Recovering from abnormal interruption of a parity update operation in a disk array system

• US 7,487,394 B2
• Filed: 04/21/2008
• Issued: 02/03/2009
• Est. Priority Date: 11/19/2004
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gerhard, Adrian Cuenin, Galbraith, Robert Edward, Forhan, Carl Edward
• Primary Examiner(s): Lohn; Joshua A
• Application Number:
  US12/106,856
• Publication Number:
  US 20080201608A1
• Time in Patent Office: 288 Days
• Field of Search: 714/6, 714/15, 714/18, 714/19, 714/21, 714/52, 714/54, 714/801, 707/202, 707/204, 711/162
• US Class Current: 714/15
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/104 Metadata, i.e. metadata associated with RAID systems with parity
• CPC Class Codes: G06F 2211/1057 Parity-multiple bits-RAID6, i.e. RAID 6 implementations
• CPC Class Codes: G06F 2211/109 Sector level checksum or ECC, i.e. sector or stripe level checksum or ECC in addition to the RAID parity calculation

Abstract

Data associated with the state of a parity update operation in a disk array system such as a RAID-6 system is stored during performance of the operation so that, in the event the operation is interrupted, recovery may be initiated using the stored data. The stored data may include a state indicator that is indicative of the status of the parity update operation, and snapshot data (e.g., a delta value indicative of a difference between new and old data) captured during the parity update operation.

Claims

1. A program product comprising:

program code configured to upon execution;

initiate a parity update operation in association with storing new data on a disk in a disk array system;

maintain a state indicator during the parity update operation, the state indicator indicative of a status of the parity update operation;

capture snapshot data during the parity update operation; and

store the snapshot data in non-volatile memory; and

a computer readable recordable medium bearing the program code.

2. The program product of claim 1, wherein the program code is further configured to:

create a parity update footprint in non-volatile memory, the footprint including the state indicator; and

change the state indicator to one of a plurality of valid states as the update operation progresses.

3. The program product of claim 1, wherein the program code is further configured to:

determine the parity update operation was interrupted before completing; and

based upon the determination, synchronize parity and data in the disk array system using at least one of the state indicator and the snapshot data.

4. The program product of claim 1, wherein the snapshot data comprises a delta value, the delta value indicative of a difference between the new data and old data being overwritten by the new data.

5. The program product of claim 1, wherein the program code is further configured to perform the parity update operation by updating the new data, updating a first parity value associated with the new data, and updating a second parity value associated with the new data, and wherein the state indicator comprises at least three states, a first of which indicating that the new data is in doubt, a second of which indicating that the first parity value is in doubt, and the third of which indicating that the second parity value is in doubt.

6. The program product of claim 5, wherein the program code is configured to initiate the parity update operation while a disk other than that to which the new data is being written is exposed, and wherein the state indicator includes a state that indicates that a parity value is in doubt but that the snapshot data is available.

7. The program product of claim 1, wherein the disk array system comprises a RAID-6 system.

8. An apparatus comprising:

an interface configured to couple to a plurality of disks in a disk array; and

a disk array controller coupled to the interface, the disk array controller configured to;

initiate a parity update operation in association with storing new data on a disk in the disk array;

maintain a state indicator during the parity update operation, the state indicator indicative of a status of the parity update operation;

capture snapshot data during the parity update operation; and

store the snapshot data in non-volatile memory.

9. The apparatus of claim 8, wherein the disk array controller is further configured to:

create a parity update footprint in non-volatile memory, the footprint including the state indicator; and

change the state indicator to one of a plurality of valid states as the update operation progresses.

10. The apparatus of claim 8, wherein the disk array controller is further configured to:

determine the parity update operation was interrupted before completing; and

based upon the determination, synchronize parity and data in the disk array system using at least one of the state indicator and the snapshot data.

11. The apparatus of claim 8, wherein the snapshot data comprises a delta value, the delta value indicative of a difference between the new data and old data being overwritten by the new data.

12. The apparatus of claim 8, wherein the disk array controller is further configured to perform the parity update operation by updating the new data, updating a first parity value associated with the new data, and updating a second parity value associated with the new data, and wherein the state indicator comprises at least three states, a first of which indicating that the new data is in doubt, a second of which indicating that the first parity value is in doubt, and the third of which indicating that the second parity value is in doubt.

13. The apparatus of claim 12, wherein the disk array controller is configured to initiate the parity update operation while a disk other than that to which the new data is being written is exposed, and wherein the state indicator includes a state that indicates that a parity value is in doubt but that the snapshot data is available.

14. The apparatus of claim 8, wherein the disk array controller comprises a RAID-6 controller.

15. The apparatus of claim 8, wherein the disk array controller comprises program code configured to perform at least one of initiating the parity update operation, maintaining the state indicator, capturing the snapshot data and storing the snapshot data.

16. The apparatus of claim 8, further comprising a plurality of disks coupled to the interface.