Abstract: An apparatus for and method of enhancing reliability and performance within a cluster lock processing system having a relatively large number of commodity instruction processors which are managed by a highly scalable, off the shelf platform. Because the commodity processors have virtually no system viability features such as memory protection, failure recovery, etc., the cluster/lock processors assume the responsibility for providing these functions. The low cost of the commodity instruction processors makes the system almost linearly scalable. The cluster/locking, caching, and mass storage accessing functions are fully integrated into a single hardware platform which performs the role of the cluster/lock master. The validity operation throughput of the clustered systems manager is increased by aging out validity entries for each of the process owners via a background operation. This minimizes the number of exclusive locks that must be utilized while performing a validity operation.

Abstract: An apparatus for and method of implementing a cluster lock processing system using highly scalable, off-the-shelf commodity processors. The cluster lock processing system is the central component of a clustered computer system, providing locking and coordination between multiple host systems. The host systems are coupled to the cluster lock processing system using off-the-shelf, low latency interconnects. The cluster lock processing system is composed of multiple commodity platforms that are also coupled to each other using low latency interconnects. Failure of one of the commodity platforms that comprise the cluster lock processing system results in no loss of functionality or interruption of service. This is made possible through the use of specialized software that runs on the commodity platforms. Through the use of custom software and inexpensive hardware the overall system cost is dramatically reduced when compared to typical solutions that use custom built hardware.

Abstract: An apparatus for and method of enhancing reliability within a cluster lock processing system having a relatively large number of commodity cluster instruction processors which are managed by a cluster lock manager. Because the commodity processors have virtually no system viability features such as memory protection, failure recovery, etc., the cluster/lock processors assume the responsibility for providing these functions. The low cost of the commodity cluster instruction processors makes the system almost linearly scalable. The cluster/locking, caching, and mass storage accessing functions are fully integrated into a single hardware platform which performs the role of the cluster/lock master. Upon failure of this hardware platform, a second redundant hardware platform converts from slave to master role. The logic for the failure detection and role swapping is placed within software, which can run as an application under a commonly available operating system.

Abstract: An apparatus for and method of enhancing throughput within a cluster lock processing system having a relatively large number of commodity cluster instruction processors which are arranged in redundant fashion to improve reliability. Because the commodity processors have virtually no system viability features such as memory protection, failure recovery, etc., the cluster/lock processors assume the responsibility for providing these functions. The low cost of the commodity cluster instruction processors makes the system almost linearly scalable. The cluster/locking, caching, and mass storage accessing functions are fully integrated into a single hardware platform which performs the role of the cluster/lock master. Upon failure of this hardware platform, a second redundant hardware platform converts from slave to master role. The logic for the failure detection and role swapping is placed within software, which can run as an application under a commonly available operating system.

Abstract: An apparatus for and method of providing failure recovery from redundancy, notwithstanding that the failed subsystem and its replacement have differing capacities. This is especially useful when implementing a cluster lock processing system having a relatively large number of commodity instruction processors which are managed by a highly scalable, cluster lock manager. Reliability is built into the managing communication processor by dividing the system into master and slave subsystems. The master has primary responsibility for system management and coordination, whereas the slave has primary responsibility to backup the master and be prepared to assume management responsibility. Upon the need to transfer responsibility from the master to the slave, whether it be manual (e.g., maintenance) or automatic (e.g., failure), the only concern is that the slave has sufficient capacity to accept the current level of processing, even though it does not have the same level of capacity as the master.

Abstract: An apparatus for and method of enhancing reliability within a cluster lock processing system having a relatively large number of commodity cluster instruction processors which are managed by a cluster lock manager. Because the commodity processors have virtually no system viability features such as memory protection, failure recovery, etc., the cluster/lock processors assume the responsibility for providing these functions. The low cost of the commodity cluster instruction processors makes the system almost linearly scalable. The cluster/locking, caching, and mass storage accessing functions are fully integrated into a single hardware platform which performs the role of the master. Upon failure of this hardware platform, a second redundant hardware platform converts from slave to master role. The logic for the failure detection and role swapping is placed within software, which can run as an application under a commonly available operating system.

Abstract: An apparatus for and method of enhancing reliability within a cluster lock processing system having a relatively large number of commodity cluster instruction processors which are managed by a cluster lock manager. Because the commodity processors have virtually no system viability features such as memory protection, failure recovery, etc., the communication processor assumes the responsibility for providing these functions. The low cost of the commodity cluster instruction processors makes the system almost linearly scalable. The cluster/locking, caching, and mass storage accessing functions are fully integrated into a single hardware platform which performs the role of the cluster/lock master. Upon failure of this hardware platform, a second redundant hardware platform converts from slave to master role. The logic for the failure detection and role swapping is placed within software, which can run as an application under a commonly available operating system.

Abstract: A disk cache translation system for mapping data record lengths between systems having different data record lengths. Command queue (315) maps into initiation queue (305) to allow I/O manager (230) to manage I/O requests from operating system (125). I/O requests are statused by I/O manager (230) using status queue (325). Store-thru cache (280) provides a single interface to disk array (270) such that disk array write operations are reported complete only when user memory (250), I/O cache (280) and disk array (270) are synchronized. Data record length translations are performed using I/O cache (280) in order to align data record length differences between operating system (125) and I/O device (270).

Abstract: Method and apparatus for tracking messages and transactions communicated between a number of users and a number of hosts, where the hosts are executing concurrent applications. During a first user session, a first user communicates with a first host. A counter associated with the first user session is incremented when the application creates an output message. The counter is decremented when the output message is released to the first user. A flag associated with the first user session is set and the counter is incremented once the flag is set, if an input message or committing transaction is received from the first user. The flag is cleared and the counter is decremented when the input message or committing transaction is processed by the concurrent application. The counter being decremented indicates there are no dependencies during the first user session with regard to the output message, input message, or committing transaction.

Abstract: An apparatus and method of efficiently recovering from physical disk drive (or logical file) failures in transaction based digital data processing systems. As transactions are sequentially processed, compacted audit trail records are prepared to indicate modifications resulting from each transaction. The audit trail records are stored in storage areas on a disk drive in accordance with the physical data base disk drive(s) or logical file(s) to which the corresponding transaction refers. A physical disk drive or logical file is dumped to magnetic tape whenever the associated audit trail storage area is full, thus clearing the audit trail storage area for further use. When a physical disk drive or logical file fails, the most recent dump is read. Modifications to each file of the dump are made as compacted audit trail data is processed. The modified files are destaged to a spare disk drive.

Abstract: Method and apparatus for providing backup memory storage for audit trail data within a computer system having a main memory storage, a non-volatile memory storage, and backup memory storage. The computer system executes a number of transaction programs which generate audit trail entries. As the audit trail entries are generated, a portion of the audit trail entries are stored in a portion of the main memory storage to create an audit trail. The audit trail entries are accumulated in the portion of the main memory storage until a request is received to write the portion of the main memory storage to a corresponding portion of the non-volatile memory. Subsequent portions of the audit trail entries are accumulated in subsequent portions of the main memory storage.

Abstract: Method and apparatus for managing the allocation and release of memory space within a number of files shared by a number of hosts in a data processing system. A number of allocate and release tables are provided which are accessible by the number of hosts for managing the allocation and release of space within the number of files. Each one of the number of allocate and release tables corresponds to one of the number of files and provides a file location, file size, and indication to the number of hosts of which of the number of blocks within the file have been allocated and which of the number of blocks have been released. Any host may allocate one or more of the number of blocks to store messages created or received by the host by determining from the allocate and release tables which one or more of the number of blocks within one of the number of files are available.

Abstract: A data processing system including a first and second host, a first and second outboard file cache connected to the first host, and a first and second secondary storage device connected to the first host. The system operation includes the first host reading file data from the first or second secondary storage device after the data is cached on both the first and second outboard file caches. File data is updated by writing to both first and second outboard file caches. File data is destaged by writing data from the first outboard file cache only, to first and second secondary storage devices. Failure of a single outboard file cache is handled by the first host not reading and writing to the failed outboard file cache. Site-wide failure of first host, first outboard file cache, and first secondary storage device is handled by establishing communication from second host to both second outboard file cache and second secondary storage device and resuming processing.

Abstract: A transaction processing audit and recovery system is disclosed. After processing a transaction, an audit manager logs in audit records only changed blocks of data of a segment of a database. Upon failure of database backing storage, a prior copy of the database is reloaded to database backing storage that is available and a recovery manager reads the audit records and copies the changed blocks back to the database backing storage. An outboard file cache system is used in conjunction with the recovery manager to recover the database. The outboard file cache provides cache storage for segments of the database and writes non-contiguous blocks of one or more segments as directed in a single input/output request initiated from the recovery manager.

Abstract: A system and method for maintaining a backup data base. An initial backup copy of a data base is made and stored separate from an active primary data base. Each time the primary data base is updated, audit information pertaining to the data base update is stored in non-volatile storage. A recovery processor continuously reads the audit information from the non-volatile storage and updates the backup data base accordingly, thereby maintaining a backup data base which is nearly up-to-date with the primary data base.

Abstract: A multiprocessor data processing system is implemented with processors, each of which may request for a temporary time the exclusive lock on an object which is stored on a data base. To achieve this a lock processor synchronizes the locking and unlocking of the objects. The requesting processor directs the storage of the object from the data base into a selected high performance storage unit, where it has exclusive rights to modify or write into the object until the object is unlocked by the processor. An audit tape or disk records all modifications made to any object during a transaction. A non-volatile cache memory is inserted in the audit trail to store a before-look image of the object that resides in the high performance storage unit. Data compaction occurs by comparison of the before-look image with an after-look image to provide a difference image, which is supplied to an audit buffer that is coupled to the audit tape.