Transcript ppt

NETWORK
D I S CON TIN U IT IES:
belaboring
the
obvious?
Ron Johnson
University of Washington,
Pacific/NorthWest Gigapop,
PACIFIC LIGHTRAIL
[email protected]
206 543 8252
12/5/01
NETWORK DISCONTINUITIES
Overall Goals
(PACIFIC
L I G H T R A I L ver.)
Bring together leading edge R&D sites,
resources, apparatus and groups in a flexible,
ultra-high performance experimental ip and p2p
wave and fiber based network fabric that can
accelerate: progress in science and medicine;
the development of Grid infrastructure and
bleeding edge applications, architectures and
content; and, the next generations network
technology and networked apparatus etc.
Accelerate progress in science, R&D & econ.
dev. that is leveraged by ultra-high perf. ip &
wave based experimental network fabric linking
key research groups, sites and apparatus.
draft 12/05/01
R&E Network Tiers
LEADERS
NETWORK TYPE
NETWORK DISCONTINUITIES
CAPABILITIES/USERS
Academic Research, papers, lab. Experiments,
spools of fiber In labs
Research
CS, Comp. Science & ‘Grid’ researchers,
Bleeding-edge e2e services & facilities
’s,
+ major experiments (eg DTF) & net.
for key experiments, programs,
P2p fiber,
experimenters + leading edge labs & >=10g ip …
projects, researchers & for next gen.
and centers, optics sys.& net.
tech., architectures, Grids, content,
apparatus, etc. ‘Things that
Industry R&D groups + I-WIRE
Experimental &
Developmental
haven’t been done before; with,
PACIFIC LIGHTRAIL +
Networks
to, on or over networks’.
Internet-2 wave projects;
Computer Science & Net. Researchers
I2-Abilene,
GigaPoPs;
Fed. ‘NGI’ Nets.
Internet-2,
GigaPoPs
I2-K20
Operational High Performance
Research Support Networks
Leading-Edge ip Services
for demanding apps .
& middleware
Common Denominator, Advanced
Services Research & Education Network
ISP’s, hosting
.com’s etc.
Commodity Internet
Advanced
Services for
R&E users
Business,.Gov.
& General Public
12/05/01
NETWORK DISCONTINUITIES
Some Specific Discontinuities/Gaps
Horizontal:
Vertical:
•
•
•
•
•
•
•
•
•
•
•
e2e physical connectivity!
Diversity of Providers
Persistence of key parts over enough time!
Physical Latency & Jitter Constraints
Ultra high performance ‘exchange’ points
Configurability
Measurement
e2e performance
Deterministic Behavior
‘User’ control panels
Repeatability/Predictability
(vs. a shared net with many variables)
• Mismatched Technologies/Architectures
(e.g. framing, channels, OS’s etc.)
• Middleware (app, auth./security, QoS?)
12/5/01
NETWORK DISCONTINUITIES
Some Specific Discontinuities/Gaps cont.
Vertical
cont.:
12/5/01
•
•
•
•
Network aware/adaptive apps.& OS
Expertise/Operations (NOC’s vs. Res. Groups)
AUPs! & Battling AUPs
Isn’t sufficiently responsive/customizable
for some/many experiments, programs,
projects, apparatus
• Hard to explore new techs.
• Doesn’t well support net. experiments
• Interoperability between experimental &
operational general purpose R&E
• Tyranny in success of IP:-) But, will our
current ‘one size fits all’ path work?
• Goals, Plan, Mechanism for persistent core
components & cost effective provisioning of
experimental nets, as and how needed
NETWORK DISCONTINUITIES
Physical
Gaps
•
•
•
•
•
•
•
e2e continuity: ge, 10ge,  … or mix
Last Interfaces
Last Riser, Closet & Horizontal
Building <–> ‘Campus’ hubs
‘local loop(s) ’Campus/Site <-> PoPs
Intra & Inter-regional segments
hardware food chains (packets, waves …)
• high performance exchange points,
‘wire` provisioning techs.

switching,
• Rebuilding the key ‘regional’ elements,
again :-(
(in cases with owned fiber &/or  iru’s)
Recalling what we knew about how hard
this is and what the best paths/hubs are
• Hub/Ring Anchor points + local build out
• For experimental/developmental nets
where/how does it make sense to deploy
12/5/01
Mainly where physical paths/hubs must be! AND
NETWORK DISCONTINUITIES
Where the (reachable) Research is
Top 251 Research Universities in Total, Federal,
Peer Reviewed, Contract and Grant Obligations1
[all > $250 million/yr & top few > $500 million/yr]
btw - LIGHTRAIL has 3 of top 5, half of top 10
(and maybe 6 of 11)
Johns Hopkins (w/APL)
U. of Washington
Stanford
U. of Michigan
UCSD
U. of Pennsylvania
UCLA
MIT
Harvard
UCSF
U. of Colorado (all)
Plus major, reachable
net oriented centers,
labs etc.
Wisconsin
Columbia
Yale
Cornell
Minnesota
Washington U.
Duke
UNC
UCB
Pittsburg
Penn State
USC
Cal. Tech
Illinois
1. Variations in how to count and financial period causes minor variations in order and inclusion at bottom end
2. Obligations lag Awards – the list of Awards is almost identical but numbers are higher
draft 11/12/01
ADDRESSING NETWORK DISCONTINUITIES
Most are locally interconnected,
increasingly with the broadband & even
private waves/fiber needed for e2e
experimental/developmental nets
DTF
Critical Mass Sites
Top 10 Res. Univ.:
Next 15 Res. Univ:
Key Centers, Labs:
Intl. 10gig & 
12/5/01
‘L I G H T RA I L’
Start-up March ‘02
PACIFIC LIGHTRAIL
10 gig. wave/ip base, adding ’s, p2p ’s etc.
- Fiber based local loops to provide e2e waves
- Includes significant dark fiber test segments
- Plan to be 1st to 40 gig. waves
10 gbs
10 gbs
or
Priority PoPs
In Process:
Stop Sought:
Bleeding-Edge e2e Services & facilities for key
researchers & for next gen.: tech., arch., Grids,
content, sensors, apparatus, etc.
draft 12/03/01
ADDRESSING NETWORK
NETWORK DISCONTINUITIES
DISCONTINUITIES
PACIFIC LIGHTRAIL
LONG LINES:
• 10 yr/IRU’s
• Options for more @ discount
• Could buy fiber (nationally)
METRO:
• Owned Fiber Rings/Segs. in
SEA, SF BAY, LA, SD & SAC
P/NWGP-Fairbanks
U. Alaska ARSC etc
Abilene?
R
SEA
P/NWGP
R
S UW
OHSU/OGI?
PDX
R
CENIC ONI
Tier 1 & 2
R
Peerings?
SAC
PROVISIONABLE DEDICATED
p2p WAVES
UCD
Peerings
UCB
EMV
R
R
? Caltech ?
ESTABLISHING KEY PIECES
FOR FLEXIBLE LONG TERM
LOW COST PROVISIONING!
Peerings
R
Stanford
SLAC
UCSF
SLO
SNY
R
UCSB
SB
R
R
LA
UCLA
ANH
ISI
USC
R
or
CHI
NCAR?!
LANL??
R
UCI
SD
SDSC
UCSD
R
DEN
S
10GbE Switch
R
10GbE Router
I-WIRE !!!
NY
NM
OC192c? WAN PHY?
DC
10GbE LAN PHY
draft 12/4/01
ADDRESSING NETWORK DISCONTINUITIES
Get critical mass connected? Cement keys?
•
•
•
•
•
Leverage Regional Connections
Incent fatter/dedicated pipes
Enable significant e2e
Connect Scientists/Labs/Devices
Establish MetaPop Centers
Critical Mass Sites
Top 10 Res. Univ.:
Next 15 Res. Univ:
Centers, Labs:
Intl. 10gig & 
Key Hubs
draft 12/4/01
NETWORK DISCONTINUITIES
What to do?
Program to establish facilities for
responsively provisioning customized and/or
dedicated ‘experimental’ end-to-end
networks [including extended backplanes]
and networking capabilities providing:
1) Custom networks dedicated to serving
specific needs of projects, programs,
experiments and apparatus etc.; and,
2) Networks which are themselves
experimental exercises.
[i.e. be facilities that can provision (& instrument)
any arbitrary networks as needed]
12/5/01
+ Lessons Successes (e.g., ARPAnet, early NSFnet), & ‘Failures’
And, Long Term
Keep the Experimental Networks realm from
sliding down the network development ‘Spiral’
Commercialization
Privatization
Today’s
Internet
Research &
Experimental
Nets
Research and
Development
Source: Ivan Moura Campos
‘NGI’ Operational
R&E efforts
Partnerships
NETWORK DISCONTINUITIES
ULTIMATE GOAL
• So we can deliver networks which
are fully responsive to, and meet the
needs of important applications,
projects, programs and users
and
• Continue to innovate with networks
and network technology in, and with
the same spirit, that brought us the
internet.