Periodicity optimization in an automated tracing system
View Patent ↗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.
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 for one or more time series data sets;
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 a size at least as large as a longest frequency observed in the one or more time series data sets; 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 two 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 two 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 collects preliminary results for one or more time series data sets;
analyzes said preliminary results to identify a set of periods within said preliminary results;
selects a first period within said set of periods;
identifies 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 a size at least as large as a longest frequency observed in the one or more time series data sets; 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; 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, said third period being larger than said first period and said second period.