MODELING MEMORY COMPRESSION

• US 20110238943A1
• Filed: 03/29/2010
• Published: 09/29/2011
• Est. Priority Date: 03/29/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: SrinivasaRaghavan, Rajalakshmi, DEVENDRAN, SARAVANAN, Hepkin, David Alan
• Granted Patent: US 8,386,740 B2
• Time in Patent Office: Days
• US Class Current: 711/170
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/1009 using page tables, e.g. page table structures
• CPC Class Codes: G06F 2212/401 Compressed data
• CPC Class Codes: H03M 7/3068 Precoding preceding compression, e.g. Burrows-Wheeler transformation

Abstract

A method, system, and computer usable program product for modeling memory compression are provided in the illustrative embodiments. A subset of candidate pages is received. The subset of candidate pages is a subset of a set of candidate pages used in executing a workload in a data processing system. A candidate page is compressible uncompressed data in a memory associated with the data processing system. The subset of candidate pages is compressed in a scratch space. A compressibility of the workload is computed based on the compression of the subset of candidate pages. Page reference information of the subset of candidate pages is received. A memory reference rate of the workload is determined. A recommendation is presented about a memory compression model for the workload in the data processing system.

Claims

1. A computer implemented method for modeling memory compression, comprising:

receiving a subset of candidate pages from a set of candidate pages used in executing a workload in a data processing system, a candidate page being compressible uncompressed data in a memory associated with the data processing system;

compressing the subset of candidate pages in a scratch space;

computing a compressibility of the workload based on the compression of the subset of candidate pages;

receiving page reference information of the subset of candidate pages;

determining a memory reference rate of the workload; and

presenting a recommendation about a memory compression model for the workload in the data processing system.

2. The computer implemented method of claim 1, further comprising:

determining a compressibility of the subset of candidate pages by computing a compression ratio of the subset of candidate pages; and

recording information of the compressibility of the subset of candidate pages.

3. The computer implemented method of claim 2, further comprising:

repeating the receiving and compressing using a second subset of candidate pages, wherein the computing the compressibility of the workload is based on the compression of more than one subset of candidate pages.

4. The computer implemented method of claim 1, wherein computing the compressibility of the workload is performed using a statistical analysis of compressibility of several subsets of candidate pages.

5. The computer implemented method of claim 4, wherein the statistical analysis is one of (i) an averaging, and (ii) an extrapolation, of the compressibility of the several subsets of candidate pages.

6. The computer implemented method of claim 1, wherein the receiving the page reference information of the subset of candidate pages is from a virtual memory page table.

7. The computer implemented method of claim 1, wherein the receiving the page reference information of the subset of candidate pages is for a first period, further comprising:

resetting the page reference information after the first period has elapsed; and

repeating the receiving for a second period.

8. The computer implemented method of claim 7, wherein the resetting and repeating are performed with respect to a second subset of candidate pages.

9. The computer implemented method of claim 1, wherein the determining the memory reference rate of the workload is performed using statistical analysis of memory reference rates of several subsets of candidate pages.

10. The computer implemented method of claim 9, wherein the statistical analysis is one of (i) an averaging, and (ii) an extrapolation, of the memory reference rates of the several subsets of candidate pages.

11. The computer implemented method of claim 1, wherein the model is an analysis of costs and benefits of at least one memory compression, wherein the benefit includes an amount of memory saving, and wherein the cost includes an amount of computing resources needed for the memory saving.

12. The computer implemented method of claim 1, wherein the scratch space is a designated space in the memory.

13. The computer implemented method of claim 1, wherein receiving the subset of candidate pages includes selecting the subset of candidate pages according to a criterion.

14. A computer usable program product comprising a computer usable storage medium including computer usable code for modeling memory compression, the computer usable code comprising:

computer usable code for receiving a subset of candidate pages from a set of candidate pages used in executing a workload in a data processing system, a candidate page being compressible uncompressed data in a memory associated with the data processing system;

computer usable code for compressing the subset of candidate pages in a scratch space;

computer usable code for computing a compressibility of the workload based on the compression of the subset of candidate pages;

computer usable code for receiving page reference information of the subset of candidate pages;

computer usable code for determining a memory reference rate of the workload; and

computer usable code for presenting a recommendation about a memory compression model for the workload in the data processing system.

15. The computer usable program product of claim 14, further comprising:

computer usable code for determining a compressibility of the subset of candidate pages by computing a compression ratio of the subset of candidate pages; and

computer usable code for recording information of the compressibility of the subset of candidate pages.

16. The computer usable program product of claim 15, further comprising:

computer usable code for repeating the receiving and compressing using a second subset of candidate pages, wherein the computing the compressibility of the workload is based on the compression of more than one subset of candidate pages.

17. The computer usable program product of claim 14, wherein the receiving the page reference information of the subset of candidate pages is for a first period, further comprising:

computer usable code for resetting the page reference information after the first period has elapsed; and

computer usable code for repeating the receiving for a second period.

18. The computer usable program product of claim 14, wherein the computer usable code is stored in a computer readable storage medium in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system.

19. The computer usable program product of claim 14, wherein the computer usable code is stored in a computer readable storage medium in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage medium associated with the remote data processing system.

20. A data processing system for modeling memory compression, the data processing system comprising:

a storage device including a storage medium, wherein the storage device stores computer usable program code; and

a processor, wherein the processor executes the computer usable program code, and wherein the computer usable program code comprises;

computer usable code for receiving a subset of candidate pages from a set of candidate pages used in executing a workload in a data processing system, a candidate page being compressible uncompressed data in a memory associated with the data processing system;

computer usable code for compressing the subset of candidate pages in a scratch space;

computer usable code for computing a compressibility of the workload based on the compression of the subset of candidate pages;

computer usable code for receiving page reference information of the subset of candidate pages;

computer usable code for determining a memory reference rate of the workload; and

computer usable code for presenting a recommendation about a memory compression model for the workload in the data processing system.