Federation optimization using ordered queues
AssigneeRed Hat, Inc.
InventorsFilip Nguyen, Filip Elias
Life of this patent
Estimating the term…
Abstract
Methods, systems, and computer program products for optimization of query processing in a data federation system using priority queuing techniques are provided. Priority queuing techniques may include generating a query vector corresponding to a query, comparing the query vector to historical query vectors to determine similarity, determining an expected processing time for the query based on the determined similarity, and inserting the query into a priority ordered queue at a particular position based on the expected processing time.
Claims20
A system comprising:
- a non-transitory memory;
- and
- one or more processors to read instructions from the non-transitory memory to perform operations comprising:
- receiving a federated query;
- identifying a historical query that has a closest measured similarity to the federated query;
- determining an estimated processing time of the federated query, the estimated processing time being based on a processing time corresponding to the identified historical query;
- assigning the federated query a federated query priority that is based on the determined estimated processing time of the federated query;
- and
- adjusting, based on a pre-configured time duration elapsing, the federated query priority by a pre-configured amount.
A method comprising:
- generating, from a federated query, a first source query and a second source query;
- identifying a historical query that has a closest measured similarity to the first source query;
- determining an estimated processing time of the first source query, the estimated processing time of the first source query being based on a processing time corresponding to the identified historical query;
- modifying, using a second estimated processing time, the estimated processing time of the first source query;
- and
- assigning the first source query a source query priority that is based on the modified estimated processing time of the first source query.
A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
- generating, from a federated query, a first source query and a second source query;
- identifying a historical query that has a closest measured similarity to the first source query;
- determining an estimated processing time of the first source query, the estimated processing time of the first source query being based on a processing time corresponding to the identified historical query;
- modifying, using a second estimated processing time, the estimated processing time of the first source query;
- and
- assigning the first source query a source query priority that is based on the modified estimated processing time of the first source query.
Dependencies are inferred from the claim text.