International Business Machines Corporation

Gerrit Huizenga

Ramachandra N Pai

Timothy C Pepper

Eric Benjamin Munson

Vivek Kashyap

Badari Pulavarty

Nathan Victor Bak

Russell H Weight

D Scott Guthridge

Wayne Alan Downer

Patricia A Gaughen

Prasadarao Akulavenkatavara

James A Keniston

Chandrasekhar Pulamarasetti

Kyle Gerhard Grieser

A method, system and computer program product for managing source annotation metadata. The metadata management technique may include maintaining a set of metadata, maintaining data/metadata relationships between individual units of the metadata and individual units of the source data, and maintaining metadata/metadata relationships between individual units of the metadata. The metadata/metadata relationships define two or more intersecting search pathways through the metadata that intersect at one or more metadata units belonging to more than one search domain.

Managing source annotation metadata

A method, system and computer program product for software debugging using annotation metadata. A set of metadata comprising source code annotation information for a software program is maintained, together with data/metadata relationships between individual units of the metadata and individual units of the source code. A software debugging point is set that is associated with debugging point metadata comprising one or more units the metadata. A debugging action is performed when execution of the software program reaches said debugging point.

Metadata-integrated debugger

A workload management system where processes associated with a class have resource management strategies that are specific to that class is provided. The system includes more than one class, with at least one unique algorithm for executing a workload associated with each class. Each algorithm may comprise a strategy for executing a workload that is specific to that class and the algorithms of one class may be completely unrelated to the algorithms of another class. The workload management system allows workloads with different attributes to use system resources in ways that best benefit a workload, while maximizing usage of the system's resources and with minimized degradation to other workloads running concurrently.

Method of managing resources within a set of processes

A method, apparatus, and article are provided for managing migration of annotations between versions of source code. Annotations associated with patterns of source code are identified. A comparison of the modified source code is conducted in conjunction with the identified annotations in a prior version of the source code to determine if the annotations may be migrated to any portions of the modified source code. The comparison includes an exact match and a partial match. With respect to the partial match, a threshold value is employed to define the parameters of a partial match. All annotations that are determine to be an exact match or a partial match are automatically migrated to a location in the modified source code determine to match within the threshold value.

Transferring annotations across versions of the data

Managing delivery of power to one or more hardware memory devices in a computer system. The computer system is configured with a processor and at least two hardware memory devices. A temperature monitor tool is employed to monitor the hardware memory devices. Management of an addressable subset of the hardware memory devices is employed in response to the monitored temperature reading.

Selective power reduction of memory hardware

For a source file on which basis a binary object file has been generated, a digital signature is generated for the source file, and the digital signature is stored. The digital signature may be secure hash algorithm (SHA) hash values. The binary object file is output. To verify that the binary object file has been generated from the source file, a digital signature is generated for the source file, and compared to the digital signature for the source file as previously stored. Where the digital signature for the source file as has been generated matches the digital signature for the source file previously stored, the binary object file is indicated as having been generated from the source file.

Verifying that binary object file has been generated from source files

A system, method and computer program product for optimizing a software system through scenario evaluation. In accordance with the disclosed technique, a request is received for evaluation of an operational scenario that operates over an environment that is a superset of existing system capabilities encompassing system features or parameters that are not available in the currently running system. A knowledge base is consulted to derive recommendations with respect to operating parameters that may be collected to evaluate the scenario, mechanisms for gathering data relating to the parameters, and data evaluator operations for deriving a data evaluation result based on the data gathering. The knowledge base is further consulted to determine a reconfiguration recommendation based on the result. Scenario evaluation is performed based on simulation of the reconfiguration recommendation using the data evaluation result to determine efficacy of the scenario.

Optimization of system performance through scenario evaluation

Managing delivery of power to one or more hardware memory devices in a computer system. The computer system is configured with a processor and at least two hardware memory devices. An energy exchange threshold for the computer system is set, and management of one or more of the hardware memory devices is employed when the computer system exceeds an energy exchange threshold.

A technique for managing application workloads in a data processing system includes establishing a reserve resource allocation of a data processing resource for use by a data processing application having a need to utilize the resource, sharing a portion of the resource that is not part of the reserve resource allocation or otherwise utilized by the application with other applications, allowing the application to consume the reserve resource allocation when the application desires to increase its utilization of the resource, and replenishing the reserve resource allocation from the sharable portion of the resource as the application consumes the reserve resource allocation. Advantageously, the reserve resource allocation can be effectively managed so that the data processing resource is available to the application in order to reduce application latency without depriving other applications of the ability to use the resource.

Method for balancing resource sharing and application latency within a data processing system

The present invention provides a probe system and method for multithreaded user-space programs. The system includes an instrumentation module that enables single stepping out of line processing for multithreaded programs, an establish probepoint module that divides up an area of the probed program's memory into a plurality of instruction slots, an ensure slot assigned module that ensures that an instruction slot is assigned to a probepoint, a slot acquisition module that acquires the instruction slot for the probepoint, stealing a slot from another probepoint as needed, and a free slot module that relinquishes the instruction slot owned by the probepoint when the probepoint is being unregistered.

Multiplexing per-probepoint instruction slots for out-of-line execution

A method, apparatus, and article of manufacture to dynamically address and resolve an improper shut-down of an application. Internal state data of the application is stored in persistent memory. New internal state data is dynamically created and authenticated following an improper shut-down of the application. Responsive to the authentication, the application is re-started with the authenticated new internal state data, without being subject to an immediate improper shut-down.

Application failure recovery

In a multiprocessor system, a method for dynamically establishing an I/O path between a processor node and an I/O device for routing data there between. The method starts with providing a configuration graph. The graph has objects associated with elements (devices) of the system and links connecting the objects. The node is identified, and links are then followed in the graph from an object associated with the I/O device to an object associated with a node. If multiple I/O paths exist and an optimal path is desired, the method includes providing in the links routing information containing nodes that can be directly reached via the link. Links are then followed, if possible, whose routing information contains the identified node. If no link having such routing information exists at an object along the path, then another link is chosen having routing information containing another node. This other link may be chosen in a round robin manner if there are multiple links to choose from. If multiple links having such routing information exist at an object along the path, then one of the links is chosen in a round robin manner. The method may also be used in uniprocessor systems such as a system with a one-processor node for simply establishing multiple paths to provide fault tolerance.

Method for routing I/O data in a multiprocessor system having a non-uniform memory access architecture

A method for configuring devices within a computer system provides device configuration information for types of devices that may be included within the computer system. The device configuration information for a device type includes interface types by which devices of that device type connect to other devices. The method includes determining the interface types of a current object associated with a device. Device types that can exist on a determined interface type of the current object are probed for. A child object is created for a device found from the probing and a link between the current object and the child object is also created. A child object is then made the current object, and the above actions are repeated at least until the devices to be configured within the system have associated objects linked together.

Growing community of inventors

Portland, OR, United States of America

Gerrit Huizenga