Management of non-volatile memory systems having large erase blocks

• US 8,117,380 B2
• Filed: 04/30/2009
• Issued: 02/14/2012
• Est. Priority Date: 12/30/2003
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: Sandisk Technologies Incorporated (Western Digital Corporation)
• Inventors: Conley, Kevin M., Gonzalez, Carlos J.
• Primary Examiner(s): Thai, Tuan V.
• Application Number:
  US12/433,702
• Publication Number:
  US 20090216938A1
• Time in Patent Office: 1,020 Days
• Field of Search: 711/100, 711/103, 711/154, 711/200, 711/218
• US Class Current: 711/103
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2212/7202 Allocation control and policies

Abstract

A non-volatile memory system of a type having blocks of memory cells erased together and which are programmable from an erased state in units of a large number of pages per block. If the data of only a few pages of a block are to be updated, the updated pages are written into another block provided for this purpose. The valid original and updated data are then combined at a later time, when doing so does not impact on the performance of the memory. If the data of a large number of pages of a block are to be updated, however, the updated pages are written into an unused erased block and the unchanged pages are also written to the same unused block. By handling the updating of a few pages differently, memory performance is improved when small updates are being made.

Claims

1. In a non-volatile memory having memory cells organized in groups of one or more blocks of a minimum number of cells that are simultaneously erasable and wherein a given number of pages of data are programmed into individual ones of the groups of blocks, a method of updating data in less than all pages of a given group of one or more blocks, comprising:

determining whether at least one predefined condition of the data update is satisfied, and

if it is determined that the condition is satisfied, thereafter writing the updated pages of data into pages of a first other group of one or more blocks having page numbers selected independently of the page numbers of the pages of data within the given group of blocks that are being updated, or

if it is determined that the condition is not satisfied, thereafter writing the updated pages of data into correspondingly numbered pages of a second other group of one or more blocks.

2. The method of claim 1, wherein, if the condition is not satisfied, data from pages of the given group of blocks not being updated is combined into a common one of the groups of blocks in correspondingly numbered pages with the updated data in other pages of the common group of blocks.

3. The method of claim 1, wherein the condition includes the number of pages being updated being less than a predetermined proportion of said given number of pages in the given group of blocks.

4. The method of claim 1, wherein the first other group of blocks is utilized to store updated versions of pages of a plurality of the individual groups of blocks including said given block.

5. The method of claim 1, wherein the first other block is utilized to store updated versions of pages of only said given group of blocks.

6. The method of claim 1, which additionally comprises consolidating data by copying both pages from the given group of blocks that have not been updated and pages from the first other group of blocks that are updated versions of data pages of the given group of blocks into a previously erased group of blocks in page number locations that correspond to those of the given group of blocks.

7. The method of claim 6, wherein the data consolidating is caused to occur repetitively at intervals after a plurality of occurrences of updating data in less than all pages of the given group of blocks.

8. The method of claim 6, which additionally comprises, after consolidating data, erasing data from said first another block.

9. The method of claim 1, additionally comprising designating said first other group of blocks to store updated versions of pages of only said given group of blocks in response to the existence of at least one data writing pattern being noted.

10. The method of claim 9, wherein said at least one data writing pattern includes repetitive writing operations to one or more pages of said given group of blocks.

11. The method of claim 9, wherein said at least one data writing pattern includes repetitively writing one or a few pages of data during individual writing operations that are less than written during a majority of the writing operations.

12. The method of claim 9, wherein said at least one data writing pattern includes designating the given group of blocks to store overhead data of others of the plurality of groups of blocks.