International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

David Lee Hermsmeier

David R Engebretsen

Cary Lee Bates

Thomas M Gooding

Amanda Peters

Gary Ross Ricard

Josep Cors

Kurt Walter Pinnow

Roy Glenn Musselman

Adam Charles Lange-Pearson

Larry William Youngren

Jaimeson Saley

Brent Allen Swartz

Ward Ray Nelson

Stephen A Knight

John J Vriezen

Benjamin R Garbers

Bryan Savoye Rosenburg

David Glenn Carlson

Kevin James Kathmann

Thomas Owen McKinley

Gary J Mincher

Rodney Lee Rabe

Paula A Kavanagh

Jin Ma

A method, data processing system and program product utilize dynamic logical storage volume sizing for burst buffers or other local storage for computing nodes to optimize job stage in, execution and/or stage out.

Burst buffer dynamic logical volume sizing in high performance computing environment

A distributed network switch includes multiple switch modules connected by one or more physical cables. One switch module may determine which connector port of a remote switch module is connected by physical cable based on information received from the remote switch module, including link identifiers, and further based on a physical topology predetermined about the type of remote switch module.

Constructing and verifying switch fabric cabling schemes

The different switch modules making up a distributed virtual switch may route configuration commands for hardware resources to different modules within the distributed switch using a distribution and routing layer. At least one of the switch modules maintains a routing table that defines which switch modules are responsible for which hardware resources. The switch module uses the routing tables to forward the commands on the distribution and routing layer to the responsible switch module which then ensures that the relevant hardware resources are configured.

Distributing functions in a distributed and embedded environment

Debugging of code of a computer program is facilitated by having a plurality of internal breakpoints associated with lines of code previously set by a processor, during a debugging session, while implementing one or more step-type operations. During execution of another operation, internal breakpoints are disabled as encountered and deemed unnecessary to completion of the another operation. A count of a number of interrupts of one or more interrupt-types experienced during execution of the another operation is maintained, and responsive to the count exceeding a threshold, the disabling is varied to remove at least N internal breakpoints responsive to encountering an internal breakpoint during execution of the another operation deemed unnecessary to completion of the another operation, where N&#x2267;2.

Varying removal of internal breakpoints during debugging of code

An interactive tool is disclosed for visualizing performance data in real-time to enable adaptive performance optimization for an application running on a massively parallel computer system. The interactive tool may be used to visualize network congestion (and other) performance counters for an application as it runs on the parallel system in real-time. Further, a developer may use the interactive tool to experiment with various tuning options and optimization approaches on-the-fly.

Interactive tool for visualizing performance data in real-time to enable adaptive performance optimization and feedback

Debugging of code of a computer program is facilitated by implementing a step-type operation using internal breakpoints to ensure debugger control of the code. During a debugging session, a step-type operation is implemented by setting active internal breakpoints on every line of code of every routine currently on the call stack referenced by the processor and on entry points of the code being debugged, and subsequently leaving in place, upon completion of the step-type operation, active internal breakpoints. Subsequent to implementing the step-type operation any active internal breakpoints encountered during execution of one or more other operations of the code and deemed unnecessary to completion of the other operation(s) are disabled, and the location of any internal breakpoints disabled during execution of the one or more other operations are tracked in a data structure(s) for subsequent use in reestablishing needed internal breakpoints for implementation of another step-type operation.

Implementing a step-type operation during debugging of code using internal breakpoints

Debugging of code of a computer program is facilitated by implementing, during a debugging session, a step-type operation by machine instruction stepping through the code, and concurrent therewith, setting up breakpoints to perform the step-type operation. Responsive to the machine instruction stepping reaching a next debuggable line of code prior to completion of setup of breakpoints to perform the step-type operation, the machine instruction stepping is discontinued, and the setting up of breakpoints to perform the step-type operation is discontinued. Alternatively, responsive to completing setup of the breakpoints to perform the step-type operation prior to machine instruction stepping reaching the next debuggable line of code, the machine instruction stepping is discontinued, and the code is executed to perform the step-type operation using the set breakpoints.

Step-type operation processing during debugging by machine instruction stepping concurrent with setting breakpoints

An apparatus, program product and method represent a database query access plan a query execution data structure including a plurality of query node objects arranged into a tree relationship to define a parent node object and at least one child node object, and an attribute data structure that references a plurality of attributes utilized by the query execution data structure. At least one of the parent and child node objects includes an attribute operation data structure configured to manipulate at least a subset of the plurality of attributes in the attribute data structure by accessing the attribute operation data structure. By partitioning the functionality of a query access plan into a collection of node objects and an attribute data structure, and then providing within at least a subset of the node objects attribute operation data structures that manipulate the attribute data structure, the resulting query engine architecture becomes significantly extendible and adaptable. Moreover, through appropriate selection of attribute operations, and coding of such operations using directly executable program code, optimal query engine performance may also be obtained.

Object-oriented query execution data structure

System control over the logging of objects in order to meet the user specified recovery requirements. Under the fixed recovery time environment, the user chooses a length of time to be spent on object recovery, and the system dynamically manages the logging of objects to meet this time. The shorter the time the user chooses, the more objects the system will log, and the more performance degradation there will be as a result of the logging at run-time. The user may partition storage into Auxiliary Storage Pools (ASPs), which are groups of non-volatile storage, and then specify the recovery time on a per ASP basis. Under the minimal impact environment, the system dynamically manages the objects to be logged such that the object logging has a minimal impact on run-time performance.

System managed logging of objects to speed recovery processing

Growing community of inventors

Oronoco, MN, United States of America

David Lee Hermsmeier