Automatic read and write acceleration of data accessed by virtual machines

• US 9,699,263 B1
• Filed: 03/15/2013
• Issued: 07/04/2017
• Est. Priority Date: 08/17/2012
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Inventors: Jelvis, Alexei, Ratty, Muthukumar, Shats, Serge, Vignanker, Eugene
• Primary Examiner(s): Avellino, Joseph E
• Assistant Examiner(s): Ngankam, Patrick
• Application Number:
  US13/831,677
• Time in Patent Office: 1,572 Days
• Field of Search: 709213, 711135, 711138
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/0804 with main memory updating G06F12/0806 takes precedence
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data

Abstract

The various implementations described herein include methods and systems for automatic management of data access acceleration in a computer system executing a plurality of clients. The method includes: receiving data access commands from two or more clients to access data in objects identified by the data access commands; and processing the data access commands to update access history information for portions of the objects identified by the data access commands. The method further includes: in accordance with the access history information, automatically identifying and marking for acceleration the portions of the objects identified by the data access commands that satisfy an access based data acceleration policy; and accelerating the object portions marked for acceleration, including accelerating data writes and data reads of the object portions to and from the persistent cache, where the persistent cache is shared by the two or more clients.

Claims

1. A method for accelerating data access, performed by a computer system having one or more processors, memory, a tiered data structure stored in the memory, the tiered data structure comprising a plurality of tiers, and a persistent cache for storing accelerated data, the method comprising:

receiving, at the computer system, data access commands from two or more clients to access data in objects identified by the data access commands;

processing, by the computer system, the data access commands to update access history information for respective object portions of the objects identified by the data access commands from the two or more clients, wherein the processing includes;

in accordance with the access history information, determining usage rates for each of the respective object portions identified by the data access commands, and

assigning each of the respective object portions identified by the data access commands to one of the plurality of tiers within the tiered data structure in accordance with a determination that a respective determined usage rate for a respective object portion is within a range of usage rates for a respective tier to which the respective object portion is assigned;

wherein each tier of the plurality of tiers within the tiered data structure stores information identifying object portions assigned to that tier;

automatically identifying and marking for acceleration at least some of the respective object portions identified by the data access commands from the two or more clients in accordance with respective tiers to which the at least some of the respective object portions have been assigned, wherein the automatically identifying and marking are performed collectively for the at least some of the respective object portions identified by the data access commands from the two or more clients; and

accelerating data access to the at least some of the respective object portions marked for acceleration, by writing the at least some respective object portions marked for acceleration to the persistent cache;

wherein the persistent cache is shared by the two or more clients.

2. The method of claim 1, wherein the persistent cache comprises non-volatile solid state storage.

3. The method of claim 1, wherein the two or more clients comprise virtual machines executed by the computer system.

4. The method of claim 1, wherein the objects comprise one or more virtual disks.

5. The method of claim 1, wherein the respective object portions comprise respective address blocks or sub-blocks of the objects.

6. The method of claim 5, wherein the access history information includes at least one usage history value for a respective address block and at least one distinct respective usage history value for each sub-block of the respective address block.

7. The method of claim 1, wherein the access history information includes at least one operations count for each respective object portion of a plurality of object portions identified by the data access commands.

8. The method of claim 1, wherein updating the access history information comprises:

incrementing a usage history value for a respective object portion assigned to a respective tier for which recent usage criteria are satisfied; and

decrementing a usage history value for other portions of objects assigned to the respective tier for which recent usage criteria are not satisfied.

20. The method of claim 1, wherein automatically identifying and marking for acceleration at least some of the respective object portions identified by the data access commands further comprises determining a threshold tier in the tiered data structure, and marking for acceleration object portions assigned to the threshold tier and all tiers higher in the tiered data structure than the threshold tier.

21. The method of claim 20, wherein all object portions assigned to the threshold tier and all tiers higher in the tiered data structure than the threshold tier cumulatively comprise a total number of address blocks that is less than or equal to the storage capacity of the persistent cache.

22. The method of claim 1, further including:

processing a data write command to write an identified object portion, the data write command received from a respective client of the two or more clients, by;

automatically marking for acceleration the identified object portion if the identified object portion is assigned to a tier at or above a threshold tier of the plurality of tiers;

in accordance with a determination that the identified object portion is marked for acceleration, writing the identified object portion to the persistent cache and subsequently or concurrently writing the identified object portion to a secondary storage; and

in accordance with a determination that the identified object portion is not marked for acceleration, writing the identified object portion to the secondary storage.

24. The method of claim 1, wherein the at least some of the respective object portions marked for acceleration include only a predefined number of the respective object portions, and the predefined number is determined based on a storage capacity of the persistent cache.

25. The method of claim 1, wherein marking a respective object portion for acceleration includes updating information accessible via the tiered data structure to indicate that the respective object portion is marked for acceleration.

9. A computer system, comprising:

one or more processors;

a persistent cache for storing accelerated data;

memory storing a tiered data structure, the tiered data structure comprising a plurality of tiers, and one or more programs for execution by the one or more processors, wherein the one or more programs include instructions that when executed by the one or more processors cause the computer system to;

receive, at the computer system, data access commands from two or more clients to access data in objects identified by the data access commands;

process, by the computer system, the data access commands to update access history information for respective object portions of the objects identified by the data access commands from the two or more clients, wherein the instructions for processing the data access commands include instructions that when executed by the one or more processors cause the computer system to;

in accordance with the access history information, determine usage rates for each of the respective object portions identified by the data access commands, and

assign each of the respective object portions identified by the data access commands to one of the plurality of tiers within the tiered data structure in accordance with a determination that a respective determined usage rate for a respective object portion is within a range of usage rates for a respective tier to which the respective object portion is assigned;

wherein each tier of the plurality of tiers within the tiered data structure stores information identifying object portions assigned to that tier;

automatically identify and mark for acceleration at least some of the respective object portions identified by the data access commands from the two or more clients in accordance with respective tiers to which the at least some of the respective object portions have been assigned, wherein the automatically identifying and marking are performed collectively for the at least some of the respective object portions identified by the data access commands from the two or more clients; and

accelerate data access to the at least some of the respective object portions marked for acceleration, by writing the at least some respective object portions marked for acceleration to the persistent cache;

wherein the persistent cache is shared by the two or more clients.

10. The computer system of claim 9, wherein the two or more clients comprise virtual machines executed by the computer system.

11. The computer system of claim 9, wherein the respective object portions comprise respective address blocks or sub-blocks of the objects.

12. The computer system of claim 11, wherein the access history information includes at least one usage history value for a respective address block and at least one distinct respective usage history value for each sub-block of the respective address block.

13. The computer system of claim 9, wherein the access history information includes at least one operations count for each respective object portion of a plurality of object portions identified by the data access commands.

23. The computer system of claim 9, wherein the instructions that when executed by the one or more processors cause the computer system to automatically identify and mark for acceleration portions of the objects identified by the data access commands further comprise instructions that when executed by the one or more processors cause the computer system to determine a threshold tier in the tiered data structure and mark for acceleration object portions assigned to the threshold tier and all tiers higher in the tiered data structure than the threshold tier.

14. A non-transitory computer readable medium storing one or more programs that when executed by one or more processors of a computer system cause the computer system to:

receive, at the computer system, data access commands from two or more clients to access data in objects identified by the data access commands;

process, by the computer system, the data access commands to update access history information for respective object portions of the objects identified by the data access commands from the two or more clients, wherein causing the computer system to process the data access commands includes causing the computer system to;

in accordance with the access history information, determine usage rates for each of the respective object portions identified by the data access commands, and

assign each of the respective object portions identified by the data access commands to one of the plurality of tiers within the tiered data structure in accordance with a determination that a respective determined usage rate for a respective object portion is within a range of usage rates for a respective tier to which the respective object portion is assigned;

wherein each tier of the plurality of tiers within the tiered data structure stores information identifying object portions assigned to that tier;

automatically identify and mark for acceleration at least some of the respective object portions identified by the data access commands from the two or more clients in accordance with respective tiers to which the at least some of the respective object portions have been assigned, wherein the automatically identifying and marking are performed collectively for the at least some of the respective object portions identified by the data access commands from the two or more clients; and

accelerate data access to the at least some of the respective object portions marked for acceleration, by writing the at least some respective object portions marked for acceleration to the persistent cache;

wherein the persistent cache is shared by the two or more clients.

15. The non-transitory computer readable medium of claim 14, wherein the two or more clients comprise virtual machines executed by the computer system.

16. The non-transitory computer readable medium of claim 14, wherein the portions of the objects comprise respective address blocks or sub-blocks of the objects.

17. The non-transitory computer readable medium of claim 16, wherein the access history information includes at least one usage history value for a respective address block and at least one distinct respective usage history value for each sub-block of the respective address block.

18. The non-transitory computer readable medium of claim 14, wherein the access history information includes at least one operations count for each respective object portion of a plurality of object portions identified by the data access commands.

19. The non-transitory computer readable medium of claim 14, wherein:

processing the data access commands to update access history information comprises assigning the portions of the objects identified by the data access commands to tiers in accordance with the data acceleration policy and the access history information; and

identifying and marking for acceleration portions of the objects comprises identifying and marking for acceleration portions of the objects in accordance with the tiers to which the portions of the objects have been assigned.