Abstract: An apparatus for controlling a log-structured data storage system, operable with a first log-structured data storage area for storing data, comprises a metadata storage component for controlling the first log-structured data storage area and comprising a second log-structured data storage area for storing metadata; and means for nesting the second log-structured data storage area for storing metadata within the first log-structured data storage area. The apparatus may further comprise at least a third log-structured data storage area for storing further metadata, and means for nesting the at least a third log-structured data storage area within the second log-structured data storage area.

Abstract: A method is disclosed for reliably updating a data group in a read-before-write data replication environment. The method reliably updates the data group by receiving an updated data group sent from a first storage medium to a second storage medium, comparing the updated data group with a previous data group previously existing on the second storage medium and writing the updated data group to the second storage medium. The read-before-write and differencing method disclosed maintain reliability by storing multiple copies of changes made to the second storage medium during and after the write process.

Abstract: An apparatus, system, and method are disclosed for reliably updating a data group in a data replication environment. The apparatus, system, and method reliably update the data group by receiving an updated data group sent from a first storage medium to a second storage medium, comparing the updated data group with a previous data group previously existing on the second storage medium and writing the updated data group to the second storage medium. The read-before-write and differencing method disclosed maintain reliability by storing multiple copies of changes made to the second storage medium during and after the write process.

Abstract: Described is a method for processing work items in a data processing system. An interrupt is generated in response to receipt of a work item on a queue and the generated interrupt is serviced to schedule a task by placing the task on a task queue for later processing of the queued work item. The interrupt is not enabled at this point and therefore the receipt of further work items will not result in the generation of interrupts. When the scheduled task reaches the head of the queue, the task is executed to process the queued work item (and all other work items that have been added to the queue since the task was scheduled). When all the work items have been processed, a further task is speculatively scheduled for processing of any work items that are subsequently placed on the work item queue.

Abstract: An apparatus configured to operate as a primary for a remote copy pair is provided. The apparatus comprises a journal component at said primary for generating journal entries for one or more uncompleted sequenced batches; a configurator responsive to an error indication from a secondary for enumeration of said one or more uncompleted sequenced batches; and a primary server responsive to said enumeration of said one or more uncompleted sequenced batches to reissue to said secondary one or more write requests for said one or more uncompleted sequenced batches, during recovery processing.

Abstract: A storage apparatus is operable as primary in a remote copy pair and comprises a remote copy component operable to establish a remote copy relationship between said primary and a secondary; a copy component operable at the primary to create a copy for download onto a portable physical storage medium for offline transport to the secondary for upload; a synchronization component for synchronizing data at said secondary with data at said primary using an online link in response to a request for synchronization from the secondary; a metadata component operable to store a dirty state indicator of a portion of a storage space at the primary after establishment of the remote copy relationship at the primary; and the metadata component being operable to limit synchronization at the secondary to the portion of storage having a dirty state indicator at the primary.

Abstract: Described is a method and apparatus for processing tasks in a data processing system including a microprocessor and an instruction cache. Tasks of different types are defined in the system with each task type having code associated therewith. The tasks are managed in a queue and are processed in order by loading the associated code into the instruction cache for execution on the microprocessor. The method comprises the steps of scheduling tasks of like type into a batch such that tasks in a batch are processed before processing the next ordered task. In the case where the code associated with a batched task fits within the instruction cache, the tasks in a batch can be processed without incurring the penalty associated with instruction cache misses.

Abstract: A data storage system (100) and a method of storing data are described including a cache (118) with a variable number of levels (210, 220, 230, 240). Each level in the cache (118) has a cache controller (212, 222, 232, 242) and a cache memory (214, 224, 234, 244) for storing data. An address mapping is recorded and applied between each of the levels of the cache (118). The address mapping corresponds to a point in time virtual copy operation such as a snapshot copy operation applied to the cache (118) and enables point in time virtual copy operations to be carried out in electronic time. A new level is created in the cache (118) when a point in time virtual copy operation is received by the cache and a corresponding address mapping is applied to the previous level in the cache (118).

Abstract: A method for performing free space collection in an information storage system and an information storage system (104) are described. The information storage system (104) is a log structured system having storage units (106) in which information segments (202, 204) are located. Free space collection is carried out in the storage units by using a fitness value to evaluate segments (204). The fitness value is determined as the product of the amount of free space in a segment (204) and the expected time the free space will last (310). Segments (204) are chosen for free space collection if they have the maximum fitness value (312). The segments (204) are sorted into groups by the amount of used data in each segment (204) and the fitness value is determined for one segment from each group.

Abstract: A log structured array (LSA) controller apparatus controls the transfer of information between a processor and a plurality of information storage devices configured as an N+1 array in which the information is stored as stripes extending across the devices of the array, each stripe comprising N information strips and one parity strip, each information strip storing an integer number of logical tracks. The controller defines an LSA directory that specifies the location of each logical track in terms of the ID of the stripe to which the track belongs and the offset of the track within the stripe; wherein on the addition of an information storage device to the array, the additional strip provided for each stripe by the storage device is logically appended to the end of each stripe in the LSA directory.

Abstract: A data processing system comprises a master processor (10), a slave processor (30), a memory (50), and a bus subsystem (20) interconnecting the master processor (10), the slave processor (30), and the memory (50). The master processor (10) is configured to generate, in response to a memory access instruction, a read request comprising a read command for execution by the slave processor (30) to read data stored in a location in the memory (50) specified by the memory access instruction, and to write the read request to the slave processor (30) via the bus subsystem (20). The slave processor (30) is configured to execute the read command received in the read request from the master processor (10) to obtain the data stored at the specified location in the memory (50) and to write the data thus obtained to the master processor (10) via the bus subsystem (20).

Abstract: A method for data sorting in an information storage system and an information storage system (104) are described. The information storage system (104) is a log structured system having storage devices (106) in which information segments (202, 204) are located. Units of data are sorted into streams (136, 138) according to the expected time until the next rewrite of the unit of data. Sorting data into streams (136, 138) improves the efficiency of free space collection in the storage devices (106). Separate streams (136, 138) are provided for rewritten data units and units of data being relocated due to free space collections in the storage devices (106). The streams (136, 138) can have fixed or dynamic boundaries.

Abstract: A method for rebuilding meta-data stored in a data storage system (104) having storage devices (106) in which segments of data are located; for example, a storage system in the form of a log structured array. Data is written in segments to the storage devices (106) from a plurality of flows (122) of data and each segment of data contains meta-data relating to that segment. The meta-data stored in the storage system (104) can be rebuilt in the event of a failure by scanning the meta-data in each segment. A first scan of the meta-data in each segment in the storage devices (106) identifies the last segment written from each flow (122) and these segments are excluded from the rebuilding process as they may contain incomplete or inconsistent information. A second scan of the meta-data in each segment in the storage devices (106) identifies any segments which do not contain any live data tracks and these segments are also excluded from the, rebuilding process.

Abstract: A data storage system and method of storing data with at least two controllers (200, 300) which share a storage space (244, 344) on an array of storage devices and which support the same set of logical upstream devices. The controllers (200, 300) share the workload by dividing the shared storage space (244, 344) into stripes where the stripes are sufficiently small to divide the workload uniformly across the storage device. This is achieved in the case of two controllers (200, 300) of a log structured array by dividing the storage space into odd and even tracks, all odd tracks being designated to one controller (300) and all even tracks to the other controller (200).

Abstract: A system and method for solving the weak membership problem in a system of nodes that might include redundancies. Each node is given the same random seed. Each node uses a link state protocol to determine the current system topography, and then an optimization such as simulated annealing is run on the topography at each node, independently of the other nodes, to determine the optimum weak membership for use thereof in subsequent system operations. Since each node starts with the same random seed, the nodes all arrive at the same solution without having to communicate a common solution between nodes.

Abstract: A log structured array (LSA) controller apparatus controls the transfer of information between a processor and a plurality of information storage devices configured as an N+1 array in which the information is stored as stripes extending across the devices of the array, each stripe comprising N information strips and one parity strip, each information strip storing an integer number of logical tracks. The controller defines an LSA directory that specifies the location of each logical track in terms of the ID of the stripe to which the track belongs and the offset of the track within the stripe; wherein on the addition of an information storage device to the array, the additional strip provided for each stripe by the storage device is logically appended to the end of each stripe in the LSA directory.

Abstract: A method for performing free space collection in an information storage system and an information storage system (104) are described. The information storage system (104) is a log structured system having storage units (106) in which information segments (202, 204) are located. Free space collection is carried out in the storage units by using a fitness value to evaluate segments (204). The fitness value is determined as the product of the amount of free space in a segment (204) and the expected time the free space will last (310). Segments (204) are chosen for free space collection if they have the maximum fitness value (312). The segments (204) are sorted into groups by the amount of used data in each segment (204) and the fitness value is determined for one segment from each group.

Abstract: A method for data sorting in an information storage system and an information storage system (104) are described. The information storage system (104) is a log structured system having storage devices (106) in which information segments (202, 204) are located. Units of data are sorted into streams (136, 138) according to the expected time until the next rewrite of the unit of data. Sorting data into streams (136, 138) improves the efficiency of free space collection in the storage devices (106). Separate streams (136, 138) are provided for rewritten data units and units of data being relocated due to free space collections in the storage devices (106). The streams (136, 138) can have fixed or dynamic boundaries.

Abstract: A data storage system (100) and a method of storing data are described including a cache (118) with a variable number of levels (210, 220, 230, 240). Each level in the cache (118) has a cache controller (212, 222, 232, 242) and a cache memory (214, 224, 234, 244) for storing data. An address mapping is recorded and applied between each of the levels of the cache (118). The address mapping corresponds to a point in time virtual copy operation such as a snapshot copy operation applied to the cache (118) and enables point in time virtual copy operations to be carried out in electronic time. A new level is created in the cache (118) when a point in time virtual copy operation is received by the cache and a corresponding address mapping is applied to the previous level in the cache (118).

Abstract: A method for rebuilding meta-data stored in a data storage system (104) having storage devices (106) in which segments of data are located; for example, a storage system in the form of a log structured array. Data is written in segments to the storage devices (106) from a plurality of flows (122) of data and each segment of data contains meta-data relating to that segment. The meta-data stored in the storage system (104) can be rebuilt in the event of a failure by scanning the meta-data in each segment. A first scan of the meta-data in each segment in the storage devices (106) identifies the last segment written from each flow (122) and these segments are excluded from the rebuilding process as they may contain incomplete or inconsistent information. A second scan of the meta-data in each segment in the storage devices (106) identifies any segments which do not contain any live data tracks and these segments are also excluded from the, rebuilding process.