REDUNDANCY SCHEMES FOR NON-VOLATILE MEMORY USING PARITY ZONES HAVING NEW AND OLD PARITY BLOCKS

• US 20140129874A1
• Filed: 11/07/2012
• Published: 05/08/2014
• Est. Priority Date: 11/07/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Zaltsman, Etai, Vlaiko, Julian, Stern, Ori Moshe, Meir, Avraham Poza
• Granted Patent: US 8,914,670 B2
• Time in Patent Office: Days
• US Class Current: 714/6.11
• CPC Class Codes: G06F 11/108 Parity data distribution in semiconductor storages, e.g. in SSD

Abstract

A method includes, in a non-volatile memory that includes multiple memory blocks, defining a redundancy zone that includes at least an old parity block, a new parity block and multiple active blocks of which one block is defined as an open block. Data is stored in the redundancy zone and the stored data is protected, such that new input data is stored in the open block, redundancy information for the active blocks including the open block is stored in the new parity block, and the redundancy information for the active blocks excluding the open block is stored in the old parity block. Upon filling the open block and the new parity block, an alternative block is assigned to serve as the open block and the new parity block is assigned to serve as the old parity block.

Claims

1. A method, comprising:

in a non-volatile memory that includes multiple memory blocks, defining a redundancy zone that comprises at least an old parity block, a new parity block and multiple active blocks of which one block is defined as an open block;

storing data in the redundancy zone and protecting the stored data such that new input data is stored in the open block, redundancy information for the active blocks including the open block is stored in the new parity block, and the redundancy information for the active blocks excluding the open block is stored in the old parity block; and

upon filling the open block and the new parity block, assigning an alternative block to serve as the open block and assigning the new parity block to serve as the old parity block.

2. The method according to claim 1, and comprising, upon detecting a failure in a memory block in the redundancy zone, reconstructing the data stored in the failed memory block using the redundancy information stored in the new parity block and in the old parity block.

3. The method according to claim 1, wherein the alternative block comprises a retired memory block that comprises only invalid data.

4. The method according to claim 1, wherein the open block and the other active blocks each comprises a respective super-block made-up of a first predefined number of the memory blocks, and wherein the new parity block and the old parity block each comprises a second predefined number of the memory blocks that is different from the first number.

5. The method according to claim 4, wherein each super-block comprises multiple super-pages, each made-up of a set of corresponding pages from the memory blocks of the super-block, and wherein storing the data comprises accumulating the new data in volatile memory until a full super-page of the new data is available for storage, and then storing and protecting the full super-page in the redundancy zone.

6. The method according to claim 4, wherein the redundancy zone comprises multiple super-blocks, and comprising, upon failure of some of the memory blocks in the super-blocks, forming a new super-block from functional memory blocks drawn from the super-blocks having the failed memory blocks.

7. The method according to claim 1, and comprising alternating an assignment of the new parity block and the old parity block among the memory blocks of the redundancy zone.

8. The method according to claim 1, wherein the memory blocks comprise multi-level memory cells that are each capable of storing at least a Least Significant Bit (LSB) and a Most Significant Bit (MSB), and wherein protecting the stored data comprises storing the redundancy information using only the LSB of the memory cells.

9. The method according to claim 1, wherein defining the redundancy zone comprises selecting the memory blocks for inclusion in the redundancy zone in an interleaved manner from a total plurality of the memory blocks of the non-volatile memory.

10. The method according to claim 1, wherein assigning the alternative block comprises assigning a new open block in another redundancy zone.

11. Apparatus, comprising:

an interface, which is configured to communicate with a non-volatile memory that includes multiple memory blocks; and

a processor, which is configured to define in the non-volatile memory a redundancy zone that comprises at least an old parity block, a new parity block and multiple active blocks of which one block is defined as an open block, to store data in the redundancy zone and protect the stored data such that new input data is stored in the open block, redundancy information for the active blocks including the open block is stored in the new parity block, and the redundancy information for the active blocks excluding the open block is stored in the old parity block, and, upon filling the open block and the new parity block, to assign an alternative block to serve as the open block and to assign the new parity block to serve as the old parity block.

12. The apparatus according to claim 11, wherein the processor is configured, upon detecting a failure in a memory block in the redundancy zone, to reconstruct the data stored in the failed memory block using the redundancy information stored in the new parity block and in the old parity block.

13. The apparatus according to claim 11, wherein the alternative block comprises a retired memory block that comprises only invalid data.

14. The apparatus according to claim 11, wherein the open block and the other active blocks each comprises a respective super-block made-up of a first predefined number of the memory blocks, and wherein the new parity block and the old parity block each comprises a second predefined number of the memory blocks that is different from the first number.

15. The apparatus according to claim 14, wherein each super-block comprises multiple super-pages, each made-up of a set of corresponding pages from the memory blocks of the super-block, and wherein the processor is configured to accumulate the new data in volatile memory until a full super-page of the new data is available for storage, and then to store and protect the full super-page in the redundancy zone.

16. The apparatus according to claim 14, wherein the redundancy zone comprises multiple super-blocks, and wherein the processor is configured, upon failure of some of the memory blocks in the super-blocks, to form a new super-block from functional memory blocks drawn from the super-blocks having the failed memory blocks.

17. The apparatus according to claim 11, wherein the processor is configured to alternate an assignment of the new parity block and the old parity block among the memory blocks of the redundancy zone.

18. The apparatus according to claim 11, wherein the memory blocks comprise multi-level memory cells that are each capable of storing at least a Least Significant Bit (LSB) and a Most Significant Bit (MSB), and wherein the processor is configured to store the redundancy information using only the LSB of the memory cells.

19. The apparatus according to claim 11, wherein the processor is configured to select the memory blocks for inclusion in the redundancy zone in an interleaved manner from a total plurality of the memory blocks of the non-volatile memory.

20. The apparatus according to claim 11, wherein the processor is configured to assign the alternative block by assigning a new open block in another redundancy zone.

21. A method, comprising:

in a non-volatile memory that includes multiple memory blocks, defining a redundancy zone that comprises at least a parity super-block and multiple active super-blocks, one of which is defined as an open super-block, wherein each of the super-blocks comprises two or more of the memory blocks of the memory;

storing data in the redundancy zone and protecting the stored data such that new input data is stored in the open super-block, redundancy information for the active super-blocks including the open super-block is stored in a first area of the parity super-block, and the redundancy information for the active super-blocks excluding the open super-block is stored in a second area of the parity super-block; and

upon detecting a failure in a memory block in the redundancy zone, reconstructing the data stored in the failed memory block using the redundancy information stored in the parity super-block.

22. Apparatus, comprising:

an interface, which is configured to communicate with a non-volatile memory that includes multiple memory blocks; and

a processor, which is configured to define in the non-volatile memory a redundancy zone that comprises at least a parity super-block and multiple active super-blocks, one of which is defined as an open super-block, wherein each of the super-blocks comprises two or more of the memory blocks of the memory, to store data in the redundancy zone and protect the stored data such that new input data is stored in the open super-block, redundancy information for the active super-blocks including the open super-block is stored in a first area of the parity super-block, and the redundancy information for the active super-blocks excluding the open super-block is stored in a second area of the parity super-block, and, upon detecting a failure in a memory block in the redundancy zone, to reconstruct the data stored in the failed memory block using the redundancy information stored in the parity super-block.