Determination of a culprit thread after a physical central processing unit lockup

• US 10,331,546 B2
• Filed: 01/25/2017
• Issued: 06/25/2019
• Est. Priority Date: 06/23/2016
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Gadi, Sowgandh Sunil, Govindarajalu, Hariprakash
• Primary Examiner(s): Contino, Paul
• Application Number:
  US15/415,261
• Publication Number:
  US 20170371766A1
• Time in Patent Office: 881 Days
• 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 11/366 using diagnostics G06F11/0703 takes precedence
• CPC Class Codes: G06F 11/3664 Environments for testing or debugging software

Abstract

An automated end-to-end analysis of customer service requests is disclosed. A core dump is received, wherein the core dump corresponds to a customer service request regarding a crash of a computer system. A processor automatically analyzes the core dump to determine if a pcpu lockup of the computer system is due to a software issue. Provided the pcpu lockup of the computer system is due to the software issue, the processor determines which thread is a culprit thread responsible for the pcpu lockup of the computer system.

Claims

1. A computer-implemented method for determining a culprit thread after a physical central processing unit (pcpu) lockup of a computer system, said method comprising:

receiving a core dump, wherein said core dump corresponds to a customer service request regarding a crash of said computer system;

automatically analyzing said core dump with a processor to determine if said pcpu lockup of said computer system is due to a software issue, wherein said automatically analyzing said core dump further comprises;

automatically determining a culprit module responsible for said crash of said computer system, said core dump including crash results corresponding to said crash; and

automatically generating a signature back trace, wherein said signature back trace pertains to a symptom of said crash of said computer system, and wherein said automatically determining a culprit module responsible for said crash of said computer system further comprises;

generating an essential stack of functions corresponding to said crash of said computer system;

determining a tag sequence and a tag depth corresponding to said essential stack of functions;

deriving a list of permissible tag permutations corresponding to said computer system; and

utilizing said tag sequence and said tag depth in combination with said list of permissible tag permutations to identify a culprit module responsible for said computer crash; and

provided said pcpu lockup of said computer system is due to said software issue, determining which thread is a culprit thread responsible for said pcpu lockup of said computer system.

2. The computer-implemented method of claim 1, wherein said receiving said core dump further comprises:

automatically receiving said core dump.

3. The computer-implemented method of claim 1, further comprising:

provided said pcpu lockup of said computer system is not due to said software issue, providing a notification that said pcpu lockup is due to a hardware issue.

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

provided said pcpu lockup of said computer system is not due to said software issue, providing a notification that said pcpu lockup is due to a firmware issue.

5. The computer-implemented method of claim 1, wherein said automatically analyzing said core dump with a processor further comprises:

automatically evaluating timestamp data associated with said pcpu lockup; and

automatically evaluating hardware-related state information associated with said pcpu lockup.

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

providing a notification for display on a graphic user interface of a computer, wherein said notification identifies said culprit thread responsible for said pcpu lockup of said computer system.

7. In an automated end-to-end system for analysis of customer service requests,

a method for analyzing a core dump corresponding to a crash of a computer system, said method comprising:

receiving a core dump, wherein said core dump corresponds to a customer service request regarding a crash of said computer system;

automatically analyzing said core dump with a processor to determine if said pcpu lockup of said computer system is due to a software issue, wherein said automatically analyzing said core dump further comprises;

automatically determining a culprit module responsible for said crash of said computer system, said core dump including crash results corresponding to said crash; and

automatically generating a signature back trace, wherein said signature back trace pertains to a symptom of said crash of said computer system, and wherein said automatically determining a culprit module responsible for said crash of said computer system further comprises;

generating an essential stack of functions corresponding to said crash of said computer system;

determining a tag sequence and a tag depth corresponding to said essential stack of functions;

deriving a list of permissible tag permutations corresponding to said computer system; and

utilizing said tag sequence and said tag depth in combination with said list of permissible tag permutations to identify a culprit module responsible for said computer crash; and

provided said pcpu lockup of said computer system is due to said software issue, determining which thread is a culprit thread responsible for said pcpu lockup of said computer system.

8. The method of claim 7, wherein said receiving said core dump further comprises:

automatically receiving said core dump.

9. The method of claim 7, further comprising:

provided said pcpu lockup of said computer system is not due to said software issue, providing a notification that said pcpu lockup is due to a hardware issue.

10. The method of claim 7, further comprising:

provided said pcpu lockup of said computer system is not due to said software issue, providing a notification that said pcpu lockup is due to a firmware issue.

11. The method of claim 7, wherein said automatically analyzing said core dump with a processor further comprises:

automatically evaluating timestamp data associated with said pcpu lockup; and

automatically evaluating hardware-related state information associated with said pcpu lockup.

12. The method of claim 7, further comprising:

providing a notification for display on a graphic user interface of a computer, wherein said notification identifies said culprit thread responsible for said pcpu lockup of said computer system.