1 / 29

The DataTAG Project

The DataTAG Project. CEOS workshop on Grid computing 6th May 2002, Frascati-Rome Mirco Mazzucato INFN-Padova Slides mainly from Olivier Martin. Presentation outline. CERN networking Grid networking requirements DataTAG project Partners Goals Positioning Grid networking issues

jeffd
Download Presentation

The DataTAG Project

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. The DataTAG Project CEOS workshop on Grid computing 6th May 2002, Frascati-Rome Mirco Mazzucato INFN-Padova Slides mainly from Olivier Martin

  2. Presentation outline • CERN networking • Grid networking requirements • DataTAG project • Partners • Goals • Positioning • Grid networking issues • Concluding remarks

  3. Long term Data Grids networking requirements • A basic assumption of Data intensive Grids is that the underlying network is more or less invisible. • A prerequisite, therefore, is very fast links between Grid nodes • Is the hierarchical structure of European academic R&E networks and the pan-European interconnection backbone GEANT a sustainable long term model, in order to adequately support Data intensive Grids such as the LHC Grid (Large Hadron Collider)? • Are lambda Grids, feasible & affordable? • Interesting to note that the original LHC computing model which was itself hierarchical (Tier0, Tier1, etc) appears to be evolving towards a somewhat more flexible model.

  4. Evolution of LHC bandwidth requirements • LHC Bandwidth Requirements (1999) • 622 Mbps between CERN and some (or all) LHC regional centers by 2005 • “There seems to be no other way to reach the LHC target than to significantly increase the budget for external networking by a factor of 3 to5, depending on when the bandwidth should be delivered”. • LHC Bandwidth Requirements (2001) • 2.5 Gbps between CERN and some (or all) LHC regional centers by 2005 • “In any case, a great deal of optimism is needed in order to reach the LHC target!” • LHC Bandwidth Requirements (2002) • 10 Gbps between CERN and some (or all) LHC regional centers by 2006 • It is very likely that the first long haul 10Gbps circuits will already appear at CERN in 2003/2004. • Evolution of circuit costs

  5. What happened? • As a result of the EU wide deregulation of the Telecom that took place in 1998, there is an extraordinary situation today where circuit prices have gone much below the most optimistic forecasts! • An issue: will this trend continue? • What’s the most efficient usage of network? • Especially for transatlantic connections

  6. The DataTAG Project http://www.datatag.org

  7. Funding agencies Cooperating Networks

  8. EU partners

  9. Associated US partners

  10. The project • European partners: INFN (IT), PPARC (UK), University of Amsterdam (NL) and CERN, as project coordinator. • INRIA (FR) will join in June/July2002. • ESA/ESRIN (IT) will provide Earth Observation demos together with NASA. • Budget: 3.98 MEUR • Start date: January, 1, 2002 • Duration: 2 years (aligned on DataGrid) • Funded manpower: ~ 15 persons/year CEOS Workshop- Frascati

  11. US Funding & collaborations • US NSF support through the existing collaborative agreement with CERN (Eurolink award). • US DoE support through the CERN-USA line consortium. • Significant contributions to the DataTAG workplan have been made by Andy Adamson (University of Michigan), Jason Leigh (EVL@University of Illinois), Joel Mambretti (Northwestern University), Brian Tierney (LBNL). • Strong collaborations already in place with ANL, Caltech, FNAL, SLAC, University of Michigan, as well as Internet2 and ESnet. CEOS Workshop- Frascati

  12. In a nutshell • Two main focus: • Grid related network research (WP2, WP3) • Interoperability between European and US Grids (WP4) • 2.5 Gbps transatlantic lambda between CERN (Geneva) and StarLight (Chicago) around July 2002 (WP1). • Dedicated to research (no production traffic) • Fairly unique multi-vendor testbed with layer2 and layer 3 capabilities • In principle open to other EU Grid projects as well as ESA for demonstrations CEOS Workshop- Frascati

  13. Multi-vendor testbed with layer3 as well as layer2 capabilities INFN (Bologna) STARLIGHT (Chicago) Abilene CERN (Geneva) GEANT ESnet 1.25Gbps Juniper Juniper 2.5Gbps Cisco 6509 M M Alcatel Alcatel Starlight GBE 622Mbps Cisco Cisco CEOS Workshop- Frascati M= Layer 2 Mux

  14. Goals • End to end Gigabit Ethernet performance using innovative high performance transport protocols. • Assess & experiment inter-domain QoS and bandwidth reservation techniques. • Interoperability between some major GRID projects in Europe and North America • DataGrid as reference…. possibly other EU funded Grid projects • PPDG, GriPhyN, Teragrid, iVDGL (USA) CEOS Workshop- Frascati

  15. UK SuperJANET4 NL SURFnet GEANT IT GARR-B DataTAG project NewYork Abilene STAR-LIGHT ESNET CERN MREN STAR-TAP Major 2.5 Gbps circuits between Europe & USA

  16. Project positioning • Why yet another 2.5 Gbps transatlantic circuit? • Most existing or planned 2.5 Gbps transatlantic circuits are for production, which makes them basically not suitable for advanced networking experiments that require a great deal of operational flexibility in order to investigate new application driven network services, e.g.: • deploying new equipment (routers, G-MPLS capable multiplexers), • activating new functionality (QoS, MPLS, distributed VLAN) • The only known exception to date is the Surfnet circuit between Amsterdam & Chicago (Starlight) • Concerns: • How far beyond Starlight can DataTAG extend? • How fast will US research network infrastructure match that of Europe! CEOS Workshop- Frascati

  17. Major Grid networking issues • QoS (Quality of Service) • still largely unresolved on a wide scale because of complexity of deployment • TCP/IP performance over high bandwidth, long distance networks • The loss of a single packet will affect a 10Gbps stream with 200ms RTT (round trip time) for 5 hours. During that time the average throughput will be 7.5 Gbps. • On the 2.5Gbps DataTAG circuit with 100ms RTT, this translates to 38 minutes recovery time, during that time the average throughput will be 1.875Gbps. • Line Error rates • A 2.5 Gbps circuit can absorb 0.2 Million packets/second • Bit error rates of 10E-9 means one packet loss every 250 mseconds • Bit error rates of 10E-11 means one packet loss every 25 seconds • End to end performance in the presence of firewalls • There is a lack of high performance firewalls, can we rely on products becoming available or should a new architecture be evolved? • Evolution of LAN infrastructure to 1Gbps then 10Gbps • Uniform end to end performance CEOS Workshop- Frascati

  18. Concluding remarks • The dream of abundant bandwith has now become a hopefully lasting reality! • Major transport protocol issues still need to be resolved. • Large scale deployment of bandwidth greedy applications still remain to be done, • Proof of concept has yet to be made. CEOS Workshop- Frascati

  19. Workplan (1) • WP1: Provisioning & Operations (P. Moroni/CERN) • Will be done in cooperation with DANTE & National Research & Education Networks (NREN) • Two main issues: • Procurement (largely done already for what concerns the circuit, equipment still to be decided). • Routing, how can the DataTAG partners access the DataTAG circuit across GEANT and their national network? • Funded participants: CERN(1FTE), INFN (0.5FTE) • WP5: Information dissemination and exploitation (CERN) • Funded participants: CERN(0.5FTE) • WP6: Project management (CERN) • Funded participants: CERN(2FTE) CEOS Workshop- Frascati

  20. Workplan (2) • WP2: High Performance Networking (Robin Tasker/PPARC) • High performance Transport • tcp/ip performance over large bandwidth*delay networks • Alternative transport solutions using: • Modified TCP/IP stack • UDP based transport conceptually similar to rate based TCP • End to end inter-domain QoS • Advance network resource reservation • Funded participants: PPARC (2FTE), INFN (2FTE), UvA (1FTE), CERN(1FTE) CEOS Workshop- Frascati

  21. Workplan (3) • WP3: Bulk Data Transfer & Application performance monitoring (Cees deLaat/UvA) • Performance validation • End to end user performance • Validation • Monitoring • Optimization • Application performance • Netlogger • Funded participants: UvA (2FTE), CERN(0.6FTE) CEOS Workshop- Frascati

  22. WP4 Workplan(Antonia Ghiselli & Cristina Vistoli / INFN) • Main Subject: • Interoperability between EU and US Grids services from DataGrid, GriPhyN, PPDG and in collaboration with iVDGL, for the HEP applications. • Objectives: • Produce an assessment of interoperability solutions • Provide test environment to LHC Applications to extend existing use-cases to test interoperability of the grid components • Provide input to a common Grid LHC solution • Support EU-US Integrated grid deployment • Funded participants: INFN (6FTE), PPARC (1FTE), UvA (1FTE) CEOS Workshop- Frascati

  23. WP4 Tasks Assuming the same grid basic services (gram,gsi,gris) between the differen grid projects, the main issues are: • 4.1 resource discovery, coord. C.Vistoli • 4.2 authorization/VO managemnt, coord. R.Cecchini • 4.3 interoperability of collective services between EU-US grid domains, coord. F.Donno • 4.4 test applications, contact people from each application : • Atlas / L.Perini, CMS / C.Grandi, • Alice / P.Cerello CEOS Workshop- Frascati

  24. WP4.1 - Resource DiscoveryObjectives • Enabling an interoperable system that allows for the discovery and access of the Grid services available at participant sites of all Grid domains, in particular between EU and US Grids. • Compatibility of the Resource Discovery System with the existent components/services of the available GRID systems. • Subproject on information schema established CEOS Workshop- Frascati

  25. WP4.2 - Objectives • Identify Authentication, Authorization and Accounting (AAA) mechanisms allowing interoperability between grids • Compatibility of the AAA mechanisms with the existing components/services of the available GRID systems • Authorization/VO management subproject established CEOS Workshop- Frascati

  26. WP4.3 / WP4.4 - Objectives • Identify grid elements in EU and US grid projects, Identify common components in the testbeds used by the HEP experiments for semi-production activities in EU and US and classify them in an architectural framework. • Plan and Setup environment with common EU-US services. • Test common solutions in a EU-US domain in collaboration with iVDGL. CEOS Workshop- Frascati

  27. DataTAG/WP4 framework and relationships Grid projects: DataGrid PPDG Griphyn LCG Globus Condor ….. input feedback ….. Grid Interoperability Activities: DataTAG/WP4 iVDGL HICB/HIJTB GGF Integration stardardization Proposals ….. Applications: LHC experiments CDF Babar ESA CEOS Workshop- Frascati

  28. Summary: The interoperability issues (1) • 1)Certificates. Solved • 2) GSI security. OK but users ask for improved error reporting for a production infrastructure  • 3)Authorization and VO management. A joint subproject has started for a common solution • 4)Information Schema. Work is progressing well and the group should be able to propose a common solution.  • 5) GIIS structure and hierarchies. Sub-project in the pipeline. • General issue of the different vision of the information system based on LDAP or on R-GMA still open CEOS Workshop- Frascati

  29. Summary: The interoperability issues (2) • 6) Scheduling, use of JDL and experiment interface Regular meetings are taking place between EDG WP1 and Condor/ PPDG people. Expected to produce a common recommendation.   • 7)Data management. A good collaboration between EDG WP2 and Globus/PPDG teams. Should be able to make a common recommendation on the usage of GDMP, Replica Catalog and Replica Manager.   • 8) Packaging. LCG should have common release, packaging and installation tools. LCG application effort to define a common LHC solution started CEOS Workshop- Frascati

More Related