High performance counter for realistic measurement of computer system load

• US 7,421,592 B1
• Filed: 02/13/2004
• Issued: 09/02/2008
• Est. Priority Date: 02/13/2004
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Kadatch, Andrew, Walsh, James E., Shan, Xiaowen, Patrick, Stuart R.
• Primary Examiner(s): Lee; Thomas C.
• Assistant Examiner(s): TRAN, VINCENT HUY
• Application Number:
  US10/779,299
• Time in Patent Office: 1,663 Days
• Field of Search: 707/10, 713/300
• US Class Current: 713/300
• CPC Class Codes: G06F 11/3423 where the assessed time is active or idle time
• CPC Class Codes: G06F 11/348 Circuit details, i.e. tracer hardware

Abstract

The present invention leverages high-frequency interrupts and/or low priority threads to accurately determine which computing resources are available. This provides a computing asset (CPUs and/or software applications) with a means to accurately compensate for resource utilization in order to increase its performance. By utilizing the present invention, the computing asset can optimize its performance in a real-time, self-tuning manner. In one instance of the present invention, high intensity, low priority threads are initiated on available CPUs (logical and/or physical) to effectively replace a CPU'"'"'s idle time with the low priority thread. This thread generally constitutes a computationally-intensive and/or a memory-intensive thread which permits a highly accurate performance measurement to be obtained for available CPU resources. In another instance of the present invention, high-frequency interrupts are initiated on CPUs to compensate for processes that are shorter than a thread'"'"'s time quantum, providing a more accurate performance counter.

Claims

1. A computer-implemented performance monitoring system, comprising:

a performance component that initiates at least one low-priority thread involving at least one computing resource and at least one high-frequency interrupt associated with at least one computing resource, the at least one low-priority thread comprising at least one of a memory-intensive operation thread or a computationally-intensive operation thread, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least approximately 300 Hertz, the at least one computing resource comprising at least one of a central processing unit (CPU) or a memory resource; and

a monitoring component that obtains at least one performance parameter for the at least one computing resource derived, at least in part, from at least one selected from the group consisting of the low-priority thread and the high-frequency interrupt initiated by the performance component, the monitoring component generates a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event, the at least one performance parameter comprising at least one of available CPU processing time, available memory, or available CPUs.

2. The system of claim 1, the monitoring component tracks multiple CPU performance of at least one of a virtual CPU or a physical CPU.

3. The system of claim 1, the monitoring component is at least one of a dynamically linked library (DLL) associated with an operating system or embedded into the operating system.

4. A device employing the system of claim 1 comprising at least one selected from the group consisting of a computer, a server, and a handheld electronic device.

5. A computer-implemented method for facilitating computing system performance, comprising:

executing at least one low-priority thread involving at least one computing resource and at least one high-frequency interrupt related to the at least one computing resource, the at least one low-priority thread comprising at least one selected from a group consisting of a memory-intensive operation thread and a computationally-intensive operation thread, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least approximately 300 Hertz, the at least one computing resource comprising at least one of a central processing unit (CPU) or a memory resource;

obtaining at least one performance parameter for the computing resource derived, at least in part, from at least one selected from the group consisting of execution of the low-priority thread and execution of the high-frequency interrupt, the at least one performance parameter comprising at least of available CPU processing time, available memory, or available CPUs; and

generating a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event.

6. An entity employing the method of claim 5 comprising at least one selected from the group consisting of a light-weight operating system, a self-tuning application, a cell phone, a personal digital assistant (PDA), a logical CPU, an application programming interface (API), a computer, a server, and a handheld electronic device.

7. A computer-implemented performance monitoring system, comprising:

a performance component that initiates at least one low-priority thread related to at least one computing resource and at least one high-frequency interrupt involving at least one computing resource, the at least one low-priority thread comprising at least one of a memory-intensive operation thread or a computationally-intensive operation thread, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least 300 Hertz, the at least one computing resource comprising at least one of a central processing unit (CPU) or a memory resource; and

a monitoring component that obtains at least one performance parameter for the computing resource derived, at least in part, from at least one selected from the group consisting of the high-frequency interrupt and the low-priority thread initiated by the performance component, the monitoring component generates a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event, the at least one performance parameter comprising at least one of available CPU processing time, available memory, or available CPUs.

8. The system of claim 7, a low-priority thread is initiated on each CPU associated with the system to facilitate preventing an idle loop, the CPU comprising at least one of a logical CPU or a physical CPU.

9. The system of claim 7, the monitoring component interfaces with a plurality of physical CPUs, the plurality of physical CPUs are at least one of situated on a common die or at least a portion of the physical CPUs are situated on separate dies.

10. A device employing the system of claim 7 comprising at least one selected from the group consisting of a computer, a server, and a handheld electronic device.

11. A computer-implemented method for facilitating computing system performance, comprising:

executing at least one high-frequency interrupt involving at least one computing resource and at least one low-priority thread related to at least one computing resource, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least 300 Hertz, the at least one low-priority thread comprising at least one of a memory-intensive operation thread or a computationally-intensive operation thread the computing resource comprising at least one of a central processing unit (CPU) or a memory resource;

obtaining at least one performance parameter for the computing resource derived, at least in part, from at least one selected from the group consisting of execution of the high-frequency interrupt and execution of the low-priority thread, the at least one performance parameter comprising at least one of available CPU processing time, available memory, or available CPUs; and

generating a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event.

12. An entity employing the method of claim 11 comprising at least one selected from the group consisting of a light-weight operating system, a self-tuning application, a cell phone, a personal digital assistant (PDA), a logical CPU, an application programming interface (API), a computer, a server, and a handheld electronic device.

13. A computer-implemented performance monitoring system, comprising:

a performance component that initiates at least one low-priority thread involving at least one computing resource and at least one high-frequency interrupt involving at least one computing resource, wherein the low-priority thread comprising at least one selected from a group consisting of a memory-intensive operation thread and a computationally-intensive operation thread, the high-frequency interrupt comprising an interrupt with a frequency of at least approximately 300 Hertz, the computing resource comprising at least one selected from the group consisting of a central processing unit (CPU) and a memory resource, and the performance parameter comprising at least one from the group consisting of available central processing unit (CPU) processing time, available memory, and available CPUs; and

a monitoring component that obtains at least one performance parameter for the computing resource derived, at least in part, from at least one selected from the group consisting of the low-priority thread and the high-frequency interrupt initiated by the performance component, the monitoring component generates a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event.

14. A device employing the system of claim 13 comprising at least one selected from the group consisting of a computer, a server, and a handheld electronic device.

15. A computer-implemented method for facilitating computing system performance, comprising:

executing at least one low-priority thread involving at least one computing resource and at least one high-frequency interrupt involving at least one computing resource, wherein the at least one low-priority thread comprising at least one selected from a group consisting of a memory-intensive operation thread and a computationally-intensive operation thread, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least approximately 300 Hertz, the computing resource comprising at least one selected from a group consisting of a central processing unit (CPU) and a memory resource;

obtaining at least one performance parameter for the computing resource derived, at least in part, from execution of at least one selected from the group consisting of the low-priority thread and the high-frequency interrupt, the at least one performance parameter comprising at least one selected from a group consisting of available CPU processing time, available memory, and available CPUs; and

generating a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event.

16. An entity employing the method of claim 15 comprising at least one selected from the group consisting of a light-weight operating system, a self-tuning application, a cell phone, a personal digital assistant (PDA), a logical CPU, an application programming interface (API), a computer, a server, and a handheld electronic device.

17. A computer-implemented system that facilitates performance monitoring, comprising:

means for initiating at least one selected from a group consisting of at least one low-priority thread involving at least one computing resource and at least one high-frequency interrupt in at least one computing resource, wherein the at least one low-priority thread comprising at least one selected from the group consisting of a memory-intensive operation thread and a computationally-intensive operation thread, the at least one high-frequency interrupt comprising an interrupt with a frequency of at least approximately 300 Hertz, the computing resource comprising at least one selected from a group consisting of a central processing unit (CPU) and a memory resource;

means for obtaining at least one performance parameter for the computing resource derived, at least in part, from at least one selected from the group consisting of the low-priority thread and the high-frequency interrupt, the at least one performance parameter comprising at least one selected from a group consisting of available CPU processing time, available memory, and available CPUs; and

means for generating a report based on the at least one performance parameter upon the occurrence of a predetermined user-selected event.