1. CEOS workshop on Grid computing Slides mainly from Olivier Martin
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 DataTAG project
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
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

7. Funding agencies
Cooperating Networks

8. EU partners

9. Associated US partners

10. CEOS Workshop- Frascati
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
11/12/2018
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 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.
11/12/2018
CEOS Workshop- Frascati

12. CEOS Workshop- Frascati
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
11/12/2018
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
11/12/2018
M= Layer 2 Mux
CEOS Workshop- Frascati

14. CEOS Workshop- Frascati
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)
11/12/2018
CEOS Workshop- Frascati

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

16. CEOS Workshop- Frascati
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!
11/12/2018
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
11/12/2018
CEOS Workshop- Frascati

18. CEOS Workshop- Frascati
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.
11/12/2018
CEOS Workshop- Frascati

19. CEOS Workshop- Frascati
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)
11/12/2018
CEOS Workshop- Frascati

20. CEOS Workshop- Frascati
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)
11/12/2018
CEOS Workshop- Frascati

21. CEOS Workshop- Frascati
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)
11/12/2018
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)
11/12/2018
CEOS Workshop- Frascati

23. CEOS Workshop- Frascati
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
11/12/2018
CEOS Workshop- Frascati

24. WP4.1 - Resource Discovery Objectives
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
11/12/2018
CEOS Workshop- Frascati

25. CEOS Workshop- Frascati
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
11/12/2018
CEOS Workshop- Frascati

26. CEOS Workshop- Frascati
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.
11/12/2018
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
11/12/2018
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 
11/12/2018
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
11/12/2018
CEOS Workshop- Frascati