A Peer-to-Peer Inverted Index Implementation for Word-based Content - - PowerPoint PPT Presentation

A Peer-to-Peer Inverted Index Implementation for Word-based Content Search

Nuno Lopes University of Minho October 2003

P2P System Characterization

• Scalable up to millions of nodes
• Highly dynamic node membership
• Reduced node uptime: 1 hour on average
• No centralized authority

c

2003 Nuno Lopes

1 SDDI 2003

1st Generation of P2P Systems File Sharing Oriented

• Napster

Centralized search with p2p file download

⇒ Single point-of-failure

• Gnutella

Broadcast based search

⇒ Network overloaded

c

2003 Nuno Lopes

2 SDDI 2003

Searching Model

• Local model

Individual peer search Examples: Gnutella, Pedone’02

• Global model

Information is placed on a global (distributed) shared index

c

2003 Nuno Lopes

3 SDDI 2003

2nd Generation of P2P Systems Distributed Hash Table (DHT) Based

• Examples: Chord, Pastry, others...
• Simple hash table operations on (key,value) pairs
• Efficient routing: O(log N) hops for any peer
• Scalable state information: O(log N) routing entries

per peer

• But... incapable of searching

c

2003 Nuno Lopes

4 SDDI 2003

Inverted Index Description

• Association word → {document location}SET
• Document Location Set is highly dynamic
• Follows Zipf distribution

100 200 300 400 500 600 700 5000 10000 15000 20000 25000 30000 35000 # Documents Words

c

2003 Nuno Lopes

5 SDDI 2003

Inverted Index API

• INSERT(word, reference)
• REMOVE(word, reference)
• HAS REF(word, reference): bool
• GET REF(word): reference
• NEXT REF(word, reference): reference

c

2003 Nuno Lopes

6 SDDI 2003

Inverted Index Implementation

Index is splited in constant size blocks, accessed through 2 layers:

• DHT as base platform for block-oriented storage

⇒ Unsuitable as a stand-alone implementation

• B+ tree for block management

Responsible for the set implementation to each word

c

2003 Nuno Lopes

7 SDDI 2003

Current Simulation Settings

• Only the B+ tree layer is simulated
• Peers store a single block each
• Messages have an atomic cost
• Single client requests index operations on the system
• Data consists on 1000 small documents with 36499

unique words

c

2003 Nuno Lopes

8 SDDI 2003

Initial Simulation Results

• B+ trees make the storage load uniform across peers
• However... root blocks for popular words have high

network load

100 200 300 400 500 600 700 800 10000 20000 30000 40000 50000 60000 Access rate Blocks

c

2003 Nuno Lopes

9 SDDI 2003

Caching Mechanism

• Clients have high probability of requesting the same

blocks for popular words

• Caching of (non-leaf) blocks reduces the number of

accesses

• In order to avoid stale copies, leaf blocks are never

cached

• Higher level blocks are less probable to become

modified and therefore stale

c

2003 Nuno Lopes

10 SDDI 2003

Simulation Results (Using Cache)

• The use of a cache mechanism (LRU) distributes

more evenly the network load on peers

• Access rates were reduced by a factor of 10

10 20 30 40 50 60 10000 20000 30000 40000 50000 60000 Access rate Blocks

c

2003 Nuno Lopes

11 SDDI 2003

Open Questions

• Measurement of DHT as stand-alone implementation
• f inverted index
• Analysis of the block caching mechanism to determine

the best cache size for different numbers of peers on the system

• Implementation of multiple blocks to peer association

for studying effective peer load

• AND and OR search operators implementation and

load measurement

c

2003 Nuno Lopes

12 SDDI 2003