Biasing active-standby determination

• US 9,619,349 B2
• Filed: 10/14/2014
• Issued: 04/11/2017
• Est. Priority Date: 10/14/2014
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Brocade Communications Systems, Inc. (Broadcom, Inc.)
• Inventors: Zhou, Bill Jianqiang, Mahoney, William R.
• Primary Examiner(s): Decady, Albert
• Assistant Examiner(s): CONTINO, PAUL F
• Application Number:
  US14/514,253
• Publication Number:
  US 20160103745A1
• Time in Patent Office: 910 Days
• Field of Search: None
• CPC Class Codes: G06F 11/0724 in a multiprocessor or a multi-core unit multiprocessors per se G06F15/80
• CPC Class Codes: G06F 11/1417 Boot up procedures
• CPC Class Codes: G06F 11/1441 Resetting or repowering
• CPC Class Codes: G06F 11/1658 Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit
• CPC Class Codes: G06F 11/184 where the redundant components implement processing functionality
• CPC Class Codes: G06F 11/202 where processing functionality is redundant redundant communication control functionality G06F11/2005, redundant storage control functionality G06F11/2089
• CPC Class Codes: G06F 11/2023 Failover techniques
• CPC Class Codes: G06F 11/2033 switching over of hardware resources
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2048 where the redundant components share neither address space nor persistent storage
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 9/445 Program loading or initiating bootstrapping G06F9/4401; security arrangements for program loading or initiating G06F21/57
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: G06F 9/5094 where the allocation takes into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

In computing systems that provide multiple computing domains configured to operate according to an active-standby model, techniques are provided for intentionally biasing the race to gain mastership between competing computing domains, which determines which computing domain operates in the active mode, in favor of a particular computer domain. The race to gain mastership may be biased in favor of a computing domain operating in a particular mode prior to the occurrence of the event that triggered the race to gain mastership. For example, in certain embodiments, the race to mastership may be biased in favor of the computing domain that was operating in the active mode prior to the occurrence of an event that triggered the race to gain mastership.

Claims

1. A method comprising:

upon the occurrence of an event that causes a race between a first domain in a computing system and a second domain in the computing system to start operating in a first mode, determining that the first computing domain did not operate in the first mode prior to occurrence of the event; and

upon determining that the first computing domain did not operate in the first mode prior to the occurrence of the event;

refraining, for a period of time, the first computing domain from attempting to start operating in the first mode;

allowing, during the period of time, the second computing domain to attempt to start operating in the first mode; and

after the period of time has passed;

determining, by the first computing domain, whether the second computing domain is operating in the first mode;

upon determining that the second computing domain is not operating in the first mode, allowing the first computing domain to attempt to operate in the first mode; and

upon determining that the second computing domain is operating in the first mode, causing the first computing domain to operate in a second mode different from the first mode.

2. The method of claim 1 wherein a set of functions is performed when operating in the first mode and not performed when operating in the second mode.

3. The method of claim 1 wherein a set of functions is performed when operating in the second mode and is not performed when operating in the first mode.

4. The method of claim 1 wherein the refraining comprises calculating the period of time.

5. The method of claim 1 wherein determining that the first computing domain did not operate in the first mode prior to the occurrence of the event comprises:

reading, by the first computing domain, information from a non-volatile memory, wherein the information is stored in the non-volatile memory prior to the occurrence of the event; and

determining, by the first computing domain, that the first computing domain did not operate in the first mode prior to the occurrence of the event based upon the information read from the non-volatile memory.

6. The method of claim 1 wherein the determining, by the first computing domain, whether the second computing domain is operating in the first mode comprises:

reading information from a memory location, the memory location being readable and writable by the first computing domain and the second computing domain; and

determining, based upon the information read from the memory location, whether the second computing domain is operating in the first mode.

7. The method of claim 1 wherein:

a first set of one or more processing units is allocated to the first computing domain; and

a second set of one or more processing units is allocated to the second computing domain;

wherein the first set of processing units includes a first core from a multicore processor; and

wherein the second set of processing units includes a second core from the multicore processor.

8. A system comprising:

a first computing domain comprising at least a first processing unit, wherein the first processing unit is a processor or a processing core; and

a second computing domain comprising at least a second processing wherein the second processing unit is a processor or a processing core;

wherein the first computing domain is configured to;

upon the occurrence of an event that causes a race between the first computing domain and the second computing domain to operate in a first mode, determine that the first computing domain did not operate in the first mode prior to occurrence of the event;

refrain from attempting to start operating in the first mode for a period of time;

after the period of time has passed;

determine whether the second computing domain is operating in the first mode;

upon determining that the second computing domain is not operating in the first mode, attempt to operate in the first mode; and

upon determining that the second computing domain is operating in the first mode, start to operate in a second mode different from the first mode; and

wherein the second computing domain is configured to, while the first computing domain is refrained from attempting to start operating in the first mode for the period of time, attempt to start operating in the first mode.

9. The system of claim 8 wherein a set of functions is performed when operating in the first mode and not performed when operating in the second mode.

10. The system of claim 8 wherein a set of functions is performed when operating in the second mode and is not performed when operating in the first mode.

11. The system of claim 8 wherein the first computing domain is configured to:

read, from a non-volatile memory, information stored in the non-volatile memory prior to the occurrence of the event; and

determine, based upon the read information, that the first computing domain did not operate in the first mode prior to the occurrence of the event.

12. The system of claim 8 wherein the first computing domain is configured to:

read information from a memory location, the memory location being readable and writable by the first computing domain and the second computing domain; and

determine, based upon the information read from the memory location, whether the second computing domain is operating in the first mode.

13. The system of claim 8 wherein:

a first set of one or more processing units is allocated to the first computing domain, the first set of processing units including a first core from a multicore processor; and

a second set of one or more processing units is allocated to the second computing domain, the second set of processing units including a second core from the multicore processor.

14. A network device comprising:

a set of one or more ports for forwarding one or more data packets from the network device;

a plurality of processing units;

a first computing domain, the first computing domain being allocated a first set of one or more processing units from the plurality of processing units;

a second computing domain, the second computing domain being allocated a second set of one or more processing units from the plurality of processing units;

wherein, in response to the occurrence of an event that causes a race between the first computing domain and the second computing domain to operate in a first mode, the first computing domain is configured to determine that the first computing domain did not operate in the first mode prior to the occurrence of the event;

wherein the first computing domain is configured to refrain from attempting to start operating in the first mode for a period of time;

wherein, in response to the occurrence of the event, the second computing domain is configured to attempt to start operating in the first mode during the period of time;

wherein, after the period of time has passed, the first computing domain is configured to;

if the second computing domain is operating in the first mode, start to operate in a second mode different from the first mode; and

if the second computing domain is not operating in the first mode, attempt to operate in the first mode.

15. The network device of claim 14 wherein a set of functions is performed by the first computing domain or the second computing domain when operating in the first mode and not performed when operating in the second mode.

16. The network device of claim 14 wherein a set of functions is performed when operating in the second mode and is not performed when operating in the first mode.

17. The network device of claim 14 wherein the first computing domain is configured to, based upon information stored prior to the occurrence of the event, determine whether the first computing domain operated in the first mode prior to the occurrence of the event.

18. The network device of claim 14 wherein:

the first set of processing units includes a first core from a multicore processor; and

the second set of processing units includes a second core from the multicore processor.

19. The network device of claim 14 wherein:

the first computing domain corresponds to a first card of the network device; and

the second computing domain corresponds to a second card of the network device.

20. The network device of claim 14 wherein the first computing domain and the second computing domain are located on a card of the network device.

21. An apparatus comprising:

upon the occurrence of an event that causes a race between a first domain in a computing system and a second domain the computing system to operate in a first mode, means for determining that the first computing domain did not operate in the first mode prior to the occurrence of the event;

means for refraining, by the first computing domain, for a period of time, from attempting to start operating in the first mode; and

means for allowing, during the period of time, the second computing domain to attempt to start operating in the first mode; and

after the period of time has passed;

means for determining, by the first computing domain, whether the second computing domain is operating in the first mode;

upon determining that the second computing domain is not operating in the first mode, means for allowing the first computing domain to attempt to operate in the first mode; and

upon determining that the second computing domain is operating in the first mode, means for causing the first computing domain to operate in a second mode different from the first mode.