Blocking write access to memory modules of a solid state drive

• US 8,495,432 B2
• Filed: 05/31/2012
• Issued: 07/23/2013
• Est. Priority Date: 12/15/2009
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Dickens, Louie Arthur, Johnson, Timothy A., Klein, Craig Anthony, Lucas, Gregg Steven, Winarski, Daniel James
• Primary Examiner(s): SCHELL, JOSEPH O
• Application Number:
  US13/484,788
• Publication Number:
  US 20120239969A1
• Time in Patent Office: 418 Days
• Field of Search: 714/5, 714/39, 714/42, 714/47, 714/718, 714/723, 714/6.1, 714/6.11, 714/6.13
• US Class Current: 714/42
• CPC Class Codes: G06F 11/073 in a memory management context, e.g. virtual memory or cache management memory management G06F12/00; testing of static memory units G11C29/00
• CPC Class Codes: G06F 11/076 by exceeding a count or rate limit, e.g. word- or bit count limit
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/0796 Safety measures, i.e. ensuring safe condition in the event of error, e.g. for controlling element
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area

Abstract

Described are embodiments of an invention for blocking write access to memory modules of a solid state drive. The solid state drive includes a controller access module or a memory access module that controls write access to the solid state drive and the memory modules of the solid state drive. Upon determining that a memory module has failed, the failed memory module or the entire solid state memory device is configured to be read only to prevent an errant write of data over critical data. Further, a failed memory module, or solid state device memory having a failed memory module, may be replaced upon failure.

Claims

1. A method comprising:

determining a failure of at least one memory module of a solid state memory device, said solid state memory device having at least one memory module; and

in response to said determination of a failure of at least one memory module of said solid state memory device, logically configuring at least a portion of said solid state memory device to be read-only by controlling power to at least one write pin corresponding to said at least one memory module for which said failure was determined.

2. The method of claim 1, wherein said determination of a failure comprises detecting a number of data access errors for each memory module of said solid state memory device and determining if a data access error threshold for at least one memory module has been reached.

3. The method of claim 2, further comprising in response to detecting a number of data access errors for at least one memory module of a solid state memory device, incrementing a data access error count for said at least one memory module.

4. The method of claim 1, wherein said at least a portion of said solid state memory device comprises the entire solid state memory device.

5. The method of claim 4, further comprising a reconstruction process said reconstruction process comprises reconstructing data on said failed memory module, copying data from non-failed memory modules, replacing said solid state memory device with a new solid state memory device and storing reconstructed data and copied data on said new solid state drive device.

6. The method of claim 1, further comprising a reconstruction process, said reconstruction process comprises copying data from said failed memory module and storing said data to an alternative memory module of said solid state memory device.

7. The method of claim 1, further comprising a reconstruction process, said reconstruction process comprises copying data from a memory module containing a mirror copy of data of said failed memory module and storing said mirror copy of data to an alternative memory module of said solid state memory device.

8. A method comprising:

detecting a number of data access errors for each memory module of a solid state memory device, the solid state memory device having at least one memory module;

determining if a data access error threshold for at least one memory module has been reached;

in response to determining said data access error threshold has been reached, logically configuring at least a portion of said solid state memory device to be read-only by controlling power to at least one write pin corresponding to said at least one memory module for which said data access error threshold has been reached; and

in response to logically configuring at least a portion of said solid state memory device to be read-only, performing a solid state memory device reconstruction process.

9. A memory system comprising:

a solid state memory device; and

a solid state drive controller coupled to said solid state memory device, said solid state drive controller configured to;

determine a failure of at least one memory module of a solid state memory device, said solid state memory device having at least one memory module; and

in response to said determination of a failure of at least one memory module of said solid state memory device, logically configure at least a portion of said solid state memory device to be read-only by controlling power to at least one write pin corresponding to said at least one memory module for which said failure was determined.

10. The memory system of claim 9 wherein said solid state drive controller is configured to perform said determination of a failure of at least one memory module of said solid state drive controller by detecting a number of data access errors for each memory module of said solid state memory device and determining if a error threshold for at least one memory module has been reached.

11. The memory system of claim 10, wherein said solid state drive controller is further configured to increment a data access error count for said at least one memory module in response to detecting a number of data access errors for at least one memory module of a solid state memory device.

12. The memory system of claim 9, wherein said at least a portion of said solid state memory device comprises the entire solid state memory device.

13. The memory system of claim 9, wherein said solid state drive controller is further configured to perform a reconstruction process, said reconstruction process comprising copying data from said failed memory module and storing said data to an alternative memory module of said solid state memory device.

14. The memory system claim 9, wherein said solid state drive controller is further configured to perform a reconstruction process, said reconstruction process comprising copying data from a memory module containing a mirror copy of data of said failed memory module and storing said mirror copy of data to an alternative memory module of said solid state memory device.

15. The memory system of claim 9, wherein said solid state drive controller is further configured to perform a reconstruction process, said reconstruction process comprising reconstructing data on said failed memory module, copying data from non-failed memory modules, replacing said solid state memory device with a new solid state memory device and storing reconstructed data and copied data on said new solid state drive device.

16. A memory system comprising:

a solid state memory device; and

a solid state drive controller coupled to said solid state memory device, said solid state drive controller configured to;

detect a number of data access errors for each memory module of a solid state memory device, the solid state memory device having at least one memory module;

determine if a data access error threshold for at least one memory module has been reached;

logically configure at least a portion of said solid state memory device to be read-only in response to said determining said data access error threshold has been reached by controlling power to at least one write pin corresponding to said at least one memory module for which said data access error threshold has been reached; and

perform a solid state memory device reconstruction process in response to said configuration of at least a portion of said solid state memory device to be read-only.