Grid computing space

• US 8,793,327 B2
• Filed: 08/30/2007
• Issued: 07/29/2014
• Est. Priority Date: 08/30/2007
• Status: Active Grant

• Current Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Original Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Inventors: Surtani, Manik Ram
• Primary Examiner(s): SCOTT, RANDY A
• Application Number:
  US11/897,749
• Publication Number:
  US 20090063653A1
• Time in Patent Office: 2,525 Days
• Field of Search: 709/213, 709/214, 709/215, 709/216, 709/223, 715/734, 711/126, 711/141
• US Class Current: 709/213
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/563 Data redirection of data network streams
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A method and apparatus for using a tree-structured cluster as a library for a computing grid. In one embodiment, a request for computation is received at a cache node of the cluster. The computation requires data from an other cache node of the cluster, and not present in the cache node receiving the request. The other cache nodes of the cluster are polled for the required data. An instance of the required data stored in the other cache node of the cluster is replicated to the cache node receiving the computation request.

Claims

1. A method comprising:

receiving, by a processing device, a request for computation at a cache node of a cluster, the computation requiring first data from a different cache node of the cluster, wherein each cache node of the cluster stores second data associated with the respective cache node and a copy of the second data is not stored in the different cache node, wherein a pool of cache nodes is formed in the cluster;

polling, by the processing device, a plurality of the different cache nodes of the cluster for the first data; and

replicating, by the processing device, an instance of the first data stored in the different cache node of the pool to the cache node of the pool receiving the computation request, wherein the cache node of the pool receiving the request is associated with the different cache node.

2. The method of claim 1 further comprising:

storing the first data in the cache node;

processing the request for computation at the cache node receiving the computation request using the stored first data;

determining whether a need still exists for the first data stored in the cache node receiving the computation request after the computation; and

deleting the first data stored in the cache node receiving the computation request upon determining that no need exists for the first data stored in the cache node receiving the computation request and that the first data is also stored in the at least one of the different cache nodes associated with the cache node of the cluster.

3. The method of claim 1 wherein receiving the request for computation further comprises:

receiving a query for the first data in the cache node of the cluster;

determining whether the first data is stored in the queried cache node;

inquiring the different cache nodes in the cluster for the first data; and

replicating an instance of the first data from a cache node storing the first data to the queried cache node.

4. The method of claim 3 wherein inquiring the different cache nodes in the cluster for the first data further comprises:

inquiring a data backup of each of the cache nodes in the cluster.

5. The method of claim 3 further comprising:

deleting the instance of the first data from the cache node storing the first data after the instance of the first data has been copied to the queried cache node.

6. The method of claim 3 further comprising:

inquiring the different cache nodes upon determining that the first data is not stored in the queried cache node.

7. The method of claim 3 further comprising:

inquiring the different cache nodes based on a per-invocation basis.

8. The method of claim 3 wherein the cluster comprises a plurality of cache nodes, each cache node selecting at least one of the different cache nodes as a backup.

9. The method of claim 3 wherein the cache nodes are located on different physical hosts.

10. The method of claim 3 wherein the cache nodes are located on different physical racks.

11. The method of claim 1 wherein the cache nodes from the pool are located on different physical racks.

12. A system comprising:

a memory to include instructions; and

a processing device, connected with the memory, to execute the instructions, wherein the instructions cause the processing device to;

receive a request for computation at a cache node of a cluster, the computation requiring first data from a different cache node of the cluster, wherein each cache node of the cluster stores second data associated with the respective cache node and a copy of the second data is not stored in the cache node, wherein a pool of cache nodes is formed in the cluster;

poll a plurality of the different cache nodes of the cluster for the first data; and

replicate, an instance of the first data stored in the different cache node of the pool to the cache node of the pool receiving the computation request, wherein the cache node of the pool receiving the request is associated with the different cache node.

13. The system of claim 12 wherein the processing device is to:

store the first data in the cache node, process the request for computation with the cache node receiving the computation request using the first data, determine whether a need still exists for the first data stored in the cache node receiving the computation request after the computation, and t-o delete the first data stored in the cache node receiving the computation request upon determining that no need exists for the first data stored in the cache node receiving the computation request and that the first data is also stored in at least one of the different cache nodes associated with the cache node of the cluster.

14. The system of claim 13 wherein the processing device is to:

receive a query for the first data in the cache node of the cluster, to determine whether the first data is stored in the queried cache node, inquire the different cache nodes in the cluster for the first data, and replicate an instance of the first data from a cache node storing the first data to the queried cache node.

15. The system of claim 14 wherein the processing device is to inquire a data backup of each of the cache nodes in the cluster.

16. The system of claim 14 wherein the processing device is to delete the instance of the first data from the cache node storing the first data after the instance of the first data has been copied to the queried cache node.

17. The system of claim 14 wherein the processing device is to inquire the different cache nodes upon determining that the first data is not stored in the queried cache node.

18. The system of claim 14 wherein the processing device is to inquire the different cache nodes based on a per-invocation basis.

19. The system of claim 14 wherein the cluster comprises a plurality of cache nodes, each cache node selecting at least one of the different cache nodes as a backup.

20. The system of claim 14 wherein the cache nodes are located on different physical hosts.

21. The system of claim 14 wherein the cache nodes are located on different physical racks.

22. The system of claim 12 wherein the cache nodes from the pool are located on different physical racks.

23. A non-transitory computer-readable storage medium, having instructions stored therein, which, when executed by a processing device cause the processing device to perform operations comprising:

receiving, by the processing device, a request for computation at a cache node of a cluster, the computation requiring first data from a different cache node of the cluster, wherein each cache node of the cluster stores second data associated with the respective cache node and a copy of the second data is not stored in the cache node, wherein a pool of cache nodes is formed in the cluster;

polling, by the processing device, a plurality of the different cache nodes of the cluster for the first data; and

replicating, by the processing device, an instance of the first data stored in the different cache node of the pool to the cache node of the pool receiving the computation request, wherein the cache node of the pool receiving the request is associated with the different cache node.

24. The non-transitory computer-readable storage medium of claim 23 wherein the operations further comprise:

storing the first data in the cache node;

processing the request for computation at the cache node receiving the computation request using the stored first data;

determining whether a need still exists for the first data stored in the cache node receiving the computation request after the computation; and

deleting the first data stored in the cache node receiving the computation request upon determining that no need exists for the first data stored in the cache node receiving the computation request and that the first data is also stored in the at least one of the different cache nodes associated with the cache node of the cluster.

25. The non-transitory computer-readable storage medium of claim 23 wherein the operations further comprise:

receiving a query for the first data in the cache node of the cluster;

determining whether the first data is stored in the queried cache node;

inquiring the different cache nodes in the cluster for the first data; and

replicating an instance of the first data from a cache node storing the first data to the queried cache node.

26. The non-transitory computer-readable storage medium of claim 23 wherein inquiring the different cache nodes in the cluster for the first data further comprises:

inquiring a data backup of each of the cache nodes in the cluster.

27. The non-transitory computer-readable storage medium of claim 23 wherein the operations further comprise:

deleting the instance of the first data from the cache node storing the first data after the instance of the first data has been copied to the queried cache node.

28. The non-transitory computer-readable storage medium of claim 23 wherein the operations further comprise:

inquiring the different cache nodes upon determining that the first data is not stored in the queried cache node.

29. The non-transitory computer-readable storage medium of claim 23 wherein the operations further comprise:

inquiring the different cache nodes based on a per-invocation basis.

30. The non-transitory computer-readable storage medium of claim 23 wherein the cluster comprises a plurality of cache nodes, each cache node selecting at least one of the different cache nodes as a backup.

31. The non-transitory computer-readable storage medium of claim 23 wherein the cache nodes are located on different physical hosts.

32. The non-transitory computer-readable storage medium of claim 23 wherein the cache nodes are located on different physical racks.

33. The non-transitory computer-readable storage medium of claim 23 wherein the cache nodes from the pool are located on different physical racks.