International Business Machines Corporation

Ted Eric Blank

Bryan Frederick Smith

Jeffrey Alan Frey

James Alan Ruddy

Fen-Ling Lin

Robert R Rogers

John Marland Garth

Donald Francis Ferguson

Hong Sang Tie

Tammie Dang

Randy Mitchell Nakagawa

Kathryn Ruth Zeidenstein

Annie S Tsang

Angelo Pruscino

Kouhorng Allen Yang

Darren Benjamin Swank

Erhard Rahm

Craig Leonard Sutton

Dino Carlo Tonelli

A method, apparatus, and article of manufacture for a computer-implemented apportioning system. Work is distributed to processors in a multi-processor system. Initially, during bind-time, a scaling factor is determined for each processor. The scaling factor represents relative processing power in relation to each other processor. Then, portions of a total amount of work are distributed to each processor based on the determined scaling factor of that processor and a determined amount of work for an average processor.

Apportioning a work unit to execute in parallel in a heterogeneous environment

A method, apparatus, and article of manufacture for a computer implemented recover/build index system. The recover/build index system builds a database index for a database file by scanning partitions of the database file in parallel to retrieve key values and their associated record identifier (rid) values. The recover/build index system then sorts the scanned key/rid values for each partition in parallel. Next, the recover/build index system performs one or more merges on the sorted key/rid values from all of the partitions to generate a single key/rid value stream. Finally, the recover/build index system builds the index using the single key/rid value stream.

High performance recover/build index system by unloading database files

Page management mechanisms provide candidates for page stealing and prefetching from a main storage data cache of shared data when the jobs sharing the data are accessing it in a sequential manner. Pages are stolen behind the first reader in the cache, and thereafter at locations least likely to be soon re-referenced by trailing readers. A 'clustering' of readers may be promoted to reduce I/O contention. Prefetching is carried out so that the pages most likely to be soon referenced by one of the readers are brought into the cache.

Cache management method and apparatus for shared, sequentially-accessed,

Growing community of inventors

San Jose, CA, United States of America

Ted Eric Blank