Managing storage resources in decentralized networks

• US 20030187973A1
• Filed: 03/27/2002
• Published: 10/02/2003
• Est. Priority Date: 03/27/2002
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wesley, Ajamu A.
• Granted Patent: US 7,251,689 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 61/00 Network arrangements, protocols or services for addressing or naming
• CPC Class Codes: H04L 61/45 Network directories; Name-to-address mapping
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/104 Peer-to-peer [P2P] networks
• CPC Class Codes: H04L 67/1044 Group management mechanisms management of multicast group membership H04L12/185; reconfiguring of node membership in a computing system to eliminate errors G06F11/1425
• CPC Class Codes: H04L 67/1046 Joining mechanisms
• CPC Class Codes: H04L 67/1048 Departure or maintenance mechanisms
• CPC Class Codes: H04L 67/1068 Discovery involving direct consultation or announcement among potential requesting and potential source peers
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

Methods, systems, and computer program products are disclosed for managing storage resources in decentralized networks. Persistent identifiers are defined for nodes, allowing nodes to be identified across sessions and invocations, even though they re-enter the network with a different network address. Paths taken by content resources as they traverse the network (e.g. which nodes forwarded the content) are persisted, along with reputation information about nodes (e.g. indicating how successful they are at answering queries from peers). Trust relationships can be derived using the persisted information. A tiered broadcast strategy is defined for reducing the number of messages exchanged. Preferred embodiments leverage a web services implementation model.

Claims

1. A method of managing storage resources in a decentralized network, comprising steps of:

associating a persistent node identifier with each node in the network, even though a current network address assigned to the node upon entering the network may vary from one entry to another;

dynamically evaluating behavior of a plurality of storage nodes, wherein the storage nodes are those nodes providing on-demand storage resources;

maintaining on-going knowledge of the dynamically evaluated behavior of the storage nodes by resolving an identity of each of the storage nodes using a mapping that correlates the current network address of each node in the network to its associated persistent node identifier; and

using the maintained knowledge to manage the storage resources of the storage nodes.

2. The method according to claim 1, wherein the dynamically evaluated behavior of each of the storage nodes comprises how efficient that storage node is at handling storage requests.

3. The method according to claim 1, wherein the dynamically evaluated behavior of each of the storage nodes comprises how well that storage node responds to storage requests.

4. The method according to claim 3, wherein how well the storage node responds to storage requests represents currently-available storage capacity of its storage resources.

5. The method according to claim 1, wherein the dynamically evaluated behavior of each of the storage nodes comprises a success measure indicating whether that storage node responded to prior storage requests satisfactorily.

6. The method according to claim 1, wherein the dynamically evaluated behavior of each of the storage nodes comprises a specification of content that is currently available from that storage node.

7. The method according to claim 1, further comprising the steps of:

determining, by one of the nodes in the network, that it needs storage resources; and

using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes currently able to provide the needed storage resources.

8. The method according to claim 4, further comprising the steps of:

determining, by a storage-needing node, that it needs to store content in storage resources; and

using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes whose storage resources have sufficient currently-available storage capacity for storing the content for the storage-needing node.

9. The method according to claim 8, further comprising the step of issuing to the selected storage node, by the storage-needing node, a request for storing the content.

10. The method according to claim 2, further comprising the steps of:

determining, by one of the nodes in the network, that it needs storage resources; and

using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes which can efficiently provide the needed storage resources.

11. The method according to claim 5, further comprising the steps of:

determining, by one of the nodes in the network, that it needs storage resources; and

using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes which has a relatively high success measure for responding to prior storage requests satisfactorily.

12. The method according to claim 6, further comprising the steps of:

determining, by a content-needing node, that it needs to retrieve content from storage resources; and

using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes whose specification of currently available content includes the content that the content-needing node needs to retrieve.

13. The method according to claim 1, wherein the network is a peer-to-peer network.

14. A system for managing storage resources in an ad hoc network, comprising:

means for associating a persistent node identifier with each node in the network, even though a current network address assigned to the node upon entering the network may vary from one entry to another;

means for maintaining on-going knowledge of dynamically evaluated behavior of a plurality of storage nodes, wherein the storage nodes are those nodes providing on-demand storage resources, by resolving an identity of each of the storage nodes using a mapping that correlates the current network address of each node in the network to its associated persistent node identifier; and

means for using the maintained knowledge to manage the storage resources of the storage nodes.

15. The system according to claim 14, wherein the dynamically evaluated behavior of each of the storage nodes comprises how efficient that storage node is at handling storage requests and wherein the means for using the maintained knowledge further comprises:

means for determining, by one of the nodes in the network, that it needs storage resources; and

means for using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes which can efficiently provide the needed storage resources.

16. The method according to claim 14, wherein the dynamically evaluated behavior of each of the storage nodes comprises currently-available storage capacity of its storage resources and wherein the means for using the maintained knowledge further comprises:

means for determining, by one of the nodes in the network, that it needs to store content in storage resources; and

means for using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes whose storage resources have sufficient currently-available storage capacity for storing the content.

17. The system according to claim 16, further comprising means for issuing a request for storing the content to the selected storage node.

18. A computer program product for managing storage resources in an ad hoc network, where a collection of nodes making up the network may change over time, the computer program product embodied on one or more computer-readable media and comprising:

computer-readable program code means for associating a persistent node identifier with each node in the network, even though a current network address assigned to the node upon entering the network may vary from one entry to another;

computer-readable program code means for maintaining on-going knowledge of dynamically evaluated behavior of a plurality of storage nodes, wherein the storage nodes are those nodes providing on-demand storage resources, by resolving an identity of each of the storage nodes using a mapping that correlates the current network address of each node in the network to its associated persistent node identifier; and

computer-readable program code means for using the maintained knowledge to manage the storage resources of the storage nodes.

19. The computer program product according to claim 18, wherein the dynamically evaluated behavior of each of the storage nodes comprises a success measure indicating whether that storage node responded to prior storage requests satisfactorily and wherein the computer-readable program code means for using the maintained knowledge further comprises:

computer-readable program code means for determining, by one of the nodes in the network, that it needs storage resources; and

computer-readable program code means for using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes which has a relatively high success measure for responding to prior storage requests satisfactorily.

20. The computer program product according to claim 18, wherein the dynamically evaluated behavior of each of the storage nodes comprises a specification of content that is currently available from that storage node and wherein the computer-readable program code means for using the maintained knowledge further comprises:

computer-readable program code means for determining, by a content-needing node, that it needs to retrieve content from storage resources; and

computer-readable program code means for using the on-going knowledge of the behavior of the storage nodes to select one of the storage nodes whose specification of currently available content includes the content that the content-needing node needs to retrieve.