Storage control system with power-off time estimation mechanism and method of operation thereof

• US 9,543,025 B2
• Filed: 04/11/2013
• Issued: 01/10/2017
• Est. Priority Date: 04/11/2013
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Inventors: Fitzpatrick, James, Higgins, James M., Rub, Bernardo, Jones, Ryan, Ellis, Robert W., Dancho, Mark, Park, Sheunghee
• Primary Examiner(s): Choe, Yong
• Assistant Examiner(s): Matin, Tasnima
• Application Number:
  US13/861,326
• Publication Number:
  US 20140310445A1
• Time in Patent Office: 1,370 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G11C 16/20 Initialising; Data preset; Chip identification
• CPC Class Codes: G11C 16/3418 Disturbance prevention or evaluation; Refreshing of disturbed memory data
• CPC Class Codes: G11C 16/349 Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles

Abstract

A storage control system, and a method of operation thereof, including: a power-down module for powering off a memory sub-system; a decay estimation module, coupled to the power-down module, for estimating a power-off decay rate upon the memory sub-system powered up, the power-off decay rate is for indicating how much data in the memory sub-system has decayed while the memory sub-system has been powered down; and a recycle module, coupled to the decay estimation module, for recycling an erase block for data retention based on the power-off decay rate.

Claims

1. A method of operation of a storage control system comprising:

powering off a memory sub-system;

estimating power-off decay in respective blocks of a set of blocks of the memory sub-system upon the memory sub-system powering up, wherein the estimated power-off decay for a particular block is a numerical value indicating how much data in the particular block of the memory sub-system has decayed while the memory sub-system has been powered down, and the estimated power-off decay for the particular block is calculated as a function of a difference between a pre-power-down threshold voltage and a post-power-up threshold voltage; and

identifying blocks in the memory sub-system for which the estimated power-off decay has reached a threshold and recycling at least the identified blocks in the memory sub-system for data retention;

wherein estimating power-off decay includes calculating a power-off time for indicating how long the memory sub-system has been powered off and estimating the power-off decay as a function of the power-off time.

2. The method as claimed in claim 1, wherein estimating includes:

in accordance with an identification of oldest data in the set of blocks, identifying an age of the oldest data in the set of blocks;

estimating data retention of the oldest data in the set of blocks based on the identified age of the oldest data in the set of blocks, the oldest data comprising data least recently written to the set of blocks;

determining, based on the estimated data retention of the oldest data, that the oldest data is at risk of data loss;

in accordance with determining that the oldest data is at risk of data loss, flagging the oldest data for data retention recycling; and

repeating the estimating, determining, and flagging with respect to a plurality of additional erase blocks in the memory sub-system, in an order corresponding to oldest-to-freshest data stored in the memory sub-system, until identifying an erase block that is not at risk of data loss.

3. The method as claimed in claim 1, wherein estimating includes:

in accordance with an identification of freshest data in the set of blocks, identifying an age of the freshest data in the set of blocks;

estimating data retention of freshest data in the set of blocks based on the identified age of the freshest data in the set of blocks, the freshest data comprising data most recently written to the set of blocks; and

using the data retention of the freshest data to estimate data retention of other erase blocks.

4. The method as claimed in claim 1, wherein estimating includes:

estimating an error rate of surrogate data as a measure of data retention for the memory sub-system, wherein the surrogate data is stored in a portion of a memory device set aside for measuring data retention.

5. The method as claimed in claim 1, wherein estimating the power-off decay comprises estimating the power-off decay as a function of time and temperature.

6. The method as claimed in claim 1, wherein estimating the power-off decay includes obtaining a power-up date and time by querying a host system and calculating a power-off time for indicating how long the memory sub-system has been powered off, the power-off time based on the obtained power-up date and time.

7. The method as claimed in claim 1, wherein estimating the power-off decay includes obtaining a power-up date and time by querying a real-time clock self-powered in the memory sub-system and calculating a power-off time for indicating how long the memory sub-system has been powered off, the power-off time based on the obtained power-up date and time.

8. The method as claimed in claim 1, wherein the recycling includes accelerating movement of the identified blocks through a write queue.

9. A storage control system comprising:

a power-down module configured to power off a memory sub-system;

a decay estimation module, coupled to the power-down module, configured to estimate power-off decay in respective blocks of a set of blocks of the memory sub-system upon the memory sub-system powering up, wherein the estimated power-off decay for a particular block is a numerical value indicating how much data in the particular block of the memory sub-system has decayed while the memory sub-system has been powered down, and the estimated power-off decay for the particular block is calculated as a function of a difference between a pre-power-down threshold voltage and a post-power-up threshold voltage; and

a recycle module, coupled to the decay estimation module, configured to identify blocks in the memory sub-system for which the estimated power-off decay has reached a threshold and recycling at least the identified blocks in the memory sub-system for data retention;

wherein the decay estimation module is configured to calculate a power-off time for indicating how long the memory sub-system has been powered off and estimating the power-off decay as a function of the power-off time.

10. The system as claimed in claim 9, wherein the decay estimation module is for:

identifying an age of the oldest data in the set of blocks in accordance with an identification of oldest data in the set of blocks;

estimating data retention of the oldest data in the set of blocks based on the identified age of the oldest data in the set of blocks, the oldest data comprising data least recently written to the set of blocks;

determining, based on the estimated data retention of the oldest data, that the oldest data is at risk of data loss;

in accordance with determining that the oldest data is at risk of data loss, flagging the oldest data for data retention recycling; and

repeating the estimating, determining, and flagging with respect to a plurality of additional erase blocks in the memory sub-system, in an order corresponding to oldest-to-freshest data stored in the memory sub-system, until identifying an erase block that is not at risk of data loss.

11. The system as claimed in claim 9, wherein the decay estimation module is for:

identifying an age of the freshest data in the set of blocks in accordance with an identification of freshest data in the set of blocks;

estimating data retention of freshest data in the set of blocks based on the identified age of the freshest data in the set of blocks, the freshest data comprising data most recently written to the set of blocks; and

using the data retention of the freshest data to estimate data retention of other erase blocks.

12. The system as claimed in claim 9, wherein the decay estimation module is for estimating an error rate of surrogate data as a measure of data retention for the memory sub-system, wherein the surrogate data is stored in a portion of a memory device set aside for measuring data retention.

13. The system as claimed in claim 9, wherein the decay estimation module is for estimating the power-off decay as a function of the power-off time and temperature.

14. The system as claimed in claim 13, wherein the decay estimation module is for obtaining a power-up date and time by querying a host system and calculating the power-off time for indicating how long the memory sub-system has been powered off, the power-off time based on the obtained power-up date and time.

15. The system as claimed in claim 13, wherein the decay estimation module is for obtaining a power-up date and time by querying a real-time clock self-powered in the memory sub-system and calculating the power-off time for indicating how long the memory sub-system has been powered off, the power-off time based on the obtained power-up date and time.

16. The system as claimed in claim 9, wherein the recycle module is for accelerating movement of the identified blocks through a write queue.