Techniques for deduplicated data access statistics management

• US 9,483,484 B1
• Filed: 05/05/2011
• Issued: 11/01/2016
• Est. Priority Date: 05/05/2011
• Status: Active Grant

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Inventors: Sridharan, Srineet, Khandelwal, Atul, Banerjee, Anindya
• Primary Examiner(s): Lee, Wilson
• Application Number:
  US13/101,668
• Time in Patent Office: 2,007 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/174 Redundancy elimination performed by the file system management of the data involved in backup or backup restore using de-duplication of the data G06F11/14
• CPC Class Codes: G06F 16/1744 using compression, e.g. sparse files

Abstract

Techniques for data access statistics management are disclosed. In one particular embodiment, the techniques may be realized as a method for data access statistics management comprising determining that a portion of data has been deduplicated, and modifying access statistics of the portion of data for each reference to the portion of data.

Claims

1. A method for data access statistics management comprising:

determining, using at least one computer processor, that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that the plurality of portions of data are going to be deduplicated into a deduplicated portion of data;

combining access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and

associating the combined access statistics with the deduplicated portion of data.

2. The method of claim 1, wherein the access statistics provide an indication of at least one of Input/Output (I/O) temperature and a access time.

3. The method of claim 1, wherein the access statistics provide an indication of Input/Output (I/O) temperature, and wherein the Input/Output (I/O) temperature is used to perform at least one of:

determining which portions of data to pre-fetch into cache memory; and

determining which portions of data to store in higher performance storage.

4. The method of claim 3, wherein higher performance storage comprises at least one of:

storage with faster access times;

storage with faster seek times; and

storage spread across multiple disks.

5. The method of claim 1, wherein the portion of data comprises a block.

6. The method of claim 1, wherein the portion of data comprises a segment.

7. The method of claim 1, further comprising:

detecting a reference being added to the deduplicated portion of data; and

incrementing the access count of the deduplicated portion of data for the reference.

8. At least one non-transitory processor readable non-transitory storage medium for storing a computer program of instructions configured to be readable by at least one processor for instructing the at least one processor to execute a computer process for performing the method as recited in claim 1.

9. An article of manufacture for data access statistics management, the article of manufacture comprising:

at least one non-transitory processor readable medium; and

instructions stored on the at least one medium;

wherein the instructions are configured to be readable from the at least one medium by at least one processor and thereby cause the at least one processor to operate so as to;

determine that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that a plurality of portions of data are going to be deduplicated into a deduplicated portion of data;

combine access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and

associate the combined access statistics with the deduplicated portion of data.

10. The article of manufacture of claim 9, wherein the access statistics are to perform at least one of:

determining which portions of data to pre-fetch into cache memory; and

determining which portions of data to store in higher performance storage.

11. The article of manufacture of claim 9, wherein the access statistics are used to determine which portions of data to store in higher performance storage, and wherein higher performance storage comprises at least one of:

storage with faster access times;

storage with faster seek times; and

storage spread across multiple disks.

12. The article of manufacture of claim 9, wherein the portion of data comprises a block.

13. The article of manufacture of claim 9, wherein the portion of data comprises a segment.

14. The article of manufacture of claim 9, wherein the instructions are configured to further cause the processor to:

detect a reference being added to the deduplicated portion of data; and

increment the access count of the deduplicated portion of data for the reference.

15. A system for data access statistics management comprising:

one or more processors communicatively coupled to a network;

wherein the one or more processors are configured to;

determine that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that a plurality of portions of data are going to be deduplicated into a deduplicated portion of data;

combine access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and

associate the combined access statistics with the deduplicated portion of data.

16. The system of claim 15, wherein the access statistics provide an indication of at least one of Input/Output (I/O) temperature and an access time.

17. The system of claim 15, wherein the access statistics provide an indication of Input/Output (I/O) temperature, and wherein the Input/Output (I/O) temperature is used to perform at least one of:

determining which portions of data to pre-fetch into cache memory; and

determining which portions of data to store in higher performance storage.