Efficient allocation policies for a system having non-volatile memory

• US 8,966,209 B2
• Filed: 08/23/2010
• Issued: 02/24/2015
• Est. Priority Date: 08/23/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Post, Daniel J., Sutton, Brian
• Primary Examiner(s): Bansal, Gurtej
• Application Number:
  US12/861,703
• Publication Number:
  US 20120047316A1
• Time in Patent Office: 1,646 Days
• Field of Search: 711/170, 711/202, 711/209
• US Class Current: 711/170
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2212/7202 Allocation control and policies
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays

Abstract

Systems and methods are disclosed for efficient allocation policies for a system having non-volatile memory. A file system allocator of the system can be configured to allocate memory regions that are aligned with one or more logical blocks of a logical space (e.g., one or more super block-aligned regions). In some embodiments, the file system allocator can monitor the number of free sectors corresponding to each logical block. In other embodiments, the file system allocator can monitor a ratio of free space to total space corresponding to each logical block. The file system allocator can select a logical block based at least in part on the number of free sectors of the logical block. In some cases, the file system allocator can allocate the free sectors of the logical block in a sequential order.

Claims

1. A method for optimal memory allocations in a logical space corresponding to a non-volatile memory (“

NVM”

), the method comprising;

receiving a request to store data associated with a file in the NVM, the NVM comprising at least two dies comprising a plurality of physical blocks, wherein each of a plurality of super blocks comprises a physical block located in each of the at least two dies, and wherein each superblock comprises super block boundaries;

selecting a logical block of the logical space with a largest number of free sectors, wherein the logical block comprises boundaries that are aligned with the super block boundaries of one of the super blocks, and wherein the free sectors within the selected logical block are randomly distributed at non-contiguous physical locations;

allocating the free sectors of the logical block in a sequential order to the file; and

writing the data to the free sectors based on the sequential order so that a write access pattern is optimized for the selected block even though the sectors are randomly distributed within the super block.

2. The method of claim 1, wherein the selecting the logical block further comprises monitoring a number of free sectors corresponding to each logical block in the logical space.

3. The method of claim 1, wherein the NVM comprises a NAND flash memory.

4. The method of claim 1, wherein the free sectors are non-contiguous.

5. The method of claim 1, wherein the free sectors are selected from contiguous and non-contiguous sectors within the logical block.

6. The method of claim 1, wherein the writing the data further comprises writing the data to a first free sector of the logical block.

7. The method of claim 6, wherein the writing the data further comprises:

determining whether a new logical block is needed; and

in response to determining that a new logical block is needed, selecting a logical block with a largest number of free sectors as the new logical block.

8. The method of claim 7, wherein the determining whether a new logical block is needed comprises monitoring an allocation point within the logical block.

9. The method of claim 7, wherein in response to determining that a new logical block is not needed, continuing to write the data to a next sequential free sector of the logical block.

10. A system comprising:

a non-volatile memory (“

NVM”

) comprising at least two dies comprising a plurality of physical blocks comprising a plurality of physical blocks, wherein each of a plurality of super blocks comprises a physical block located in each of the at least two dies, and wherein each superblock comprises super block boundaries; and

a file system allocator for allocating free sectors contained within logical blocks of a logical space to files, wherein each of the logical blocks has boundaries that are is aligned with the super block boundaries of at least one super block of the NVM, the file system allocator operative to;

receive a request to store data associated with a file in the NVM;

select a logical block as a current logical block based at least in part on a number of free sectors associated with the logical block, wherein the free sectors within the selected logical block are randomly distributed at non-contiguous physical locations;

allocate, in a sequential order, at least a portion of the free sectors of the current logical block to the file; and

write the data to the free sectors based on the sequential order so that a write access pattern is optimized for the selected block even though the sectors are randomly distributed within the super blocks.

11. The system of claim 10, wherein the file system allocator is operative to:

determine that the system has logical blocks that are constant in size; and

select the logical block that has a largest number of free sectors.

12. The system of claim 10, wherein the file system allocator is operative to:

determine that the system has logical blocks that are variable in size; and

select the logical block that has a largest ratio of free space to total space.

13. The system of claim 10, wherein the NVM comprises a NAND flash memory.

14. The system of claim 10, wherein the free sectors are non-contiguous.

15. The method of claim 10, wherein the free sectors are selected from contiguous and non-contiguous sectors within the logical block.

16. The system of claim 10, wherein the file system allocator is operative to:

allocate a first free sector of the current logical block to the file;

determine that additional free sectors are needed;

determine if a new logical block is needed; and

in response to determining that a new logical block is not needed, allocate a second sector of the free sectors of the current logical block to the file.

17. The system of claim 16, wherein the file system allocator is operative to determine that a new logical block is not needed based on determining that an allocation point has not reached the number of free sectors in the current logical block.

18. The system of claim 16, wherein the file system allocator is operative to determine that a new logical block is not needed based on failing to detect an end of the current logical block.

19. The system of claim 16, wherein the file system allocator is operative to determine that a new logical block is not needed based on detecting additional free space in the current logical block.

20. The system of claim 16, wherein in response to determining that a new logical block is needed, the file system allocator is operative to:

select a new logical block as the current logical block based at least in part on a number of free sectors associated with the new logical block; and

allocate at least a portion of the free sectors of the new logical block to the file.

21. The system of claim 10, wherein the file system allocator is operative to maintain an array of a number of free sectors corresponding to each logical block of the logical space.

22. The system of claim 21, wherein the array is an array of integers.