Methods and mechanisms for proactive memory management

• US 20050228964A1
• Filed: 06/09/2005
• Published: 10/13/2005
• Est. Priority Date: 10/04/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Fortin, Michael R., Ergan, Cenk, Iyigun, Mehmet, Sechrest, Stuart
• Granted Patent: US 7,185,155 B2
• Time in Patent Office: Days
• US Class Current: 711/170
• CPC Class Codes: G06F 12/121 using replacement algorithms
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value

Abstract

A proactive, resilient and self-tuning memory management system and method that result in actual and perceived performance improvements in memory management, by loading and maintaining data that is likely to be needed into memory, before the data is actually needed. The system includes mechanisms directed towards historical memory usage monitoring, memory usage analysis, refreshing memory with highly-valued (e.g., highly utilized) pages, I/O pre-fetching efficiency, and aggressive disk management. Based on the memory usage information, pages are prioritized with relative values, and mechanisms work to pre-fetch and/or maintain the more valuable pages in memory. Pages are pre-fetched and maintained in a prioritized standby page set that includes a number of subsets, by which more valuable pages remain in memory over less valuable pages. Valuable data that is paged out may be automatically brought back, in a resilient manner. Benefits include significantly reducing or even eliminating disk I/O due to memory page faults.

Claims

1. A computer-readable medium having computer-executable instructions, which when executed perform steps, comprising:

observing a need for pages of memory;

determining values for the pages based on the observed need; and

loading at least part of the memory based on the values of the pages.

2. The computer-readable medium of claim 1 wherein loading at least part of the memory comprises selecting pages based on the values.

3. The computer-readable medium of claim 1 wherein loading at least part of the memory comprises loading the entire memory.

4. The computer-readable medium of claim 1 wherein loading at least part of the memory comprises loading memory that is free.

5. The computer-readable medium of claim 1 further comprising, identifying low-value pages in memory, and wherein loading at least part of the memory comprises replacing at least some of the low value pages.

6. The computer-readable medium of claim 1 wherein observing a need for pages comprises tracking actual usage of pages, and/or training to determine likely needed pages.

7. The computer-readable medium of claim 1 wherein observing a need for pages comprises training to determine likely needed pages, wherein the training includes performing act least one action of a set of actions, the actions including, simulating page use, analyzing code, and running programs on a training computer system and using the values on another computer system.

8. The computer-readable medium of claim 1 further comprising, building a persistent repository of information including the values, and storing the persistent repository in a file.

9. A computer implemented method, comprising:

identifying low-value pages; and

maintaining memory management information in the memory, including information on the low value pages.

10. The method of claim 9 wherein maintaining the memory management information comprises maintaining rich use information, comprising at least one of pattern, frequency, grouping and context information.

11. The method of claim 10 further comprising, reprioritizing pages in memory based on the rich use information.

12. The method of claim 10 wherein maintaining the rich use information comprises keeping working set entries containing the rich use information for pages that are no longer in memory but are valid in the address space for the working set.

13. The method of claim 10 wherein maintaining the rich use information comprises allocating physical page descriptors and entries for maintaining the rich use information for pages that leave memory.

14. The method of claim 9 wherein maintaining memory management information includes maintaining data for pages that have been but are no longer in the memory, and for pages that have not been in the memory.

15. The method of claim 9 wherein maintaining memory management information includes maintaining statistics in memory from which rich use information, comprising at least one of pattern, frequency, grouping and context information, may be derived.

16. The method of claim 15 wherein maintaining the statistics comprises maintaining at least one statistical item of a set, the set containing, per pages entries, entries for groups of pages, entries for files, and state data on at least one page.

17. The method of claim 9 further comprising, using the memory management information to prioritize pages in memory into subsets.

18. The method of claim 9 further comprising, using the memory management information to protect more valuable pages from being repurposed.

19. A computer-readable medium having computer-executable instructions, which when executed perform steps, comprising:

receiving an event related to a context; and

prioritizing the memory in response to the event, such that pages more likely to be used in the context are higher in value relative to pages less likely to be used.

20. The computer-readable medium of claim 19 wherein prioritizing the memory comprises performing at least one action of a set, the set containing, changing a subset to which a page of memory is classified, loading at least one page from the secondary storage to memory and replacing pages in the memory with pages from the secondary storage.