Transcript P4P Working Group

P4P Working
Group
Doug Pasko, Co-Chair, Verizon
Laird Popkin, Co-Chair, Pando
Haiyong Xie, Principle P4P Researcher,
LANS, Yale
P4P Mission Statement
To work jointly and cooperatively with leading
Internet service providers (ISPs), peer-to-peer
(P2P) software distributors, and technology
researchers to ascertain appropriate and voluntary
best practices to accelerate distribution of content
and optimize utilization of ISP network resources in
order to provide the best possible performance to
end-user customers
60+ P4P WG Members
Core
Group
AT&T
Bezeq Intl
BitTorrent
Cisco Systems
Comcast
Grid Networks
Joost
LimeWire
Manatt
Oversi
Pando Networks
PeerApp
Solid State
Telefonica Group
Velocix
VeriSign
Verizon
Vuze
University of
Toronto
Univ of
Washington
Yale University
Observers
Abacast
AHT Intl
AjauntySlant
Akamai
Alcatel Lucent
CableLabs
Cablevision
Cox Comm
Exa Networks
Juniper Networks
Lariat Network
Level 3 Communications
Limelight Networks
Microsoft
MPAA
NBC Universal
Nokia
Orange
Princeton University
RawFlow
RSUC/GweepNet
SaskTel
Solana Networks
Speakeasy Network
Stanford University
Thomson
Time Warner Cable
Turner Broadcasting
UCLA
P4P Enables Efficient Delivery
Traditional CDN
P2P
P2P with P4P
Internet Transit
Regional Routers
Edge Network
More Viewers =
Worse performance
Higher cost
More Viewers =
Better performance
Lower cost
Network Aware P2P will reduce costs, improve performance
8
P4P: Architecture
pTracker
Use BitTorrent in a single ISP as
an example
iTracker
2
pTracker runs P2P system
iTracker makes suggestions for
peering relationships
3
1
4
Information flow:
ISP A
1.
peer queries pTracker
2.
pTracker asks iTracker for guidance
(occasionally)
3.
iTracker returns high-level peering
suggestions
4.
pTracker selects and returns a set of
active peers, according to the
peer
suggestions
10
Network Map (Illustration)
30%
PID 70%
1
PID
6
PID
2
10%
PID 60%
5
PID
4
20%
PID
3
Each PID has:
•IP “prefix”
•Uplink/Downlink Capacity
•Links (with weights)
Links weights are directional.
Weight Matrix (Illustration)
Are connected to users in these PID’s
PID1
PID1
Users PID2
PID3
in
PID’s PID4
PID5
PID6
30%
30%
7%
4%
30%
PID2
30%
50%
10%
6%
25%
PID3
10%
20%
2%
1%
5%
PID4
5%
10%
5%
60%
2%
PID5
3%
6%
3%
60%
1%
PID6
20%
10%
7%
3%
1%
Dispelling Myths of P4P
P4P Test Methodology
Simulations by Yale on data from AT&T,
Telefonica, Verizon
Field Test by Telefonica, Verizon, Yale and
Pando.
P4P Architecture (for test)
ISP
P2P
Tracker
iTracker
Telefonica
Weight Matrix
Network
Maps
Yale
Peer Loc’s
Pando
Verizon
iTracker is intermediary between ISP’s
and P2P’s
Can be operated by ISP’s
Can be operated by third parties
P2P
Clients
P4P Test Results
Haiyong
P4P Test Results
FTTH 209% faster
Non-FTTH 20% faster
Slide 18 | Pando Confidential
12
Implications for ISP’s and P2P’s
Laird Popkin
Doug Pasko
Field Tests
Multi-ISP Field Test in June
Additional P2P Company Field Tests
following shortly
Sub-Groups
Caching
Telco
Cable
Hardware
Standards
Research
Live P2P
Wireless
IP Policy/Guidelines
Questions?
Interested?
P4P WG is free to join.
Monthly phone calls
Email List
For more info, email Martin Lafferty:
[email protected]
or [email protected]
or [email protected]
15