Abstract: Aspects for handling destage requests during shutdown in a log-structured array storage subsystem are described. In a method aspect, the method includes receiving a shut-down command, and utilizing at least three data structures for tracking destage requests when the shut-down command is received, wherein closing of open segments before completion of the shut-down is ensured. A further method aspect includes maintaining an outstanding requests list and destage requests list, forming a missing requests list based on the contents of the outstanding requests list and destage requests list when a shut-down command occurs, and tracking destage request processing with the outstanding requests list, destage requests list and missing requests list until all destage requests have been successfully completed.

Abstract: Aspects for increasing concurrency during staging and destaging of a log structured array (LSA) are described. In an exemplary method aspect, the method includes determining a process type making a request for access to a locking mechanism associated with an LSA directory entry for a logical track, and determining a lock status for the locking mechanism. Access to the locking mechanism is then provided according to the determined process type and lock status. Further, a destaging process is allowed to obtain an available locking mechanism in a read-write mode, a staging process is allowed to obtain an available locking mechanism in a read-only mode, and a garbage collection process is allowed to obtain an available locking mechanism initially in a read-only mode and subsequently in a read-write mode, wherein increased concurrency results during the staging and destaging processes.

Abstract: A method and apparatus for sharing distributed spares of a first array with a second array in a storage subsystem which included a number of storage arrays requires that at least a first array of the subsystem has available distributed spares, and that at least a second array has a same number of "rows" as the first array, for spare sharing. When a device failure occurs on the second array, the data and parity blocks of the failed device are reconstructed and placed in the spares of the first array, and the block addresses are appropriately remapped to the spares. Distributed spare sharing is possible because the first array is configured to include at least one spare region/row, and the second array will never lose a number of blocks greater than the common number of rows in the first array in a single device failure.