Method of detecting heartbeats and device thereof

• US 20070294600A1
• Filed: 05/08/2006
• Published: 12/20/2007
• Est. Priority Date: 05/08/2006
• Status: Abandoned Application

• Current Assignee: Inventec Corporation
• Original Assignee: Inventec Corporation
• Inventors: Chen, Tom, Liu, Win-Ham, Wang, Xing-Jia
• Application Number:
  US11/429,245
• Publication Number:
  US 20070294600A1
• Time in Patent Office: Days
• US Class Current: 714/55
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/0757 by exceeding a time limit, i.e. time-out, e.g. watchdogs

Abstract

A method of detecting heartbeats and the device thereof are applied to a cluster server. It includes a first controller, a second controller, and a detecting module. The detecting module does the counting according to a first predetermined period. If the detecting module receives a first reset signal of the first controller before the first predetermined period, it determines that the operation of the first controller is normal. If the detecting module has not receive the first reset signal of the first controller before the first predetermined period, then the operation of the first controller is determined to be abnormal. The detecting module sends out a control signal to start the second controller. The second controller communicates with the first controller to execute the corresponding failure transfer program and to interrupt the operation of the first controller.

Claims

1. A heartbeat detection method, used in a cluster server with a first controller, a second controller, and a detecting module, comprising the steps of:

providing a detecting module and setting a first predetermined period so as to enable the detecting module to count in accord with the first predetermined period;

starting the first controller and sending a first reset signal to the detecting module in accord with a second predetermined period;

wherein when the detecting module receives the first reset signal before the first predetermined period, restarting the counting of the detecting module; and

wherein when the detecting module has not received the first reset signal before the first predetermined period, sending a control signal from the detecting module to start the second controller.

2. The heartbeat detection method of claim 1, further comprising the step of:

letting the second controller communicate with the first controller after its start so as to execute a corresponding failure transfer program.

3. The heartbeat detection method of claim 1, wherein the first predetermined period is variable.

4. The heartbeat detection method of claim 1, wherein the first predetermined period is greater than the second predetermined period.

5. The heartbeat detection method of claim 1, further comprising the step of:

when the detecting module receives again the first reset signal sent from the first controller, restarting the counting of the detecting module in accord with the first predetermined period, executing a corresponding failure transfer program in order to restore the operation of the first controller, and sending a control signal to interrupt the operation of the second controller.

6. A heartbeat detection device used in a cluster server, comprising:

a first controller, which sends out a first reset signal in accord with a second predetermined period;

a second controller, which controls the operation of the cluster server; and

a detecting module, which has a counting function, counts in accord with a first predetermined period, and sends a control signal to the second controller;

wherein the detecting module resets its counting in accord with the first reset signal.

7. The heartbeat detection device of claim 6, wherein the first predetermined period is variable.

8. The heartbeat detection device of claim 6, wherein the first predetermined period is greater than the second predetermined period.

9. The heartbeat detection device of claim 6, wherein the second controller communicates with the first controller after it receives the control signal and executes a corresponding failure transfer program.