Switch - DataTAG

Download Report

Transcript Switch - DataTAG

DataTAG overview
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 1)
Summary

Why DataTAG?

DataTAG project

General information

Test-bed extensions

Network map

Research topics

Issues

Acknowledgements
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 2)
Background for DataTAG






CERN is building the LHC (start-up in 2007?): an
unprecedented amount of data will have to be
analyzed and CERN alone will not have enough
computing resources to process it
The planned computing model is distributed
geographically (GRID)
The EU-DataGrid project is addressing the
middleware problem
Reliable, advanced networking is needed
underneath
Traffic will not look like any IP commodity traffic
now
A lot of bandwidth is necessary, but it won’t be
enough
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 3)
Addressing the problem

Buy a lot of bandwidth

Buy (expensive) network equipment

Address security issues without compromising
performance (firewalls)

Tune some more or less obvious TCP parameter

Design the network for reliability and performance

Plan for interconnection with key research
networks
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 4)
Why network research?





Need to enhance data transport protocols (TCP)
Need to measure the perceived application
performance
Need to try the GRID software in a WAN
environment and at high speed: what is actually
going wrong if things go wrong in the network?
Need to test the compatibility between EU and US
GRIDs (middleware integration)
Need to test network technology with enough
speed and enough features to support the planned
GRID workload (end-to-end inter-domain QoS)
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 5)
DataTAG project





“Research and technological development for a transatlantic GRID” (project full title)
IST project (EU funded), supported by the NSF
and the DoE (Caltech)
Partners: PPARC (UK), INRIA (FR), University of
Amsterdam (NL), INFN (IT) and CERN (CH)
Researchers from Caltech, SLAC and Canada
Test-bed kernel: a transatlantic STM-16 (Tsystems) between Geneva (CERN) and Chicago
(StarLight), with interconnected workstations
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 6)
General information

2-years project: 2002 and 2003

Dedicated staff (recruited on project budget)

Part-time staff, shared with other activities


Open to cooperate with other projects: EUDataGrid, GEANT, Abilene, TeraGrid,
NetherLight, etc.
Typical EU work package structure: quarterly
reports, deliverables at fixed deadlines, periodic
reviews by external inspectors. Very formal and
structured framework, but effective to avoid
project drifting, delays and wastes
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 7)
DataTAG Network map
R06chi-Alcatel7770
W01chi
w02chi
w03chi
w04chi
w05chi
w06chi
ONS15454
SURFNET
2x1GE
R06gva-Alcatel7770
V10chi
v11chi
v12chi
v13chi
4x1GE
8x1GE
Alcatel 1670
ONS15454
R05chi-JuniperM10
ABILENE
Stm64(L3)
2x1GE
2x1GE
VTHD/INRIA
1GE
Stm16 (FranceTelecom)
1GE
2x1GE
Stm16(DTag)
Extreme
Summit5i
10GE
Stm16(GC)
4x1GE
2x1GE
SUNNYVALE
2x1GE
Alcatel 1670
10x1GE
1GE
SURFNET
W03gva
w04gva
1GE
CANARIE
2x1GE
ONS15454
W01gva
w02gva
w05gva
w06gva
R04chi-Cisco7609
R04gva-Cisco7606
1GE
R05gva-JuniperM10
Extreme
Summit1i
1GE
2x1GE
10GE
Cisco5505-management
Chicago Geneva
CERN External Network
1GE
Vlan4
Vlan5
1GE
Vlan7
DataTAG
1GE
Teragrid JuniperT640
1GE
Stm4(DTag)
1GE
Stm16(Swisscom)
Cisco2950-management
ar3-chicago -Cisco7606
Cernh4-Cisco7609
SWITCH
Cernh7-Cisco7609
GEANT
Stm16(Colt)
backup+projects
GARR/CNAF
[email protected] - last update: 20021204
Management addresses and path to reach them from the interne
Datatag testbed addresses
Path of the CCC tunnel from CNAF
Path between the OC farms in Chicago and Geneva
Path between Sunnyvale and the PC farm in Geneva
DataTAG Routing map
W01chi
w02chi
w03chi
w04chi
w05chi
w06chi
SURFNET
R06gva
R06chi
V10chi
v11chi
v12chi
v13chi
W01gva
w02gva
w05gva
w06gva
SURFNET
W03gva
w04gva
CANARIE
VTHD/INRIA
R05gva
R05chi
R04gva
R04chi
SUNNYVALE
ABILENE
192.91.236.0/23 192.91.238.0/23
Cisco5505-management
Teragrid JuniperT640
Chicago Geneva
192.91.246.192/26
192.91.244.0/27
DataTAG
CERN External Network
SWITCH
Cisco2950-management
ar3-chicago
Cernh4
Cernh7
GEANT
GARR/CNAF
[email protected] - last update: 20021204
(some) Research topics
(I)





Linux kernel tuning for high performance: for
example, 8 Terabytes in 24 hours, memory-tomemory (achieved by S .Ravot, Caltech)
Bulk file transfer (Terabyte disk-to-disk, at 2
Gbps, achieved by Canadian researchers between
TRIUMF and CERN)
TCP stack improvements (things get worse with
longer RTT)
Application-level performance measurement
GRID middleware interoperability between EU and
US
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 10)
(some) Research topics
(II)




10 Gb tests (10GbE and transatlantic link
upgrade, tentatively in September 2003)
at layer 2 and layer 3
Multi-vendor equipment (Alcatel 1670 and
7770, Cisco 760x, Juniper M10, Extreme
Summit switches)
QoS tests, advanced reservation
Optical networking: validation of
equipment
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 11)
Issues (I)


Electrical power in Chicago (!!!)
Broken network hardware (mainly 10 GbE cards,
but not only)

Broken PCs

Hung routers

Never enough workstations available for testing



Reservation system: it will never be sophisticated
enough
Network topology: each research group has
different requirements
Alcatel 1670: needs STM-16 reconfiguration
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 12)
Issues (II)




Cisco 760x components (un)availability
Demo workshops (iGRID2002, SC2002, …): nice to
see, but organizational nightmares
KPNQwest collapse (re-procurement via Tsystems)
Routing: interconnections with CERN production
network, with external production networks, with
external test networks, even with commodity
Internet; furthermore, routing is open for
experiments

Management access to devices

OOB access (Chicago)
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 13)
Issues (III)





A lot of enthusiasm and interest, not always
supported by adequate planning
When adequate planning is there, it is ignored
(because of the enthusiasm, of course)
Partners coordination is not straightforward: mix
of shared and private resources
DNS, security, access control, management
servers, VLANs, WWW site, IP addressing (>100
addresses assigned), etc.: all need planning, work
and maintenance
PoP management (run out of rack space) +
installation issues (mainly, but not only, Alcatel)
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 14)
Acknowledgements



DataTAG is for what you would have always liked
to do and you never dared to do because it was
too risky, or too expensive, or too complicated, or
because you could not afford a test laboratory
Many thanks to DANTE/GEANT and DoE/Caltech,
who are actively supporting the project
http://www.datatag.org
23 January 2003
SWITCH-cc meeting
Paolo Moroni (Slide 15)