Академический Документы
Профессиональный Документы
Культура Документы
Distribution Networks:
Techniques and Challenges
Pei Cao
Stanford University
Traditional Intra-Provider
Content Distribution Networks
National Center
Regional Center
. . .
Branch
Users
...
...
...
...
...
...
Peer-to-Peer Content
Distribution
National Center
Regional Center
. . .
Branch
Users
...
...
...
...
...
...
P2P vs CDN
P2P:
No infrastructure cost
Supply grows linearly with demand
Simple distributed, randomized algorithms
No QoS
CDN:
Outline
Review of BitTorrent
Traffic-shaping BitTorrent: biased
neighbor selection
QoS in BitTorrent: delivery time
prediction
BitTorrent: Neighbor
Selection
Tracker
file.torrent
Seed 1
Whole file
4
3
Tracker
file.torrent
3
5
Analysis of BitTorrent
Conclusion from modeling studies:
BitTorrent is nearly optimal in
idealized, homogeneous networks
Traffic-Shaping BitTorrent
P2P Applications:
No knowledge of underlying ISP topology
Use randomized algorithms that dont do
well under clustering
A Network-Friendly
BitTorrent?
ISPs inform BitTorrent of its link
preferences
Algorithm of BitTorrent is adjusted
such that both users and ISPs benefit
Evaluation Methodology
Event-driven simulator
Use actual client and tracker codes as much as
possible
Calculate bandwidth contention, assume perfect fairshare from TCP
Network settings
14 ISPs, each with 50 peers, 100Kb/s upload, 1Mb/s
download
Seed node, 400Kb/s upload
Optional university nodes (1Mb/s upload)
Optional ISP bottleneck to other ISPs
Limitation of Throttling
Importance of Rarest-First
Replication
Random piece replication performs
badly
Conclusions
By choosing neighbors well, BitTorrent
can achieve high peer performance
without increasing ISP cost
Motivation
Provide delivery time guarantee under
P2P+CDN
What contributes to delivery time of a
download via BitTorrent?
From simulations: seed bandwidth and
even replication of blocks
Missing: node join/leave dynamics, TCP
effects, etc.
Side-by-Side Live
Experiments
Two clients, running on the same
Close Neighbors
90% of data downloaded from 1-4%
of neighbors
Let F(p) and G(p) be the number of
neighbors that provides p of data to
peers F and G, then
F(p) > G(p) peer F is slower than G
This holds for p = 90%, 75%, and 50%
A: Random disconnect
B: Finished downloading
C: Peer broke off the relationship
D: Neighbor broke off the relationship
Conclusions
Content delivery time in BitTorrent is
determined by:
delivery time
Neighbors may leave due to random
disconnection, completion of download, or
finding faster neighbors
Summary
A way to shape BitTorrent traffic
Predicting BitTorrent performance by
monitoring close peer relationship
Related Work
Many modeling studies of BitTorrent
Simulation studies
Measurements of real torrents
Ongoing Work
Live experiments with biased
neighbor selections
A k-regular graph algorithm with
faster convergence
Prototype implementation of
P2P+CDN