Comparing Hybrid PeerPeer Systems

1
Comparing Hybrid Peer-Peer Systems

• Beverly Yang
• Hector Garcia-Molina
• Stanford University
• Presented by Kalyan Boggavarapu

2
Different Modals 1
3
Hybrid modal1
4
Query model 1 f query selection power g
query popularity Correlate f and g with
exponential distribution

• Eg Napster
• Currently we study OpenNap
• New issues IR in P2P, co-operative web caching
• Modeling peer-peer systems 1
• Query modeling,
• performance modeling,
• validation with real data OpenNap

5
Architecture
Experimentation Hybrid architecture, OpenNap

• Logins batch incremental
• Types of architecture (partly 1)
• Chained forward a query
• Large and diverse data not many servers.
• Dis expensive if many servers have to satisfy
  the query
• Full replication make a copy of indexes on
  every server.
• Dis login information must be sent to every
  server
• Hash holds subset of index of words
• Bandwidth consumption would be more.
• Unchained- Napster
• High data redundancy, Many servers
• Dis restricted access to files, they cannot see
  the user files in other systems.

Query model assumption 1 Most popular query
has the largest selection power.

• Assumptions for the experiment 1
• Servers are connected via LAN
• Users and servers are connected via same LAN
  network

6
Comparing P2P systems

• Conclusions 1
• Incremental login scales better than batch login
  
• Unchained architecture results in lower number
  of
• results returned
• Hash architecture is resource intensive
• Full replication works well when result sets are
• large
• Chained architecture is well-suited for
  music-sharing,
• but suffers from poor query performance

References 1 http//db.uwaterloo.ca/tozsu/cour
ses/cs856/presentations/jinxiao.pdf
7
(No Transcript)