136 |
lookup substantially. The above enhancment cannot be implemented in a natural way in any of the well-known DHTs |
lookup substantially. The above enhancment cannot be implemented in a natural way in any of the well-known DHTs |
137 |
(distributed hash tables) such as Chord, Pastry, Tapestry, etc. since the design of their routing tables allows |
(distributed hash tables) such as Chord, Pastry, Tapestry, etc. since the design of their routing tables allows |
138 |
for no such flexibility, and hence they would require additional data structures to accommodate temporary contacts. |
for no such flexibility, and hence they would require additional data structures to accommodate temporary contacts. |
139 |
|
|
140 |
|
2.6 Coral |
141 |
|
Coral is a peer-to-peer content distribution system that creates self-organizing clusters of nodes that fetch |
142 |
|
information from each other to avoid communicating with more distant or heavily-loaded servers. Coral is |
143 |
|
designed to index local data, such as the files in a node's web cache, to ensure that content is replicated |
144 |
|
exactly in proportion to its use. Coral uses two novel mechanisms to achieve scalability and high performance. |
145 |
|
First, a new abstraction called a distributed sloppy hash table (DSHT) lets nodes locate nearby copies of a |
146 |
|
file without causing hot spots, regardless of its popularity. Second, based on the DSHT interface, a |
147 |
|
decentralized clustering algorithm allows nodes to can find each other and form clusters of varying network |
148 |
|
diameters. |
149 |
|
|
150 |
|
Efficient peer-to-peer lookup based on distributed tries. |
151 |
|
|
152 |
|
hemppah: This is very interesting approach (tuomasl et all, comments ?) |
153 |
|
|
154 |
|
|
155 |
|
|