Abstract: In a data processing system having a plurality of queues for prioritizing I/O requests to a storage device, the priority of the queues for servicing is dynamically adjustable as opposed to each queue having a fixed priority. Dynamically adjusting the priority of a queue allows the priority of a queue with "stuck" requests to be raised so the "stuck" requests can be serviced very quickly.

Abstract: An array controller of a log structured array dynamically defines segments as data is taken from a write buffer and recorded into disk storage units of the log structured array such that a segment includes blocks selected from the various disk storage units at the time of segment definition so as to minimize disk arm travel. Each time a segment from the write buffer must be written to disk, the new disk segment is defined in response to current disk arm position for each disk platter in a disk storage unit. The array controller maintains a segment definition table that indicates the disk storage unit locations corresponding to each segment. In addition, garbage collection of used blocks is performed in response to disk arm idle time such that garbage collection is not performed only when there are too few empty segments. Rather, garbage collection is performed when a disk arm has been idle for a predetermined time. A variety of garbage collection schemes are described.

Abstract: A log-structured array (LSA) includes a relatively large, non-volatile cache memory as well as a memory segment write buffer. The LSA cache memory contains both updated logical tracks received from the host system and also clean logical tracks read from direct access storage devices of the array. When the fraction of updated tracks in the cache memory exceeds a threshold value, updated tracks are moved from the LSA cache memory to the memory segment. With each modified track to be moved, adjacent modified tracks also are moved. The updated tracks are moved regardless of their location in the updated LRU list. Clean tracks in the LSA cache memory are moved into the memory segment as well, when additional clean tracks are needed in the cache memory. The clean tracks are selected from the bottom of the LSA cache clean track LRU list. Checking for adjacency also can occur at garbage collection time, performed in a background mode.

Abstract: A method for managing a cache hierarchy having a fixed total storage capacity is disclosed. The cache hierarchy is logically partitioned to form a least recently used (LRU) global cache and a plurality of LRU destaging local caches. The global cache stores objects of all types and maintains them in LRU order. In contrast, each local cache is bound to objects having a unique data type T(i), where i is indicative of a DataType. Read and write accesses by referencing processors or central processing units (CPU's) are made to the global cache. Data not available in the global cache is staged thereto either from one of the local caches or from external storage. When a cache full condition is reached, placement of the most recently used (MRU) data element to the top of the global cache results in an LRU data element of type T(i) being destaged from the global cache to a corresponding one of the local caches storing type T(i) data.