Skewing of scheduled search queries
AssigneeSplunk Inc.
InventorsPaul J. Lucas, Eric Woo
Life of this patent
Estimating the term…
Abstract
Techniques for scheduling search queries in a computing environment are disclosed. A search query scheduling system associates a first set of queries with a first skew tolerance, the first set of queries scheduled to be performed during a first period, where the first skew tolerance is based on a duration of the first period. The search query scheduling system reschedules a first subset of search queries included in the first set of queries by skewing the first subset of search queries over a first portion of the first period based on the first skew tolerance.
Claims21
A computer-implemented method, comprising:
- associating a first set of queries with a skew amount, wherein the first set of queries is scheduled to be performed during each occurrence of a first period, and the skew amount is associated with a first portion of the first period;
- computing a first hash value based on one or more attributes associated with a first query included in the first set of queries;
- computing a first skew value associated with the first query based on performing one or more operations on the first hash value and the skew amount;
- and
- rescheduling the first query for execution during the first portion of the first period based on the first skew value,
- wherein the first query is executed via one or more processors based on the rescheduling of the first query for execution during the first portion of the first period based on the first skew value.
One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
- associating a first set of queries with a skew amount, wherein the first set of queries is scheduled to be performed during each occurrence of a first period, and the skew amount is associated with a first portion of the first period;
- computing a first hash value based on one or more attributes associated with a first query included in the first set of queries;
- computing a first skew value associated with the first query based on performing one or more operations on the first hash value and the skew amount;
- and
- rescheduling the first query for execution during the first portion of the first period based on the first skew value,
- wherein the first query is executed via one or more processors based on the rescheduling of the first query for execution during the first portion of the first period based on the first skew value.
A computing device, comprising:
- one or more memories that include a query scheduling program;
- and
- one or more processors that are coupled to the one or more memories and, when executing the query scheduling program, are configured to:
- associate a first set of queries with a skew amount, wherein the first set of queries is scheduled to be performed during each occurrence of a first period, and the skew amount is associated with a first portion of the first period;
- compute a first hash value based on one or more attributes associated with a first query included in the first set of queries;
- compute a first skew value associated with the first query based on performing one or more operations on the first hash value and the skew amount;
- and
- reschedule the first query for execution during the first portion of the first period based on the first skew value,
- wherein the first query is executed via one or more processors based on the rescheduling of the first query for execution during the first portion of the first period based on the first skew value.
Dependencies are inferred from the claim text.