REAL TIME MONITORING OF COMPUTER FOR DETERMINING SPEED AND ENERGY CONSUMPTION OF VARIOUS PROCESSES

• US 20130024731A1
• Filed: 09/27/2012
• Published: 01/24/2013
• Est. Priority Date: 10/29/2008
• Status: Active Grant

• Current Assignee: Riverbed Technology, LLC (Riverbed Technology Incorporated)
• Original Assignee: Aternity Information Systems Ltd.
• Inventors: Shochat, Eden, Elkind, David
• Granted Patent: US 9,032,254 B2
• Time in Patent Office: Days
• US Class Current: 714/38.1
• CPC Class Codes: G06F 11/0715 in a system implementing multitasking multitasking per se G06F9/46
• 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 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 11/3612 by runtime analysis performance monitoring G06F11/3466
• CPC Class Codes: G06F 2201/86 Event-based monitoring
• CPC Class Codes: G06F 2201/875 Monitoring of systems including the internet
• CPC Class Codes: G06F 2201/88 Monitoring involving counting
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The presently disclosed subject matter includes a system and method which enable to identify one or more causes for excessive energy consumption in a computer executing one or more processes. Information indicating that consumption of a computer-resource of at least one of said processes is greater than a predefined threshold is obtained and one or more threads of said at least one process which are in running state are identified. Thread performance information of at least one thread in running state is collected and used for identifying one or more functions that are the cause for said state of the respective thread. The identified functions are associated with their respective modules in order to identify one or more modules of said process, which are the cause for said excessive energy consumption.

Claims

1. A system comprising at least one processor operatively associated with a computer memory, the processor being configured to identify one or more causes for excessive energy consumption in a computer executing one or more processes, each of said one or more processes comprising one or more threads, the processor being operable to:

obtain information indicating that consumption of a computer-resource of at least one of said processes is greater than a predefined threshold;

detect states of one or more threads of said at least one process, and identify at least one thread in running state;

collect thread performance information of said at least one thread in running state, said performance information including data indicative of a performance of different functions of said process;

identify based on said performance information, one or more functions which are the cause for said state;

associate between said identified functions and their respective modules; and

identify, based on at least, said performance information of said one or more functions and on data related to their associated respective modules, one or more modules from among said modules, which are the cause for said excessive energy consumption.

2. The system of claim 1 wherein said computer resource is one or more of:

CPU resources, computer disk resources, network resources.

3. The system of claim 1, wherein said processor is configured to periodically poll said one or more threads of the one or more processes, in order to detect said states.

4. The system of claim 1, also including:

a data repository for storing a configured for storing said thread performance information.

5. The system of claim 1, wherein said one or more threads are UI threads.

6. The system of claim 1 wherein said processor is configured to utilize hooking of voluntary API calls in order to collect said performance information.

7. The system of claim 6, wherein said one or more threads are UI threads.

8. The system of claim 1, wherein said processor is further operable to utilize a knowledge base to store information for translating said performance information into data indicative of one or more functions and respective modules which are the cause for said excessive energy consumption.

9. The system of claim 8, wherein said information stored in said knowledge base includes one or more of:

historical, cross-system module baseline information.

10. The system of claim 1, wherein said processor is configured to utilize an Operating System maintained thread state store in order to detect states of said one or more threads.

11. The system of claim 1, wherein said performance information is normalized with respect to time.

12. The system of claim 1 wherein said processor is configured to intercept a respective process launch event of said one or more processes, thereby enable to detect states of said one or more threads.

13. The system of claim 1 wherein said processor is configured to poll call stacks of said at least one thread in running state, in order to collect said performance information.

14. The system of claim 13 wherein said processor is configured to count the number of times a function call of each given function is identified in said call stack and identify one or more functions with the highest counts as functions which are the cause for said state.

15. The system of claim 1 wherein said processor is configured to utilize heuristics in order to identify, based on said performance information, one or more functions and their respective modules from among said modules, which are the cause for said excessive energy consumption.

16. The system of claim 1, wherein said processor is configured to utilize a data storage containing data mapping between functions and respective modules in order to associate between said functions and their respective modules.

17. A method of identifying one or more causes for excessive energy consumption in a computer executing one or more processes, each of said one or more processes comprising one or more threads, the method comprising:

obtaining information indicating that consumption of a computer-resource of at least one of said processes is greater than a predefined threshold;

detecting states of one or more threads of said at least one process, and identify at least one thread in a running state;

collecting thread performance information of said at least one thread in running state, said performance information including data indicative of a performance of different functions of said process;

identifying based on said performance information, one or more functions which are the cause for said state;

associating between said identified functions and their respective modules; and

identify, based on at least, said performance information of said one or more functions and on data related to their associated respective modules, one or more modules from among said modules, which are the cause for said excessive energy consumption.

18. The method according to claim 17 further comprising:

periodically polling said one or more threads of the one or more processes, in order to detect said states.

19. The method according to claim 17 further comprising:

utilizing a knowledge base to store information for translating said performance information into data indicative of one or more functions and respective modules which are the cause said excessive energy consumption.

20. The method according to claim 17 further comprising:

normalizing said performance information with respect to time.

21. The method according to claim 17 further comprising:

intercepting a respective process launch event of said one or more processes, thereby enable to detect states of said one or more threads.

22. The method according to claim 17 further comprising:

polling call stacks of said at least one thread in running state, in order to collect said performance information.

23. The method according to claim 22 further comprising:

counting the number of times a function call of each given function is identified in said call stack and identify one or more functions with the highest counts as functions which are the cause for said state.

24. The method according to claim 17 further comprising:

utilizing heuristics in order to identify, based on said performance information, one or more functions and their respective modules from among said modules, which are the cause for said excessive energy consumption.

25. The method according to claim 17 further comprising:

utilizing a data storage containing data mapping between functions and respective modules in order to associate between said functions and their respective modules.

26. A none-transitory program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps of a method of identifying one or more causes for excessive energy consumption in a computer executing one or more processes, each of said one or more processes comprising one or more threads, the method comprising:

obtaining information indicating that consumption of a computer resource of at least one of said processes is greater than a predefined threshold;

detecting states of one or more threads of said at least one process, and identify at least one thread in a running state;

collecting thread performance information of said at least one thread in running state, said performance information including data indicative of a performance of different functions of said process;

identifying based on said performance information, one or more functions which are the cause for said state;

associating between said identified functions and their respective modules; and

identify, based on at least, said performance information of said one or more functions and on data related to their associated respective modules, one or more modules from among said modules, which are the cause for said excessive energy consumption.