Flash memory data correction and scrub techniques

• US 8,004,895 B2
• Filed: 03/31/2009
• Issued: 08/23/2011
• Est. Priority Date: 10/03/2003
• Status: Expired due to Fees

• 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): Luu; Pho M
• Application Number:
  US12/415,158
• Publication Number:
  US 20090187785A1
• Time in Patent Office: 875 Days
• Field of Search: 365/185.11, 365/230.03, 365/185.12, 365/185.17
• US Class Current: 365/185.11
• CPC Class Codes: G06F 11/106 Correcting systematically all correctable errors, i.e. scrubbing
• CPC Class Codes: G06F 11/1068 in sector programmable memories, e.g. flash disk G06F11/1072 takes precedence
• CPC Class Codes: G11C 8/08 Word line control circuits, e.g. drivers, boosters, pull-up circuits, pull-down circuits, precharging circuits, for word lines

Abstract

In order to maintain the integrity of data stored in a flash memory that are susceptible to being disturbed by operations in adjacent regions of the memory, disturb events cause the data to be read, corrected and re-written before becoming so corrupted that valid data cannot be recovered. The sometimes conflicting needs to maintain data integrity and system performance are balanced by deferring execution of some of the corrective action when the memory system has other high priority operations to perform. In a memory system utilizing very large units of erase, the corrective process is executed in a manner that is consistent with efficiently rewriting an amount of data much less than the capacity of a unit of erase.

Claims

1. A method of operating an erasable and re-programmable non-volatile memory system having an array of memory cells organized into blocks of a minimum number of memory cells that are erasable together that include a plurality of pages individually storing one or more units of data, comprising:

in response to the occurrence of at least one of a plurality of predefined events, identifying at least one page of at least one block to be scrubbed,

reading data stored in said at least one page with a first set of read conditions comprising a first set of breakpoint levels,

determining whether there are any errors in the read data,

if there are errors in the read data, determining whether the errors can be corrected,

in response to determining that the errors in the read data cannot be corrected, re-reading the data stored in said at least one page with a second set of read conditions comprising a second set of breakpoint levels shifted with respect to the first set of breakpoint levels within guardbands separating memory storage levels,

determining whether there are any errors in the re-read data, and, if so, whether the errors can be corrected,

in response to other memory activity being scheduled, deferring further action with respect to the read or re-read data,

after the other memory activity is completed and in response to determining that the errors in either of the read or re-read data can be corrected, correcting such errors to provide corrected data, and

writing the corrected data into at least a second page of a second block different from said one block.

2. The method of claim 1, additionally comprising copying unchanged data from pages within said at least one block other than said one block into the second block.