Data storage

• US 6,826,778 B2
• Filed: 03/13/2002
• Issued: 11/30/2004
• Est. Priority Date: 04/15/1996
• Status: Expired due to Term

• Current Assignee: Autodesk, Inc.
• Original Assignee: Autodesk, Inc.
• Inventors: Bopardikar, Raju C., Braine, Adrian R.
• Primary Examiner(s): BOCCIO, VINCENT F
• Application Number:
  US10/096,565
• Publication Number:
  US 20020094195A1
• Time in Patent Office: 993 Days
• Field of Search: H04/N.5781, H04/N.591, 386/125-126, 386/46, 386/52, 725/145, 725/146, 725/92, 725/93, 714/6, 714/7
• US Class Current: 725/145
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G11B 20/1833 by adding special lists or symbols to the coded information G11B20/1806, G11B20/1866 take precedence
• CPC Class Codes: G11B 2220/415 Redundant array of inexpensive disks [RAID] systems
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: H04N 11/20 Conversion of the manner in which the individual colour picture signal components are combined, e.g. conversion of colour television standards
• CPC Class Codes: H04N 21/2182 involving memory arrays, e.g. RAID disk arrays RAID arrays per se G06F3/0689; use of parity to protect data in RAID systems G06F11/1008
• CPC Class Codes: H04N 5/262 Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
• CPC Class Codes: H04N 5/781 on disks or drums
• CPC Class Codes: H04N 5/945 for signals recorded by pulse code modulation

Abstract

Video data in the form of a plurality of digitized frames, is stored on a plurality of magnetic disks. Each image frame is striped across a plurality of disks and redundant parity information, derived from the stripes, is written to an additional disk. Disk failure is detected and in response to this detection missing data is regenerated from the parity information. This allows the transfer of video data in real time to be maintained for output so that the system remains operational. While data is being read in real time, derived from regenerated data, the regenerated data is written to an operational disk, thereby reprotecting the data in the event of a subsequent failure. Frame supplied to output are labelled as being protected or unprotected and application programs may respond to this status information as considered appropriate.

Claims

1. Data storage apparatus comprising storage means, transfer means and processing means, wherein

said storage means comprises a plurality of storage devices configured to store respective portions of a data file with redundant data derived from said portions;

said transfer means is arranged to transfer said data portions between said storage means and said processing means by utilising available transfer bandwidth;

said processing means is configured to regenerate lost data from said redundant data during a reading operation to provide output data in the form of a complete data file that includes regenerated data; and

said processing means is configured to write said regenerated data to an operational storage device using said transfer bandwidth such that the regenerated data file is protected against further losses and does not require regeneration on a subsequent reading operation.

2. Apparatus according to claim 1, wherein said storage devices are magnetic disks.

3. Apparatus according to claim 2, wherein each data portion is written to a respective disk and said redundant data is written to a separate disk.

4. Apparatus according to claim 3, wherein said redundant data is parity data derived by an exclusive ORing operation.

5. Apparatus according to claim 1, wherein output data is written to a data buffer.

6. Apparatus according to claim 5, wherein two output frame buffers alternate in operation, to effect double buffering in which a first buffer is written randomly from the storage devices and a second buffer is read sequentially.

7. Apparatus according to claim 1, wherein said processing means detects data errors and initiates data regeneration in response to said detection.

8. Apparatus according to claim 1, wherein a spare drive is maintained in an array to receive regenerated data.

9. Apparatus according to claim 1, wherein said processing means is configured to label image frames as being protected or as being unprotected.

10. Apparatus according to claim 1, wherein said processing means is configured to perform additional regeneration of data not requested for output during relatively idle periods.

11. Apparatus according to claim 1, wherein said processing means is configured to detect disk imbalance conditions after data has been regenerated.

12. A method of storing data, wherein

data portions derived from data files in combination with redundant data derived from said portions are stored on a plurality of storage devices;

data portions are transferred between said storage devices and processing means by uzilising available transfer bandwidth;

a lost or corrupted data portion is regenerated from said redundant data during a reading operation;

said regenerated data is written to an operational storage device utilising the available transfer bandwidth while output data is being transferred to a compositing process, wherein said output data includes said regenerated data.

13. A method according in claim 12, wherein data errors are detected during the replay of stored data and data regeneration is initiated in response to said detection.

14. A method according to claim 12, wherein output data files are labelled as being protected or as being unprotected, wherein an unprotected label indicated that data has been regenerated.

15. A method according to claim 12, wherein additional regeneration of data is effected during idle periods.

16. A method according to claim 12, including procedures for detecting disk imbalance conditions after data has been regenerated.