System and method for providing trace information data reduction

• US 6,055,492 A
• Filed: 12/12/1997
• Issued: 04/25/2000
• Est. Priority Date: 12/12/1997
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Berry, Robert Francis, Alexander, William Preston III, Urguhart, Robert John
• Primary Examiner(s): Hoff, Marc S.
• Assistant Examiner(s): Bui, Bryan
• Application Number:
  US08/989,725
• Time in Patent Office: 865 Days
• Field of Search: 702/179, 702/186-187, 395/183.15, 395/185.04, 395/182.18, 395/704, 714/25-27
• US Class Current: 702/179
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 11/348 Circuit details, i.e. tracer hardware

Abstract

The present invention is a system, method, and computer readable medium for representing program event trace information in a way which is very compact and efficient, and yet supports a wide variety of queries regarding system performance. The tracing and reduction of the present invention may be dynamic, in which case information is obtained and added to the trace representation in real-time. Alternately, the tracing and reduction may be static, in which case a trace text file or binary file is obtained from a trace buffer, and the reduction takes place using the trace file as input. The trace information, whether obtained statically or dynamically, is represented as a tree of events. The present invention may be used to present many types of trace information in a compact manner which supports performance queries. For example, the tree structure of the present invention may reflect the call stacks observed during a program'"'"'s execution, and statistics regarding the time spent in the various routines and call stacks may be stored at each node of the tree. The tree structure may be used to store performance information regarding Java bytecodes executed, memory allocated, or other types of performance information. The trace information is presented in a manner which is compact and efficient, and may be used to quickly and easily answer a variety of performance queries. Further, a system may be traced for long periods of time without losing useful performance information due to a limited buffer space.

Claims

1. A method for monitoring the performance of a program, comprising the steps of:

obtaining a plurality of trace events which occur as the program executes;

representing the trace events as one or more nodes in a tree structure;

recording one or more performance statistics at each node in the tree structure;

determining if a selected event is represented in the tree structure; and

if the selected event is not represented in the tree structure, adding a new node for the selected event to the tree structure, wherein the new node is a child node descending from a parent node representing another event.

2. A method according to claim 1, wherein said obtaining step further comprises the step of parsing a trace file to obtain one or more trace events stored in the trace file.

3. A method according to claim 1, wherein said obtaining step comprises the step of identifying each trace event in real time as it occurs during execution of the program.

4. A method according to claim 3, wherein said representing step comprises the step of adding each trace event to the tree structure in real time as the trace event occurs.

5. A method according to claim 4, wherein said recording step comprises the step of updating the performance statistics for each trace event in real time as the trace event occurs.

6. A method for monitoring the performance of a program, comprising the steps of:

obtaining a plurality of trace events which occur as the program executes;

representing the trace events are one or more nodes in a tree structure; and

recording one or more performance statistics at each node in the tree structure, wherein said obtaining step comprises the step of identifying one or more call stacks present as the program executes, wherein each call stack is an ordered list of one or more routines that have been entered during execution of the program.

7. A method according to claim 6, wherein said representing step comprises the step of representing each call stack as a set of nodes in a tree structure, wherein each node represents a routine in the call stack.

8. A method according to claim 7, further comprising the steps of:

determining if a selected routine is represented in the tree structure; and

if the selected routine is not represented in the tree structure, adding a new node for the selected routine to the tree structure, wherein the new node is a child node descending from a parent node representing a calling routine.

9. An information handling system, comprising:

a processor;

a program which executes on the processor;

means for obtaining a plurality of trace events which occur as the program executes;

means for representing the trace events as one or more nodes in a tree structure; and

means for recording one or more performance statistics at each node in the tree structure, wherein said means for obtaining comprises means for identifying one or more call stacks present as the program executes, wherein each call stack is an ordered list of one or more routines that have been entered during execution of the program.

10. An information handling system according to claim 9, wherein said means for obtaining further comprises means for parsing a trace file to obtain one or more trace events stored in the trace file.

11. An information handling system according to claim 9, wherein said means for obtaining comprises means for identifying each trace event in real time as it occurs during execution of the program.

12. An information handling system according to claim 11, wherein said means for representing comprises means for adding each trace event to the tree structure in real time as the trace event occurs.

13. An information handling system according to claim 12, wherein said means for recording comprises means for updating the performance statistics for each trace event in real time as the trace event occurs.

14. An information handling system according to claim 9, wherein said means for representing comprises means for representing each call stack as a set of nodes in a tree structure, wherein each node represents a routine in the call stack.

15. An information handling system according to claim 14, further comprising:

means for determining if a selected routine is represented in the tree structure; and

means for adding a new node for the selected routine to the tree structure, wherein the new node is a child node descending from a parent node representing a calling routine.

16. An information handling system, comprising:

a processor;

a program which executes on the processor;

means for obtaining a plurality of trace events which occur as the program executes;

means for representing the trace events as one or more nodes in a tree structure;

means for recording one or more performance statistics at each node in the tree structure;

means for determining if a selected event is represented in the tree structure; and

means for adding a new node for the selected event to the tree structure, wherein the new node is a child node descending from a parent node representing another event.

17. A computer readable medium, comprising:

means for obtaining a plurality of trace events which occur as a program executes;

means for representing the trace events as one or more nodes in a tree structure;

means for recording one or more performance statistics at each node in the tree structure;

means for determining if a selected event is represented in the tree structure; and

means for adding a new node for the selected event to the tree structure, wherein the new node is a child node descending from a parent node representing another event.

18. A computer readable medium according to claim 17, wherein said means for obtaining further comprises means for parsing a trace file to obtain one or more trace events stored in the trace file.

19. A computer readable medium according to claim 17, wherein said means for obtaining comprises means for identifying each trace event in real time as it occurs during execution of the program.

20. A computer readable medium according to claim 19, wherein said means for representing comprises means for adding each trace event to the tree structure in real time as the trace event occurs.

21. A computer readable medium according to claim 20, wherein said means for recording comprises means for updating the performance statistics for each trace event in real time as the trace event occurs.

22. A computer-readable medium, comprising:

means for obtaining a plurality of trace events which occur as a program executes;

means for representing the trace events as one or more nodes in a tree structure; and

means for recording one or more performance statistics at each node in the tree structure, wherein said means for obtaining comprises means for identifying one or more call stacks present as the program executes, wherein each call stack is an ordered list of one or more routines that have been entered during execution of the program.

23. A computer readable medium according to claim 22, wherein said means for representing comprises means for representing each call stack as a set of nodes in a tree structure, wherein each node represents a routine in the call stack.

24. A computer readable medium according to claim 23, further comprising:

means for determining if a selected routine is represented in the tree structure; and

means for adding a new node for the selected routine to the tree structure, wherein the new node is a child node descending from a parent node representing a calling routine.