Periodicity optimization in an automated tracing system

• US 8,997,063 B2
• Filed: 02/12/2013
• Issued: 03/31/2015
• Est. Priority Date: 02/12/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Concurix Corporation
• Inventors: Krajec, Russell S., Li, Ying
• Primary Examiner(s): TECKLU, ISAAC TUKU
• Application Number:
  US13/765,654
• Publication Number:
  US 20130283241A1
• Time in Patent Office: 777 Days
• Field of Search: None
• US Class Current: 717/130
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3447 Performance evaluation by modeling
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 11/3604 Software analysis for verifying properties of programs byte-code verification G06F9/44589
• CPC Class Codes: G06F 11/3636 by tracing the execution of the program
• CPC Class Codes: G06F 11/3644 by instrumenting at runtime
• CPC Class Codes: G06F 2201/865 Monitoring of software
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Periodicity similarity between two different tracer objectives may be used to identify additional input parameters to sample. The tracer objectives may be individual portions of a large tracer operation, and each of the tracer objectives may have separate set of input objects for which data may be collected. After collecting data for a tracer objective, other tracer objectives with similar periodicities may be identified. The input objects from the other tracer objectives may be added to a tracer objective and the tracer objective may be executed to determine a statistical significance of the newly added objective. An iterative process may traverse multiple input objects until exhausting possible input objects and a statistically significant set of input objects are identified.

Claims

1. A method performed by a computer processor, said method comprising:

receiving an application to instrument;

performing a preliminary trace of said application while said application executes and collecting preliminary results;

analyzing said preliminary results to identify a set of periods within said preliminary results;

selecting a first period within said set of periods;

identifying a first trace objective for said application, said first trace objective comprising a plurality of data items to collect and a first collection window comprising at least three times said first period; and

causing said first trace objective to be executed and collecting a first results set comprising said plurality of data items and a first input stream.

2. The method of claim 1 further comprising:

performing a first autocorrelation analysis of a first data item, said first data item being one of said plurality of data items, said first autocorrelation analysis being performed on said first results set; and

identifying a first derived period for said first data item.

3. The method of claim 2 further comprising:

selecting a second period within said set of periods;

creating a second trace objective for said application, said second trace objective comprising said plurality of data items to collect and a second collection window comprising at least three times said second period; and

causing said second trace objective to be executed and collecting a second results set comprising said plurality of data items and a second input stream.

4. The method of claim 3 further comprising:

performing a second autocorrelation analysis of said first data item, said second autocorrelation analysis being performed on said second results set; and

identifying a second derived period for said first data item.

5. The method of claim 4 further comprising:

comparing said first derived period and said second derived period; and

when said first derived period and said second derived period are statistically different, creating a third trace objective comprising a third collection window comprising at least three times a third period, said third period being larger than said first period and said second period.

6. The method of claim 5 further comprising:

when said first derived period and said second derived period are statistically similar, using said first derived period within a profile model for said first data item.

7. The method of claim 6, said second trace objective being executed on a first processor during a first time period, said third trace objective being executed on said first processor at during a second time period.

8. The method of claim 7, said first time period overlapping said second time period.

9. The method of claim 7, said first time period not overlapping said second time period.

10. The method of claim 6, said second trace objective being executed on a first processor and said second trace objective being executed on a second processor.

11. The method of claim 10, said second trace objective being executed during a first time period and said third trace objective being executed during a second time period.

12. The method of claim 11, said first time period overlapping said second time period.

13. The method of claim 11, said first time period not overlapping said second time period.

14. The method of claim 11, said first processor and said second processor being comprised in a first device.

15. The method of claim 11, said first processor being comprised in a first device, said second processor being comprised in a second device.

16. A system comprising:

a processor;

a trace objective generator executing on said processor that;

receives an application to instrument;

performs a preliminary trace of said application while said application executes and collecting preliminary results;

analyzes said preliminary results to identify a set of periods within said preliminary results;

selects a first period within said set of periods;

identifying a first trace objective for said application, said first trace objective comprising a plurality of data items to collect and a first collection window comprising at least three times said first period; and

causes said first trace objective to be executed and collecting a first results set comprising said plurality of data items and a first input stream.

17. The system of claim 16, said trace objective generator that further:

performs a first autocorrelation analysis of a first data item, said first data item being one of said plurality of data items, said first autocorrelation analysis being performed on said first results set; and

identifies a first derived period for said first data item.

18. The system of claim 17, said trace objective generator that further:

selects a second period within said set of periods;

creates a second trace objective for said application, said second trace objective comprising said plurality of data items to collect and a second collection window comprising at least three times said second period; and

causes said second trace objective to be executed and collecting a second results set comprising said plurality of data items and a second input stream.

19. The system of claim 18, said trace objective generator that further:

performs a second autocorrelation analysis of said first data item, said second autocorrelation analysis being performed on said second results set; and

identifies a second derived period for said first data item.

20. The system of claim 19, said trace objective generator that further:

compares said first derived period and said second derived period; and

when said first derived period and said second derived period are statistically different, creates a third trace objective comprising a third collection window comprising at least three times a third period, said third period being larger than said first period and said second period.