Methods and systems for storing data in a redundant manner on a plurality of storage units of a storage system

• US 9,563,509 B2
• Filed: 07/15/2014
• Issued: 02/07/2017
• Est. Priority Date: 07/15/2014
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Nimble Storage Inc (Hewlett-Packard Enterprise Company)
• Inventors: Han, Chunqi, Nanduri, Anil, Vishnumolakala, Murali Krishna
• Primary Examiner(s): Maskulinski, Michael
• Assistant Examiner(s): Amoroso, Anthony J
• Application Number:
  US14/332,282
• Publication Number:
  US 20160019114A1
• Time in Patent Office: 938 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1084 Degraded mode, e.g. caused by single or multiple storage removals or disk failures
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1096 Parity calculation or recalculation after configuration or reconfiguration of the system

Abstract

Described herein are techniques for storing data in a redundant manner on a plurality of storage units of a storage system. While all of the storage units are operating without failure, only error-correction blocks are stored on a first one of the storage units, while a combination of data blocks and error-correction blocks are stored on a second one of the storage units. Upon failure of the second storage unit, one or more data blocks and one or more error-correction blocks formerly stored on the second storage unit are reconstructed, and the one or more reconstructed data blocks and the one or more reconstructed error-correction blocks are stored on the first storage unit.

Claims

1. A method for a storage system having a plurality of storage units, the method comprising:

while all of the storage units are operating without failure, storing only error-correction blocks on a first one of the storage units and storing a combination of data blocks and error-correction blocks on a second one of the storage units; and

upon failure of the second storage unit, (i) reconstructing one or more data blocks and one or more error-correction blocks formerly stored on the second storage unit, and (ii) storing the one or more reconstructed data blocks and the one or more reconstructed error-correction blocks on the first storage unit in an offset manner such that the storing of a first reconstructed block belonging to a first stripe on the first storage unit does not involve writing over an error-correction block belonging to the first stripe on the first storage unit.

2. The method of claim 1, further comprising:

prior to storing the one or more reconstructed data blocks and one or more error-correction blocks on the first storage unit, backing up one or more of the error-correction blocks on the first storage unit on a persistent storage device.

3. The method of claim 2, wherein at least one of the reconstructed data blocks overwrites the one or more error-correction blocks on the first storage unit that have been backed up onto the persistent storage device.

4. The method of claim 3, wherein at least one of the error-correction blocks that is backed up belongs to the first stripe, and the at least one of the error-correction blocks that is backed up and belongs to the first stripe is overwritten by at least one reconstructed data block that belongs to a second stripe.

5. The method of claim 2, wherein at least one of the reconstructed error-correction blocks overwrites the one or more error-correction blocks on the first storage unit that have been backed up onto the persistent storage device.

6. The method of claim 5, wherein at least one of the error-correction blocks that is backed up belongs to the first stripe, and the at least one of the error-correction blocks that is backed up and belongs to the first stripe is overwritten by at least one reconstructed error-correction block that belongs to a second stripe.

7. The method of claim 1, wherein at least one of the reconstructed data blocks overwrites at least one of the error-correction blocks on the first storage unit.

8. The method of claim 7, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed data block that belongs to a second stripe.

9. The method of claim 1, wherein at least one of the reconstructed error-correction blocks overwrites at least one of the error-correction blocks on the first storage unit.

10. The method of claim 9, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed error-correction block that belongs to a second stripe.

11. A storage system, comprising:

a plurality of storage units;

a main memory;

a processor communicatively coupled to the plurality of storage units and the main memory; and

a set of instructions on the main memory that, when executed by the processor, cause the processor to;

while all of the storage units are operating without failure, store only error-correction blocks on a first one of the storage units and store a combination of data blocks and error-correction blocks on a second one of the storage units; and

upon failure of the second storage unit, (i) reconstruct one or more data blocks and one or more error-correction blocks formerly stored on the second storage unit, and (ii) store the one or more reconstructed data blocks and one or more reconstructed error-correction blocks on the first storage unit in an offset manner such that the storing of a first reconstructed block belonging to a first stripe on the first storage unit does not involve writing over an error-correction block belonging to the first stripe on the first storage unit.

12. The storage system of claim 11, wherein at least one of the reconstructed data blocks overwrites at least one of the error-correction blocks on the first storage unit.

13. The storage system of claim 12, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed data block that belongs to a second stripe.

14. The storage system of claim 11, wherein at least one of the reconstructed error-correction blocks overwrites at least one of the error-correction blocks on the first storage unit.

15. The storage system of claim 14, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed error-correction block that belongs to a second stripe.

16. A non-transitory machine-readable storage medium for a storage system having a plurality of storage units, a main memory, and a processor communicatively coupled to the plurality of storage units and the main memory, the non-transitory machine-readable storage medium comprising software instructions that, when executed by the processor, cause the processor to:

while all of the storage units are operating without failure, store only error-correction blocks on a first one of the storage units and store a combination of data blocks and error-correction blocks on a second one of the storage units; and

upon failure of the second storage unit, (i) reconstruct one or more data blocks and one or more error-correction blocks formerly stored on the second storage unit, and (ii) store the one or more reconstructed data blocks and one or more reconstructed error-correction blocks on the first storage unit in an offset manner such that the storing of a first reconstructed block belonging to a first stripe on the first storage unit does not involve writing over an error-correction block belonging to the first stripe on the first storage unit.

17. The non-transitory machine-readable storage medium of claim 16, wherein at least one of the reconstructed data blocks overwrites at least one of the error-correction blocks on the first storage unit.

18. The non-transitory machine-readable storage medium of claim 17, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed data block that belongs to a second stripe.

19. The non-transitory machine-readable storage medium of claim 16, wherein at least one of the reconstructed error-correction blocks overwrites at least one of the error-correction blocks on the first storage unit.

20. The non-transitory machine-readable storage medium of claim 19, wherein at least one of the error-correction blocks that is overwritten belongs to the first stripe, and the at least one of the error-correction blocks that is overwritten and belongs to the first stripe is overwritten by at least one reconstructed error-correction block that belongs to a second stripe.