Call stack sampling for a multi-processor system

• US 8,286,134 B2
• Filed: 07/15/2008
• Issued: 10/09/2012
• Est. Priority Date: 07/15/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jones, Scott Thomas, Levine, Frank Eliot
• Primary Examiner(s): Zhen, Wei
• Assistant Examiner(s): Wu, Junchun
• Application Number:
  US12/173,107
• Publication Number:
  US 20100017584A1
• Time in Patent Office: 1,547 Days
• Field of Search: 717/124
• US Class Current: 717/124
• CPC Class Codes: G06F 11/3612 by runtime analysis performance monitoring G06F11/3466

Abstract

A computer implemented method for sampling call stack information. Responsive to identifying a set of interrupts, a determination is made as to whether all processors in a plurality of processors have generated the set of interrupts. A number of addresses are identified for a set of interrupted threads identified by the set of interrupts response to a determination that all of the processors have generated the set of interrupts. A determination is made as to whether the identified address falls within a set of address ranges. Responsive to a determination that the identified address falls within the set of address ranges, a sampler thread is notified to obtain call stack information.

Claims

1. A computer implemented method for sampling call stack information, the computer implemented method comprising:

responsive to identifying a set of interrupts, determining whether all processors in a plurality of processors have generated the set of interrupts, wherein each of the plurality of processors is a processor unit that has a counter set after generating an interrupt and a determination as to whether all processors in the plurality of processors have generated the set of interrupts is made by checking all counters in the plurality of processors to determine that all counters have been set;

responsive to a determination that all of the processors have generated the set of interrupts, receiving an identification for a set of executable code in a user input and converting the identification to a set of identified addresses for the set of executable code to form a set of address ranges;

determining whether any address within the set of identified addresses falls within the set of address ranges; and

responsive to a determination that the any address within the set of identified addresses falls within the set of address ranges, notifying a sampling thread to obtain the call stack information.

2. The computer implemented method of claim 1 further comprising:

receiving user input identifying at least one of the set of executable code and a set of data objects;

identifying the set of address ranges from the user input; and

storing the set of address ranges in a work area.

3. The computer implemented method of claim 2, wherein the receiving step comprises:

receiving the user input identifying at least one of the set of executable code and the set of data objects at a profiler.

4. The computer implemented method of claim 1 further comprising:

responsive to a change in an address range within the set of address ranges during execution of the set of executable code, identifying a new address range.

5. The computer implemented method of claim 1, wherein the determining step and the sampling step are performed by a deferred procedure call handler.

6. The computer implemented method of claim 1 further comprising:

responsive to a determination that at least one of the set of identified addresses does not fall in the set of address ranges, performing an action.

7. The computer implemented method of claim 6, wherein the action is at least one of incrementing a counter and notifying the sampling thread to sample the call stack information for each address within the set of identified addresses falling within the set of address ranges.

8. A computer comprising:

a bus;

a storage device connected to the bus, wherein program code is stored on the storage device; and

a processor unit connected to the bus, wherein the processor unit executes the program code to determine whether all processors in a plurality of processors have generated a set of interrupts in response to identifying the set of interrupts, wherein the processor unit has a counter set after generating an interrupt and a determination as to whether all processors in the plurality of processors have generated the set of interrupts is made by checking all counters in the plurality of processors to determine that all counters have been set;

identify a number of addresses for a set of interrupted threads identified by the set of interrupts to form a set of identified addresses in response to a determination that all of the processors have generated the set of interrupts, receive an identification for a set of executable code in a user input and convert the identification to a set of identified addresses for the set of executable code to form a set of address ranges;

determine whether any address within the set of identified addresses falls within set of address ranges; and

notify a sampling thread to obtain the call stack information in response to a determination that any address within the set of identified addresses falls within the set of address ranges.

9. The computer of claim 8, wherein the processor unit further executes the program code to receive user input identifying at least one of the set of executable code and a set of data objects;

identify the set of address ranges from the user input; and

store the set of address ranges in a work area.

10. The computer of claim 9, wherein in executing the program code to receive the user input identifying at least one of the set of executable code and the set of data objects, the processor unit executes the program code to receive the user input identifying at least one of the set of executable code and the set of data objects at a profiler.

11. The computer of claim 8, wherein the processor unit further executes the program code to perform an action in response to a determination that at least one of the set of identified addresses does not fall in the set of address ranges.

12. The computer of claim 11, wherein the action is at least one of incrementing a counter and notifying the sampling thread to sample the call stack information for each address within the set of identified addresses falling within the set of address ranges.

13. A computer program product for sampling call stack information, the computer program product comprising:

a non-transitory computer readable storage medium;

program code, stored on the non-transitory computer readable storage medium, responsive to identifying a set of interrupts, for determining whether all processors in a plurality of processors have generated the set of interrupts, wherein each of the plurality of processors is a processor unit that has a counter set after generating an interrupt and a determination as to whether all processors in the plurality of processors have generated the set of interrupts is made by checking all counters in the plurality of processors to determine that all counters have been set;

program code, stored on the non-transitory computer readable storage medium, responsive to a determination that all of the processors have generated the set of interrupts, for receiving an identification for a set of executable code in a user input and converting the identification to a set of identified addresses for the set of executable code to form a set of address ranges;

program code, stored on the non-transitory computer readable storage medium, for determining whether any address within the set of identified addresses falls within the set of address ranges; and

program code, stored on the non-transitory computer readable storage medium, responsive to a determination that any address within the set of identified addresses falls within the set of address ranges, for notifying a sampling thread to obtain the call stack information.

14. The computer program product of claim 13 further comprising:

program code, stored on the non-transitory computer readable storage medium, for receiving user input identifying at least one of the set of executable code and a set of data objects; and

program code, stored on the non-transitory computer readable storage medium, for identifying the set of address ranges from the user input.