Redundant backup using non-volatile memory

• US 8,904,098 B2
• Filed: 09/24/2012
• Issued: 12/02/2014
• Est. Priority Date: 06/01/2007
• Status: Active Grant

• Current Assignee: Netlist, Inc.
• Original Assignee: Netlist, Inc.
• Inventors: Amidi, Mike Hossein, Chen, Chi-She, Solomon, Jeffrey C., Milton, Scott H., Bhakta, Jayesh
• Primary Examiner(s): Rojas, Midys
• Application Number:
  US13/625,563
• Publication Number:
  US 20130019076A1
• Time in Patent Office: 799 Days
• Field of Search: 711/100, 711/111, 711/154, 711/160, 711/161, 711/162, 711/104, 711/170, 711/171, 711/172
• US Class Current: 711/104
• CPC Class Codes: G06F 11/1441 Resetting or repowering
• CPC Class Codes: G06F 11/1612 where the redundant component is persistent storage
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays

Abstract

Data stored in a volatile memory subsystem is backed up redundantly into first and second channels of a non-volatile memory subsystem. The data is retrieved from the volatile memory subsystem upon detection of a trigger condition indicative of real or imminent power loss or reduction and multiple copies are stored in dedicated non-volatile memory channels. The stored copies may be error checked and corrected, and re-written if necessary. The redundantly backed up data can be subsequently retrieved from the non-volatile memory subsystem, error-corrected, and an error-free copy communicated to the volatile memory subsystem.

Claims

1. In a host computer memory system having a volatile memory subsystem, a non-volatile memory subsystem, and a controller for managing the non-volatile subsystem, a method for redundantly backing up the volatile memory subsystem, the method comprising:

detecting a trigger condition;

decoupling the volatile memory subsystem from the host computer based on the detected trigger condition;

using the controller to communicate one or more blocks of data from the volatile memory subsystem to the non-volatile memory subsystem while the volatile memory subsystem is decoupled from the host computer; and

redundantly storing said communicated one or more blocks of data in the non-volatile memory subsystem, said redundantly storing including;

writing to a first channel of the non-volatile memory subsystem a first copy of the one or more blocks of data; and

writing to a second channel of the non-volatile memory subsystem a second copy of the one or more blocks of data.

2. The method of claim 1, wherein redundantly storing further includes determining if the first and second copies written respectively into the first and second channels are substantially the same as the original data communicated from the volatile memory subsystem.

3. The method of claim 2, wherein redundantly storing further includes re-writing the first copy into the first channel if the first copy is not substantially the same as the one or more blocks of data communicated from the volatile memory subsystem, and re-writing the second copy into the second channel if the second copy is not substantially the same as the one or more blocks of data communicated from the volatile memory subsystem.

4. The method of claim 3, wherein the writing to a second channel comprises writing to a first memory location in the second channel, and the re-writing into the second channel comprises re-writing to a second, different memory location in the second channel.

5. The method of claim 3, wherein the writing to a first channel comprises writing to a first memory location in the first channel, and the re-writing into the first channel comprises re-writing to a second, different memory location in the first channel.

6. The method of claim 1, further comprising error checking the one or more blocks communicated from the volatile memory subsystem.

7. The method of claim 1, wherein the trigger condition comprises at least one of an actual loss of power, an imminent loss of power, a reduction of power, or an indication from the host computer.

8. A method for restoring to a volatile memory subsystem data that is redundantly-backed up in first and second channels of a non-volatile memory subsystem, the method comprising:

retrieving a first copy of the data from the first channel of the non-volatile memory subsystem;

retrieving a second copy of the data from the second channel of the non-volatile memory subsystem;

error-checking the first and second copies;

communicating an error-free copy to the volatile memory subsystem, the error-free copy being generated using any one of (i) the retrieved first copy, (ii) the retrieved second copy, or (iii) a recovered error-free copy, wherein the recovered error-free copy is generated by correcting one or more data errors using data from any one of the first and second copies; and

replacing at least one of the first and second copies with the error-free copy.

9. The method of claim 8, further comprising communicating an error indication if the first and second copies contain data errors.

10. The method of claim 8, wherein replacing the at least one of the first and second copies with the error-free copy comprises storing the error-free copy in a different location in the channel from which the copy containing the one or more data errors was retrieved.

11. The method of claim 8, wherein replacing the at least one of the first and second copies with the error-free copy comprises storing the error-free copy in the same location in the channel from which the copy containing the one or more data errors was retrieved.

12. A memory system comprising:

a non-volatile memory subsystem;

a volatile memory subsystem couplable to a host; and

a switching circuit operable to decouple the volatile memory subsystem from the host and to couple the volatile memory to the non-volatile memory subsystem based on a trigger condition,

wherein the non-volatile memory subsystem includes;

a first set of one or more memory elements;

a second set of one or more memory elements; and

a controller coupled to the first and second sets of memory elements and configured to operate the first set as a first channel to which a first copy of one or more blocks of data from the volatile memory subsystem is written in response to the trigger condition, and to operate the second set as a second channel to which a second copy of the one or more blocks of data from the volatile memory subsystem is written in response to the trigger condition.

13. The memory system of claim 12, wherein the controller is further configured to determine if the first and second written copies are substantially the same as the one or more blocks of data from the volatile memory subsystem.

14. The memory system of claim 13, wherein the controller is further configured to re-write the first copy into the first channel if the first copy is not substantially the same as the one or more blocks of data from the volatile memory subsystem, and re-write the second copy into the second channel if the second copy is not substantially the same as the one or more blocks of data from the volatile memory subsystem.

15. The memory system of claim 13, wherein the writing to a first channel comprises writing to a first memory location in the first channel, and the re-writing into the first channel comprises re-writing to a second, different memory location in the first channel.

16. The memory system of claim 13, wherein the writing to a second channel comprises writing to a first memory location in the second channel, and the re-writing into the second channel comprises re-writing to a second, different memory location in the second channel.

17. The memory system of claim 12, further comprising error-checking the one or more blocks from the volatile memory subsystem.

18. The memory system of claim 12, wherein the trigger condition comprises at least one of an actual loss of power, an or imminent loss of power, a reduction of power, or an indication from the host.

19. A memory system comprising:

a volatile memory subsystem couplable to a host; and

a non-volatile memory subsystem, the non-volatile memory subsystem including;

a first set of one or more memory elements;

a second set of one or more memory elements; and

a controller coupled to the first and second sets of memory elements and configured to operate the first set as a first channel in which a first copy of one or more blocks of data from the volatile memory subsystem is backed up, and to operate the second set as a second channel in which a second copy of the one or more blocks of data from the volatile memory subsystem is backed up, and to retrieve and error-check the first and second copies, and communicate an error-free copy of the first and second copies to the volatile memory subsystem.

20. The memory system of claim 19, wherein the controller is further operative to correct one or more errors found in any one of the first and second copies using data from any one of the first and second copies, and, if one of the first or second copies is found to contain an uncorrectable error, store the other of the first or second copies in the channel from which the uncorrectable error-containing copy was retrieved.

21. The memory system of claim 20, wherein said storing is in a different location in the channel from which the uncorrectable error-containing copy was retrieved.

22. The memory system of claim 19, wherein said storing is in the same location in the channel from which the uncorrectable error-containing copy was retrieved.