Abstract: Machines, systems and methods for providing a job description for execution in a computing environment, the method comprising receiving a job description, wherein the job description defines a set of job alternatives based on an order of priority and conditions associated with execution of the job alternatives; processing the job alternatives to determine whether resources for executing at least a first job alternative are available, considering respective first conditions defined in the job description for the first job alternative; selecting a first computing element implemented in a virtualized computing environment, wherein the selected first computing element has sufficient resources to satisfy resource requirements defined in the job description for the first job alternative; and submitting the job to the first computing element for execution.

Abstract: Machines, systems and methods for providing a job description for execution in a computing environment, the method comprising receiving a job description, wherein the job description defines a set of job alternatives based on an order of priority and conditions associated with execution of the job alternatives; processing the job alternatives to determine whether resources for executing at least a first job alternative are available, considering respective first conditions defined in the job description for the first job alternative; selecting a first computing element implemented in a virtualized computing environment, wherein the selected first computing element has sufficient resources to satisfy resource requirements defined in the job description for the first job alternative; and submitting the job to the first computing element for execution.

Abstract: A method for managing a data storage system includes copying data stored on a first storage subsystem to a second storage subsystem in an asynchronous mirroring process. A record is maintained on the second storage subsystem, indicative of locations at which the data have been updated on the first storage subsystem and have not yet been copied to the second storage subsystem. Upon receiving at the second storage subsystem, from a host processor, a request to access the data stored at a specified location on the data storage system, if the specified location is included in the record, the second storage subsystem initiates a synchronous transfer of the data at the specified location from the first storage subsystem.

Abstract: A method for managing a data storage system includes copying data stored on a first storage subsystem to a second storage subsystem in an asynchronous mirroring process. A record is maintained on the second storage subsystem, indicative of locations at which the data have been updated on the first storage subsystem and have not yet been copied to the second storage subsystem. Upon receiving at the second storage subsystem, from a host processor, a request to access the data stored at a specified location on the data storage system, if the specified location is included in the record, the second storage subsystem initiates a synchronous transfer of the data at the specified location from the first storage subsystem.

Abstract: A computer-implemented method for reducing a computing overhead associated with objects that are local to a particular thread and can be accessed solely by that thread. Dynamically during run-time, an object is determined to be local to a particular thread and can be accessed solely by that thread, whereby a computing overhead associated with that object may be reduced. Likewise, cache locality may be optimized in respect of objects that are determined to be global so as to avoid putting them in the same cache line, whilst thread-local objects are preferably stored in a cache line associated with that thread.

Abstract: A method for packaging program resources includes collecting a set of the program resources that comprises a plurality of object files, which contain data structures having entries that are constants and methods that reference the entries. The data structures in at least some of the object files are combined into a common data pool, in which semantically-identical entries in different ones of the files are represented by a single consolidated entry, irrespective of whether the entries in the different files are syntactically identical. The set of the program resources is packaged together with the common data pool in a combined output file.

Abstract: This disclosure presents a technique of field-level caching in distributed object-oriented systems, in which a speculative approach is taken to identify opportunities for caching. The speculative approach is particularly suitable for exploitation of opportunities for caching. Invalidation protocols, which are fully compliant with the Java memory model, are provided to recover from incorrect speculation, while incurring only a low overhead. The technique has been implemented on a cluster of machines, and has been found to be readily scalable with multi-threaded applications. Field caching, optionally combined with other optimizations, produces a practically important performance step up in distributed environments, such as the cluster virtual machine for Java, which transparently distributes an application's threads and objects among the nodes of a cluster.

Abstract: A method for packaging program resources includes collecting a set of the program resources that comprises a plurality of object files, which contain data structures having entries that are constants and methods that reference the entries. The data structures in at least some of the object files are combined into a common data pool, in which semantically-identical entries in different ones of the files are represented by a single consolidated entry, irrespective of whether the entries in the different files are syntactically identical. The set of the program resources is packaged together with the common data pool in a combined output file.

Abstract: A data structure and associated mechanism for implementing object oriented programming language, comprising at least two code blocks for at least one method of an object of a specified class, each of the code blocks containing a different implementation of the at least one method. An access mechanism is provided for accessing a desired code block at run-time on a per object instance basis so as to allow selection of a desired implementation of the at least one method without requiring instantiation of an object of a different class. The selection of which implementation to invoke is integrated into an existing invocation method of the language and is thus transparent to a calling application invoking the method.

Abstract: This disclosure presents a technique of field-level caching in distributed object-oriented systems, in which a speculative approach is taken to identify opportunities for caching. The speculative approach is particularly suitable for exploitation of opportunities for caching. Invalidation protocols, which are fully compliant with the Java memory model, are provided to recover from incorrect speculation, while incurring only a low overhead. The technique has been implemented on a cluster of machines, and has been found to be readily scalable with multi-threaded applications. Field caching, optionally combined with other optimizations, produces a practically important performance step up in distributed environments, such as the cluster virtual machine for Java, which transparently distributes an application's threads and objects among the nodes of a cluster.