Map Based Striping of Data in a Distributed Volatile Memory Environment

• US 20080126695A1
• Filed: 11/29/2006
• Published: 05/29/2008
• Est. Priority Date: 11/29/2006
• Status: Active Grant

• Current Assignee: International Business Machines Corporation, ServiceNow Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Berg, Douglas Charles
• Granted Patent: US 7,624,231 B2
• Time in Patent Office: Days
• US Class Current: 711/113
• CPC Class Codes: G06F 12/0806 Multiuser, multiprocessor or multiprocessing cache systems

Abstract

An apparatus, program product and method stripe value data associated with each of a plurality of keyed data sets across a plurality of processes in a data process set and accessing a first keyed data set among the plurality of keyed data sets using at least one of the plurality of processes. Value data is striped by dividing a keyed data set among the plurality of keyed data sets across the plurality of processes in the data process set based on a striping strategy.

Claims

1. A computer implemented method for caching data, the method comprising:

striping value data associated with each of a plurality of keyed data sets across a plurality of processes in a data process set; and

accessing a first keyed data set among the plurality of keyed data sets using at least one of the plurality of processes.

2. The method of claim 1, wherein striping the value data comprises, in a first process among the plurality of processes, dividing a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy.

3. The method of claim 2, wherein the striping strategy comprises a RAID striping strategy.

4. The method of claim 3 wherein the RAID striping strategy is a RAID 0 striping strategy.

5. The method of claim 2, wherein the first process is a primary process and each process in the data process set other than the first process is a secondary process, the method further comprising, in response to a failure in the first process, upgrading a secondary process from the data process set to a primary process.

6. The method of claim 2 further comprising re-dividing a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy in response to a change in the data process set.

7. The method of claim 1, wherein accessing the first keyed data set includes retrieving the first keyed data set from the data process set in response to a client request.

8. The method of claim 7, wherein retrieving the first keyed data set from the data process set comprises:

retrieving at least one keyed data set segment from at least one secondary process among the plurality of processes in the data process set; and

assembling the at least one keyed data set segment retrieved from the at least one secondary process into the keyed data set.

9. The method of claim 7, further comprising caching the keyed data set in a local cache.

10. The method of claim 7, wherein accessing the first keyed data set further includes checking a local cache for a copy of the keyed data set prior to attempting to retrieve the first keyed data set from the data process set.

11. The method of claim 10, wherein the local cache is accessible to a primary process among the plurality of processes in the data process set, and wherein retrieving the first keyed data set from the data process set includes sending a request from the primary process to at least one secondary process among the plurality of processes in the data process set if the keyed data set is not available in the local cache.

12. The method of claim 10, wherein the local cache is accessible to the client, and wherein retrieving the first keyed data set from the data process set includes sending a request from the client to a primary process among the plurality of processes in the data process set if the keyed data set is not available in the local cache.

13. The method of claim 12, wherein the local cache is a first local cache, and wherein retrieving the first keyed data set from the data process set further includes checking a second local cache accessible to the primary process for a copy of the keyed data set and sending a request from the primary process to at least one secondary process among the plurality of processes in the data process set if the keyed data set is not available in the second local cache.

14. The method of claim 1, wherein accessing the first keyed data set includes:

sending the keyed data set from a client to a primary process among the plurality of processes in the data process set;

dividing the keyed data set into at least one keyed data set segment with the primary process based on a striping strategy; and

sending the at least one keyed data set segment to at least one secondary process among the plurality of processes in the data process set based on the striping strategy.

15. The method of claim 1, wherein striping the value data includes storing the value data in a cache framework.

16. The method of claim 15, wherein the cache framework is a volatile cache.

17. The method of claim 1, wherein the plurality of processes includes a primary process having exclusive write access to the keyed data set and a plurality of secondary processes having read access to the keyed data set.

18. The method of claim 1, further comprising rebuilding the keyed data set in response to a failure in one of the processes in the data process set.

19. The method of claim 1, wherein the data process set hosts all of the keyed data set.

20. An apparatus comprising:

a memory; and

program code, resident in the memory, the program code configured to stripe value data associated with each of a plurality of keyed data sets across a plurality of processes in a data process set, and access a first keyed data set among the plurality of keyed data sets using at least one of the plurality of processes.

21. The apparatus of claim 20, wherein the program code is configured to stripe the value data by, in a first process among the plurality of processes, dividing a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy.

22. The apparatus of claim 20 wherein the program code is further configured to re-divide a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy in response to a change in the data process set.

23. A program product, comprising:

program code configured to stripe value data associated with each of a plurality of keyed data sets across a plurality of processes in a data process set, and access a first keyed data set among the plurality of keyed data sets using at least one of the plurality of processes; and

a computer readable medium bearing the program code.

24. The program product of claim 23, wherein the program code is configured to stripe the value data by, in a first process among the plurality of processes, dividing a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy.

25. The program product of claim 23 wherein the program code is further configured to re-divide a keyed data set among the plurality of keyed data sets across the data process set based on a striping strategy in response to a change in the data process set.