Method and apparatus for transparent, real time reconstruction of corrupted data in a redundant array data storage system

• US 5,623,595 A
• Filed: 09/26/1994
• Issued: 04/22/1997
• Est. Priority Date: 09/26/1994
• Status: Expired due to Term

• Current Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Original Assignee: Oracle Corporation
• Inventors: Bailey, William
• Primary Examiner(s): Beausoliel, Jr., Robert W.
• Assistant Examiner(s): Wright, Norman M.
• Application Number:
  US08/312,509
• Time in Patent Office: 939 Days
• Field of Search: 371/10.1, 371/40.1, 371/40.2, 371/10.2, 371/40.4, 395/575, 395/182.04, 395/182.05, 395/182.06, 395/182.03, 395/185.07
• US Class Current: 714/6.12
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• 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: H04N 7/17336 Handling of requests in head-ends

Abstract

A method and apparatus for providing transparent, real time reconstruction of corrupted data from a redundant array of storage units in a manner that imposes no performance degradation for reconstruction of such corrupted data and that does not tie up system resources. The present invention is particularly suited to applications in which data is retrieved from storage equipment in approximately equally sized parcels. Each parcel is divided into "N" blocks of data. An "N+1st" parity block for each parcel is derived based on the content of the "N" blocks of data. The "N" blocks of data and the parity block for each parcel are stored in stripes of blocks in a redundancy group consisting of "N+1" data storage units. Data is read from the storage units an entire stripe at a time. To read a stripe, a read request is concurrently sent to each storage unit in the redundancy group, requesting the block of data in that storage unit that corresponds to the stripe being read. Each storage unit independently processes the read request it has received and sends back the requested block as soon as it has been read. As soon as the first "N" blocks are received, they are XOR'"'"'d together to reconstruct the outstanding "N+1st" block. The "N" received blocks and the XOR'"'"'d sum, representing a reconstruction of the outstanding "N+1st" block, are delivered to the requesting device or process. The same procedure is used each time data is read. The present invention thus delivers data at a consistent rate regardless of whether a storage unit failure occurs.

Claims

1. A computer-implemented method for providing real time reconstruction of corrupted data from a redundant array storage system containing "N+1" data storage units, comprising the steps of:

storing a first stripe of data comprising "N" blocks of data and one block of redundancy information on said "N+1" data storage units such that one of each of said "N" blocks of data is stored on each of "N" of said "N+1" data storage units and said block of redundancy information is stored on a remaining one of said data storage units;

issuing simultaneous read requests during normal system operation for all "N+1" blocks of said first stripe when any of said data stored in said first stripe is retrieved; and

reconstructing an "N+1st" block of said first stripe from contents of a first "N" blocks received in response to said simultaneous read requests, said reconstructing step being performed only if after a predetermined amount of time, said "N+1st" block has not yet been received and one of said first "N" blocks received comprises said block of redundancy information.

2. The computer-implemented method of claim 1 wherein said one block of redundancy information comprises an XOR'"'"'d sum of the data contained in said "N" blocks of data.

3. The computer-implemented method of claim 2 wherein said step of reconstructing an "N+1st" block of said first stripe from contents of said first "N" blocks received in response to said simultaneous read requests is performed by XOR'"'"'ing said contents of said first "N" blocks as said first "N" blocks are received with an XOR'"'"'d sum of any previously received blocks.

4. The computer-implemented method of claim 1 wherein said step of issuing said simultaneous read requests is performed in response to a request from a process for retrieval of data stored in said first stripe and wherein an end of said period of time is determined by said process.

5. The computer-implemented method of claim 1 wherein said "N" blocks of data of said first stripe comprise a first portion of a file of data, a second portion of said file of data being stored on said data storage units in a second stripe of blocks contiguous to said first stripe of blocks.

6. The computer-implemented method of claim 1 wherein each of said blocks contains at least 32 KB of data.

7. The computer-implemented method of claim 1 wherein said storage units comprise disk drive storage units comprising storage media divided into sectors.

8. The computer-implemented method of claim 7 wherein each of said blocks of data contains an amount of data that can be stored in an integer multiple of said sectors.

9. The computer-implemented method of claim 8 wherein said integer multiple is 1.

10. The computer-implemented method of claim 1 wherein said step of issuing said simultaneous read requests is performed in response to a request from a process for retrieval of data stored in said first stripe.

11. The computer-implemented method of claim 10 wherein said process utilizes data in increments of a predetermined size.

12. The computer-implemented method of claim 11 wherein the amount of data stored in said "N" blocks of data of said first stripe is approximately equal to said predetermined size of one of said increments.

13. A redundant array of data storage system comprising:

"N+1" data storage units;

a first stripe of data comprising "N" blocks of data and one block of redundancy information stored on said "N+1" data storage units such that one of each of said "N" blocks of data is stored on each of "N" of said "N+1" data storage units and said block of redundancy information is stored on a remaining one of said data storage units;

means for issuing simultaneous read requests for all of said "N+1" blocks in said first stripe when any data stored in said stripe is retrieved; and

means for reconstructing an "N+1st" block of said first stripe from a contents of a first "N" blocks received in response to said read requests only if after a predetermined amount of time, said "N+1st" block has not yet been received and one of said first "N" blocks received comprises said block of redundancy information.

14. The data storage system of claim 13 further comprising means for determining whether any block received in response to said read requests comprises said block of redundancy information.

15. The data storage system of claim 13 wherein said "N" blocks of data of said first stripe comprise a first portion of a file of data, a second portion of said file of data being stored on said data storage units in a second stripe of blocks contiguous to said first stripe.

16. The data storage system of claim 13 wherein each of said blocks contains at least 32 KB of data.

17. The data storage system of claim 13 wherein said data storage units comprise disk drive storage units comprising storage media divided into sectors.

18. The data storage system of claim 17 wherein each of said blocks of data contains the amount of data that can be stored in an integer multiple of said sectors.

19. The data storage system of claim 13 wherein said "N" blocks of data of said first stripe comprise a first portion of a file of data, a second portion of said file of data being stored on said data storage unit in a second stripe of blocks contiguous to said first stripe of blocks.

20. The data storage system of claim 19 wherein said file comprises video data.

21. An article of manufacture comprising a computer usable mass storage medium having computer readable program code means embodied therein for causing a processing means to provide real time reconstruction of corrupted data from a redundant array storage system containing "N+1" data storage units, said computer readable program code means in said article of manufacture comprising:

a means for storing a first stripe of data comprising "N" blocks of data and one block of redundancy information on said "N+1" data storage units such that one of each of said "N" blocks of data is stored on each of "N" of said "N+1" data storage units and said block of redundancy information is stored on a remaining one of said data storage units;

a means for issuing simultaneous read requests during normal system operation for all "N+1" blocks of said first stripe when any of said data stored in said first stripe is retrieved; and

a means for reconstructing an "N+1st" block of said first stripe from contents of a first "N" blocks received in response to said simultaneous read requests only if after a predetermined amount of time, said "N+1st" block has not yet been received and one of said first "N" blocks received comprises said block of redundancy information.

22. The article of manufacture of claim 21 wherein said one block of redundancy information comprises an XOR'"'"'d sum of the data contained in said "N" blocks of data.

23. The article of manufacture of claim 21 wherein said means for reconstructing an "N+1st" block of said first stripe from contents of said first "N" blocks received in response to said simultaneous read requests further XOR'"'"'s said contents of said first "N" blocks as said first "N" blocks are received with an XOR'"'"'d sum of any previously received blocks.

24. The article of manufacture of claim 21 wherein said means for issuing said simultaneous read requests performs in response to a request from a process for retrieval of data stored in said first stripe and wherein an end of said period of time is determined by said process.

25. The article of manufacture of claim 21 wherein said "N" blocks of data of said first stripe comprise a first portion of a file of data, a second portion of said file of data being stored on said data storage units in a second stripe of blocks contiguous to said first stripe of blocks.

26. The article of manufacture of claim 21 wherein each of said blocks contains at least 32 KB of data.

27. The article of manufacture of claim 21 wherein said storage units comprise disk drive storage units comprising storage media divided into sectors.

28. The article of manufacture of claim 27 wherein each of said blocks of data contains an amount of data that can be stored in an integer multiple of said sectors.

29. The article of manufacture of claim 28 wherein said integer multiple is 1.

30. The article of manufacture of claim 21 wherein said means for issuing said simultaneous read requests performs in response to a request from a process for retrieval of data stored in said first stripe.

31. The article of manufacture of claim 30 wherein said process utilizes data in increments of a predetermined size.

32. The article of manufacture of claim 31 wherein the amount of data stored in said "N" blocks of data of said first stripe is approximately equal to said predetermined size of one of said increments.