Method and apparatus for selecting nodes in configuring massively parallel systems

• US 6,412,002 B1
• Filed: 11/15/1999
• Issued: 06/25/2002
• Est. Priority Date: 11/15/1999
• Status: Expired due to Term

• Current Assignee: Teradata US, Inc. (Teradata Corporation)
• Original Assignee: NCR Corporation (NCR Voyix Corporation)
• Inventors: Merritt, John E., Denman, Robert W.
• Primary Examiner(s): Coleman, Eric
• Application Number:
  US09/440,807
• Time in Patent Office: 953 Days
• Field of Search: 712/28, 709/224, 709/244, 709/242, 340/506
• US Class Current: 709/224
• CPC Class Codes: G06F 15/177 Initialisation or configuration control processor initialisation G06F9/4405

Abstract

A method, apparatus, article of manufacture, and a memory structure for selecting nodes while configuring a parallel processing system is disclosed. The method comprises the steps of multicasting a request from a coordinator node to the non-coordinator node to transmit a list of nodes reachable by the non-coordinator node; receiving the list of nodes reachable by the non-coordinator node in the coordinator node; generating a global view of the nodes reachable by the non-coordinator node; generating a node list having member nodes belonging to the configured parallel processing system according to a first criteria; and transmitting the parallel processing node list to the member nodes. The apparatus comprises a means for performing the steps described above, and the article of manufacture comprises a program storage device tangibly embodying computer instructions for performing the above method steps.

Claims

1. A method of configuring a parallel processing system having a plurality of interconnected nodes including a coordinator node a non-coordinator node, comprising the steps of:

multicasting a request from a coordinator node to the non-coordinator node to transmit a list of nodes reachable by the non-coordinator node;

receiving the list of nodes reachable by the non-coordinator node in the coordinator node;

generating a global view of the nodes reachable by the non-coordinator node and the coordinator node;

generating a node list having member nodes belonging to the configured parallel processing system according to a first criteria; and

transmitting the node list to the member nodes.

2. The method of claim 1, wherein the parallel processing system comprises a plurality of non-coordinator nodes, and the step of receiving the list of nodes reachable by the non-coordinator node in the coordinator node is repeated for each non-coordinator node in the parallel processing system.

3. The method of claim 1, wherein non-member nodes are nodes which are not member nodes and the method further comprises the step of transmitting a message to the non-member nodes indicating that the non-member nodes are excluded from the configured parallel processing system.

4. The method of claim 1, wherein the step of generating a node list having member nodes belonging to the configured parallel processing system according to the first criteria comprises the step of:

selecting the configured parallel processing system as the parallel processing system with a maximum number of reachable nodes.

5. The method of claim 4, wherein the interconnected nodes define a plurality of networks, and the method further comprises the step of:

selecting the configured parallel processing system as the parallel processing system with access to the greatest number of networks if there are more than one parallel processing system configurations with the maximum number of reachable nodes.

6. An apparatus for configuring a parallel processing system having a plurality of interconnected nodes including a coordinator node a non-coordinator node, the apparatus comprising:

means for multicasting a request from a coordinator node to the non-coordinator node to transmit a list of nodes reachable by the non-coordinator node;

means for receiving the list of nodes reachable by the non-coordinator node in the coordinator node;

means for generating a global view of the nodes reachable by the non-coordinator node and the coordinator node;

means for generating a node list having member nodes belonging to the configured parallel processing system according to a first criteria; and

means for transmitting the node list to the member nodes.

7. The apparatus of claim 6, wherein the parallel processing system comprises a plurality of non-coordinator nodes, and the means for receiving the list of nodes reachable by the non-coordinator node in the coordinator node further comprises means for receiving the list of nodes from each non-coordinator node in the parallel processing system.

8. The apparatus of claim 6, wherein non-member nodes are nodes which are not member nodes and the apparatus further comprises means for transmitting a message to the non-member nodes indicating that the non-member nodes are excluded from the configured parallel processing system.

9. The apparatus of claim 6, wherein the means for generating a node list having member nodes belonging to the configured parallel processing system according to the first criteria comprises:

means for selecting the configured parallel processing system as the parallel processing system with a maximum number of reachable nodes.

10. The apparatus of claim 9, wherein the interconnected nodes define a plurality of networks, and the apparatus further comprises:

means for selecting the configured parallel processing system as the parallel processing system with access to the greatest number of networks if there are more than one parallel processing system configurations with the maximum number of reachable nodes.

11. A program storage device, readable by a computer, tangibly embodying at least one program of instructions executable by the computer to perform method steps of configuring a parallel processing system having a plurality of interconnected nodes including a coordinator node a non-coordinator node, the method steps comprising the steps of:

multicasting a request from a coordinator node to the non-coordinator node to transmit a list of nodes reachable by the non-coordinator node;

receiving the list of nodes reachable by the non-coordinator node in the coordinator node;

generating a global view of the nodes reachable by the non-coordinator node and the coordinator node;

generating a node list having member nodes belonging to the configured parallel processing system according to a first criteria; and

transmitting the node list to the member nodes.

12. The program storage device of claim 11, wherein the parallel processing system comprises a plurality of non-coordinator nodes, and the method step of receiving the list of nodes reachable by the non-coordinator node in the coordinator node is repeated for each non-coordinator node in the parallel processing system.

13. The program storage device of claim 11, wherein non-member nodes are nodes which are not member nodes and the method steps further comprises the method step of transmitting a message to the non-member nodes indicating that the non-member nodes are excluded from the configured parallel processing system.

14. The program storage device of claim 11, wherein the method step of generating a node list having member nodes belonging to the configured parallel processing system according to the first criteria comprises the method step of:

selecting the configured parallel processing system as the parallel processing system with a maximum number of reachable nodes.

15. The program storage device of claim 14, wherein the interconnected nodes define a plurality of networks, and the method steps further comprise the method step of:

selecting the configured parallel processing system as the parallel processing system with access to the greatest number of networks if there are more than one parallel processing system configurations with the maximum number of reachable nodes.