Multi-node discovery and master election process for chassis management

Patent metadata

Field	Value
Publication number	US-10979497-B2
Application number	US-201916453019-A
Country	US
Kind code	B2
Filing date	Jun 26, 2019
Priority date	Jul 19, 2018
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

In a chassis including a plurality of nodes, a network switch, and a programmable device configured to manage a shared resource of the chassis, a method includes establishing, using the network switch, a dedicated network among baseboard management controllers of respective nodes in the plurality of nodes; and using the dedicated network, automatically selecting a given node from the plurality of nodes to function as a master node to program the programmable device on behalf of all nodes in the plurality of nodes to manage the shared resource of the chassis on behalf of all the nodes in the plurality of nodes.

First claim

What is claimed is:

1. A method comprising:
in a chassis comprising a plurality of nodes, a network switch, and a programmable device configured to manage a shared resource of the chassis, establishing, using the network switch, a dedicated network among respective baseboard management controllers of nodes in the plurality of nodes;
using the dedicated network, automatically selecting a first node from the plurality of nodes as a master node to program the programmable device on behalf of all nodes in the plurality of nodes to manage the shared resource of the chassis on behalf of all the nodes in the plurality of nodes; and
when the first node receives a communication from a second node from the plurality of nodes indicating that the second node is also, simultaneously, functioning as the master node, selecting the first node over the second as the master based on a physical slot position in the chassis of the first node,
wherein each of the respective baseboard management controllers of nodes is configured to periodically receive node data, via a broadcasted transmission, from each other node in the plurality of nodes via the dedicated network, such that respective baseboard management controllers of the nodes store, in memory, node data from each other node in the plurality nodes.

2. The method of claim 1 , further comprising the respective baseboard management controllers communicating with an enterprise local area network over a network, different from the dedicated network, to manage the respective baseboard management controllers.

3. The method of claim 1 , wherein the shared resource comprises at least one of a fan for the chassis, a power supply unit for the chassis, light emitting diodes (LEDs) on a front panel of the chassis, and a temperature sensor for the chassis.

4. The method of claim 1 , further comprising providing a communication path, different from the dedicated network, between each node of the plurality of nodes and the programmable device that is used to program the programmable device.

5. The method of claim 4 , wherein the communication path is one of an Inter-Integrated Circuit (I2C) bus or general purpose input output line.

6. The method of claim 1 , further comprising causing the first node to function as the master node after listening for, but not receiving after a predetermined amount of time, a master data packet from any other nodes in the plurality of nodes.

7. The method of claim 6 , wherein the predetermined amount of time is determined based on a physical slot on the chassis in which the first node is mounted.

8. The method of claim 1 , further comprising causing the first node to no longer function as the master node when the first node receives a master data packet from another node in the plurality of nodes.

9. The method of claim 1 , further comprising receiving from another node in the plurality of nodes a master grant request which causes the first node to no longer function as the master node.

10. An apparatus comprising:
a chassis;
a network switch;
a programmable device configured to manage a shared resource of the chassis; and
a plurality of nodes disposed in the chassis, wherein each node in the plurality of nodes comprises a baseboard management controller and a network interface to communicate with the network switch, wherein the plurality of nodes and the network switch define a dedicated network,
wherein respective baseboard management controllers of each of the nodes in the plurality of nodes are configured to automatically select a first node from the plurality of nodes as a master node to program the programmable device on behalf of all nodes in the plurality of nodes to manage the shared resource of the chassis on behalf of all the nodes in the plurality of nodes,
wherein when the first node receives a communication from a second node from the plurality of nodes indicating that the second node is also, simultaneously, functioning as the master node, selecting the first node over the second as the master node based on a physical slot position of the first node in the chassis, and
wherein each of the respective baseboard management controllers of nodes is configured to periodically receive node data, via a broadcasted transmission, from each other node in the plurality of nodes via the dedicated network, such that respective baseboard management controllers of the nodes store, in memory, node data from each other node in the plurality nodes.

11. The apparatus of claim 10 , wherein each respective baseboard management controller comprises another network interface to an enterprise local area network, different from the dedicated network, to manage each respective baseboard management controller.

12. The apparatus of claim 10 , wherein the shared resource comprises at least one of a fan for the chassis, a power supply unit for the chassis, light emitting diodes (LEDs) on a front panel of the chassis, and a temperature sensor for the chassis.

13. The apparatus of claim 10 , further comprising a communication path, different from the dedicated network, between each node of the plurality of nodes and the programmable device that is used to program the programmable device.

14. The apparatus of claim 13 , wherein the communication path is one of an Inter-Integrated Circuit (I2C) bus or a general purpose input output line.

15. The apparatus of claim 10 , wherein the baseboard management controller of the first node in the plurality of nodes is configured to cause the first node to function as the master node after listening for, but not receiving for a predetermined amount of time, a master data packet from any other nodes in the plurality of nodes.

16. A non-transitory computer readable storage media encoded with instructions that, when executed by a processor, cause the processor to:
establish, using a network switch, a dedicated network among respective baseboard management controllers of nodes in a plurality of nodes;
using the dedicated network, automatically select a first node from the plurality of nodes as a master node to program a programmable device on behalf of all nodes in the plurality of nodes to manage shared resource of a chassis on behalf of all the nodes in the plurality of nodes; and
when the first node receives a communication from a second node from the plurality of nodes indicating that the second node is also, simultaneously, functioning as the master node, select the first node over the second as the master node based on a physical slot position of the first node in the chassis,
wherein each of the respective baseboard management controllers of nodes is configured to periodically receive node data, via a broadcasted transmission, from each other node in the plurality of nodes via the dedicated network, such that respective baseboard management controllers of the nodes store, in memory, node data from each other node in the plurality nodes.

17. The non-transitory computer readable storage media of claim 16 , wherein the instructions, when executed by the processor, cause the processor to communicate with an enterprise local area network over a network, different from the dedicated network, to manage the respective baseboard management controllers.

18. The non-transitory computer readable storage media of claim 16 , wherein the shared resource comprises at least one of a fan for the chassis, a power supply unit for the chassis, light emitting diodes (LEDs) on a front panel of the chassis, and a temperature sensor for the chassis.

Assignees

• Cisco Tech Inc

Inventors

• Rajagopalan Harikrishnan
• Kakkar Kanika

Classifications

• G06F11/3041

  where the computing system component is an input/output interface (interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units G06F13/00) · CPC title

• G06F15/161

  Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning (casings, cabinets, racks or drawers for data centers H05K5/00) · CPC title

• G06F11/3055

  Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available (error or fault processing without redundancy G06F11/0703; error detection or correction by redundancy in data representation G06F11/08; error detection or correction of the data by redundancy in operations G06F11/14; error detection or correction by redundancy in hardware G06F11/16) · CPC title

• H04L67/1051 Primary

  Group master selection mechanisms · CPC title

• H04L49/30

  Peripheral units, e.g. input or output ports · CPC title