초록 ▼

When parity checking in a disk array such as a RAID-6 system determines data and parity information is unsynchronized, additional calculations are performed to determine whether the error may be attributed to faulty data on a disk drive or to a more systemic problem such as a faulty controller. In p

When parity checking in a disk array such as a RAID-6 system determines data and parity information is unsynchronized, additional calculations are performed to determine whether the error may be attributed to faulty data on a disk drive or to a more systemic problem such as a faulty controller. In particular, for each particular error detected, the parity generating information is analyzed to determine if each error involves a common disk index. If so, the data can be corrected on that disk; if not other corrective procedures are implemented.

대표청구항 ▼

What is claimed is: 1. A method for performing parity checking in a RAID-6 environment in which a plurality of bytes over a plurality of disks are checked to ensure parity data is in sync, each such byte associated with a first parity value and a second parity value, the method comprising the steps

What is claimed is: 1. A method for performing parity checking in a RAID-6 environment in which a plurality of bytes over a plurality of disks are checked to ensure parity data is in sync, each such byte associated with a first parity value and a second parity value, the method comprising the steps of: performing parity checking to determine whether parity data is in sync; during the step of performing parity checking, identifying each byte for which a first parity equation is not satisfied; for each identified byte, calculating a first error value using the first parity equation; for each identified byte, calculating a second error value using a second parity equation; and based on the first error value and the second error value for each identified byte, identifying a faulty disk drive in the RAID-6 environment, wherein the step of identifying includes the steps of: for each of the plurality of bytes, determining as a first condition if the first error value and the second error value are either both non-zero or both zero; for each of the identified bytes, determining as a second condition if the first and second error values indicate a valid disk index within the RAID-6 environment; and for each of the identified bytes, determining as a third condition if the valid disk index is the same for all such bytes. 2. The method of claim 1, further comprising the step of: correcting data on the faulty disk drive. 3. The method of claim 1, wherein the step of determining whether a valid disk index is indicated, further comprises the steps of: calculating a value for the logarithm of the ratio between the second error value and the first error value; and determining if the calculated value is less than the number of disks in the plurality of disks. 4. The method of claim 1, wherein if each of the first, second and third conditions are satisfied, then identifying the faulty disk drive based on the valid disk index. 5. The method of claim 1, wherein if one of the first, second, and third conditions are not satisfied, then determining the first parity equation was not satisfied because of a decoding failure. 6. The method of claim 1, wherein if one of the first, second and third conditions are not satisfied, then identifying a non-disk error as a cause of the first parity equation not being satisfied.