Coherency of data in data relocation

• US 10,282,130 B2
• Filed: 11/03/2016
• Issued: 05/07/2019
• Est. Priority Date: 01/27/2014
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Inventors: Chen, Albert H., Malina, James N.
• Primary Examiner(s): Schnee, Hal
• Application Number:
  US15/342,895
• Publication Number:
  US 20170068485A1
• Time in Patent Office: 915 Days
• CPC Class Codes: G06F 12/023 Free address space management
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 12/0253 Garbage collection, i.e. reclamation of unreferenced memory
• CPC Class Codes: G06F 2212/1036 Life time enhancement
• CPC Class Codes: G06F 2212/1044 Space efficiency improvement
• CPC Class Codes: G06F 2212/217 Hybrid disk, e.g. using both magnetic and solid state storage devices
• CPC Class Codes: G06F 2212/7205 Cleaning, compaction, garbage collection, erase control
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G06F 2212/7211 Wear leveling
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0649 Lifecycle management
• CPC Class Codes: G06F 3/0652 Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
• CPC Class Codes: G06F 3/0676 Magnetic disk device
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

At least one attribute defined by a host is used to identify data and/or a location for a destination portion for relocating data from a source portion to the destination portion. The data is relocated from the source portion to the destination portion in accordance with the identification of the data to be relocated and/or the location for the destination portion, and it is determined if a change was made to relevant data stored in the source portion while relocating the data from the source portion to the destination portion. If a change was made to relevant data stored in the source portion while relocating the data to the destination portion, the changed relevant data is relocated from the source portion to the destination portion.

Claims

1. A method for managing data in a data storage system including a plurality of Data Storage Devices (DSDs), each of the DSDs including a plurality of zones for storing data, the method comprising:

identifying, based on at least one attribute defined by a host, at least one data item of the data to be relocated for a garbage collection operation from a source portion of the plurality of DSDs to a destination portion of the plurality of DSDs or a location for the destination portion, wherein the source portion comprises multiple zones of the plurality of zones assigned to a logical volume and the destination portion comprises one or more zones of the plurality of zones that are outside of the logical volume;

relocating the at least one data item from the source portion to the destination portion in accordance with the identification of the at least one data item or the location for the destination portion;

determining if a change was made to a first portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion;

in response to determining that the change was made to the first portion of the at least one data item during the relocating, relocating the changed first portion of the at least one data item from the source portion to the destination portion; and

designating the source portion as a new destination portion.

2. The method of claim 1, wherein the determining comprises comparing metadata for the source portion from before and after initiating the relocating process of the first portion of the at least one data item.

3. The method of claim 2, wherein the compared metadata is provided by a Copy On Write (COW)-based file system that generates a change in metadata when there is a change in a file.

4. The method of claim 1, further comprising:

determining if a further change was made to a second portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the further change was made to the second portion of the at least one data item during the relocating, relocating the changed second portion of the at least one data item from the source portion to the destination portion.

5. The method of claim 4, further comprising blocking further changes to the source portion while relocating the changed second portion of the at least one data item.

6. The method of claim 4, further comprising:

determining if a second further change was made to a third portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the second further change was made to the third portion of the at least one data item during the relocating, relocating the changed third portion of the at least one data item from the source portion to the destination portion.

7. The method of claim 1, further comprising determining a time for relocating the at least one data item from the source portion to the destination portion to reduce an impact on Input Output (IO) performance of the data storage system.

22. The method of claim 1, wherein the at least one attribute comprises at least one of an expiration of the data, a frequency of access of the data, ownership of the data, a fragmentation level of the data, one or more conditions of the source portion on which a garbage collection operation is performed, or one or more conditions of the destination portion for storing valid data resulting from the garbage collection operation being performed.

23. The method of claim 22, wherein the one or more conditions of the source or destination portions comprise at least one of a reliability condition, an environmental condition, a wear level, an available data capacity, a distance from previous users of the data, a network bandwidth available between the source and destination portions, an availability of the source or destination portions, or an energy cost in operating the source or destination portions.

24. The method of claim 23, wherein the environmental condition comprises a temperature or vibration condition.

25. The method of claim 24, further comprising relocating the at least one data item from the source portion experiencing a high temperature or high vibration condition to the destination portion experiencing a lower temperature or lower vibration condition.

26. The method of claim 1, wherein relocating the changed first portion of the at least one data item provides coherency between the source and destination portions while allowing for changes to the data being relocated.

27. The method of claim 1, wherein the determining and the relocating of the changed first portion are repeatedly performed until there is no change made to the at least one data item during the relocating.

28. The method of claim 1, further comprising designating the new destination portion as a new source portion.

29. The method of claim 1, wherein the method further comprises determining one of the zones with a lower usage or wear;

and designating the determined zone as the destination portion.

8. A data storage system, comprising:

a host including a processor; and

at least one Data Storage Device (DSD) in communication with the host, wherein each of the DSDs includes a plurality of zones configured to store data;

wherein the processor is configured to;

identify, based on at least one attribute defined by the host, at least one data item of the data to be relocated for a garbage collection operation from a source portion of the at least one DSD to a destination portion of the at least one DSD or a location for the destination portion, wherein the source portion comprises multiple zones of the plurality of zones assigned to a logical volume and the destination portion comprises one or more zones of the plurality of zones that are outside of the logical volume;

relocate the at least one data item of the data from the source portion to the destination portion in accordance with the identification of the at least one data item or the location for the destination portion;

determine if a change was made to a first portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion;

in response to determining that the change was made to the first portion of the at least one data item during the relocating, relocate the changed first portion of the at least one data item from the source portion to the destination portion so as to provide for coherency between the source and destination portions while allowing for changes to the data being relocated; and

set the source portion as a new destination portion.

9. The data storage system of claim 8, wherein the processor is further configured to perform the determining by comparing metadata for the source portion from before and after initiating the relocating process of the first portion of the at least one data item.

10. The data storage system of claim 9, wherein the compared metadata is provided by a Copy On Write (COW)-based file system that generates a change in metadata when there is a change in a file.

11. The data storage system of claim 8, wherein the processor is further configured to:

determine if a further change was made to a second portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the further change was made to the at least one data item during the relocating, relocate the changed second portion of the at least one data item from the source portion to the destination portion.

12. The data storage system of claim 11, wherein the processor is further configured to block further changes to the source portion while relocating the changed second portion of the at least one data item.

13. The data storage system of claim 11, wherein the processor is further configured to:

determine if a second further change was made to a third portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the second further change was made to the at least one data item during the relocating, relocate the changed third portion of the at least one data item from the source portion to the destination portion.

14. The data storage system of claim 8, wherein the processor is further configured to determine a time for relocating the at least one data item from the source portion to the destination portion to reduce an impact on Input Output (IO) performance of the data storage system.

15. A Data Storage Device (DSD) in communication with a host, the DSD comprising:

at least one non-volatile memory including a plurality of zones for storing data; and

a controller configured to;

identify, based on at least one attribute defined by the host, at least one data item of the data to be relocated for a garbage collection operation from a source portion of the at least one non-volatile memory to a destination portion of the at least one non-volatile memory or a location for the destination portion in the at least one non-volatile memory, wherein the source portion comprises multiple zones of the plurality of zones assigned to a logical volume and the destination portion comprises one or more zones of the plurality of zones that are outside of the logical volume;

relocate the at least one data item from the source portion to the destination portion in accordance with the identification of the at least one data item or the location for the destination portion;

determine if a change was made to a first portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion;

in response to determining that the change was made to the first portion of the at least one data item during the relocating, relocate the changed first portion of the at least one data item from the source portion to the destination portion so as to provide for coherency between the source and destination portions while allowing for changes to the data being relocated; and

assign the source portion as a new destination portion.

16. The DSD of claim 15, wherein the controller is further configured to perform the determining by comparing metadata for the source portion from before and after initiating the relocating process of the first portion of the at least one data item.

17. The DSD of claim 16, wherein the compared metadata is provided by a Copy On Write (COW)-based file system that generates a change in metadata when there is a change in a file.

18. The DSD of claim 15, wherein the controller is further configured to:

determine if a further change was made to a second portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the further change was made to the at least one data item during the relocating, relocate the changed second portion of the at least one data item from the source portion to the destination portion.

19. The DSD of claim 18, wherein the controller is further configured to block further changes to the source portion while relocating the changed second portion of the at least one data item.

20. The DSD of claim 18, wherein the controller is further configured to:

determine if a second further change was made to a third portion of the at least one data item while relocating the at least one data item from the source portion to the destination portion; and

in response to determining that the second further change was made to the third portion of the at least one data item during the relocating, relocate the changed third portion of the at least one data item from the source portion to the destination portion.

21. The DSD of claim 15, wherein the controller is further configured to determine a time for relocating the at least one data item of the data from the source portion to the destination portion to reduce an impact on Input Output (IO) performance of the DSD.