Abstract: A storage system includes a group of storage devices which include back-up devices configured to assure appropriate response time. When a data request from a host computer arrives, and the number of failed devices has changed as shown by a device state management table, a determination is made regarding the number of devices from which to read data. This determination is made based on an indication of redundancy which indicates how many of the disk devices are allowed to be in a failed state at the time of data reading. Typically, the indication of redundancy is determined by the sum of the number of failed devices and a predetermined number. The determined number of devices are selected in accordance with a selection factor, and a selection result is written into a disk management table. Then, the reading process is executed with respect to the target disk devices.

Abstract: A method, system, and data processing system for dynamic detection of problem components in a hot-plug processing system and automatic removal of the problem component via hot-removal methods without disrupting processing of the overall system. A data processing system that provides a non-disruptive, hot-plug functionality is designed with a additional logic for initiating and/or completing a sequence of factory level tests on hot-pluggable components to determine if the component if functioning properly. When a component is not functioning properly, the OS re-allocates the workload of the component to other component so the system, and when the OS completes the re-allocation, the service element initiates the hot removal of the component so that the component is logically and electrically separated from the system.

Abstract: A system and method are disclosed for providing journal recovery in a multi-node environment which comprises determining whether a block was last updated by a first node; determining whether the block is associated with a lock held by a second node; and writing the block to a final location if the block is not associated with a lock held by the second node. In another embodiment, a system and method are disclosed for providing journal recovery in a multi-node environment which comprises determining whether a block is associated with metadata; determining whether the block is associated with a lock held by a surviving node; and writing the block to a final location if the block is not associated with a lock held by the surviving node.