Method and system for throttling log messages for multiple entities

• US 8,914,684 B2
• Filed: 05/26/2009
• Issued: 12/16/2014
• Est. Priority Date: 05/26/2009
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Cota-Robles, Erik, Korsunsky, Igor
• Primary Examiner(s): SCHELL, JOSEPH O
• Application Number:
  US12/472,180
• Publication Number:
  US 20100306599A1
• Time in Patent Office: 2,030 Days
• Field of Search: 714/20, 714/45, 714/44, 714/57, 719/318, 719/321
• US Class Current: 714/44
• CPC Class Codes: G06F 11/0706 the processing taking place on a specific hardware platform or in a specific software environment
• CPC Class Codes: G06F 11/0712 in a virtual computing platform, e.g. logically partitioned systems
• CPC Class Codes: G06F 11/0784 Routing of error reports, e.g. with a specific transmission path or data flow
• CPC Class Codes: G06F 13/102 where the programme performs an interfacing function, e.g. device driver G06F13/105 takes precedence; scheduling within device drivers G06F9/52; contention policies within device drivers G06F9/4881

Abstract

A software module capable of simultaneously supporting multiple services provides log message throttling for each service with a separate “per service” log message buffer. When the software module is a device driver, for example, each device controlled by the device driver is allocated a message buffer to store descriptive log messages. Upon generation of a warning log message, descriptive log messages in the message buffer are flushed to a log file for review by an administrator. Furthermore, log message throttling may be implemented by only flushing the message buffer upon certain occurrences of warning log messages, such as in accordance with an exponential back-off algorithm.

Claims

1. A method for logging messages relating to a plurality of devices simultaneously supported by a device driver, the method comprising:

allocating, by the device driver, a message buffer for each of the plurality of devices, wherein each message buffer is allocated to store log messages for a corresponding device;

generating a first warning log message in response to interacting with a first device in the plurality of devices;

flushing log messages in the message buffer corresponding to the first device to a log file upon generating the first warning log message in accordance with a log message throttling heuristic;

generating a second warning log message in response to interacting with a second device in the plurality of devices; and

flushing log messages in the message buffer corresponding to the second device to the log file upon generating the second warning log message in accordance with the log message throttling heuristic.

2. The method of claim 1, further comprising, for each of the plurality of devices, maintaining a count of occurrences of warning log messages and a corresponding specified limit for the count.

3. The method of claim 2, wherein the specified limit for each of the counts corresponding to each of the devices is configurable.

4. The method of claim 2, wherein the log message throttling heuristic comprises:

determining whether the count for a given device in the plurality of devices has exceeded the corresponding specified limit for the count; and

performing exponential back-off on the occurrences of warning log messages for the given device to determine if a currently generated warning log message causes the log messages in the message buffer corresponding to the given device to be flushed to the log file by the device driver.

5. The method of claim 1, wherein the log message throttling heuristic further comprises flushing the log messages in the message buffer corresponding to a given device to the log file if the currently generated warning log message is a 2^N occurrence of a warning log message for the given device.

6. The method of claim 1, wherein each message buffer is a circular buffer comprising a plurality of entries for storing text strings relating to log messages.

7. The method of claim 6, wherein the circular buffer further includes a start index and a current index that are utilized to flush the circular buffer in a correct order.

8. The method of claim 1, wherein each of the message buffers are allocated during an initialization process upon a connection of a corresponding device to the computer system.

9. A non-transitory computer-readable medium including instructions that, when executed by a processing unit of a computer system having a device driver capable of simultaneously supporting a plurality of devices, causes the processing unit to log messages relating to interactions between the device driver and the plurality of devices to a log file, by performing steps of:

allocating, by the device driver, a message buffer for each of the plurality of devices, wherein each message buffer is allocated to store log messages for a corresponding device;

generating a first warning log message in response to interacting with a first device in the plurality of devices;

flushing log messages in the message buffer corresponding to the first device to the log file upon generating the first warning log message in accordance with a log message throttling heuristic;

generating a second warning log message in response to interacting with a second device in the plurality of devices; and

flushing log messages in the message buffer corresponding to the second device to the log file upon generating the second warning log message in accordance with the log message throttling heuristic.

10. The non-transitory computer-readable medium of claim 9, wherein the processing unit further performs, for each of the plurality of devices, maintaining a count of occurrences of warning log messages and a corresponding specified limit for the count.

11. The non-transitory computer-readable medium of claim 10, wherein the specified limit for each of the counts corresponding to each of the devices is configurable.

12. The non-transitory computer readable medium of claim 10, wherein the log message throttling heuristic comprises:

determining whether the count for a given device in the plurality of devices has exceeded the corresponding specified limit for the count; and

performing exponential back-off on the occurrences of warning log messages for the given device to determine if a currently generated warning log message causes the log messages in the message buffer corresponding to the given device to be flushed to the log file by the device driver.

13. The non-transitory computer readable medium of claim 12, wherein the log message throttling heuristic further comprises flushing the log messages in the message buffer corresponding to a given device to the log file if the currently generated warning log message is a 2^N occurrence of a warning log message for the given device.

14. A method for logging messages for a software module simultaneously supporting a plurality of services, the method comprising:

allocating a message buffer for each of the plurality of services, wherein each message buffer is allocated to store log messages for a corresponding service;

generating a first warning log message in response to interacting with a first service in the plurality of services;

flushing log messages in the message buffer corresponding to the first service to a log file upon generating the first warning log message in accordance with a log message throttling heuristic;

generating a second warning log message in response to interacting with a second service in the plurality of services; and

flushing log messages in the message buffer corresponding to the second service to the log file upon generating the second warning log message in accordance with the log message throttling heuristic.

15. The method of claim 14, wherein each service in the plurality of services is a virtual machine.

16. The method of claim 15, wherein the software module is an error handler component of a hypervisor.

17. A method for logging messages for a software module simultaneously supporting a plurality of services, the method comprising:

allocating a message buffer for each of the plurality of services, wherein each message buffer is allocated to store log messages for a corresponding service;

generating a first warning log message in response to interacting with a first service in the plurality of services;

flushing log messages in the message buffer corresponding to the first service to a log file upon generating the first warning log message in accordance with a log message throttling heuristic;

generating a second warning log message in response to interacting with a second service in the plurality of services;

flushing log messages in the message buffer corresponding to the second service to the log file upon generating the second warning log message in accordance with the log message throttling heuristic; and

for each of the plurality of services, maintaining a count of occurrences of warning log messages and a corresponding specified limit for the count.

18. The method of claim 17, wherein the specified limit for each of the counts corresponding to each of the services is configurable.

19. The method of claim 17, wherein the log message throttling heuristic comprises:

determining whether the count for a service in the plurality of services has exceeded the corresponding specified limit for the count; and

performing exponential back-off on the occurrences of warning log messages for the service to determine whether to throttle back a currently generated warning log message for the service; and

if the currently generated warning log message for the service is not to be throttled back, flushing the log messages corresponding to the service to the log file.

20. The method of claim 17, wherein the throttling heuristic further comprises flushing the log messages in the message buffer corresponding to the service to the log file if the currently generated warning log message is a 2^N occurrence of a warning log message for the device.