Achieving ultra-high availability using a single CPU

• US 9,026,848 B2
• Filed: 06/24/2013
• Issued: 05/05/2015
• Est. Priority Date: 07/23/2010
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Brocade Communications Systems, Inc. (Broadcom, Inc.)
• Inventors: Abraham, Vineet M., Chin, Bill Ying, Mahoney, William R., Saxena, Aditya, Liang, Xupei, Zhou, Bill Jianqiang
• Primary Examiner(s): Lottich, Joshua P
• Application Number:
  US13/925,696
• Publication Number:
  US 20140095927A1
• Time in Patent Office: 680 Days
• Field of Search: 714/4.11, 714/4.12, 714/11, 714/13
• US Class Current: 714/11
• CPC Class Codes: G06F 11/00 Error detection; Error correction; Monitoring error detection, correction or monitoring in information storage based on relative movement between record carrier and transducer G11B20/18; monitoring, i.e. supervising the progress of recording or reproducing G11B27/36; in static stores G11C29/00
• CPC Class Codes: G06F 11/1482 by means of middleware or OS functionality
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 11/2017 where memory access, memory control or I/O control functionality is redundant redundant communication control functionality G06F11/2005; redundant storage control functionality G06F11/2089

Abstract

Techniques for achieving high-availability using a single processor (CPU). In a system comprising a multi-core processor, at least two partitions may be configured with each partition being allocated one or more cores of the multiple cores. The partitions may be configured such that one partition operates in active mode while another partition operates in standby mode. In this manner, a single processor is able to provide active-standby functionality, thereby enhancing the availability of the system comprising the processor.

Claims

1. A system comprising:

a memory, wherein a first portion of the memory is allocated to a first partition and a second portion of the memory is allocated to a second partition; and

a processor comprising a plurality of cores, wherein a first set of one or more cores from the plurality of cores is allocated to the first partition and a second set of one or more cores from the plurality of cores is allocated to the second partition;

wherein the first partition is configured to operate in a first mode and perform a function in the first mode;

wherein the second partition is configured to operate in a second mode when the first partition is operating in the first mode, the second mode being different from the first mode, wherein the function performed in the first mode is not performed by the second partition when operating in the second mode;

wherein the second partition is configured to start operating in the first mode instead of the second mode and to perform the function; and

wherein the first partition is configured to operate in the second mode when the second partition is operating in the first mode and the function is not performed by the first partition when operating in the second mode.

2. The system of claim 1 wherein:

the first set of cores allocated to the first partition comprises a first core when the first partition is operating in the first mode; and

the first core is allocated to the second partition instead of the first partition when the second partition operates in the first mode.

3. The system of claim 1 wherein the function performed by a partition operating in the first mode is analyzing a packet received by the system via a port of the system.

4. The system of claim 1 wherein the function performed in the first mode is performing processing to determine a port of the system to be used for forwarding a packet from the system.

5. The system of claim 1 wherein the function performed in the first mode is maintaining a routing table used for routing a packet from the system.

6. The system of claim 1 further comprising:

a port; and

a card configured to process a packet received via the port, wherein the card comprises the processor.

7. The system of claim 1 further comprising:

a first card configured to perform processing for forwarding a packet from the system using a port of the system; and

a second card communicatively coupled with the first card, the second card comprising the processor;

wherein the function performed in the first mode is downloading, from the second card to the first card, information that enables the first card to perform processing for forwarding the packet from the system.

8. The system of claim 1 wherein:

the second partition is configured to start operating in the first mode upon the occurrence of an event;

wherein the event is one of an occurrence of a reset or reboot of the first partition, receipt of a signal to perform a software upgrade for the first partition, a failure in operation of the first partition, or receipt of a signal to cause the second partition to operate in the first mode instead of the first partition.

9. The system of claim 1 wherein:

the second partition is configured to start operating in the first mode upon the occurrence of an event that triggers a failover to occur.

10. A method comprising:

causing, in a system comprising a processor providing a plurality of cores, a first set of one or more cores from the plurality of cores to be allocated to a first partition and a second set of one or more cores from the plurality of cores to be allocated to a second partition;

operating the first partition in a first mode;

performing, by the first partition, a function performed in the first mode;

operating the second partion in a second mode, wherein the function is not performed by the second partition when operating in the second mode; and

causing the second partition to start operating in the first mode instead of the second mode;

performing, by the second partition, the function when the second partition operates in the first mode; and

causing the first partition to operate in the second mode when the second partition is operating in the first mode.

11. The method of claim 10 wherein causing the second partition to start operating in the first mode instead of the second mode comprises:

for a first core in the first set of cores allocated to the first partition, allocating the first core to the second partition instead of the first partition when the second partition starts to operate in the first mode.

12. The method of claim 10 wherein the function is analyzing a packet received by the system via a port of the system.

13. The method of claim 10 wherein the function is performing processing to determine a port of the system to be used for forwarding a packet from the system.

14. The method of claim 10 wherein the function is maintaining a routing table used for routing a packet from the system.

15. The method of claim 10 further comprising:

providing a card in the system for processing a packet received via a port of the system; and

providing the processor on the card.

16. The method of claim 10 further comprising:

providing a first card and a second card in the system; and

providing the processor on the second card;

wherein the function is downloading, from the second card to the first card, information that enables the first card to perform processing for forwarding a packet from the system.

17. The method of claim 10 wherein causing the second partition to start operating in the first mode instead of the second mode comprises:

detecting, by the system, the occurrence of an event; and

causing the second partition to start operating in the first mode in response to detecting the occurrence of the event;

wherein the event is one of an occurrence of a reset or reboot of the first partition, receipt of a signal to perform a software upgrade for the first partition, a failure in operation of the first partition, or receipt of a signal to cause the second partition to operate in the first mode instead of the first partition.

18. The method of claim 10 wherein causing the second partition to start operating in the first mode instead of the second mode comprises:

detecting, by the system, the occurrence of an event that causes a failover to occur; and

causing the second partition to start operating in the first mode in response to detecting the occurrence of the event.

19. A non-transitory computer-readable medium storing a plurality of instructions for execution by a system comprising a processor, the processor comprising a plurality of cores, the plurality of instructions comprising:

instructions that cause a first partition to operate in a first mode, the first partition allocated a first set of cores from the plurality of cores, wherein a function is performed in the first mode;

instructions that cause a second partition to operate in a second mode when the first partition is operating in the first mode, wherein the function is not performed in the second mode, the second partition allocated a second set of cores from the plurality of cores;

instructions that, in response to an event, cause;

the second partition to start operating in the first mode instead of the second mode and to perform the function; and

the first partition to operate in the second mode when the second partition operates in the first mode.

20. The non-transitory computer-readable medium of claim 19 wherein the plurality of instructions further comprises:

instructions that cause, for a first core in the first set of cores allocated to the first partition, the first core to be allocated to the second partition instead of the first partition when the second partition starts to operate in the first mode.