Method and system for storing excess data in a redundant array of independent disk level 6

• US 8,145,840 B2
• Filed: 06/05/2009
• Issued: 03/27/2012
• Est. Priority Date: 06/05/2009
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: LSI Corporation (Broadcom, Inc.)
• Inventors: KOUL, SUNNY, Kumar, Ranjan, Morabad, Gururaj Shivashankar
• Primary Examiner(s): Tran, Denise
• Application Number:
  US12/478,771
• Publication Number:
  US 20100312961A1
• Time in Patent Office: 1,026 Days
• Field of Search: None
• US Class Current: 711/114
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/1004 Adaptive RAID, i.e. RAID system adapts to changing circumstances, e.g. RAID1 becomes RAID5 as disks fill up
• CPC Class Codes: G06F 2211/1057 Parity-multiple bits-RAID6, i.e. RAID 6 implementations

Abstract

A method and system for storing excess data in a redundant array of independent disks (RAID) level 6 are disclosed. In one embodiment, a method for storing excess data in a RAID 6 volume includes writing excess data to Q parity blocks of a first RAID 6 volume when a receipt of the excess data directed to the first RAID 6 volume is detected subsequent to a saturation of the first RAID 6 volume, where the first RAID 6 volume is converted to a pseudo-RAID 5 volume with P parity blocks. The method further includes re-computing the P parity blocks of the pseudo-RAID 5 volume based on data blocks of the pseudo-RAID 5 volume. In addition, the method includes constructing a second RAID 6 volume based on the pseudo-RAID 5 volume when at least one additional drive is inserted to the pseudo-RAID 5 volume.

Claims

1. A method for storing excess data in a redundant array of independent disks (RAID) 6 volume, comprising:

writing excess data to Q parity blocks of a first RAID 6 volume when a receipt of the excess data directed to the first RAID 6 volume is detected subsequent to a saturation of the first RAID 6 volume, wherein the first RAID 6 volume is converted to a pseudo-RAID 5 volume with P parity blocks;

re-computing the P parity blocks of the pseudo-RAID 5 volume based on data blocks of the pseudo-RAID 5 volume; and

constructing a second RAID 6 volume based on the pseudo-RAID 5 volume when at least one additional drive is inserted to the pseudo-RAID 5 volume.

2. The method of claim 1, wherein the writing the excess data to the Q parity blocks further comprises writing signature data subsequent to the excess data to fill the Q parity blocks if a size of the excess data is less than a size of the Q parity blocks in aggregate.

3. The method of claim 1, wherein the writing the excess data comprises forwarding a flag signal to indicate the receipt of the excess data.

4. The method of claim 3, wherein the flag signal comprises an aural alarm, a visual alert, and an event post.

5. The method of claim 3, wherein the writing the excess data comprises forwarding a prompt signal for inserting the at least one additional drive to the pseudo-RAID 5 volume.

6. The method of claim 1, wherein the constructing the second RAID 6 volume comprises:

rearranging the data blocks of the pseudo-RAID 5 volume based on a set configuration; and

computing P parity blocks and Q parity blocks of the second RAID 6 volume upon completion of the rearranging the data blocks.

7. The method of claim 1, wherein the first RAID 6 volume comprises five stripes in four physical drives.

8. The method of claim 7, wherein a first drive of the four physical drives comprises a data block 0, data block 3, a P parity block 3, a Q parity block 4, and a data block 8;

a second drive of the four physical drives comprises a data block 1, a P parity block 2, a Q parity block 3, a data block 6, and a data block 9;

a third drive of the four physical drives comprises a P parity block 1, a Q parity block 2, a data block 4, a data block 7, and a P parity block 5; and

a fourth drive of the four physical drives comprises a Q parity block 1, a data block 2, a data block 5, a P parity block 4, and a Q parity block 5.

9. The method of claim 8, wherein the excess data comprise a data block 10, a data block 11, a data block 12, a data block 13, and a data block 14.

10. The method of claim 9, wherein data blocks of the pseudo-RAID 5 volume comprises the data block 10 written to the Q parity block 5, the data block 11 written to the Q parity block 4, the data block 12 written to the Q parity block 3, the data block 13 written to the Q parity block 2, and the data block 14 written to the Q parity block 1.

11. The method of claim 10, wherein the re-computing the P parity blocks comprises re-computing the P parity block 1 based on the data block 0, the data block 1, and the data block 14;

re-computing the P parity block 2 based on the data block 3, the data block 13, and the data block 2;

re-computing the P parity block 3 based on the data block 12, the data block 4, and the data block 5;

re-computing the P parity block 4 based on the data block 11, the data block 6, and the data block 7; and

re-computing the P parity block 5 based on the data block 8, the data block 9, and the data block 10.

12. The method of claim 11, wherein the at least one additional drive comprises a fifth drive inserted in a middle of the four physical drives.

13. The method of claim 12, wherein the constructing the second RAID 6 volume comprises:

rearranging the data blocks of the pseudo-RAID 5 volume based on a set configuration; and

computing P parity blocks and Q parity block for the second RAID 6 volume upon completion of the rearranging the data blocks.

14. The method of claim 13, wherein the set configuration comprises the first drive of the second RAID 6 volume to include the data block 0, the data block 4, the data block 8, a re-computed P parity block 4, and a re-computed Q parity block 5;

the second drive of the second RAID 6 volume to include the data block 1, the data block 5, a re-computed P parity block 3, a re-computed Q parity block 4, and the data block 12;

the third drive of the second RAID 6 volume to include a re-computed P parity block 1, a re-computed Q parity block 2, the data block 6, the data block 10, and the data block 14;

the fourth drive of the second RAID 6 volume to include a re-computed Q parity block 1, the data block 3, the data block 7, the data block 11, and a re-computed P parity block 5; and

the fifth drive of the second RAID 6 volume to include the data block 2, a re-computed P parity block 2, a re-computed Q parity block 3, the data block 9, and the data block 13.

15. A system in a storage control device for storing excess data in a redundant array of independent disks (RAID) 6 volume, comprising:

a processor; and

a memory coupled to the processor and configured for temporarily storing a set of instructions, when executed by the processor, causes the processor to perform a method comprising;

writing excess data to Q parity blocks of a first RAID 6 volume when a receipt of the excess data directed to the first RAID 6 volume is detected subsequent to a saturation of the first RAID 6 volume, wherein the first RAID 6 volume is converted to a pseudo-RAID 5 volume with P parity blocks;

re-computing the P parity blocks of the pseudo-RAID 5 volume based on data blocks of the pseudo-RAID 5 volume; and

constructing a second RAID 6 volume based on the pseudo-RAID 5 volume when at least one additional drive is inserted to the pseudo-RAID 5 volume.

16. The system of claim 15, wherein the storage control device comprises a RAID controller.

17. The system of claim 15, wherein the storage control device comprises an array controller.

18. The system of claim 15, wherein the memory comprises a non-volatile memory.

19. A non-transitory computer readable medium for storing excess data in a redundant array of independent disks (RAID) 6 volume having instructions that, when executed by a computer, cause the computer to perform a method comprising:

writing excess data to Q parity blocks of a first RAID 6 volume when a receipt of the excess data directed to the first RAID 6 volume is detected subsequent to a saturation of the first RAID 6 volume, wherein the first RAID 6 volume is converted to a pseudo-RAID 5 volume with P parity blocks;

re-computing the P parity blocks of the pseudo-RAID 5 volume based on data blocks of the pseudo-RAID 5 volume; and

constructing a second RAID 6 volume based on the pseudo-RAID 5 volume when at least one additional drive is inserted to the pseudo-RAID 5 volume.

20. The non-transitory computer readable medium of claim 19, wherein the constructing the second RAID 6 volume comprises:

rearranging the data blocks of the pseudo-RAID 5 volume based on a set configuration; and

computing P parity blocks and Q parity blocks of the second RAID 6 volume upon completion of the rearranging the data blocks.