Autonomic workload classification using predictive assertion for wait queue and thread pool selection

• US 20050183084A1
• Filed: 02/13/2004
• Published: 08/18/2005
• Est. Priority Date: 02/13/2004
• Status: Active Grant

• Current Assignee: X Corp. (f/k/a Twitter, Inc.) (X Holdings Corp.)
• Original Assignee: International Business Machines Corporation
• Inventors: Daughtrey, Erik A., Cuomo, Gennaro A.
• Granted Patent: US 7,703,101 B2
• Time in Patent Office: Days
• US Class Current: 718/100
• CPC Class Codes: G06F 9/505 considering the load

Abstract

Incoming work units (e.g., requests) in a computing workload are analyzed and classified according to predicted execution. Preferred embodiments track which instrumented wait points are encountered by the executing work units, and this information is analyzed to dynamically and autonomically create one or more recognizers to programmatically recognize similar, subsequently-received work units. When a work unit is recognized, its execution behavior is then predicted. Execution resources are then allocated to the work units in view of these predictions. The recognizers may be autonomically evaluated or tuned, thereby adjusting to changing workload characteristics. The disclosed techniques may be used advantageously in application servers, message-processing software, and so forth.

Claims

1. A method of programmatically analyzing execution behavior of work units, comprising steps of:

recording, for each of a plurality of executing work units, information regarding one or more instrumented wait points encountered by the work unit;

grouping the recorded information for the encountered work units; and

programmatically determining characteristics of those work units that encountered the wait points in the groups.

2. The method according to claim 1, wherein the work units are execution requests.

3. The method according to claim 2, wherein the execution requests are content requests.

4. The method according to claim 2, wherein the execution requests are Web services requests.

5. The method according to claim 2, wherein the execution requests specify method/class names to be executed.

6. The method according to claim 1, wherein the recorded information comprises an identifier of each wait point.

7. The method according to claim 6, wherein the recorded information further comprises time spent waiting at each wait point.

8. The method according to claim 1, wherein the characteristics comprise parameter names and values thereof.

9. The method according to claim 1, wherein the grouping step further comprises the steps of:

determining, from the recorded information, a set of the wait points encountered by each of the work units; and

determining all unique ones of the determined sets.

10. The method according to claim 9, wherein the step of programmatically determining the characteristics further comprises the step of evaluating occurrence of the characteristics among the unique sets.

11. The method according to claim 1, wherein the programmatically determining step further comprises the step of determining which of the characteristics are discriminators as to the wait points that are encountered.

12. The method according to claim 1, further comprising the step of using the programmatically-determined characteristics to programmatically build one or more recognizers which are adapted to recognizing those characteristics in arriving work units that are to be subsequently executed.

13. The method according to claim 12, further comprising the step of executing the recognizers to recognize the characteristics in the arriving work units.

14. The method according to claim 12, further comprising the step of classifying the arriving work units using the recognizers.

15. The method according to claim 1, further comprising the step of using the programmatically-determined characteristics when allocating execution resources to subsequently-arriving work units.

16. The method according to claim 12, further comprising the step of using the programmatically-built recognizers when allocating execution resources to subsequently-arriving work units.

17. The method according to claim 15, wherein the allocation resources are threads in thread pools.

18. The method according to claim 12, further comprising the step of programmatically evaluating effectiveness of one or more of the recognizers, in view of its ability to predict which of the instrumented wait points will be encountered by the arriving work units.

19. The method according to claim 18, further comprising the step of programmatically destroying ones of the programmatically-evaluated recognizers for which the effectiveness falls below a threshold value.

20. A system for programmatically analyzing execution behavior of work units, comprising:

means for recording, for each of a plurality of executing work units, information regarding one or more instrumented wait points encountered by the work unit;

means for grouping the recorded information for the encountered work units; and

means for programmatically determining characteristics of those work units that encountered the wait points in the groups.

21. The system according to claim 20, further comprising means for using the programmatically-determined characteristics when allocating execution resources to subsequently-arriving work units.

22. The system according to claim 21, wherein the allocation resources are threads in thread pools.

23. The system according to claim 20, further comprising:

means for using the programmatically-determined characteristics to programmatically build one or more recognizers which are adapted to recognizing those characteristics in arriving work units that are to be subsequently executed;

means for executing the recognizers to programmatically recognize the characteristics in the arriving work units; and

means for using the programmatically-recognized characteristics when allocating execution resources to subsequently-arriving work units.

24. A computer program product for programmatically analyzing execution behavior of work units, the computer program product embodied on one or more computer-readable media and comprising:

computer-readable program code means for recording, for each of a plurality of executing work units, information regarding one or more instrumented wait points encountered by the work unit;

computer-readable program code means for grouping the recorded information for the encountered work units; and

computer-readable program code means for programmatically determining characteristics of those work units that encountered the wait points in the groups.

25. The computer program product according to claim 24, further comprising computer-readable program code means for using the programmatically-determined characteristics when allocating execution resources to subsequently-arriving work units, wherein the allocation resources are threads in thread pools.

26. The computer program product according to claim 24, further comprising:

computer-readable program code means for using the programmatically-determined characteristics to programmatically build one or more recognizers which are adapted to recognizing those characteristics in arriving work units that are to be subsequently executed;

computer-readable program code means for executing the recognizers to programmatically recognize the characteristics in the arriving work units; and

computer-readable program code means for using the programmatically-recognized characteristics when allocating execution resources to subsequently-arriving work units.

27. A method of doing business by analyzing execution information for work units, comprising steps of:

grouping information that has been recorded for each of a plurality of executing work units regarding one or more instrumented wait points encountered by the work unit;

programmatically determining characteristics of those work units that encountered the wait points in the groups; and

charging a fee for carrying out the grouping and programmatically determining steps.

28. The method according to claim 27, further comprising the step of using the programmatically-determined characteristics to create predictive assertions for allocating execution resources.