International Business Machines Corporation

William John Durica

M Amine Hajji

Joseph S Hyde, Ii

Ronald J Venturi

A method, apparatus, and computer program product for performing a set of operations on a data storage device is provided. A data storage device is flagged as suspect. The adapter suspends the suspect data storage device from participation in the RAID array, assigns the suspect data storage device to a pool of data storage devices to be retested, selects a data storage device from a pool of spare data storage devices, rebuilds contents of the suspect data storage device on the selected disk drive, assigns the substitute data storage device to the RAID array, invokes a diagnostic test on the suspect data storage device, and analyzes the diagnostic result. Responsive to the diagnostic result exceeding a threshold, the suspect data storage device is repaired. The adapter assigns the repaired data storage device to the pool of spare data storage devices and increments a counter of the repaired data storage device.

Data storage device in-situ self test, repair, and recovery

Provided are a method, system, and article of manufacture, wherein a request to write data to a storage medium is received. The data requested to be written to the storage medium is stored in a cache. A writing of the data is initiated to the storage medium. A periodic determination is made as to whether the stored data in the cache is the same as the data written to the storage medium.

Detection and recovery of dropped writes in storage devices

A self healing system in a RAID array to reduce the risk of loss of data on a disk drive caused by grown media defects on the disk drive. The grown media defects include radial and spiral scratches on the disk drive. When a first defect on a disk drive of the RAID array is located, the self healing system inspects adjacent areas around the first defect on the disk drive in order to immediately locate any additional defects which exist in adjacent areas around the first defect on the disk drive. The self healing system reconstructs the data associated with the first defect using parity, and then reconstructs the data associated with any additional defects using parity. This can be accomplished in the background to allow the host unimpeded access to customer data. As a result, the self healing system can eliminate a potential single point of failure when data is subsequently read from the RAID array.

Growing community of inventors

Morgan Hill, CA, United States of America

William John Durica