Partitioning data in a parallel database system
AssigneeNCR Corporation
InventorAmbuj Shatdal
Life of this patent
Estimating the term…
Abstract
A parallel database system includes multiple processing units and associated storage modules. To achieve even distribution of workload, rows of a table are distributed as evenly as possible across the multiple processing units using a predefined partitioning algorithm. The predefined partitioning algorithm defines groups and probabilities assigned to boundary points defining the groups. Partitioning of data is based on the boundary points and the assigned probabilities.
Claims34
A method for use in a parallel database system having plural processing units, comprising:
- assigning probabilities to boundary points of defined groups of values of a partitioning attribute;
- and
- partitioning data across the plural processing units based at least in part on the boundary points and the probabilities assigned to the boundary points.
A parallel database system comprising:
- M processing units;
- and
- a controller to:
- assign probabilities to boundary points of defined groups of values of a partitioning attribute;
- and
- partition data across the M processing units based at least in part on the probabilities assigned to the boundary points.
An article comprising at least one storage medium containing instructions that when executed cause a parallel database system with plural processing units to:
- assign probabilities to boundary points of defined groups of values of a partitioning attribute;
- and
- partition data across the plural processing units based at least in part on the probabilities assigned to the boundary points.
Dependencies are inferred from the claim text.