrastructure). This tutorial will introduce usage of most commonly used clients
      for job and data management.

      This user oriented tutorial is based on the first release of the EMI middleware, EMI-1 "Kebnekaise".
      It will provide an overview of EMI clients
      for Computing and Data Services, giving concrete examples and highlighting best practices
      and most common mistakes.

      Convener: Kathryn Cassidy (TCD)
      slides
    • 11:00 12:30
      Grid2011: Distributed Production Cyberinfrastructure and Middleware: I Pasteur (Universe)

      Pasteur

      Universe

      • 11:00
        A WS-Agreement-based QoS Auditor Negotiation Mechanism for Grids 30m
        Speakers: Alba Cristina Magalhães de Melo, Alisson Andrade
      • 11:30
        Mediation of Service Overhead in Service-Oriented Grid Architectures 30m
        Speakers: E. Elmroth, P.-O. Östberg
      • 12:00
        Mutual job submission architecture that considered workload balance among computing resources in the grid interoperation 30m
        Speakers: Kazushige Saga, Kenichi Miura, Kento Aida
    • 11:00 12:30
      NGI User Support Teams Rhone 2 (Universe)

      Rhone 2

      Universe

      The stated goal of EGI is to provide significant added value for existing and new user communities. The main providers of User Support service in EGI are National Grid Initiatives (NGIs), under the coordination of the User Community Support Team (UCST) of EGI.eu in Amsterdam. While NGI teams primarily serve national users, using the communication and coordination services by UCST the needs of multi-national, structured scientific user communities can be also addressed by NGIs.

      The session presents the structure and achievements of NGI user support activities, through a sample of presentations by NGIs with active user support teams. The presentations will provide information about various reusable human and software services and best practices that NGIs develop and use, for training, application access, application porting, portal development, documentation, VO setup and testing.

      • 11:00
        User Support in EGI - reactive and proactive services 12m
        Speaker: Gergely Sipos (EGI.EU)
        Slides
      • 11:12
        User support activites in Slovenia 13m
        "Beginning Knowledge of grid technologies in Slovenia was very poor when NGI Slovenia was established. Our first task was identifying new and existent grid users. At the beginning we were more involved in dissemination activities, we presented grid technologies and the role of NGI/EGI to the public, prepared some presentations, articles and meetings. It turned out that grid technology was needed in the following disciplines: physics, bioinformatics, civil engineering, meteorology, medicine and mechanical engineering. Current state Extensive documentation for end users and site administrators is done and available on our wiki pages and NGI website, a national VO is available, we offer individual trainings and consulting, technical support is available to our users by phone, instant messaging and email. We are supporting both ARC and gLite middleware on both clusters. Most common user problems: sometimes lack of computer knowledge, unsupported operating systems (Linux Redhat x64 and derivates required for gLite), jobs that last too long (proxy expiration) etc. Plans Arc school for end users at the end of the year, more dissemination activities (articles in newspapers, brochures, meetings etc), joining new clusters (at least 2 new clusters are expected to join the NGI), new HPC cluster at Arnes. There is still room for improvement: ticketing system, FAQ, trainings for end users and site administrators. Major problem is still not knowing the technology very well and difficulty of usage (if user is new to grid). "
        Speaker: Barbara Krasovec (ARNES)
        Slides
      • 11:25
        GC3Pie: A Python framework for high-throughput computing and Grid proxies 13m
        "GC3Pie is a suite of Python classes (and command-line tools built upon them) to aid in submitting and controlling batch jobs to clusters and grid resources seamlessly. GC3Pie aims at providing the building blocks by which Python scripts that combine several applications in a dynamic workflow can be quickly developed. GC3Libs, the main component of the GC3Pie framework, provides services for submitting computational jobs to Grids and batch systems and controlling their execution, persisting job information, and retrieving the final output. GC3Libs takes an application-oriented approach to batch computing. A generic Application class provides the basic operations for controlling remote computations, but different Application subclasses can expose adapted interfaces, focusing on the most relevant aspects of the application being represented. GC3Libs can run applications in parallel, or sequentially, or any combination of the two, and do arbitrary processing of data in the middle. It provides a programing model to dynamically create workflow-like execution logic."
        Speaker: sergio maffioletti (UZH)
        Slides
      • 11:38
        Grid User Support activities in Hungary 13m
        The three institutes (BME, KFKI RMKI, SZTAKI), that are involved in Hungarian Grid User Support activities have put great effort in serving the Hungarian user community, especially through Hungrid, the Hungarian catch-all Virtual Organisation of EGI. An inverted process is present in Hungary, we do not have many VOs, we have mostly individual users, who feel the need of a more powerful infrastructure e.g. grid, but do not know how to get involved or they cannot join a field-specific VO. Thus Hungrid has twofold goal: serve as a catch-all VO for individual users, and to provide a sandbox (testing environment for prospective Hungarian VOs). In Hungary (NGI-HU) grid operation procedures and user support procedures are working under the umbrella of Hungrid VO.
        Speaker: Agnes Szeberenyi (MTA SZTAKI)
        Slides
      • 11:51
        User support in IGI: related tools and services in Italy 13m
        This presentation provides an overview of recent developments relevant to user support tools and services in Italy.
        Speaker: Giuseppe Giuseppe (INFN)
        Slides
      • 12:04
        User support activites in Germany 13m
        This presentation will highlight three activities concerning the user support in Germany which might be of interest for other NGIs. The GridKA school is a summer school on Grid and Cloud Computing with lectures, tutorials and workshops held in Karlsruhe annually since 2003. The GridKA T1 centre has on-site experiment contacts for the LHC experiments, this might serve as a model for other big sites. The xGUS helpdesk template provides an easy way for NGIs or User Communities to get an own GGUS-interfaced helpdesk portal without the need for local installation.
        Speaker: Dr Torsten Antoni (Karlsruhe Institute of Technology)
        Slides
      • 12:17
        HPC Cloud - Interactive User Support 13m
        For the BiGGrid, the National Grid Initiative of the Netherlands, SARA hosts a HPC Cloud service for the community. We use a redmine portal for user support and to facilitate collaboration between users. Most tickets can be searched and read by users and can reference the documentation. It is easy to create public and private projects and hasa role based authentication/authorisation model. The HPC Cloud is a user focussed project and we extend that to our method of support as well.
        Speaker: Floris Sluiter (SARA)
        Slides
    • 11:00 12:30
      Operations documentation Rhone 4 (Universe)

      Rhone 4

      Universe

      • 11:00
        Decommission of GOCWIKI 20m
        Speaker: Andres Aeschlimann (SWITCH)
        Slides
      • 11:20
        Presentation of PROC01 30m
        Speaker: Mr Ulf Tigerstedt (CSC)
        Slides
      • 11:50
        SAM Nagios training for ROD and admin 30m
        Speaker: Mr Emir Imamagic (SRCE)
        Slides
      • 12:20
        FAQs from GGUS. Discussion and needs. 10m
        Speakers: Andres Aeschlimann (SWITCH), Mr Ulf Tigerstedt (CSC)
    • 11:00 12:30
      Software Provisioning in EGI St Clair 3a (90T)

      St Clair 3a (90T)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 11:00
        Software Provisioning in EGI 1h 30m
        • Introduction & overview 10m
          An introduction to the Software Provisioning process in EGI providing the overview of the provisioning process, and connection points where interaction with other areas of EGI take place and drive the evolution of software within EGI
          Speaker: Michel Drescher (EGI.EU)
        • Quality Criteria, and QC management 10m
          Speaker: Enol Fernandez del Castillo (CSIC)
        • Software Verification and the Verification Testbed 10m
          Speaker: Alvaro Simon (FCTSG)
        • Provisioning infrastructure and the UMD Repository 10m
          Speaker: Kostas Koumantaros (GRNET)
        • Deployed Middleware Support Unit 10m
          Speaker: Ales Krenek (CESNET)
          Slides
        • Summary and outlook 10m
          Speaker: Michel Drescher (EGI.EU)
        • Questions and Answers 30m
    • 11:00 12:30
      Tutorial: Towards better managed Grids. IT Service Management best practices based on ITIL V3 1h 30m St Clair 1 (60) (Universe)

      St Clair 1 (60)

      Universe

      The IT Infrastructure Library (ITIL) is a today widely-used collection of best practices in IT Service Management that has, of all standardization efforts, gained the most popularity. Since it combines the principles of service- and process-orientation in IT management and is easily accessible, it has become increasingly attractive for IT organizations of almost any size, branch or organizational setup. But is ITIL also applicable in Grid environments? What would be the impact, and why should we care about it? The scope of ITIL is not limited to technical issues, but also covers the organizational, human and economic dimensions of managing distributed services. In this tutorial, we give an overview of the ITIL framework, covering its most important concepts and contents, including an outline of those management practices and processes that might be most interesting for site managers, NGI managers or Grid operations/technology experts. The processes selected for presentation within the tutorial include Incident Management, Problem Management, Change Management, Configuration Management, Capacity Management, Availability Management, Security Management, Service Level Management, and Demand Management. Participants will learn more about how ITIL helps to deal with unexpected situations, to manage changes and the configuration in a distributed environment, to define and manage quality of service, and how it supports the continual improvement and alignment to customer and user needs. The goal of this training/tutorial is to deliver insight into the topics of IT Service Management and ITIL, and in addition: provide some ideas on how ITIL may be relevant and useful in the Grid context. The session is run by members of the gSLM project (www.gslm.eu), which is funded by the EC to bring commercial ITSM approaches such as ITIL to the Grid community and more broadly improve grid Service Level Management. This tutorial is targeted to people who have no or few previous knowledge on ITIL.
      Speaker: Dr Thomas Schaaf (Ludwig-Maximilians-Universität München)
      Slides
    • 12:30 14:00
      Lunch break 1h 30m
    • 14:00 15:30
      Development Accounting Workshop St Clair 1

      St Clair 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Report on preliminary steps on the accounting for new resource types (TJRA1.4) and next steps.

      slides
      • 14:00
        Introduction 15m
        Speaker: Dr John Gordon (STFC)
        Minutes
        Slides
      • 14:15
        CPU 15m
        Speaker: Andrea Guarise (INFN-Torino)
        Slides
      • 14:30
        Storage Accounting 1h
        • StAR and OGF 15m
          Speaker: Jon Kerr Nilsen (UIO)
          Slides
        • Gratia 15m
          Speaker: Tanya Levshina (FNAL)
          Slides
        • DGAS 15m
          Speakers: Andrea Cristofori, Enrico Fattibene (INFN)
          Slides
        • Other 15m
        • An EGI Profile 15m
          Speaker: Dr John Gordon (STFC)
    • 14:00 15:30
      EGI Council (Closed) St Clair 2 (60)

      St Clair 2 (60)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Dr Per Oster (CSC)
    • 14:00 15:30
      EGI-InSPIRE
      • 14:00
        SA2 F2F 1h 30m
        Speaker: Michel Drescher (EGI.EU)
    • 14:00 15:30
      EUMEDGrid-Support Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

      Conveners: Federico Ruggieri (INFN - Roma Tre), Dr Mario Reale (GARR), Roberto Barbera (University of Catania and INFN)
    • 14:00 15:30
      Grid2011: Clouds and Virtualization: I Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 14:00
        Energy-Aware Ant Colony Based Workload Placement in Clouds 30m
        Speaker: Eugen Feller
      • 14:30
        Graph-Cut Based Coscheduling Strategy towards Efficient Execution of Scientific Workflows in Collaborative Cloud Environments 30m
        Speakers: Dong Yuan, Jinjun Chen, Junqiang Song, Kaijun Ren, Kefeng Deng
      • 15:00
        Optimizing Resource Consumptions in Clouds 30m
        Speaker: Ligang He
    • 14:00 15:30
      Key Results from the Services for Heavy User Communities (SA3) Workpackage St Clair 3

      St Clair 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      These sessions highlight the key results from the SA3 workpackage which focusses on the needs of the so-called Heavy User Communities (HUCs). The HUCs include High Energy Physics (HEP), Life Sciences (LS), Astronomy and Astrophysics (A&A), Earth Sciences (ES), each of which is supported by a dedicated task, together with Shared Tools and Services which support these and other communities (including a number outside the HUC domain).

      • 14:00
        Scientific Data Preservation 20m
        Speaker: Dr Cristinel Diaconu (CPP Marseille)
        Slides
      • 14:20
        Data Caching in Life Sciences 15m
        Speaker: Tristan Glatard (CNRS)
        Slides
      • 14:35
        Data Management and Caching 20m
        The Large Hadron Collider, the world’s largest scientific machine, is in operation since the beginning of 2010 and currently relies on the WorldWide LHC Computing Grid and EGI infrastructures for the offline computing needs of the 4 main experiments that will take data at this facility. Each experiment manages multi-Petabyte data volumes across tens of computing centers throughout the world that are analyzed by a community of few thousand physicists. Since the resources are limited, it is a crucial task to optimize the available storage and network resources. At the same time, given the complexity of the experiments' data management systems and the daily amount of files that are created, replicated and deleted, operational tasks need to be as automized as possible in order to keep the manual interventions on a minimum. Different activities comprised in the TSA3.3 have successfully focused on these matters and the achievements have impacted on the evolution of the High Energy Physics computing models. This presentation will cover the key achievements of this work-package and also talk about the future trends that are being adopted in the experiments. The talk will propose solutions that can be of InSPIRE-ation for other virtual organizations that are using the grid to store their data.
        Speaker: Fernando Barreiro Megino (CERN / EGI-InSPIRE TSA3.3)
        Slides
      • 14:55
        Monitoring - The Experiment Dashboard 15m
        The Experiment Dashboard was developed in order to address the monitoring needs of the LHC experiments. It covers data management, job processing and infrastructure monitoring and works transparently across the various middleware flavours used by the LHC VOs. This presentation will summarise the key results and recent developments in monitoring of the LHC computing activities for the High Energy Physics (HEP) Heavy User Community (HUC).
        Speaker: Dr Edward Karavakis (CERN)
        Slides
      • 15:10
        Analysis Tools and Support 20m
        This talk will summarize the recent key results in analysis support for the high energy physics HUC. We will first review the user analysis activity in 2011 for the ATLAS and CMS experiments. Next, the development achievements and plans for the Ganga and CRAB grid analysis tools and the HammerCloud analysis testing service will be discussed. We will conclude with some key operational experiences in relation to these tools.
        Speaker: Dr Daniel Colin VAN DER STER (CERN)
        Slides
    • 14:00 15:30
      Operations training 1h 30m Rhone 1 (Universe)

      Rhone 1

      Universe

      Topics of the training will be defined in the coming weeks.
      Speaker: Ulf Tigerstedt (CSC)
      • SAM Nagios training 30m
        Training for RODs and SAM Nagios admins.
    • 14:00 15:30
      StratusLab Training 1h 30m St Clair 4

      St Clair 4

      Lyon Conference Centre

      StratusLab develops and provides an open-source cloud distribution that allows data centers to expose their computing resources as an "Infrastructure as a Service" (IaaS) type cloud. Administrators can run their services over the cloud to improve availability, scalability, and maintainability of their grid and non-grid services. Virtual organizations and users can use the cloud to develop custom computing environments and domain-specific services. This tutorial presents the main features of the current StratusLab distribution. Using the project's reference cloud infrastructure, participants will see how those features can be used by system administrators and scientists. The tutorial concludes with a presentation of the project's development roadmap and schedule of future releases. Participants will be provided credentials for accessing the StratusLab reference cloud infrastructure. Participants will learn about cloud technologies in general and will understand the distinction between Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS) infrastructures. They will understand how infrastructures based on the StratusLab distribution can be integrated with the European Grid Infrastructure and how the cloud services complement grid services. Practical exercises will teach the participants how to launch virtual machines, customize their computing environment, share those customized environments with others, manage virtual disks, and define complete services.
      Speaker: Charles Loomis (CNRS/LAL)
    • 14:00 15:30
      Training: Joint security training for system admins and alike
      Convener: John White (University of Helsinki, Finland)
      • 14:00
        How to install and configure glexec 45m
        Speaker: Dennis van Dok (FOM)
        Slides
      • 14:45
        How to install Argus policies 45m
        Speaker: Andrea Ceccanti (INFN)
        Slides
    • 14:00 19:30
      eConcertation Meeting (By Invitation Only) Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 14:00
        Exhibition scientific data 1h 20m
      • 15:20
        e-Science environments perspectives 15m
        Speaker: Dr Zajzon-Laszlo Bodo (European Commission)
        Slides
      • 15:35
        Strategic Plan for a Scientific Cloud Computing infrastructure for Europe 25m
        Speaker: Dr Maryline Lengert (ESA)
        Slides
      • 16:00
        Panel e-science environments: meeting user needs 1h 30m
        Speaker: Dr Sverker Holmgren (Nordforsk)
      • 17:30
        Exhibition e-Science environments & networking cocktail 2h
    • 15:30 16:00
      Coffee Break 30m
    • 16:00 17:30
      Development Accounting Workshop St Clair 1

      St Clair 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Report on preliminary steps on the accounting for new resource types (TJRA1.4) and next steps.

      slides
      • 16:00
        Applications 20m
        Speaker: Ivan Diaz Alvarez (FCTSG)
        Slides
      • 16:20
        MPI 15m
        Speakers: Enol Fernandez del Castillo (CSIC), John Walsh (TCD)
        Slides
      • 16:35
        Virtual Machines 20m
        Speaker: David wallom
        Slides
      • 16:55
        Other Suggestions 20m
    • 16:00 17:30
      EGI Council (Closed) St Clair 2 (60)

      St Clair 2 (60)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
    • 16:00 17:30
      EGI-InSPIRE
      • 16:00
        SA2 F2F 1h 30m
        Tentative agenda: Morning: - SA2 state of affairs - UMD 1.x maintenance - UMD 2.0 planning - Next 6 months in SA2 Afternoon - SA2 and IaaS
        Speaker: Michel Descher
    • 16:00 17:30
      EUMEDGrid-Support Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

    • 16:00 17:30
      Grid Oversight 1h 30m Rhone 1 (75) (Universe)

      Rhone 1 (75)

      Universe

      There will be four slots in this session. 1. Grid Oversight Issues and Topics 2. Results of the Questionnaire In this slot we will discuss the outcome of the questionnaire that we have sent to the ROD teams 3. Discussion on our requirements. 4. Latest developments of the Dashboard A presentation on the latest developments of the dashboard that are important for RODs.
      Speakers: Cyril Lorphelin (CNRS), Malgorzata Krakowian (CYFRONET), Ron Trompert (SARA)
    • 16:00 17:30
      Grid2011: Tools & Services, Resource Management and Runtime Environments: I Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 16:00
        A Strategy to Improve Resource Utilization in Grids Based on Network-Aware Meta-Scheduling in Advance 30m
        Speakers: Agustin Caminero, Blanca Caminero, Carmen Carrion, Luis Tomas
      • 16:30
        A Highly Scalable Decentralized Scheduler of Tasks with Deadlines 30m
        Speakers: J Celaya, U Arronategui
      • 17:00
        Adaptive Scheduling on Power-Aware Managed Data-Centers using Machine Learning 30m
        Speakers: J Torres, J.Ll. Berral, R Gavalda
    • 16:00 17:30
      Key Results from the Services for Heavy User Communities (SA3) Workpackage St Clair 3

      St Clair 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      These sessions highlight the key results from the SA3 workpackage which focusses on the needs of the so-called Heavy User Communities (HUCs). The HUCs include High Energy Physics (HEP), Life Sciences (LS), Astronomy and Astrophysics (A&A), Earth Sciences (ES), each of which is supported by a dedicated task, together with Shared Tools and Services which support these and other communities (including a number outside the HUC domain).

      • 16:00
        GRelC database access and integration service 20m
        The management of databases plays a crucial role in different scientific domains like Earth Science, High Energy Physics, Life Science, etc. In the EGI-InSPIRE context, the GRelC project has been supporting the HUC from several points of view through the development of domain-based use cases, tutorial activities, website, etc. A key activity related to the GRelC task (as part of the HUC support) is the DashboardDB interface. It aims at providing a web access interface to the database resources available in the EGI production grid. Such a “registry” complements the functionalities provided by the EGI Application Database and will support the users through social-oriented functionalities such as the possibility to post messages on the DashboardDB platform, create discussion groups, rate existing resources, etc. The users will be able to publish their resources and discover new ones already deployed through search & discovery functionalities. During the talk, the most relevant outcomes related to the first year of activity on the GRelC task will be presented and discussed.
        Speaker: Sandro Fiore (SPACI)
        Slides
      • 16:20
        Hydra Encryption Service 10m
        Speaker: Franck MICHEL (CNRS)
        Slides
      • 16:30
        VisIVO 20m
        Speaker: Giuliano Taffoni
        Slides
      • 16:50
        Workflows and Schedulers 20m
        Slides
        • Kepler
          Speakers: Antonio Gomez, Francisco Castejon (CIEMAT), Marcin Plociennik (ICBP)
          Slides
      • 17:10
        MPI 20m
        Speaker: Alessandro Costantini
        Slides
    • 16:00 17:30
      StratusLab Training 1h 30m St Clair 4

      St Clair 4

      Lyon Conference Centre

      StratusLab develops and provides an open-source cloud distribution that allows data centers to expose their computing resources as an "Infrastructure as a Service" (IaaS) type cloud. Administrators can run their services over the cloud to improve availability, scalability, and maintainability of their grid and non-grid services. Virtual organizations and users can use the cloud to develop custom computing environments and domain-specific services. This tutorial presents the main features of the current StratusLab distribution. Using the project's reference cloud infrastructure, participants will see how those features can be used by system administrators and scientists. The tutorial concludes with a presentation of the project's development roadmap and schedule of future releases. Participants will be provided credentials for accessing the StratusLab reference cloud infrastructure. Participants will learn about cloud technologies in general and will understand the distinction between Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS) infrastructures. They will understand how infrastructures based on the StratusLab distribution can be integrated with the European Grid Infrastructure and how the cloud services complement grid services. Practical exercises will teach the participants how to launch virtual machines, customize their computing environment, share those customized environments with others, manage virtual disks, and define complete services.
      Speaker: Dr Charles Loomis (none)
      StratusLab Client
      TTYLINUX URL
    • 16:00 17:30
      Training: Joint security training for system admins and alike
      • 16:00
        Open discussion 1h 30m
    • 17:30 19:00
      Grid2011: e-Research, Applications and Distributed Data-Intensive Science Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 17:30
        Exploiting Inherent Task-Based Parallelism in Object-Oriented Programming 30m
        Speakers: E Tejedor, F Lordan, R Badia
      • 18:00
        MARIANE: MApReduce Implementation Adapted for HPC Environments 30m
        Speakers: E Dede, L Ramakrishnan, M Govindaraju, Z Fadika
      • 18:30
        Benchmarking MapReduce Implementations for Application Usage Scenarios 30m
        Speakers: E Dede, L Ramakrishnan, M Govindaraju, Z Fadika
    • 08:30 10:30
      Grid2011: Distributed Production Cyberinfrastructure and Middleware: II Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 08:30
        Adjustable Module Isolation for Distributed Computing Infrastructures 30m
        Speakers: S Schulz, W Blochinger
      • 09:00
        Improved Grid Security Posture through Multi-factor Authentication 30m
        Speakers: M Ezell, M Johnson, P Kovatch, P Redd, V Hazelwood
      • 09:30
        Scalable and Distributed Processing of Scientific XML Data 30m
        Speakers: C Gupta, E Dede, M Govindaraju, Z Fadika
      • 10:00
        Detecting Credential Abuse in the Grid using Bayesian Networks 30m
        Speakers: C Kunz, M Smith, N Tahmasebi, T Risse
    • 09:00 10:30
      Desktop Grid Rhone 1 (75)

      Rhone 1 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Following the Desktop Grid session at EGI UF in Vilnius which had its focus more on applications, we now propose a session that focuses more on the infrastructure. How can you connect Desktop Grids into EGI infrastructures. We will show howto's for gLite, based on long time experiences.

      In addition the EDGI project, the organiser of this session has also build a bridge between Arc based Grids and Desktop grids. First results and experiences will be reported here.

      The proposal is to have 3 parts in the session.
      - A training part, including an overview of all technologies.
      - An introduction to the International Desktop Grid Federation (IDGF) and activities and services useful for EGI/NGI infrastructure providers, sys admins, and Grid operators. IDGF is a lively community with over 25 research organisations as participant.
      - An infrastructure overview. It shows how the 150.000+ computers in EDGI connected Desktop Grids are bridged into gLite and Arc based Grids. The DEGISCO project operates a similar infrastructure (with some overlap).

      Programme

      9h00 - 10h15 Part 1 - Training session (three IDGF training modules)

      • Introduction to desktop Grids: Ad Emmen
      • Basic Grid installation, including volunteer and local DGs: Jozsef Kovacs
      • Extending gLite and ARC with Desktop Grids: Zoltan Farkas
      • The last part discusses the monitoring facilities of the integrated infrastructure and some use cases of experience with connecting and using these type of infrastructures: Zoltan Farkas

      10h15 - 10h45 Part 2 - Desktop Grids intro and IDGF overview

      • What IDGF can do for you: Introduction into Desktop Grids: Ad Emmen and Peter Kacsuk
      • Applications that run on Desktop Grids: Tamas Kiss

      10h45 - 11h15 Break

      11h15 - 12h30 Part 3 - Infrastructure overview

      • EDGI/DEGISCO infrastructures, Desktop Grids and their monitoring: Zoltan Farkas
      • Bridging with gLite and Arc: Zoltan Farkas
      • Access the infrastructure by a production gateway, including demo: Zoltan Farkas
      • Extending DG systems with Clouds, including demo: Jozsef Kovacs
      • Adding quality of service to Desktop Grids with SpeQulos: Simon Delamare

      • Connecting YoYo@home: Robert Lovas

      • 09:00
        Desktop Grids at EGI TF in Lyon 1h 30m
        Following the Desktop Grid session at EGI UF in Vilnius which had its focus more on applications, we now propose a session that focuses more on the infrastructure. How can you connect Desktop Grids into EGI infrastructures. We will show howto's for gLite, based on long time experiences. In addition the EDGI project, the organiser of this session has also build a bridge between Arc based Grids and Desktop grids. First results and experiences will be reported here. The session had 3 parts: - A training part, including an overview of all technologies. - An introduction to the International Desktop Grid Federation (IDGF) and activities and services useful for EGI/NGI infrastructure providers, sys admins, and Grid operators. IDGF id a lively community with over 25 research organisations as participant. - An infrastructure overview. It shows how the 150.000+ computers in EDGI connected Desktop Grids are bridged into gLite and Arc based Grids. The DEGISCO project operates a similar infrastructure (with some overlap).
        Speakers: Ad Emmen (EDGI, DEGISCO, e-IRGSP3 projects), Prof. Peter Kacsuk (MTA SZTAKI, EDGI)
        Slides
    • 09:00 10:30
      EUMEDGrid-Support Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

      • 09:00
        EUMEDGrid-Support 1h 30m
    • 09:00 10:30
      Training: Joint security training for system admins and alike Rhone 1 (Universe)

      Rhone 1

      Universe

    • 09:00 10:35
      eConcertation Meeting (By Invitation Only) Pasteur (Universe)

      Pasteur

      Universe

      • 09:00
        Keynote 25m
        Speaker: Rob Pennington
        Slides
      • 09:25
        HPC policy, PRACE and results from exascale call 20m
        Speaker: Dr Bernhard Fabianek (European Commission)
        Slides
      • 09:45
        HPC software: Presentation of the study 25m
        Speaker: Dr Steve Conway
        Slides
      • 10:10
        PRACE initiatives 25m
        Speaker: Dr Catherine Riviere
        Slides
    • 10:30 11:00
      Coffee break 30m
    • 11:00 12:30
      Desktop Grid Rhone 4 (Universe)

      Rhone 4

      Universe

      Following the Desktop Grid session at EGI UF in Vilnius which had its focus more on applications, we now propose a session that focuses more on the infrastructure. How can you connect Desktop Grids into EGI infrastructures. We will show howto's for gLite, based on long time experiences.

      In addition the EDGI project, the organiser of this session has also build a bridge between Arc based Grids and Desktop grids. First results and experiences will be reported here.

      The proposal is to have 3 parts in the session.
      - A training part, including an overview of all technologies.
      - An introduction to the International Desktop Grid Federation (IDGF) and activities and services useful for EGI/NGI infrastructure providers, sys admins, and Grid operators. IDGF is a lively community with over 25 research organisations as participant.
      - An infrastructure overview. It shows how the 150.000+ computers in EDGI connected Desktop Grids are bridged into gLite and Arc based Grids. The DEGISCO project operates a similar infrastructure (with some overlap).

      Programme

      9h00 - 10h15 Part 1 - Training session (three IDGF training modules)

      • Introduction to desktop Grids: Ad Emmen
      • Basic Grid installation, including volunteer and local DGs: Jozsef Kovacs
      • Extending gLite and ARC with Desktop Grids: Zoltan Farkas
      • The last part discusses the monitoring facilities of the integrated infrastructure and some use cases of experience with connecting and using these type of infrastructures: Zoltan Farkas

      10h15 - 10h45 Part 2 - Desktop Grids intro and IDGF overview

      • What IDGF can do for you: Introduction into Desktop Grids: Ad Emmen and Peter Kacsuk
      • Applications that run on Desktop Grids: Tamas Kiss

      10h45 - 11h15 Break

      11h15 - 12h30 Part 3 - Infrastructure overview

      • EDGI/DEGISCO infrastructures, Desktop Grids and their monitoring: Zoltan Farkas
      • Bridging with gLite and Arc: Zoltan Farkas
      • Access the infrastructure by a production gateway, including demo: Zoltan Farkas
      • Extending DG systems with Clouds, including demo: Jozsef Kovacs
      • Adding quality of service to Desktop Grids with SpeQulos: Simon Delamare

      • Connecting YoYo@home: Robert Lovas

      • 11:00
        Desktop Grid 1h 30m
    • 11:00 12:30
      EUMEDGrid-Support Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

      • 11:00
        EUMEDGrid-Support 1h 30m
    • 11:00 12:30
      Grid2011: Clouds and Virtualization: II Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 11:00
        Differentiated Availability in Cloud Computing SLAs 30m
        Speakers: A Chilwan, A Undheim, P Heegaard
      • 11:30
        Migration of Multi-tier Applications to Infrastructure-as-a-Service Clouds: An Investigation Using Kernel-based Virtual Machines 30m
        Speakers: J Lyon, K Rojas, M Arabi, O David, S Pallickara, W Lloyd
      • 12:00
        Embedded Processor Virtualization for Broadband Grid Computing 30m
        Speakers: A Shabarshin, L Carloni, R Neill, S Tcherepanov, V Sigaev
    • 11:00 12:30
      Training: Joint security training for system admins and alike
      • 11:00
        Incident workflow and forensic tools 45m
        Speaker: Leif Nixon (LIU)
        Slides
      • 11:45
        Linux rootkit and TTY hijacking 30m
        Speaker: Mr Antonio Perez Perez (CERN)
        Slides
      • 12:15
        Vulnerability handling (what to do if you find a vulnerability and How are they handled) 15m
        Speaker: Linda Cornwall (STFC)
        Slides
    • 11:00 12:30
      eConcertation Meeting (By Invitation Only) Pasteur (Universe)

      Pasteur

      Universe

    • 12:30 14:00
      Lunch break 1h 30m
    • 14:00 15:30
      Grid2011: Tools & Services, Resource Management and Runtime Environments: II Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 14:00
        Autonomic Resource Management with Support Vector Machines 30m
        Speakers: A Brinkmann, A Krieger, J Simon, O Niehörster
      • 14:30
        Supporting Deadline Constrained Distributed Computations on Grids 30m
        Speakers: N Jamali, X Zhao
      • 15:00
        Performance Evaluation of Overload Control in Multi-Cluster Grids 30m
        Speakers: A Iosup, D Epema, N Yigitbasi, O Sonmez
    • 14:00 15:30
      SHIWA Simulation Platform 1h 30m Rhone 1 (75)

      Rhone 1 (75)

      Lyon Conference Centre

      A large number of research teams creates and runs workflows to support their applications. There are two key players in this process: e-scientists who use workflows and workflow developers who create workflows. Elaborating a workflow may require significant efforts and specific expertise. Workflow developers have to be familiar with both the research area which they address and workflow systems they use. Workflow development, testing and validation is a time consuming process and it requires specific expertise. These constrains limit the number of available workflows, so it is important to reuse them. However, there is a further obstacle to workflow dissemination: there are many workflow systems, and workflows developed for one workflow system is normally not compatible with workflows of other workflow systems. As a result research communities cannot easily use workflows. This situation can be resolved by workflow interoperability according to which publicly available workflows can be and should be used by different research communities on different workflow systems and on multiple distributed computing infrastructures. The SHIWA Simulation Platform (SSP) was designed to provide a platform through which scientists can share and re-use their workflows. The production SSP v1.0 is available since mid March. SSP v1 supports coarse-grained workflow interoperability where nodes of a native workflow can be workflows written in other workflow languages and systems and are considered as black boxes. In SSP v1.0 the native workflow system is the P-GRADE workflow system. The coarse-grained interoperability enables either embedding or invoking ASKALON, GWES, Kepler, MOTEUR, Taverna and Triana workflows. SSP v1 allows e-scientists to search workflows uploaded to the SHIWA Repository and use them in their experiments. The workshop will show the concept and technical details of SSP v1.0 as well as some application examples where SSP v1.0 was actively used.
      Speakers: Dr Gabor Terstyanszky (Univ. of Westminster), Prof. Peter Kacsuk (MTA SZTAKI), Mr Tamas Kukla (Univ. of Westminster)
    • 15:30 16:00
      Coffee break 30m
    • 16:00 18:00
      Grid2011: Distributed Production Cyberinfrastructure and Middleware: III Rhone 3

      Rhone 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      Convener: Shantenu Jha
      • 16:00
        Using the Gfarm File System as a POSIX compatible storage platform for Hadoop MapReduce applications 30m
        Speakers: K Ohta, O Tatebe, S Mikami
      • 16:30
        A Fast Location Service for Partial Spatial Replicas 30m
        Speakers: Ph Rhodes, Y Tian
      • 17:00
        Replicated Grid Resources 30m
        Speakers: A Grimshaw, S Valente
      • 17:30
        Beyond batch computing on the WLCG Grid 30m
        Speaker: M Meoni
    • 00:30 02:00
      Key Results from the Services for Heavy User Communities (SA3) Workpackage St Clair 3

      St Clair 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Key Results from the Services for Heavy User Communities (SA3) Workpackage
      Description
      These sessions highlight the key results from the SA3 workpackage which focusses on the needs of the so-called Heavy User Communities (HUCs). The HUCs include High Energy Physics (HEP), Life Sciences (LS), Astronomy and Astrophysics (A&A), Earth Sciences (ES), each of which is supported by a dedicated task, together with Shared Tools and Services which support these and other communities (including a number outside the HUC domain).

      Key issues for SA3 are sustainability and the (related) drive towards common solutions.

      Convener: Jamie Shiers (CERN)
    • 01:05 02:35
      EGI Council (Closed) St Clair 2 (60)

      St Clair 2 (60)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 01:05
        EGI Council (closed) 1h 30m
    • 02:35 04:35
      eConcertation Meeting (By Invitation Only) Pasteur (Lyon Convention Centre)

      Pasteur

      Lyon Convention Centre

      • 02:35
        Update session with Q/A on Call 10 2h
        Speaker: Dr Krystyna Marek (European Commission)
        Slides
    • 05:00 06:30
      EUMEDGrid-Support Rhone 2 (75)

      Rhone 2 (75)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

      • 05:00
        EUMEDGrid-Support 1h 30m
    • 06:30 08:00
      EGI Council (Closed) St Clair 2 (60)

      St Clair 2 (60)

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 06:30
        EGI Council (closed) 1h 30m
    • 07:35 10:05
      NSF Workshop (Closed) Pasteur

      Pasteur

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France
      • 07:35
        Welcome 15m
        Speakers: Dr Alan Blatecky (Office of Cyberinfrastructure, NSF), Dr Pekka Karp (European Commission)
      • 07:50
        Scientific Data: State of play 15m
        Speakers: Alan Blatecky (Office of Cyberinfrastructure, NSF), Pekka Karp (European Commission)
      • 08:05
        Panel and Open Discussion 1h 45m
        Speaker: Herbert Van de Sompel (Los Alamos National Laboratory)
      • 09:50
        Wrap up and next steps 15m
    • 10:05 11:35
      EUMEDGrid-Support: F2F (Closed) Rhone 4 (40)

      Rhone 4 (40)

      Lyon Conference Centre

      The User Forum will showcase the most relevant scientific and technological results achieved by Virtual Research Communities supported by the project and those existing around the world and will be an occasion to discuss policies and plans for the long term sustainability of regional e-infrastructures in the Mediterranean area.
      The event will bring together a community of researchers, developers, practitioners, service providers and users involved in Grid technology and Distributed Computing Infrastructures (DCI), as well as policy makers and government representatives.
      The User Forum will feature invited keynote addresses and refereed paper presentations through an open call for papers. The selected papers will published in the User Forum Proceedings.
      The call for papers is open at www.eumedgrid.eu/index.php/paper-submission.
      Important dates are:
      1. Deadline for abstract submssion: 29 July 2011;
      2. Acceptance notification: 5 August 2011;
      3. Camera ready papers: 9 September 2011.

      Conveners: Federico Ruggieri (INFN - Roma Tre), Dr Mario Reale (GARR), Roberto Barbera (University of Catania and INFN)
      • 10:05
        EUMEDGrid-Support 1h 30m
    • 14:00 15:30
      Development Accounting Workshop St Clair 1

      St Clair 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Report on preliminary steps on the accounting for new resource types (TJRA1.4) and next steps.

    • 16:05 16:35
      Coffee break 30m
    • 20:05 21:35
      Key Results from the Services for Heavy User Communities (SA3) Workpackage St Clair 3

      St Clair 3

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Key Results from the Services for Heavy User Communities (SA3) Workpackage
      Description
      These sessions highlight the key results from the SA3 workpackage which focusses on the needs of the so-called Heavy User Communities (HUCs). The HUCs include High Energy Physics (HEP), Life Sciences (LS), Astronomy and Astrophysics (A&A), Earth Sciences (ES), each of which is supported by a dedicated task, together with Shared Tools and Services which support these and other communities (including a number outside the HUC domain).

      Key issues for SA3 are sustainability and the (related) drive towards common solutions.

      Convener: Jamie Shiers (CERN)
    • 00:35 02:05
      EMI: User Tutorial St Clair 4

      St Clair 4

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      The European Middleware Initiative (EMI)
      aims to deliver a consolidated set of middleware components
      for deployment in Distributed Computing Infrastructures, extending the
      interoperability between grids and other computing
      infrastructures, strengthening the reliability of the services, and
      establish a sustainable model to maintain and
      evolve the middleware, fulfilling the requirements of user
      communities.

      EMI middleware is not build from ground up, but rather,
      delivers a consolidated and streamlined set of services and
      components from existing middleware projects ARC, gLite, UNICORE and dCache by
      re-factoring existing components, defining and implementing standards
      and phasing out duplicate or obsolete
      components from the original middleware stacks. The middleware
      components are divided in four areas (Compute, Data, Security,
      Infrastructure). This tutorial will introduce usage of most commonly used clients
      for job and data management.

      This user oriented tutorial is based on the first release of the EMI middleware, EMI-1 "Kebnekaise".
      It will provide an overview of EMI clients
      for Computing and Data Services, giving concrete examples and highlighting best practices
      and most common mistakes.

      Convener: Kathryn Cassidy (TCD)
      slides
    • 02:05 02:35
      Coffee break 30m
    • 02:35 04:05
      Development Accounting Workshop St Clair 1

      St Clair 1

      Lyon Conference Centre

      Lyon Conference Centre, Lyon, France

      Report on preliminary steps on the accounting for new resource types (TJRA1.4) and next steps.