1. Why is optical networking interesting?
Cees de Laat

2. Why is optical networking interesting?
Cees de Laat
Cees de aat EU
SURFnet
University of Amsterdam
SARA
NIKHEF
serena

3. What is this buzz about optical networking
Networks are already optical for ages
Users won’t see the light
Almost all current projects are about SONET circuits and Ethernet (old wine in new bags?)
Are we going back to the telecom world, do NRN’s want to become telco’s
Does it scale
Is it all about speed or is it integrated services

4. Current technology + (re)definition
Current (to me) available technology consists of SONET/SDH switches
Changing very soon!
DWDM+switching coming up
Starlight uses for the time being VLAN’s on Ethernet switches to connect [exactly] two ports
So redefine a l as:
“a l is a pipe where you can inspect packets as they enter and when they exit, but principally not when in transit. In transit one only deals with the parameters of the pipe: number, color, bandwidth”

5. VLBI

6. Know the user # of users A B C F(t) BW requirements
ADSL
GigE LAN
F(t)
BW requirements
A -> Lightweight users, browsing, mailing, home use
B -> Business applications, multicast, streaming, VPN’s, mostly LAN
C -> Special scientific applications, computing, data grids, virtual-presence

7. What the user Total BW A B C BW requirements
(4 of 12)
Total BW A B C
ADSL
GigE LAN
BW requirements
A -> Need full Internet routing, one to many
B -> Need VPN services on/and full Internet routing, several to several
C -> Need very fat pipes, limited multiple Virtual Organizations, few to few

8. So what are the facts
(5 of 12)
Costs of fat pipes (fibers) are one/third of equipment to light them up
Is what Lambda salesmen tell me
Costs of optical equipment 10% of switching 10 % of full routing equipment for same throughput
100 Byte 10 Gb/s -> 80 ns to look up in 100 Mbyte routing table (light speed from me to you on the back row!)
Big sciences need fat pipes
Bottom line: create a hybrid architecture which serves all users in one consistent cost effective way

9. (5b of 12)
Scale

10. Services 2 Metro 20 National/ regional 200 World A Switching/ routing
(5c of 12) 2
Metro 20
National/
regional
200
World A
Switching/
routing
Routing
ROUTER$ B
VPN’s, (G)MPLS
VPN’s C
#l ~ 200/RTT
dark fiber
Optical switching
Lambda switching
Sub-lambdas, ethernet-sdh
COST

11. lambda for high bandwidth applications
(6 of 12)
Application
Application
High bandwidth app
Middleware
Middleware
Transport
Transport
Switch
lambda for high bandwidth applications
Bypass of production network
Middleware may request (optical) pipe
RATIONALE:
Lower the cost of transport per packet
2.5Gb lambda
Router
UvA
GbE
SURFnet5
ams
Router
Lambda
Switch
Router
chi
GbE
3rd party carriers
Router
Lambda
Switch
Router
GbE
Router
UBC
Vancouver
Switch

12. Possible future CA*net 4 node
(7 of 12)
CA*net 4 Architecture
CANARIE
GigaPOP
ORAN DWDM
Carrier DWDM
Edmonton
Saskatoon
Calgary
St. John’s
Regina
Winnipeg
Quebec
Charlottetown
Thunder Bay
Montreal
Victoria
Ottawa
Vancouver
Fredericton
Halifax
Boston
Seattle
Chicago
New York
CA*net 4 node)
Toronto
Possible future CA*net 4 node
Windsor 10 10 9 9 9 10 10 10 10 10 10 10 10

13. Architectures - L1 - L3 R R SW R R Internet L2 VPN’s Internet
(8 of 12) R
Internet R
L2 VPN’s SW
Internet R R
Bring plumbing to the users, not just create sinks in the middle of nowhere

14. Distributed L2
(8a of 12)

15. Transport in the corners
(9 of 13)
BW*RTT ? C
Needs more App & Middleware interaction
Full optical future
For what current Internet was designed B A
# FLOWS

16. (9a of 13)

17. Layer - 2 requirements from 3/4
(10 of 14) WS
fast L2
fast->slow
high RTT L2
slow->fast
fast WS
TCP is bursty due to sliding window protocol and slow start algorithm. So pick from menu:
Flow control
Traffic Shaping
RED (Random Early Discard)
Self clocking in TCP
Deep memory
Window = BandWidth * RTT & BW == slow
fast - slow
Memory-at-bottleneck = ___________ * slow * RTT
fast

18. Forbidden area, solutions for s when f = 1 Gb/s, M = 0.5 Mbyte
AND NOT USING FLOWCONTROL
= 158 ms = RTT Amsterdam - Vancouver or Berkeley s
rtt

19. Daisy Chain control model of administrative domains
Selector
Switch
Distributor
Switch
AAA
AAA
Domain X
Domain Y

20. Collective Grid Services
Problem Solving Environment
(12 of 14)
Applications and Supporting Tools
Application Development Support
Collective Grid Services
Global Queuing
Co-Scheduling
Data Cataloguing
Fault Management
Brokering
Auditing
Authorization
Monitoring
Common Grid Services
Grid Information Service
Uniform Resource Access
Global Event Services
Uniform Data Access
Communication Services
(Resource)
the neck
Grid Security Infrastructure (authentication, proxy, secure transport)
What services are the basic building blocks?
Communication
Grid access (proxy authentication, authorization, initiation)
Fabric
Grid task initiation
Resource Manager
CPUs
Resource Manager
Monitors
Resource Manager
On-Line Storage
Resource Manager
Scientific Instruments
Resource Manager
Tertiary Storage
Resource Manager
Highspeed Data Transport
Resource Manager
net QoS
Local Resources
layers of increasing abstraction taxonomy

21. CE L1 L2 SE L3 L3 NE UE (13 of 14) GRID-Layer GRID-Layer ISP’s peering
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 CE
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 L1
7, 6, 5, 4, 3, 2, 1 L2
7, 6, 5, 4, 3, 2, 1 SE L3
GRID-Layer
7, 6, 5, 4, 3, 2, 1 L3
7, 6, 5, 4, 3, 2, 1
ISP’s
peering
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 NE
7, 6, 5, 4, 3, 2, 1 UE
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1

22. CE L3/4 L2 L1 L1 SE L1 NE UE (13b of 14) ISP’s GRID-Layer GRID-Layer
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 CE
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
L3/4
7, 6, 5, 4, 3, 2, 1 L2 L1 L1
7, 6, 5, 4, 3, 2, 1 SE
GRID-Layer
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 L1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
l-tranport
ISP’s NE
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1 UE
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1
7, 6, 5, 4, 3, 2, 1

23. Research needed Optical devices Internet Architecture
(13c of 14)
Optical devices
Internet Architecture
Network Elements as Grid Resources
Transport protocols get in other corners
How dynamic must your optical underware be
Don’t mix trucks and Ferrari’s

24. Revisiting the truck of tapes
Consider one fiber
Current technology allows 320 in one of the frequency bands
Each  has a bandwidth of 40 Gbit/s
Transport: 320 * 40*109 / 8 = 1600 GByte/sec
Take a 10 metric ton truck
One tape contains 50 Gbyte, weights 100 gr
Truck contains ( / 0.1 ) * 50 Gbyte = 5 PByte
Truck / fiber = 5 PByte / 1600 GByte/sec = 3125 s ≈ one hour
For distances further away than a truck drives in one hour (50 km) minus loading and handling tapes the fiber wins!!!

25. The END TERENA: David Williams SURFnet: Kees Neggers
(15 of 14)
The END
Thanks to
TERENA: David Williams
SURFnet: Kees Neggers
UIC&iCAIR: Tom DeFanti, Joel Mambretti
CANARIE: Bill St. Arnaud
Support from:
SURFnet
EU-IST project DATATAG
26/11/ /9/2002