Abstract: A storage system and method for prestaging data in a cache based on relative changes in the frequency of data access and relative changes in the effectiveness of previous prestage operations. The relative changes in the frequency of data access are determined by storing statistics of data access to all regions in the system and comparing recent access statistics to the stored data. Access statistics include data location, I/O size and access frequency. The relative changes in the effectiveness of previous prestage operations are detected by recording the number of previous prestaging operations for a region, recording the number of I/O requests for data that has been prestaged, and dividing the number of I/O requests for previously prestaged data in a region during a time period by the number of previous prestage operations for the region during the same time.

Abstract: A method, apparatus, and article of manufacture provide the ability to maintain cache in a clustered environment. The cache is maintained in both a primary and secondary node. When data is requested, a symbolic list in a cache directory is examined to determine which node's cache contains the requested data. If the symbolic list indicates data is not currently in cache of any node, any node may be used as the secondary node. However, if an original primary node maintains the data in cache, the original primary node is selected as the secondary node. Once a new write I/O operation is performed, the symbolic list is updated to provide. To install a new node, after applying for cluster admission, symbolic information and a modified track list is requested. The modified track list is merged with new symbolic entries and the new node then broadcasts its availability to the cluster.

Abstract: The present invention discloses a method, apparatus, and article of manufacture for implementing a locking structure for supporting parity protection in a RAID clustered environment. When updating parity, the parity is locked so that other nodes cannot access or modify the parity. Accordingly, the parity is locked, read, generated, written, and unlocked by a node. An enhanced protocal may combine the lock and read functions and the write and unlock functions. Further, the SCSI RESERVE and RELEASE commands may be utlized to lock/unlock the parity data. By locking the parity in this maner, overhead is mininized and does not increase as the number of nodes increases.

Abstract: Providing high availability cache coherency in a distributed cache environment for a storage cluster. An extent owner node in a cluster controls extent disk requests and the locking and demotion of extent data. An extent client node may access the data but does not control destaging or locking. The extent client waits for a lock state grant prior to completing any I/O request. An extent client is allowed to receive data from a host for a write request and later let the extent owner sort out the proper cache coherency order. An extent client is not required to request a lock state change from the extent owner when a read cache hit occurs in the extent client. When a read miss occurs in an extent client, the extent client can initiate a stage request from disk and request the owner for a lock state change at a later time.

Abstract: A method, apparatus, article of manufacture, and a memory structure for an internode network. Nodes are active-active using commodity hardware so that the system can perform I/O together between any number of nodes, and data can be located on any given node. A single modified image is configured to maintain recent and updated data. At least one failure can occur (and be corrected) in the nodes before data is written to disk. A history of access points is kept in a cache directory, and it is assumed that the nodes most frequently accessed in the past are likely to be the most frequently accessed in the near future. One or more embodiments of the invention move this data to where it will likely be needed. This means that data is delivered to hosts quickly, as is required in high volume enterprise web environments. The symbolic list in the cache directory provides a history of the nodes that have previously performed I/O operations.

Abstract: Providing high availability cache coherency in a distributed cache environment for a storage cluster. An extent owner node in a cluster controls extent disk requests and the locking and demotion of extent data. An extent client node may access the data but does not control destaging or locking. The extent client waits for a lock state grant prior to completing any I/O request. An extent client is allowed to receive data from a host for a write request and later let the extent owner sort out the proper cache coherency order. An extent client is not required to request a lock state change from the extent owner when a read cache hit occurs in the extent client. When a read miss occurs in an extent client, the extent client can initiate a stage request from disk and request the owner for a lock state change at a later time.

Abstract: To address the requirements described above, the present invention discloses a method, apparatus, article of manufacture, and a locking structure for supporting parity protected RAID in a clustered environment. When updating parity, the parity is locked so that other nodes cannot access or modify the parity. Accordingly, the parity is locked, read, generated, written, and unlocked by a node. An enhanced protocol may combine the lock and read functions and the write and unlock functions. Further, the SCSI RESERVE and RELEASE commands may be utilized to lock/unlock the parity data. By locking the parity in this manner, overhead is minimized and does not increase as the number of nodes increases.