THE BITTORRENT P2P FILESHARING SYSTEM: MEASUREMENTS AND ANALYSIS

1
THE BITTORRENT P2P FILE-SHARING SYSTEM
MEASUREMENTS AND ANALYSIS

• Chen Ming
• 4/8/2005

2
Outline

• Why Bit Torrent?
• Brief introduction to BT
• Methodology
• Observations
• Free Discussion

3
Why Bit Torrent?

• Bit-Torrent is one of the few that has managed to
  attract millions of users
• Measurements on Internet backbones indicate that
  BitTorrent has evolved into one of the most
  popular networks
• BitTorrent traffic made up 53 of all P2P
  traffic in June 2004

4
Brief introduction to BT

• Web Server
• .Torrent Files Server
• Tracker Server
• Seeds
• Peers

5
Brief introduction to BT
6
Brief introduction to BT
7
Methodology

• Measurement software
• Monitoring the global Bit-Torrent/Suprnova
  components
• Mirror script which measures the availability and
  response time of the Suprnova mirrors
• HTML script which gathers and parses the HTML
  pages of the Suprnova mirrors and downloads all
  new .torrent files
• Tracker script which parses the .torrent files
  for new trackers and checks the status of all
  trackers
• Monitoring actual peers
• Hunt script selects a file to follow and
  initiates a measurement of all the peers
  downloading this particular file
• Getpeer script contacts the tracker for a given
  file and gathers the IP addresses of peers
  downloading the file
• Peerping script contacts numerous peers in
  parallel and (ab)uses the BitTorrent protocol to
  measure their download progress and uptime

8
Methodology

• Measurement objects

9
Observations

• Overall System Activity
• Availability
• Integrity
• Flashcrowds
• Download Performance
• Lifetime

10
Observations

• Overall System Activity

11
Observations

• Overall System Activity notices
• Daily cycle the minimum and maximum (at around
  2300 GMT) number of downloads occur at roughly
  the same time each day
• Large variation due to failures of either the
  mirroring system across the Suprnova mirrors, of
  the mirrors themselves, of the .torrent servers,
  or of the trackers
• The number of active users in the system is
  strongly influenced by the availability of the
  global components in BitTorrent/Suprnova.

12
Observations

• Availability

13
Observations

• Availability

14
Observations

• Integrity

15
Observations

• Flashcrowds

16
Observations

• Download Performance

17
Observations

• Lifetime

18
Free Discussion

• A tension exists between availability, which is
  improved when there are no global components, and
  data integrity, which benefits from
  centralization.