Method and apparatus for monitoring the availability of nodes in a communications network

• US 6,735,200 B1
• Filed: 03/21/2000
• Issued: 05/11/2004
• Est. Priority Date: 03/21/2000
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Novaes, Marcos N.
• Primary Examiner(s): Jung, Min
• Assistant Examiner(s): LEE, CHI HO A
• Application Number:
  US09/532,834
• Time in Patent Office: 1,512 Days
• Field of Search: 370/255, 370/252, 370/256, 370/254, 370/432, 370/400, 370/408, 370/351, 370/390, 370/389, 370/392
• US Class Current: 370/390
• CPC Class Codes: H04L 12/1854 with non-centralised forwarding system, e.g. chaincast
• CPC Class Codes: H04L 12/1868 Measures taken after transmission, e.g. acknowledgments
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/16 Multipoint routing
• CPC Class Codes: H04L 45/26 Route discovery packet
• CPC Class Codes: H04L 45/46 Cluster building

Abstract

A method and apparatus for managing communications in a distributed computing system wherein a plurality of computers are interconnected with a communications network. At least a portion of the network is established as a subnetwork with at least one node attached to the subnetwork. The node in the subnetwork multicast a verification message over the subnetwork in which it is attached. A subnetwork leader for each subnetwork is identified and gathers the verification message sent from each node in the subnetwork. The subnetwork leader assembles each verification received into a subnetwork list. The subnetwork list is sent a node identified as the network leader. The network leader assembles each subnetwork list received into a master list and sends this master list out to the subnetwork leaders. In turn, the subnetwork leaders for each subnetwork multicast the master list out to each node.

In one embodiment, the communications between each subnetwork leader and the network leader is over multicast.

In another embodiment, a system and computer readable medium is disclosed to carry out the above method.

Claims

1. A method for determining the availability of at least one node in a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader, and the communications network comprises one node identified as a network leader, the method comprising:

periodically multicasting on a subnetwork, a verification message from at least one node coupled on the subnetwork;

building on the subnetwork leader for a group of one or more subnetworks, a subnetwork list of nodes that have sent the verification message;

transferring the subnetwork list from the subnetwork leader for the group of one or more subnetworks to the network leader node;

assembling on the network leader, a master list comprising at least one subnetwork list of nodes that have sent the verification message; and

transferring the master list from the network leader to the subnetwork leader for the group of one or more subnetworks.

2. The method according to claim 1, further comprising the step of:

multicasting from the subnetwork leader for the group of one or more subnetworks from the master list.

3. The method according to claim 1, further comprising the step of:

selecting a subnetwork leader on at least one subnetwork from the at least one node coupled thereto.

4. The method according to claim 3, wherein each node is given an address and the step of selecting a subnetwork leader includes dynamically selecting a subnetwork leader by choosing a node in the group of one or more subnetworks that is capable of sending verification messages that has the highest network address.

5. The method according to claim 1, further comprising the step of:

selecting a network leader on the communications network.

6. The method according to claim 5, wherein each node is given an address and the step of selecting a network leader includes selecting a network leader with the highest network address.

7. The method according to claim 5, further comprising the step of waiting a predetermined period of time for network leader to send the master list, and if the network leader fails to send the master list, selecting a new network leader on the communications network.

8. The method according to claim 3, further comprising the step of waiting a predetermined period of time for the subnetwork leader to forward the master lists received from the subnetwork leader and if the subnetwork leader fails to respond, selecting a new subnetwork leader on the communication network.

9. The method according to claim 1, wherein the periodically multicasting includes multicasting using IP multicast on a first channel and wherein transferring the subnetwork list includes transferring the subnetwork list on a second multicast channel and wherein transferring the master list includes transferring the master list on the second multicast channel.

10. A method on a first node for determining the availability of at least one node in a communications network with one or more subnetworks, the method comprising the steps of:

coupling the first node to a subnetwork in the communications network containing at least one subnetwork with one or more nodes coupled thereto;

determining if any subnetwork leader node is identified in the subnetwork, and if there is no subnetwork leader node identified, then identifying the first node as a subnetwork leader node; and

periodically multicasting on the subnetwork, a verification message for reception by the subnetwork leader; and

receiving a master list from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from a group of one or more subnetworks, each subnetwork list containing a list of the verification message received by a subnetwork leader of each node coupled to the subnetwork, the master list assembled by a network leader from the group of one or more subnetworks that have sent the subnetwork list to the network leader node, and the master list sent from the network leader to subnetwork leader for the group of one or more subnetworks.

11. The method at a first node according to claim 10, further comprising the step of:

determining if any network leader node is identified in the communications network, and if there is no network leader node identified, then identifying the first node as a network leader node.

12. The method at a first node according to claim 10, wherein the step of receiving a master list from the subnetwork leader includes receiving a master list via multicast from the subnetwork leader.

13. The method at a first node according to claim 10, wherein the step of receiving a master from the subnetwork leader includes receiving a master list from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from the group of one or more subnetworks, each subnetwork list containing a list of the verification message received by a subnetwork leader from each node coupled to the subnetwork, the master list assembled by a network leader of the group of one or more subnetworks that have sent the subnetwork list to the network leader node, and the master list sent from the network leader via multicast protocol to the subnetwork leader for the group of one or more subnetworks.

14. The method at a first node according to claim 10, wherein the step of receiving a master from the subnetwork leader includes receiving a master list from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from the group of one or more subnetworks, each subnetwork list containing a list of the verification message received by the subnetwork leader from each node coupled to the subnetwork, the master list assembled by a network leader of the group of one or more subnetworks that have sent via multicast protocol the subnetwork list to the network leader node, and the master list sent from the network leader to the subnetwork leader for the group of one or more subnetworks.

15. The method at a first node according to claim 10, wherein the step of periodically mutlicasting includes multicasting using IP multicast on a first channel and wherein the step of receiving a master list from the subnetwork leader includes receiving a master list on a second multicast channel.

16. A method at a subnetwork leader on a subnetwork for determining the availability of at least one node in a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader, and the communications network comprises one node identified as a network leader, the method comprising the steps of:

receiving a multicast verification message on the subnetwork from at least one node coupled on the subnetwork;

building a subnetwork list of nodes that have sent the verification message;

transferring the subnetwork list from the subnetwork leader to the network leader node; and

receiving from the network leader a master list assembled comprising at least one subnetwork list of nodes that have sent the verification message.

17. The method at a subnetwork leader according to claim 16, further comprising the step of:

multicasting the master list on the subnetwork.

18. The method at a subnetwork leader according to claim 16, wherein the step of receiving multicast verification message includes receiving a multicast verification message on the subnetwork that contains a status from at least one node coupled on the subnetwork.

19. The method at a first node according to claim 16, wherein the step of receiving a multicast verification message includes receiving a multicast verification message on a first multicast channel and wherein the step of receiving a master list from the subnetwork leader includes receiving the master list on a second multicast channel.

20. A system for determining the availability of at least one node in a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader, and the communications network comprises one node identified as a network leader, the system comprising:

a multicast transmitter on at least one node in the one or more subnetworks for periodically multicasting on a subnetwork, a verification message from at least one node coupled on the subnetwork;

a subnetwork list of nodes that have sent the verification message assembled by on the subnetwork leader for a group of one or more subnetworks,

an Internet protocol multicast transceiver on at least one subnetwork leader for transferring the subnetwork list from the subnetwork leader for the group of one or more subnetworks to the network leader node;

a master list comprising at least one subnetwork list of nodes that have sent the verification message assembled by the network leader; and

an Internet protocol transceiver on the network leader for transferring the master list from the network leader to the subnetwork leader for the group of one or more subnetworks.

21. The system according to claim 20, further comprising:

a multicast transceiver for multicasting from the subnetwork leader for the group of one or more subnetworks the master list.

22. The system according to claim 20, further comprising:

means for selecting a subnetwork leader on at least one subnetwork from the at least one node coupled thereto.

23. The system according to claim 20, wherein the multicast transmitter transmits on a first multicast channel and the Internet protocol transceiver transmits on a second multicast channel.

24. A first node for determining the availability of at least one node in a communications network with one or more subnetworks comprising:

a first node coupled to a subnetwork in a communications network containing at least one subnetwork with one or more nodes coupled thereto;

means for determining if any subnetwork leader node is identified in the subnetwork, and if there is no subnetwork leader node identified, then identifying the first node as a subnetwork leader node; and

a multicast transceiver for periodically multicasting on the subnetwork, a verification message for reception by the subnetwork leader; and

a master list sent from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from the group of one or more subnetworks, each subnetwork list containing a list of the verification message received by a subnetwork leader from each node coupled to the subnetwork, the master list assembled by a network leader of the group of one or more subnetworks that have sent the subnetwork list to the network leader node, and the master list sent from the network leader to subnetwork leader for the group of one or more subnetworks.

25. The first node according to claim 24, further comprising the step of:

means for determining if any network leader node is identified in the communications network, and if there is no network leader node identified, then identifying the first node as a network leader node.

26. The first node according to claim 24, wherein the master list received from the subnetwork leader is received via multicast.

27. The first node according to claim 24, wherein the master list received from the subnetwork leader includes receiving a master list from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from the group of one or more subnetworks, each subnetwork list containing a list of the verification message received by a subnetwork leader from each node coupled to the subnetwork, the master list assembled by a network leader of the group of one or more subnetworks that have sent the subnetwork list to the network leader node, and the master list sent from the network leader via multicast protocol to the subnetwork leader for the group of one or more subnetworks.

28. The first node according to claim 24, wherein the master list received from the subnetwork leader includes receiving a master list from the subnetwork leader in the subnetwork of the communications network, the master list contains an assembly of a subnetwork list from the group of one or more subnetworks, each subnetwork list containing a list of the verification message received by the subnetwork leader from each node coupled to the subnetwork, the master list assembled by a network leader of the group of one or more subnetworks that have sent via multicast protocol the subnetwork list to the network leader node, and the master list sent from the network leader to the subnetwork leader for the group of one or more subnetworks.

29. The node according to claim 24, wherein the multicast transmitter periodically multicast a verification message on a first multicast channel and wherein the master list sent from the subnetwork leader is sent on a second multicast channel.

30. A subnetwork leader on a subnetwork for determining the availability of at least one node in a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader, and the communications network comprises one node identified as a network leader, comprising:

multicast transceiver for receiving a multicast verification message on the subnetwork from at least one node coupled on the subnetwork;

a subnetwork list of nodes that have sent the verification message;

a transceiver for transferring the subnetwork list from the subnetwork leader to the network leader node and for receiving from the network leader a master list assembled comprising at least one subnetwork list of nodes that have sent the verification message.

31. The subnetwork leader according to claim 30, further comprising:

a multicasting transceiver for multicasting the master list on the subnetwork.

32. The subnetwork leader according to claim 30, wherein verification message contains the status from least one node coupled on the subnetwork.

33. The subnetwork leader according to claim 30, wherein the multicast transmitter receives a multicast message on a first multicast channel and wherein the transceiver for transferring the subnetwork list includes transferring the subnetwork list on a second multicast channel.

34. A computer program product comprising a computer readable medium having computer readable program code therein for determining the availability of at least one node in a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader, and the communications network comprises one node identified as a network leader, said computer readable program code in said computer program product comprising:

computer readable program code for periodically multicasting on a subnetwork, a verification message from at least one node coupled on the subnetwork;

computer readable program code for building on the subnetwork leader for a group of one or more subnetworks, a subnetwork list of nodes that have sent a verification message;

computer readable program code for transferring the subnetwork list from the subnetwork leader for the group of one or more subnetworks to the network leader node;

computer readable program code for assembling on the network leader, a master list comprising at least one subnetwork list of nodes that have sent a verification message; and

computer readable program code for transferring the master list from the network leader to the subnetwork leader for the group of one or more subnetworks.