Enhancing data caching performance

• US 9,645,944 B2
• Filed: 05/07/2012
• Issued: 05/09/2017
• Est. Priority Date: 05/07/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Roy, Subhojit, Hyde, II, Joseph Smith
• Primary Examiner(s): Verbrugge, Kevin
• Assistant Examiner(s): PUCHE, TAHILBA O
• Application Number:
  US13/465,476
• Publication Number:
  US 20130297885A1
• Time in Patent Office: 1,828 Days
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value
• CPC Class Codes: G06F 12/123 with age lists, e.g. queue, most recently used [MRU] list or least recently used [LRU] list

Abstract

For a cache in which a plurality of frequently accessed data segments are temporarily stored, reference count information of the plurality of data segments, in conjunction with least recently used (LRU) information, is used to determine a length of time to retain the plurality of data segments in the cache according to a predetermined weight, where notwithstanding the LRU information, those of the plurality of data segments having a higher reference counts are retained longer than those having lower reference counts.

Claims

1. A system for improving caching performance in a computing environment, comprising:

a deduplication engine;

a plurality of data segments processed by the deduplication engine, the plurality of data segments being frequently accessed;

a cache configured for at least temporarily storing the plurality of data segments; and

a cache management module in operable communication with the cache;

wherein the cache management module is configured for, in conjunction with using least recently used (LRU) information;

obtaining and examining reference count information concurrent with a deduplication operation for those of the plurality of data segments retained in the cache, wherein the reference count information is a number of chunks of virtual storage that map onto a single chunk of physical storage,

using the reference count information of the plurality of data segments to add to the cache the plurality of data segments and using the reference count information, the LRU information, statistical information, and a data storage policy to determine a length of time to retain each one of the plurality of data segments in the cache according to a predetermined weight correlated to the reference count information, assigned to each one of the plurality of data segments, wherein notwithstanding yet considering the LRU information, those of the plurality of data segments having a higher reference counts are retained longer in the cache than those having lower reference counts,

determining if the reference count information of the plurality of data segments added to the cache has been updated or a predetermined time interval has expired, wherein, if the reference count information has not been updated and the predetermined time interval has not expired;

redetermining if the reference count information of the plurality of data segments added to the cache has been updated and the predetermined time interval has expired following a second predetermined time interval,

re-determining a length of time following an expiration of the predetermined time interval, wherein the predetermined weight decreases according to the passage of the predetermined time interval, and

adding to or removing from the cache portions of the plurality of data segments in the cache based on the reference count information.

2. The system of claim 1, wherein the reference count information is obtained from the deduplication engine.

3. The system of claim 1, further including a policy module in operable communication with the cache management module, wherein the policy module is configured for, pursuant to determining the length of time to retain the plurality of data segments in cache, implementing at least one policy corresponding to each of:

the length of time to retain the plurality of data segments in cache, at least one of the plurality of data segments, and the predetermined weight.

4. The system of claim 3, wherein the policy module is further configured for selecting one of an available plurality of policies for implementing.

5. The system of claim 4, wherein each of the available plurality of policies corresponds to at least one of a predetermined number of the plurality of data segments and a predetermined time to retain some of the plurality of entries.

6. The system of claim 1, wherein the deduplication engine is configured for, in conjunction with the determining the length of time to retain the plurality of data segments in cache, performing a deduplication operation for those of the plurality of data segments retained in the cache concurrent with the determining.

7. The system of claim 1, wherein the cache management module is further configured for re-determining the length of time to retain the plurality of data segments in cache based on an update to the reference count information, wherein the predetermined weight decreases according to a decrease in the reference count, and increases according to an increase in the reference count.

8. A computer program product for improving caching performance in a computing environment by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for a cache in which a plurality of data segments that are frequently accessed and are temporarily stored, and in conjunction with the cache using least recently used (LRU) information;

obtaining and examining reference count information concurrent with a deduplication operation for those of the plurality of data segments retained in the cache, wherein the reference count information is a number of chunks of virtual storage that map onto a single chunk of physical storage,

using the reference count information of the plurality of data segments to add to the cache the plurality of data segments and using the reference count information, the LRU information, statistical information, and a data storage policy to determine a length of time to retain each one of the plurality of data segments in the cache according to a predetermined weight correlated to the reference count information, assigned to each one of the plurality of data segments, wherein notwithstanding yet considering the LRU information, those of the plurality of data segments having a higher reference counts are retained longer in the cache than those having lower reference counts,

determining if the reference count information of the plurality of data segments added to the cache has been updated or a predetermined time interval has expired, wherein, if the reference count information has not been updated and the predetermined time interval has not expired;

redetermining if the reference count information of the plurality of data segments added to the cache has been updated and the predetermined time interval has expired following a second predetermined time interval,

re-determining a length of time following an expiration of the predetermined time interval, wherein the predetermined weight decreases according to the passage of the predetermined time interval, and

adding to or removing from the cache portions of the plurality of data segments in the cache based on the reference count information.

9. The computer program product of claim 8, further including a second executable portion for obtaining the reference count information from a data deduplication engine.

10. The computer program product of claim 8, further including a second executable portion for, pursuant to determining the length of time to retain the plurality of data segments in cache, implementing at least one policy corresponding to each of:

one of the length of time to retain the plurality of data segments in cache, at least one of the plurality of data segments, and the predetermined weight.

11. The computer program product of claim 8, further including a second executable portion for, pursuant to determining the length of time to retain the plurality of data segments in cache, performing a deduplication operation for those of the plurality of data segments retained in the cache concurrent with the determining.

12. The computer program product of claim 8, further including a second executable portion for re-determining the length of time to retain the plurality of data segments in cache based on an update to the reference count information, wherein the predetermined weight decreases according to a decrease in the reference count, and increases according to an increase in the reference count.