System and method of redundantly storing and retrieving data with cooperating storage devices

• US 7,827,439 B2
• Filed: 09/11/2008
• Issued: 11/02/2010
• Est. Priority Date: 09/28/2007
• Status: Expired due to Fees

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Symantec Corporation (NortonLifeLock Inc.)
• Inventors: Kiselev, Oleg, Harmer, Craig K., Mathew, George, Karr, Ronald S.
• Primary Examiner(s): Chu; Gabriel L
• Application Number:
  US12/208,882
• Publication Number:
  US 20090089612A1
• Time in Patent Office: 782 Days
• Field of Search: None
• US Class Current: 714/5.11
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/1038 LFS, i.e. Log Structured File System used in RAID systems with parity
• CPC Class Codes: G06F 2211/1054 Parity-fast hardware, i.e. dedicated fast hardware for RAID systems with parity

Abstract

A system and method for data storage in an array. A system includes a client coupled to a storage subsystem. The storage subsystem comprises data storage locations addressable as rows and columns in an array. Each column comprises a separate storage device. Each row includes redundant data. For a given row, a coordinating storage device receives data from the client, coordinates computation and storage of redundant data, and forwards data to other storage devices. In response to receiving data targeted for storage in a given storage location, a non-volatile, temporary storage device that is associated with the separate storage device that includes the given storage location buffers the received data. The coordinating storage device conveys a write completion message to the client in response to detecting that the data has been buffered in the non-volatile, temporary storage devices. At least two storage devices are coordinating storage devices in separate rows.

Claims

1. A computer system comprising:

a client; and

a storage subsystem coupled to the client, wherein the storage subsystem comprises a plurality of data storage locations addressable as rows and columns in an array, each column of the array comprising a separate storage device of a plurality of storage devices;

wherein at least two of the separate storage devices of the plurality of storage devices are predetermined as coordinating storage devices for different rows of the array, and wherein for a corresponding row in the array, only a single storage device is configured to act as a coordinating storage device at a given time;

wherein for a given row in the array, a coordinating storage device is configured to;

receive data from the client for storage in the given row;

forward one or more portions of the received data to one or more other ones of the plurality of storage devices; and

coordinate the computation and storage of redundant data in the given row.

2. The system as recited in claim 1, wherein in response to receiving a portion of data targeted for storage in a given storage location of a particular storage device, a non-volatile temporary storage device associated with the particular storage device is configured to buffer the received portion of data prior to the received portion of data being stored in the given storage location.

3. The system as recited in claim 2, wherein the coordinating storage device is further configured to convey a write completion message to the client in response to detecting that one or more copies of the one or more portions of data have been buffered in a non-volatile temporary storage devices associated with one or more storage devices of the given row.

4. The system as recited in claim 3, wherein the system is configured to:

detect a failure of at least one of the plurality of storage devices; and

if the failure occurred after a write completion message has been conveyed and before at least a portion of the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuild the data stored in the given row including the at least some redundant data from the data that was stored in the non-volatile temporary storage devices; and

if the failure occurred after the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuild the data stored in the given row including the at least some redundant data from the data that was stored in the given row.

5. The system as recited in claim 1, wherein the coordinating storage device is further configured to compute first parity values of a plurality of portions of data stored in the given row.

6. The system as recited in claim 5, wherein in response to detecting that data for computing parity values have been received by the coordinating storage device for the given row, non-volatile temporary storage devices associated with each of the plurality of storage devices are further configured to transfer a buffered portion of data to a storage location in the given row of the associated storage device.

7. The system as recited in claim 1, wherein the array utilizes at least one of a RAID-1 layout, a RAID-5 layout, a RAID-6 layout, or another erasure-coded layout.

8. The system as recited in claim 5,

wherein for a given row in the array, the coordinating storage device is further configured to forward the one or more received portions of data to a second one of the separate storage devices in the given row;

and

wherein the second one of the separate storage devices is configured to compute second parity values of a plurality of portions of data stored in the given row using the forwarded portions of data.

9. A method of storing data in storage locations of an array comprising a plurality of storage devices, wherein the storage locations are addressable as rows and columns, each column of the array comprising a separate storage device, the method comprising:

designating at least two of the separate storage devices of the plurality of storage devices as coordinating storage devices for different rows of the array, wherein for a corresponding row in the array, only a single storage device is configured to act as a coordinating storage device at a given time;

receiving data at a predetermined one of the plurality of storage devices designated as a coordinating storage device for a given row of the array, wherein the data is targeted for storage in the given row; and

forwarding one or more portions of the data from the predetermined coordinating storage device to one or more other ones of the plurality of storage devices.

10. The method of claim 9, wherein in response to receiving a portion of data targeted for storage in a given storage location of a particular storage device, the method further comprises a non-volatile temporary storage device associated with the particular storage device buffering the received portion of data prior to the received portion of data being stored in the given storage location.

11. The method as recited in claim 10, further comprising conveying a write completion message to a client in response to detecting that one or more copies of the one or more portions of data have been buffered in non-volatile temporary storage devices associated with one or more storage devices of the given row.

12. The method as recited in claim 11, further comprising:

detecting a failure of at least one of the plurality of storage devices; and

if the failure occurred after a write completion message has been conveyed and before at least a portion of the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuilding the data stored in the given row including at least some redundant data from the data that was stored in the non-volatile temporary storage devices; and

if the failure occurred after the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuilding the data stored in the given row including the at least some redundant data from the data that was stored in the given row.

13. The method as recited in claim 9, further comprising the coordinating storage device computing parity values of a plurality of portions of data stored in the given row.

14. The method as recited in claim 13, wherein in response to detecting that data for computing parity values have been received by the coordinating storage device for the given row, the method further comprises non-volatile temporary storage devices associated with each of the plurality of storage devices transferring a buffered portion of data to a storage location in the given row of the associated storage device.

15. The method as recited in claim 9, wherein the array utilizes at least one of a RAID-1 layout, a RAID-5 layout, a RAID-6 layout, or another erasure-coded layout.

16. A plurality of computer readable storage media storing computer instructions that are executable by a processor to:

access storage locations of a storage array comprising a plurality of storage devices, wherein the storage locations are addressable as rows and columns, each column of the array comprising a separate storage device;

designate at least two of the separate storage devices of the plurality of storage devices as coordinating storage devices for different rows of the array, wherein for a corresponding row in the array, only a single storage device is configured to act as a coordinating storage device at a given time;

receive data at a predetermined one of the plurality of storage devices designated as a coordinating storage device for a given row of the array, wherein the data is targeted for storage in the given row; and

forward one or more portions of the data from the predetermined coordinating storage device to one or more other ones of the plurality of storage devices.

17. The computer readable storage media of claim 16, wherein the instructions are further executable to buffer the received portion of data in a non-volatile temporary storage device associated with a storage device that includes a given storage location, in response to receiving a portion of data targeted for storage in the given storage location.

18. The computer readable storage media as recited in claim 17, wherein the instructions are further executable to convey a write completion message to a client in response to detecting that one or more copies of the one or more portions of data have been buffered in non-volatile temporary storage devices associated with one or more storage devices of a given row.

19. The computer readable storage media as recited in claim 18, wherein the instructions are further executable to:

detect a failure of at least one of the plurality of storage devices; and

if the failure occurred after a write completion message has been conveyed and before at least a portion of the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuild the data stored in the given row including the at least some redundant data from the data that was stored in the non-volatile temporary storage devices; and

if the failure occurred after the buffered data has been transferred from the non-volatile temporary storage devices to associated storage locations in a given row, rebuild the data stored in the given row including the at least some redundant data from the data that was stored in the given row.

20. The computer readable storage media as recited in claim 16, wherein the instructions are further executable to:

cause the coordinating storage device to compute parity values of a plurality of portions of data stored in the given row; and

cause each non-volatile temporary storage device to transfer a buffered portion of data to a storage location in the given row of an associated separate storage device, in response to detecting that data for computing parity values have been received by the coordinating storage device for the given row.