Paraccel LLC

Actian Sub Iii, Inc.

David Benedict Galimberti

Brian Pak-Ning Chu

David G Wilhite, Jr

Mayank Pradhan

Adam Birnbaum

Raymi Dyskant

Richard Glick

Ravindra Prakash

A system, for example, an online system or a database system schedules requests received for execution. The system maintains consumer groups and receives a measure of amount of resources allocated for each consumer group. The system maintains a measure of accumulated elapsed time of execution of requests received from each consumer group. If the system determines that resources are available for executing a request, the system selects a request for execution from a consumer group based on the measure of accumulated elapsed time for processing queries for the consumer group and the measure of amount of resources allocated for the consumer group. The system maintains relative cumulative elapsed times of queries across consumer groups in the same ratio as the allocated share for the consumer groups. Accordingly, the system schedules requests such that each consumer group approaches its allocation of resources compared to other groups smoothly over time.

Scheduling database queries based on elapsed time of queries

A database system performs hash join process for processing queries that join an inner and an outer database table. The hash join processes builds a hash table in memory for the inner table. The database system receives a limit on the memory for storing the hash table. The database system maximizes the number of partitions stored in memory for the hash table. If the hash table exceeds the limit of the memory while adding rows from the inner table, the database system selects a partition for spilling to a persistent storage. The partition selected for spilling to may be the largest partition or a partition larger than most of the partitions. The database system initializes the hash table to a number of partitions that is substantially equal to half of the total number of blocks that can be stored within the specified limit of memory for the hash table.

Disk-based hash join process

A database system maintains table data in sorted order. The table data becomes unsorted over time due to add, delete, and update operations. These operations are performed such that the table comprises an initial sorted region followed by an unsorted region. The database system performs an incremental operation to rewrite the table in sorted order. The database system partitions the unsorted region into a plurality of partitions comprising sorted rows within each partition. The database system iteratively merges rows from the partitions to the sorted region of the table. The database system selects a set of lowest tanked rows from the partitions. The database system merges these lowest ranked rows with the sorted region while maintaining the sort order of the sorted region. The database system repeats these steps until all the partitions are processed. The database may store data in columnar fashion.

Maintaining sort order of data in databases

Growing community of inventors

Ann Arbor, MI, United States of America

David Benedict Galimberti