Data replica selector

• US 7,778,183 B2
• Filed: 02/20/2007
• Issued: 08/17/2010
• Est. Priority Date: 03/31/2006
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Liu, Zhen, Halim, Nagui, Fan, Jinliang, Pendarakis, Dimitrios
• Primary Examiner(s): Chou; Albert T
• Application Number:
  US11/676,631
• Publication Number:
  US 20080198752A1
• Time in Patent Office: 1,274 Days
• Field of Search: 370/254, 714/4
• US Class Current: 370/238
• CPC Class Codes: H04Q 3/0079 involving restoration of networks, e.g. disaster recovery, self-healing networks

Abstract

A method is provided for selecting a replication node from eligible nodes in a network. A multidimensional model is constructed that defines a multidimensional space and includes the eligible nodes, with each of the dimensions of the multidimensional model being a system characteristic. A data availability value is determined for each of the eligible nodes, and a cost of deploying is determined for each of at least two availability strategies to the eligible nodes. At least one of the eligible nodes is selected for replication of data that is stored on a source node in the network. The selecting step includes selecting the eligible node whose: data availability value is determined to be highest among the eligible nodes whose cost of deploying does not exceed a specified maximum, or cost of deploying is determined to be lowest among the eligible nodes whose data availability value does not exceed a specified minimum.

Claims

1. A computer-implemented method for selecting at least one replication node from a plurality of eligible nodes in a network, the method comprising the steps of:

constructing a multidimensional model that defines a multidimensional space, the multidimensional model including the eligible nodes, and each of the dimensions of the multidimensional model being a system characteristic;

determining a data availability value for each of the eligible nodes;

determining a cost of deploying each of at least two availability strategies to the eligible nodes; and

selecting, by a processor, at least one of the eligible nodes for replication of data that is stored on a source node in the network,

wherein the selecting step comprises selecting the eligible node whose;

data availability value is determined to be highest among the eligible nodes whose cost of deploying does not exceed a specified maximum cost, or

cost of deploying is determined to be lowest among the eligible nodes whose data availability value does not exceed a specified minimum data availability value.

2. The computer-implemented method according to claim 1, wherein the step of determining a data availability value includes the sub-steps of:

determining a distance value for each of the eligible nodes; and

determining a probability of an independent failure of each of the eligible nodes,

wherein the determination of the data availability value for each of the eligible nodes is based on the determined distance value and the determined probability of an independent failure for that eligible node.

3. The computer-implemented method according to claim 2, wherein the step of determining a data availability value further includes the sub-step of:

determining a probability of a correlated failure for combinations of the eligible nodes,

wherein the determination of the data availability value for each of the eligible nodes is also based on the determined probability of a correlated failure for that eligible node.

4. The computer-implemented method according to claim 1, wherein the eligible nodes comprise geographically distributed data storage entities.

5. The computer-implemented method according to claim 1, wherein the system characteristics comprise at least three of a geographic location, an administrative domain, a hardware type, a hardware version, an operating system type, an operating system version, a network type, and a network service provider.

6. The computer-implemented method according to claim 1, wherein the cost of deploying comprises at least one of a data transfer cost and a hardware cost.

7. The computer-implemented method according to claim 1, further comprising the step of replicating data located on the source node on the at least one eligible node that was selected.

8. A system for replicating data, the system comprising:

a source node storing data;

a plurality of replication nodes each coupled to the source node via a network;

a node selector for selecting at least one of the replication nodes for replication of at least some of the data that is stored on the source node, the node selector including;

a model constructor for constructing a multidimensional model that defines a multidimensional space, the multidimensional model including the replication nodes, and each dimension of the multidimensional model being a system characteristic;

a first determiner for determining a data availability value for each of the replication nodes;

a second determiner for determining a cost of deploying each of at least two availability strategies to the replication nodes; and

a selector for selecting the replication node whose;

data availability value is determined to be highest among the replication nodes whose cost of deploying does not exceed a specified maximum cost, or

cost of deploying is determined to be lowest among the replication nodes whose data availability value does not exceed a specified minimum data availability value.

9. The system according to claim 8, wherein the first determiner determines a distance value for each of the eligible nodes, determines a probability of an independent failure of each of the eligible nodes, and determines the data availability value for each of the eligible nodes based on the determined distance value and the determined probability of an independent failure for that eligible node.

10. The system according to claim 9, wherein the first determiner also determines a probability of a correlated failure for combinations of the eligible nodes, and determines the data availability value for each of the eligible nodes also based on the determined probability of a correlated failure for that eligible node.

11. The system according to claim 8, wherein the system characteristics comprise at least three of a geographic location, an administrative domain, a hardware type, a hardware version, an operating system type, an operating system version, a network type, and a network service provider.

12. The system according to claim 8, wherein the cost of deploying comprises at least one of a data transfer cost and a hardware cost.

13. The system according to claim 8, wherein the source node replicates data stored on the source node on the at least one replication node that was selected.

14. A computer readable storage medium storing a computer program for selecting at least one replication node from a plurality of eligible nodes in a network, the computer program comprising instructions for performing the steps of:

constructing a multidimensional model that defines a multidimensional space, the multidimensional model including the eligible nodes, and each of the dimensions of the multidimensional model being a system characteristic;

determining a data availability value for each of the eligible nodes;

determining a cost of deploying each of at least two availability strategies to the eligible nodes; and

selecting at least one of the eligible nodes for replication of data that is stored on a source node in the network,

wherein the selecting step comprises selecting the eligible node whose;

data availability value is determined to be highest among the eligible nodes whose cost of deploying does not exceed a specified maximum cost, or

cost of deploying is determined to be lowest among the eligible nodes whose data availability value does not exceed a specified minimum data availability value.

15. The computer readable storage medium according to claim 14, wherein the step of determining a data availability value includes the sub-steps of:

determining a distance value for each of the eligible nodes; and

determining a probability of an independent failure of each of the eligible nodes,

wherein the determination of the data availability value for each of the eligible nodes is based on the determined distance value and the determined probability of an independent failure for that eligible node.

16. The computer readable storage medium according to claim 15, wherein the step of determining a data availability value further includes the sub-step of:

determining a probability of a correlated failure for combinations of the eligible nodes,

wherein the determination of the data availability value for each of the eligible nodes is also based on the determined probability of a correlated failure for that eligible node.

17. The computer readable storage medium according to claim 14, wherein the cost of deploying comprises at least one of a data transfer cost and a hardware cost.

18. The computer readable storage medium according to claim 14, wherein the computer program further comprises instructions for performing the step of replicating data located on the source node on the at least one eligible node that was selected.