Recipient-centred proactive caching in a peer-to-peer system

• US 20050120133A1
• Filed: 11/22/2004
• Published: 06/02/2005
• Est. Priority Date: 11/28/2003
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Slack-Smith, David Geoffrey
• Granted Patent: US 7,627,644 B2
• Time in Patent Office: Days
• US Class Current: 709/234
• CPC Class Codes: G06F 12/0862 with prefetch
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

A method (100) of caching data is disclosed. The method (100) optimises proactive caching of data by estimating future demand for particular data within a computer system (1900). The computer system (1900) is typically configured in accordance with the hybrid peer-to-peer model. The method (100) maintains the bandwidth cost of proactive caching in proportion to expected demand for particular data. The method (100) also determines the availabiliy of a peer. The availability of a peer is defined herein as the probability of a peer being online, for example, when particular data is required by another peer.

Claims

1. A method of caching data over a network, said method comprising the steps of:

estimating demand for said data from one or more peers connected to said network;

estimating transmission capacity of at least one of said peers;

selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

processing at least a portion of said data or further data associated with one or more of the selected peers in order to enable at least said portion of data to be cached over said network.

2. A method according to claim 1, wherein said processing comprises the step of caching at least said portion of data on one or more of the selected peers.

3. A method according to claim 1, wherein said processing comprises the step of deleting at least a portion of said further data from at least one of the selected peers if said transmission capacity is greater than said demand.

4. A method according to claim 1, wherein the estimating transmission capacity step comprises the step of determining availability of one or more of said peers.

5. A method according to claim 1, wherein the estimating transmission capacity step comprises the step of determining bandwidth available to one or more of said peers.

6. A method according to claim 1, wherein the estimating demand step comprises the step of determining desirability of data originating from one or more of said peers.

7. A method according to claim 1, wherein the estimates of any one or more of demand, capacity and desirability are executed on a central server connected to said network.

8. A method according to claim 1, further comprising the step of estimating supply of at least said one portion of data over one or more of said peers.

9. A method according to claim 8, wherein the supply estimate is subtracted from said demand prior to selection of said one or more peers.

10. A method according to claim 1, further comprising the step of selecting a subset of the peers connected to said network based on which of said peers are online when an amount of necessary capacity is at a maximum.

11. A method according to claim 10, wherein the selecting peers step comprises the step of assigning a weight to each peer in said subset.

12. A method of caching data over a network, said method comprising the steps of:

estimating demand for said data from one or more peers connected to said network;

estimating transmission capacity of each of said peers;

selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

instructing one or more of the selected peers to cache at least a portion of said data.

13. A method according to claim 12, further comprising the step of deleting at least a portion of further data from at least one of the selected peers if said transmission capacity is greater than said demand.

14. A method according to claim 12, wherein the estimates of any one or more of demand, capacity and desirability are executed on a central server connected to said network.

15. A method according to claim 12, further comprising the step of estimating supply of at least said one portion of data over one or more of said peers.

16. A method according to claim 12, wherein the supply estimate is subtracted from said demand before the selection of said one or more peers.

17. A method of downloading data over a network from one or more peers connected to said network, said method comprising the step of:

selecting a subset of said peers based on which of said peers are available at a particular time, each peer of said subset containing at least a portion of said data stored thereon;

assigning a weight to each of the peers of said subset depending on bandwidth available to each of the peers of said subset; and

downloading said data at said particular time, from at least a particular one of the peers of said subset, depending on the weight assigned to said particular peer.

18. A method according to claim 17, wherein the weight assigned to a selected peer is dependent upon a bandwidth available to the selected peer.

19. An apparatus for caching data over a network, said apparatus comprising:

demand estimation means for estimating demand for said data from one or more peers connected to said network;

transmission capacity estimation means for estimating transmission capacity of each of said peers;

peer selection means for selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

data processor means for processing at least a portion of said data or further data associated with one or more of the selected peers in order to enable at least said portion of data to be cached over said network.

20. An apparatus for caching data over a network, said apparatus comprising:

demand estimation means for estimating demand for said data from one or more peers connected to said network;

transmission capacity estimation means for estimating transmission capacity of each of said peers;

peer selection means for selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

instructing means for instructing one or more of the selected peers to cache at least a portion of said data.

21. An apparatus for downloading data over a network from one or more peers connected to said network, said apparatus comprising:

peer selection means for selecting a subset of said peers based on which of said peers are available at a particular time, each peer of said subset containing at least a portion of said data stored thereon;

weight assignment means for assigning a weight to each of the peers of said subset depending on bandwidth available to each of the peers of said subset; and

downloading means for downloading said data at said particular time, from at least a particular one of the peers of said subset, depending on the weight assigned to said particular peer.

22. A computer program for caching data over a network, said program comprising:

code for estimating demand for said data from one or more peers connected to said network;

code for estimating transmission capacity of each of said peers;

code for selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

code for processing at least a portion of said data or further data associated with one or more of the selected peers in order to enable at least said portion of data to be cached over said network.

23. A computer program for caching data over a network, said program comprising:

code for estimating demand for said data from one or more peers connected to said network;

code for estimating transmission capacity of each of said peers;

code for selecting one or more of said peers, based on the estimated transmission capacity of each of said peers, in order to meet said demand; and

code for instructing one or more of the selected peers to each at least a portion of said data.

24. A computer program for downloading data over a network from one or more peers connected to said network, said program comprising:

code of selecting a subset of said peers based on which of said peers are available at a particular time, each peer of said subset containing at least a portion of said data stored thereon;

code for assigning a weight to each of the peers of said subset depending on bandwidth available to each of the peers of said subset; and

code for downloading said data at said particular time, from at least a particular one of the peers of said subset, depending on the weight assigned to said particular peer.