Multi-stage switch fabric fault detection and handling

1. A method of verifying fabric connectivity with a multi-stage switch fabric having a plurality of fabric planes each having a plurality of stages to switch data units between any of a plurality of fabric endpoints, the method comprising:

receiving, by a first-stage switch of a first fabric plane of the multi-stage switch fabric, a first fault data unit that includes an indication of a connectivity fault;

after receiving the first fault data unit, by the first-stage switch, waiting a predefined time;

receiving, by the first-stage switch, a second fault data unit that includes the indication of the connectivity fault; and

sending, in response to expiry of the predefined time and after receiving the second fault data unit, by the first-stage switch to a final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a fault notification data unit that includes the indication of the connectivity fault.

2. The method of claim 1 ,

wherein receiving the first fault data unit comprises receiving, by the first-stage switch, the first fault data unit from a first fabric endpoint of the plurality of fabric endpoints, and

wherein receiving the second fault data unit comprises receiving, by the first-stage switch, the second fault data unit from a second fabric endpoint of the plurality of fabric endpoints.

3. The method of claim 1 , wherein the plurality of fabric endpoints comprises a plurality of forwarding components interconnected within a network router by the multi-stage switch fabric.

4. The method of claim 1 , wherein the plurality of fabric endpoints comprises a plurality of edge devices interconnected within a data center by the multi-stage switch fabric.

5. The method of claim 1 , wherein the predefined time is 1 millisecond.

6. The method of claim 1 , wherein the indication of the connectivity fault identifies the first fabric plane.

7. The method of claim 1 ,

wherein the final-stage switch comprises a first final-stage switch, and

wherein the fault notification data unit comprises a first fault notification data unit, the method further comprising:

sending, by the first-stage switch to a second final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a second fault notification data unit that includes the indication of the connectivity fault.

8. The method of claim 1 , further comprising:

sending, by the final-stage switch in response to receiving the fault notification data unit from the first-stage switch, respective fault notification data units to fabric endpoints of the plurality of fabric endpoints that are coupled to the final-stage switch.

9. A method of verifying fabric connectivity with a multi-stage switch fabric having a plurality of fabric planes each having a plurality of stages to switch data units between any of a plurality of fabric endpoints, the method comprising:

sending, by a first fabric endpoint of the plurality of fabric endpoints in response to the first fabric endpoint detecting a first connectivity fault for the first fabric endpoint with the switch fabric, a first fault data unit that includes an indication of the first connectivity fault to a first-stage switch of a first fabric plane of the multi-stage switch fabric;

receiving, by the first-stage switch, the first fault data unit;

sending, by a second fabric endpoint of the plurality of fabric endpoints in response to the second fabric endpoint detecting a second connectivity fault for the second fabric endpoint with the switch fabric, a second fault data unit that includes an indication of the second connectivity fault to the first-stage switch;

receiving, by the first-stage switch, the second fault data unit; and

sending, by the first-stage switch to a final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a fault notification data unit that includes an indication of the first connectivity fault and the second connectivity fault.

10. The method of claim 9 , wherein the indication of the first connectivity fault identifies the first fabric plane.

11. A switching system comprising:

a plurality of fabric endpoints;

a multi-stage switching fabric having a plurality of fabric planes each having a plurality of stages to switch data units between any of the plurality of fabric endpoints,

wherein a first-stage switch of a first fabric plane of the multi-stage switch fabric is configured to receive a first fault data unit that includes an indication of a connectivity fault,

wherein the first-stage switch is configured to, after receiving the first fault data unit, wait a pre-defined time,

wherein the first-stage switch is configured to receive a second fault data unit that includes the indication of the connectivity fault, and

wherein the first-stage switch is configured send, in response to expiry of the predefined time and after receiving the second fault data unit, to a final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a fault notification data unit that includes the indication of the connectivity fault.

12. The switching system of claim 11 ,

wherein the first-stage switch is configured to receive the first fault data unit from a first fabric endpoint of the plurality of fabric endpoints, and

wherein the first-stage switch is configured to receive the second fault data unit from a second fabric endpoint of the plurality of fabric endpoints.

13. The switching system of claim 11 , wherein the plurality of fabric endpoints comprises a plurality of forwarding components interconnected within a network router by the multi-stage switch fabric.

14. The switching system of claim 11 , wherein the plurality of fabric endpoints comprises a plurality of edge devices interconnected within a data center by the multi-stage switch fabric.

15. The switching system of claim 11 , wherein the predefined time is 1 millisecond.

16. The switching system of claim 11 , wherein the indication of the connectivity fault identifies the first fabric plane.

17. The switching system of claim 11 ,

wherein the final-stage switch comprises a first final-stage switch, and

wherein the fault notification data unit comprises a first fault notification data unit,

wherein the first-stage switch is configured to send, to a second final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a second fault notification data unit that includes the indication of the connectivity fault.

18. The switching system of claim 11 ,

wherein the final-stage switch is configured to send, in response to receiving the fault notification data unit from the first-stage switch, respective fault notification data units to fabric endpoints of the plurality of fabric endpoints that are coupled to the final-stage switch.

19. A switching system comprising:

a plurality of fabric endpoints; and

a multi-stage switching fabric having a plurality of fabric planes each having a plurality of stages to switch data units between any of the plurality of fabric endpoints,

wherein a first fabric endpoint of the plurality of fabric endpoints is configured to, in response to the first fabric endpoint detecting a first connectivity fault for the first fabric endpoint with the switch fabric, send a first fault data unit that includes an indication of the first connectivity fault to a first-stage switch of a first fabric plane of the multi-stage switch fabric,

wherein the first-stage switch is configured to receive the first fault data unit,

wherein a second fabric endpoint of the plurality of fabric endpoints is configured to, in response to the second fabric endpoint detecting a second connectivity fault for the second fabric endpoint with the switch fabric, send a second fault data unit that includes an indication of the second connectivity fault to the first-stage switch,

wherein the first-stage switch is configured to receive the second fault data unit, and

wherein the first-stage switch is configured send, to a final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a fault notification data unit that includes an indication of the first connectivity fault and the second connectivity fault.

20. The switching system of claim 19 , wherein the indication of the first connectivity fault identifies the first fabric plane.

21. A computer-readable storage medium, the computer-readable storage medium comprising instructions for causing at least one programmable processor of a multi-stage switch fabric, having a plurality of fabric planes each having a plurality of stages to switch data units between any of a plurality of fabric endpoints, to:

receive, by a first-stage switch of a first fabric plane of the multi-stage switch fabric, a first fault data unit that includes an indication of a connectivity fault;

after receiving the first fault data unit, by the first-stage switch, wait a predefined time;

receive, by the first-stage switch, a second fault data unit that includes the indication of the connectivity fault; and

send, in response to expiry of the predefined time and after receiving the second fault data unit, by the first-stage switch to a final-stage switch of the first fabric plane and after consolidating the first fault data unit and the second fault data unit, a fault notification data unit that includes the indication of the connectivity fault.