APPLICATION PERFORMANCE MONITORING

• US 20150199254A1
• Filed: 01/16/2015
• Published: 07/16/2015
• Est. Priority Date: 01/16/2014
• Status: Active Grant

• Current Assignee: Appnomic Systems Pvt. Ltd.
• Original Assignee: Appnomic Systems Pvt. Ltd.
• Inventors: Narasappa, Sumanth, Desikachari, Padmanabhan, Vesepogu, Nageswara Rao
• Granted Patent: US 10,198,340 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 2201/865 Monitoring of software
• CPC Class Codes: G06F 2201/87 Monitoring of transactions

Abstract

Various techniques associated with application performance monitoring are disclosed. In some embodiments, a subset of application methods is configured to capture response time metrics, and response time metrics for a prescribed application transaction are computed by summing corresponding response time metrics of methods of the subset that are executed during each transaction invocation. Method and transaction response time metrics are collected for each of a plurality of observation intervals, and the collected response time metrics are analyzed to identify anomalous method and transaction states. Co-occurring anomalous transaction and method states are correlated to identify a set of hotspot methods for the transaction, wherein hotspot methods comprise expected root causes for anomalies of the transaction.

Claims

1. A method, comprising:

configuring a subset of application methods to capture response time metrics;

computing response time metrics for a prescribed application transaction by summing corresponding response time metrics of methods of the subset that are executed during each transaction invocation;

collecting method and transaction response time metrics for each of a plurality of observation intervals;

analyzing the collected response time metrics to identify anomalous method and transaction states; and

correlating co-occurring anomalous transaction and method states to identify a set of hotspot methods for the transaction, wherein hotspot methods comprise expected root causes for anomalies of the transaction.

2. The method of claim 1, wherein the subset does not include all methods executed during each transaction invocation.

3. The method of claim 1, wherein response time metrics are captured or computed for each method or transaction invocation.

4. The method of claim 1, wherein an observation interval comprises a time window.

5. The method of claim 1, wherein analyzing the collected response time metrics to identify anomalous method and transaction states comprises generating a state matrix for the transaction and associated methods across the plurality of observation intervals.

6. The method of claim 1, further comprising refining the set of hotspot methods to identify and eliminate non-participating methods.

7. The method of claim 1, further comprising refining the set of hotspot methods to identify and add correlated rarely failing methods.

8. A system, comprising:

a monitoring agent configured to;

instrument a subset of application methods to capture response time metrics;

compute response time metrics for a prescribed application transaction by summing corresponding response time metrics of methods of the subset that are executed during each transaction invocation; and

collect method and transaction response time metrics for each of a plurality of observation intervals;

an anomaly detection module configured to analyze the collected response time metrics to identify anomalous method and transaction states; and

a correlation module configured to correlate co-occurring anomalous transaction and method states to identify a set of hotspot methods for the transaction, wherein hotspot methods comprise expected root causes for anomalies of the transaction

9. The system of claim 8, wherein the subset does not include all methods executed during each transaction invocation.

10. The system of claim 8, wherein response time metrics are captured or computed for each method or transaction invocation.

11. The system of claim 8, wherein an observation interval comprises a time window.

12. The system of claim 8, wherein to analyze the collected response time metrics to identify anomalous method and transaction states comprises generating a state matrix for the transaction and associated methods across the plurality of observation intervals.

13. The system of claim 8, wherein the correlation module is further configured to refine the set of hotspot methods to identify and eliminate non-participating methods.

14. The system of claim 8, wherein the correlation module is further configured to refine the set of hotspot methods to identify and add correlated rarely failing methods.

15. A computer program product embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

configuring a subset of application methods to capture response time metrics;

computing response time metrics for a prescribed application transaction by summing corresponding response time metrics of methods of the subset that are executed during each transaction invocation;

collecting method and transaction response time metrics for each of a plurality of observation intervals;

analyzing the collected response time metrics to identify anomalous method and transaction states; and

correlating co-occurring anomalous transaction and method states to identify a set of hotspot methods for the transaction, wherein hotspot methods comprise expected root causes for anomalies of the transaction.

16. The computer program product of claim 15, wherein the subset does not include all methods executed during each transaction invocation.

17. The computer program product of claim 15, wherein response time metrics are captured or computed for each method or transaction invocation.

18. The computer program product of claim 15, wherein an observation interval comprises a time window.

19. The computer program product of claim 15, wherein analyzing the collected response time metrics to identify anomalous method and transaction states comprises generating a state matrix for the transaction and associated methods across the plurality of observation intervals.

20. The computer program product of claim 15, further comprising computer instructions for refining the set of hotspot methods.