Understanding Peer-level Performance in BitTorrent: A Measurement Study

1
Understanding Peer-level Performance in
BitTorrent A Measurement Study

• Amir Rasti
• Reza Rejaie

Dept. of Computer Science University of Oregon
2
Introduction

• Peer-to-peer systems have become increasingly
  popular
• Millions of simultaneous users
• Significant percentage of Internet traffic
• is one of the most popular
  p2p applications
• Responsible for 35 of all Internet traffic
  Parker05
• BitTorrent is important because
• Popularity
• Its impact on the network

3
BitTorrent A brief overview
Introduction

• Scalable one to many peer-to-peer file
  distribution
• Overlay Unstructured, Random, High degree
• Swarming
• File is divided into segments
• Segments are randomly distributed among peers
  Get rarest seg. first
• Contribution
• Peers exchange segments and contribute their
  outgoing bandwidth
• Incentive Tit-for-Tat
• Tracker
• Torrent coordinator
• Periodic peer status updates
• Performance Intuitively depends on
• Peer properties (BW, Contribution, etc. )
• Group properties (Population, Content
  availability, Churn)

4
Previous Studies on BitTorrent
Related work

• Modeling and analytical studies
• Simulation studies
• Empirical studies
• Capture BitTorrent system properties in operation
  through measurement (instrumented
  clients)Legout06
• Group propertiesIzal04 Population, Average
  cont. avail., ..
• No explicit notion of performance
• No study on the effects of underlying factors of
  peer performance

• Characterization
• Understanding group-level and peer-level
  properties in a torrent
• Analysis
• What are the main factors that affect observed
  performance by individual peers?

5
Methodology
Methodology/Approach

• Common approach Instrumented clients
• Detailed and flexible
• Representative?
• Our approach Tracker logs
• Coarse granularity(30 min)
• Global view
• Data Sets

Source Torrents Start Date End Date Reports Sessions
RedHat 1 3/03 8/03 2M 170k
Debian 1599 2/05 3/05 32M 1268k
Games 2585 8/03 12/04 38M 4416k
Torrent File Size Sessions, rank Duration
RedHat 1.8GB 170k, 3rd 146d
Debian 677MB 139k, 6th 51d
Games 363MB 195k, 2th 66d
Tracker logs sets
Selected Torrents
6
Peer-level properties
Methodology

• Session
• Set of all updates from a particular peer from
  its arrival till departure
• Peer-level properties
• Represent the peers status during a session
• Average download rate
• Average upload rate

Download Complete
Session Start
Avg download rate
Slope upload rate
Slopes upload rates
Download rate
Download rates
Studied zone(leeching)
7
Group-level properties
Measurement methodology

• Population, Avg. Content Availability, Churn
• Sampling approach
• Once every t minutes
• Last update before and first update after each
  sample
• Interpolation
• Averaging across peers
• t determines sampling resolution
• t gt average update interval
• Peer view
• Average of the samples during peers download time

Update Time
t
8
Performance metrics
Methodology

• Is Download Rate a good performance metric ?
• A reference is needed to evaluate peers download
  rate
• Ideally peer performance is
• Accurate measurement of Utilization is difficult
• We use maximum observed download rate as a
  (lower bound) estimate for incoming bandwidth.
• Standard deviation of download rate captures
  stability of download rate
• Rates close to avg. ? higher performance
• Normalization ? comparability
• Two performance metrics

9
Distribution of Performance Metrics
Characterization Results/Peer-Properties

• Similar distribution across 3 different torrents
• Utilization has an almost uniform distribution
• Nearly Fixed probability density
• 90 show closely uniform distribution
• Diverse performance
• No dominant modes

10
Peer-View of Group Properties
Characterization Results/Peer-view of group
properties

• Content availability
• 75 of peers in RH observe an average cont.
  avail. of 50
• No content shortage
• Avg. Population
• Very different
• Flash crowd in RH

Initial flash crowd
11
Underlying factors

• Remember the second questions
• What are the peer- or group-level properties that
  primarily determine the observed performance by
  individual peers in a torrent?
• Performance metrics
• Utilization and Stability
• Possible Underlying factors
• Group-level properties Population, Churn ,
  Content avail.
• Peer-level properties Upload rate, etc.
• Approach To Identify Underlying factors
• Scatter-plot
• Linear Regression (Using S-plus)
• Spearmans rank correlation (S-Plus)

12
Scatterplots
Statistical Analysis/Scatter-plots

• Utilization vs. Average group content
  availability
• No obvious correlation
• Utilization vs. Average group population
• Vertical patterns
• No obvious correlation

13
Sample Regression Result Utilization in RedHat
torrent
Statistical Analysis/Linear Regression

• Several values to consider
• R-Squared determines goodness of fit 01
• P-value determines Probability of obtaining a
  result as impressive just by chance

• Suggested techniques result in marginal
  improvement (R-squared)
• No single parameter with dominant effect
• Seed percentage was removed by step() ? suggests
  number of seeds is sufficient

14
Spearmans rank correlation coefficients
Statistical Analysis/Spearmans Rank correlation

• Highest correlation with deviation of upload rate
  for all torrents -gt Tit-for-tat effect
• Two perf. metrics are similarly affected with
  opposite signs
• GA Little correlation with util. -gt unreliable
  metric
• DE Slightly larger effect from content avail.

15
Conclusion and Future Work

• Conclusions
• No single factor determines observed performance
  by peers
• Outgoing bandwidth seems to have the largest
  effect
• Tit-for-tat is working
• There often appears to be sufficient number of
  seeds available (non-factor on performance)
• Capturing comparable performance is hard
• Performance of the peers in a torrent is rather
  diverse
• Instrumented clients cannot reflect a
  representative picture.
• Future work
• Active monitoring of BitTorrent
• BitTorrent overlay topology using peer exchange
  feature
• Characterizing new features
• DHT, super-seeding, peer exchange

16
Thank you !