DISTRIBUTED EXECUTION OF EXPRESSIONS IN A QUERY

• US 20150347512A1
• Filed: 03/20/2015
• Published: 12/03/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Luo, Lin, Petitclerc, Martin
• Granted Patent: US 10,242,061 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/24545 Selectivity estimation or determination
• CPC Class Codes: G06F 16/24549 Run-time optimisation
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/283 Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A computer-implemented method for executing a query specification can include evaluating the query specification by a first computing device to identify a candidate expression in the query specification to be executed by a second computing device hosting a source of data specified in the candidate expression. A cost estimate for executing the candidate expression at the first computing device is determined. Whether the cost estimate of executing the candidate expression at the first computing device is greater than a threshold is determined. The candidate expression is replaced with a native query function when the cost estimate of executing the candidate expression at the first computing device is greater than the threshold. The native query function can be executed at the second computing device. It can be determined whether a runtime context is necessary, and if necessary, a context parameter is injected into the native query function.

Claims

1. A computer-implemented method for executing a query specification, comprising:

evaluating the query specification, by a first computing device, to identify an expression in the query specification as a candidate expression to be executed by a second computing device hosting a source of data specified in the candidate expression;

determining a cost estimate of executing the candidate expression at the first computing device;

determining whether the cost estimate of executing the candidate expression at the first computing device is greater than a threshold; and

replacing the candidate expression with a native query function when the cost estimate of executing the candidate expression at the first computing device is greater than the threshold.

2. The method of claim 1, further comprising executing the native query function at the second computing device hosting the source of data specified in the candidate expression.

3. The method of claim 1, further comprising determining whether a runtime context is necessary to execute the native query function.

4. The method of claim 3, further comprising generating a context parameter for the native query function.

5. The method of claim 1, wherein the determining of the cost estimate of executing the candidate expression at the first computing device includes determining one of a first amount of memory required at the first computing device, a first amount of bandwidth required to transfer a result set from the second computing device to the first computing device, or a first number of CPU cycles required at the first computing device.

6. The method of claim 1, wherein the threshold is one of a first amount of memory, a first amount of bandwidth, or a first number of CPU cycles.

7. The method of claim 1, further comprising translating a term of the candidate expression expressed into a term understood by the second computing device hosting the source of data specified in the candidate expression.

8. The method of claim 1, further comprising parsing the query specification to identify a particular expression in the query specification as a candidate expression.