Systems and methods for managing storage endurance

Patent metadata

Field	Value
Publication number	US-9766819-B2
Application number	US-201514661971-A
Country	US
Kind code	B2
Filing date	Mar 18, 2015
Priority date	Dec 30, 2014
Publication date	Sep 19, 2017
Grant date	Sep 19, 2017

Abstract

Storage divisions of a non-volatile storage medium may have a writable state and an unwritable state. Storage divisions may be reclaimed by, inter alia, resetting the storage division from an unwritable state to a writable state. Writable storage divisions may be used to service incoming storage requests. If no writable storage divisions are available, requests may stall. One or more storage divisions may be held in a writable state to avoid stall conditions. This, however, may increase the erase dwell time of the storage divisions, which can result in increased wear and reduce the usable life of the storage device. Storage divisions may be prepared for use such that the storage divisions are transitioned to a writable state such that erase dwell time of the storage divisions is reduced, and the storage divisions are available as needed to service incoming requests.

First claim

I claim:

1. An apparatus, comprising:
a storage manager configured to write data to a first storage division of a solid-state storage medium; and
an erase manager configured to perform an erase operation to reset a second storage division of the solid-state storage medium from an unwritable state to a writable state,
wherein the erase manager is configured to maintain the second storage division in the unwritable state until data have been written to a threshold amount of a storage capacity of the first storage division.

2. The apparatus of claim 1 , wherein the erase manager is configured to delay the erase operation of the second storage division until the threshold amount of the storage capacity of the first storage division is filled.

3. The apparatus of claim 1 , further comprising a storage division selector configured to select the second storage division for recovery, wherein the erase manager is configured to delay the erase operation on the second storage division in response to selection of the second storage division for recovery.

4. The apparatus of claim 3 , wherein the erase manager is configured to delay the erase operation on the second storage division in response to selection of the second storage division for recovery by the storage division selector.

5. The apparatus of claim 1 , wherein the threshold is based on one or more of a program latency for the first storage division, and a projected latency of the erase operation to reset the second storage division from the unwritable state to the writable state.

6. The apparatus of claim 1 , wherein the erase manager is configured to determine the threshold based on a projected fill time of the first storage division, and wherein the projected fill time is based on one or more of a wear level of the first storage division, measured program latency of the first storage division, measured program latency of a plurality of storage divisions of the solid-state storage medium, and a projected rate for write operations on the first storage division.

7. The apparatus of claim 1 , wherein the erase manager is configured to determine the threshold based on a projected latency of the erase operation to reset the second storage division from the unwritable state to the writable state, and wherein the projected latency of the erase operation is based on one or more of a wear level of the second storage division, a latency for previous erase operations performed on the second storage division, and a latency for previous erase operations on other storage divisions of the solid-state storage medium.

8. The apparatus of claim 1 , wherein the erase manager is configured to maintain the second storage division in the unwritable state until the storage manager writes data to a third storage division of the solid-state storage medium.

9. The apparatus of claim 1 , wherein the storage manager services write requests by sequentially writing data at an append point within the first storage division, and wherein the erase manager is configured to maintain the second storage division in the unwritable state until data are appended to the threshold amount of the storage capacity of the first storage division.

10. The apparatus of claim 1 , further comprising a garbage collector configured to prepare the second storage division for the erase operation by relocating valid data stored on the second storage division to one or more other storage divisions of the solid-state storage medium, wherein the erase manager is configured to maintain the second storage division in the unwritable state after relocation of the valid data from the second storage division.

11. A system, comprising:
a storage device comprising a non-volatile storage medium having a plurality of erase blocks, the storage device configured to append data to a storage log on the non-volatile storage medium at an append point within a current erase block of the plurality of erase blocks; and
a media manager configured to prepare erase blocks for use as append points of the storage log, wherein, to prepare a particular erase block for use as a next append point of the storage log, the media manager is configured to hold the particular erase block in an un-erased state, and erase the particular erase block responsive to data being appended to a threshold number of pages of the current erase block.

12. The system of claim 11 , wherein the media manager is configured to start an operation to transition the selected erase block to an erased state in response to data being programmed to the threshold number of pages of the current erase block.

13. The system of claim 11 , wherein the media manager is configured to relocate data from the particular erase block.

14. The system of claim 11 , wherein the media manager is configured to determine the threshold number of pages based on one or more of a projected fill rate for the current erase block and a projected latency for an erase operation to erase the particular erase block.

15. The system of claim 11 , wherein the media manager determines the threshold number of pages based on a difference between a projected fill time of the current erase block, and a projected latency of an erase operation to transition the particular erase block to an erased state.

16. The system of claim 11 , wherein the media manager is configured to determine the threshold number of pages based on a rate at which data are being appended to the storage log.

17. A method, comprising:
programming data to erased storage locations within respective erase divisions of a solid-state storage medium; and
erasing selected erase divisions of the solid-state storage medium, wherein erasing a selected erase division comprises:
leaving the selected erase division in a non-erased state until a write capacity threshold is satisfied, wherein the write capacity threshold corresponds to a storage capacity of erased storage locations on the solid-state storage medium, and
transitioning storage locations of the selected erase division to an erased state in response to determining that the write capacity threshold is satisfied.

18. The method of claim 17 , wherein satisfying the write capacity threshold comprises determining that the solid-state storage medium comprises fewer than a threshold number of erased storage locations.

19. The method of claim 17 , further comprising scheduling two or more erase operations to transition different respective sets of storage locations of the selected erase division to the erased state.

20. The method of claim 17 , further comprising:
programming data to a first one of a plurality of erase divisions of the solid-state storage medium; and
determining that the write capacity threshold is satisfied in response to filling a threshold portion of a storage capacity of the first erase division.

21. The method of claim 17 , further comprising preparing the selected erase division to be erased, and leaving the selected erase division in the non-erased state after preparing the selected erase division to be erased until the write capacity threshold is satisfied.

22. The method of claim 21 , wherein preparing the selected erase division to be erased comprises relocating valid data stored on the selected erase division to one or more other erase divisions of the solid-state storage medium.

Assignees

• Sandisk Technologies Llc

Inventors

• Janik Gary

Classifications

• G06F3/0611 Primary

  in relation to response time · CPC title

• G06F3/0652

  Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title

• G06F3/0655

  Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices · CPC title

• G06F3/0688

  Non-volatile semiconductor memory arrays · CPC title