System and method for supporting subnet number aliasing in a high performance computing environment

1. A method for supporting subnet number aliasing in a high performance computing environment, comprising:

providing, at one or more computers, including one or more microprocessors

a network fabric, the network fabric comprising

a first subnet, the first subnet comprising a first set of network switches;

a global fabric manager, the global fabric manager having administrative control within the first subnet and second subnet;

assigning, by the global fabric manager, a first fabric local subnet number (FLSN) to the first subnet;

reconfiguring the network fabric, wherein reconfiguring the network fabric comprises splitting the first subnet into the first subnet and a second subnet, wherein a second FLSN is assigned by the global fabric manager to the second subnet, wherein the first FLSN and the second FLSN have different values; and

upon reconfiguring the network fabric, assigning at least one alias FLSN to the second subnet for a period of time.

2. The method of claim 1 ,

wherein the at least one alias FLSN has a same value as the first FLSN.

3. The method of claim 1 ,

wherein the period of time is set by the global fabric manager.

4. The method of claim 3 ,

wherein the period of time is determined by the global fabric manager, said determination being based upon a route recalculation time of the network fabric based upon the splitting of the first subnet into the first subnet and the second subnet.

5. The method of claim 4 ,

wherein said route recalculation time is determined by the global fabric manager upon receiving a confirmation message from a node.

6. The method of claim 3 ,

wherein upon the period of time expiring, the global fabric manager removes the at least one alias FLSN from the second subnet.

7. The method of claim 3 ,

wherein the period of time is preconfigured.

8. A system for supporting subnet number aliasing in a high performance computing environment, the system comprising:

one or more computers, including one or more microprocessors;

a network fabric, the network fabric comprising:

a first subnet, the first subnet comprising a first set of network switches;

a global fabric manager, the global fabric manager having administrative control within the first subnet and second subnet;

wherein the global fabric manager assigns a first fabric local subnet number (FLSN) to the first subnet;

wherein the network fabric is reconfigured, wherein reconfiguring the network fabric comprises splitting the first subnet into the first subnet and a second subnet, wherein a second FLSN is assigned by the global fabric manager to the second subnet, wherein the first FLSN and the second FLSN have different values; and

wherein upon reconfiguring the network fabric, at least one alias FLSN is assigned to the second subnet for a period of time.

9. The system of claim 8 ,

wherein the at least one alias FLSN has a same value as the first FLSN.

10. The system of claim 8 ,

wherein the period of time is set by the global fabric manager.

11. The system of claim 10 ,

wherein the period of time is determined by the global fabric manager, said determination being based upon a route recalculation time of the network fabric based upon the splitting of the first subnet into the first subnet and the second subnet.

12. The system of claim 11 ,

wherein said route recalculation time is determined by the global fabric manager upon receiving a confirmation message from a node.

13. The system of claim 10 ,

wherein upon the period of time expiring, the global fabric manager removes the at least one alias FLSN from the second subnet.

14. The system of claim 10 ,

wherein the period of time is preconfigured.

15. A non-transitory machine readable storage medium, including instructions stored thereon for supporting subnet number aliasing in a high performance computing environment, which when read and executed by one or more computers caused the one or more computers to perform steps comprising:

providing, at one or more computers, including one or more microprocessors

a network fabric, the network fabric comprising

a first subnet, the first subnet comprising a first set of network switches;

a global fabric manager, the global fabric manager having administrative control within the first subnet and second subnet;

assigning, by the global fabric manager, a first fabric local subnet number (FLSN) to the first subnet;

reconfiguring the network fabric, wherein reconfiguring the network fabric comprises splitting the first subnet into the first subnet and a second subnet, wherein a second FLSN is assigned by the global fabric manager to the second subnet, wherein the first FLSN and the second FLSN have different values; and

upon reconfiguring the network fabric, assigning at least one alias FLSN to the second subnet for a period of time.

16. The non-transitory machine readable storage medium of claim 15 ,

wherein the at least one alias FLSN has a same value as the first FLSN.

17. The non-transitory machine readable storage medium of claim 15 ,

wherein the period of time is set by the global fabric manager.

18. The non-transitory machine readable storage medium of claim 17 ,

wherein the period of time is determined by the global fabric manager, said determination being based upon a route recalculation time of the network fabric based upon the splitting of the first subnet into the first subnet and the second subnet.

19. The non-transitory machine readable storage medium of claim 18 ,

wherein said route recalculation time is determined by the global fabric manager upon receiving a confirmation message from a node.

20. The non-transitory machine readable storage medium of claim 17 ,

wherein upon the period of time expiring, the global fabric manager removes the at least one alias FLSN from the second subnet.