Fault tolerant symmetric multi-computing system

• US 7,525,902 B2
• Filed: 09/15/2004
• Issued: 04/28/2009
• Est. Priority Date: 09/22/2003
• Status: Active Grant

• Current Assignee: Anilkumar Dominic
• Original Assignee: Anilkumar Dominic
• Inventors: Dominic, Anilkumar
• Primary Examiner(s): Patel; Ajit
• Application Number:
  US10/942,260
• Publication Number:
  US 20050063300A1
• Time in Patent Office: 1,686 Days
• Field of Search: None
• US Class Current: 370/216
• CPC Class Codes: H04L 2101/663 Transport layer addresses, e.g. aspects of transmission control protocol [TCP] or user datagram protocol [UDP] ports
• CPC Class Codes: H04L 61/5069 for group communication, multicast communication or broadcast communication
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism

Abstract

A system enabled for fault-tolerant symmetric multi-computing using a group of nodes is described hereon. A symmetrical group of nodes networked using a reliable, ordered, and atomic group-to-group TCP communication system is used in providing fault-tolerance and single system image to client applications. The communication between the client and the group is standards based. The processing load is shared among a group of nodes with transparent distribution of tasks to application segments. The system is fault-tolerant in that if a node fails remaining replicas if any continue service without disruption of service or connection. Nodes may be added to or retired from the group in a manner transparent to the client as well as server applications.

Claims

1. A fault-tolerant multi-computing system, the system comprising:

a first application at a first group comprised of one or more first application segments, each first application segment having a plurality of first replicas, and each first replica residing in a node in the first group;

a second application at a second group comprised of one or more second application segments, each second application segment having a plurality of second replicas, and each second replica residing in a node in the second group;

a logical connection interconnecting the first group and the second group, the logical connection comprised of a plurality of endpoints, each endpoint coupled to a node; and

each of the plurality of first replicas of a first application segment configured to process a request received from the second group, the request intended for the first application segment.

2. The system of claim 1, wherein each of the plurality of endpoints is configured to allow the exchange of data between the first group and the second group.

3. The system of claim 1, wherein each endpoint coupled to a node in the first group is configured to:

compare a first response by a first replica of a first application segment to a second response by at least one other first replica of the first application segment; and

determine the appropriate response to transmit to the second group based on the comparison.

4. The system of claim 3, wherein the first replica resides in a node coupled to the endpoint and the other first replica resides in a distinct node.

5. The system of claim 3, wherein the appropriate response to transmit to the second group is determined by applying at least one of the following policies during the comparison:

equal output, majority agreement, correct result, and successful operation output.

6. The system of claim 1, wherein the request received by each of the plurality of first replicas of the first application segment is received directly from the second group.

7. The system of claim 1, wherein each of the plurality of endpoints comprises a protocol stack.

8. The system of claim 1, wherein each of the plurality of endpoints is configured to deliver requests received to application segments coupled to the endpoint in a specific order.

9. The system of claim 1, wherein each of the plurality of endpoints is configured to atomically deliver requests received to a node coupled to the endpoint.

10. The system of claim 1, wherein the logical connection comprises Transmission Control Protocol (TCP) and corresponding interfaces.

11. A method for processing requests with fault-tolerance by one or more nodes within a computing system, the method comprising:

dividing a first application at a first group into one or more first application segments, each first application segment having a plurality of first replicas, and each first replica residing in a node in the first group;

dividing a second application at a second group into one or more second application segments, each second application segment having a plurality of second replicas, and each second replica residing in a node in the second group;

establishing a logical connection interconnecting the first group and the second group, the logical connection comprised of a plurality of endpoints, each endpoint coupled to a node; and

processing a request received from the second group by each of the plurality of replicas of a first application segment, the request intended for the application segment.

12. The method of claim 11, wherein each of the plurality of endpoints allows the exchange of data through the logical connection between the first group and the second group.

13. The method of claim 11, further comprising:

comparing a first response by a first replica of a first application segment to a second response by at least one other first replica of the first application segment; and

determining the appropriate response to transmit to the second group based on the comparison.

14. The method of claim 13, wherein the appropriate response to transmit to the second group is determined by applying one or more of the following policies during the comparison:

equal output, majority agreement, correct result, and successful operation output.

15. The system of claim 11, wherein the request received by each of the plurality of first replicas of the first application segment is received directly from the second group.

16. The system of claim 11, wherein each of the plurality of endpoints comprises a protocol stack.

17. The system of claim 11, wherein requests received are delivered to application segments in a specific order.

18. The system of claim 11, wherein requests received are atomically delivered to nodes.

19. The system of claim 11, wherein the logical connection comprises Transmission Control Protocol (TCP) and corresponding interfaces.