End-to end lossless Ethernet in Ethernet fabric
One embodiment of the present invention provides a computing system. The computing system includes a packet processor, a buffer management module, a data monitoring module, and a flow control module. The packet processor identifies a class of service indicating priority-based flow control associated with a remote computing system from a notification message. The buffer management module creates a buffer dedicated for frames belonging to the class of service from the remote computing system in response to identifying the class of service. The data monitoring module detects a potential overflow of the buffer. The flow control module operates in conjunction with the packet processor to generate a pause frame in response to detecting a potential overflow.
1. A switch, comprising:
one or more ports;
a memory;
packet processing circuitry configured to identify a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates a class of service associated with priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first switch identifier identifying the switch and a second switch identifier identifying a second switch in a routed network; and
flow control circuitry configured to, in response to detecting a potential buffer overflow for the class of service, generate a pause frame comprising a second inner layer-2 header for the class of service associated with the priority-based flow control, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising the second switch identifier as a destination identifier, and wherein the first and second outer encapsulation headers are based on a same encapsulation protocol.
2. The switch of claim 1 , wherein the potential buffer overflow is for a buffer configured to store the packet in response to the packet processor identifying the priority value indicating the class of service in the first inner layer-2 header of the packet.
3. The switch of claim 1 , wherein the pause frame includes the priority value indicating the class of service.
4. The switch of claim 1 , wherein the first inner layer-2 header is an Ethernet header and the first outer encapsulation header is forwardable in the routed network.
5. The switch of claim 1 , wherein the first switch identifier is a virtual switch identifier associated with a virtual switch.
6. The switch of claim 1 , wherein the switch is in a plurality of switches participating in a link aggregation, wherein the link aggregation includes a plurality of physical links operating as a single aggregated link, and wherein the plurality of switches are associated with a same media access control (MAC) address.
7. A switch, comprising:
identification circuitry configured to identify a class of service associated with priority-based flow control configured for the switch;
packet processing circuitry configured to identify a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates the class of service associated with the priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first switch identifier identifying the switch in a routed network; and
notification circuitry configured to generate a notification message comprising a second inner layer-2 header in response to identifying the class of service, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising a second switch identifier identifying a second switch in the routed network, and wherein the notification message specifies the class of service associated with the priority-based flow control configured for the switch.
8. The switch of claim 7 , wherein the first inner layer-2 header is an Ethernet header and the first outer encapsulation header is forwardable in the routed network.
9. The switch of claim 7 , wherein the switch is in a plurality of switches participating in a link aggregation, wherein the link aggregation includes a plurality of physical links operating as a single aggregated link, and wherein the plurality of switches are associated with a same media access control (MAC) address.
10. A method, comprising:
identifying, by a switch, a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates a class of service associated with priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first switch identifier identifying the switch and a second switch identifier identifying a second switch in a routed network; and
in response to detecting a potential buffer overflow for the class of service, generating a pause frame comprising a second inner layer-2 header for the class of service associated with the priority-based flow control, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising the second switch identifier as a destination identifier, and wherein the first and second outer encapsulation headers are based on a same encapsulation protocol.
11. The method of claim 10 , wherein the potential buffer overflow is for a buffer configured to store the packet in response to identifying the priority value indicating the class of service in the first inner layer-2 header of the packet.
12. The method of claim 10 , wherein the pause frame includes the priority value indicating the class of service.
13. The method of claim 10 , wherein the first inner layer-2 header is an Ethernet header and the first outer encapsulation header is forwardable in the routed network.
14. The method of claim 10 , wherein the first switch identifier is a virtual switch identifier associated with a virtual switch.
15. The method of claim 10 , wherein the switch is in a plurality of switches participating in a link aggregation, wherein the link aggregation includes a plurality of physical links operating as a single aggregated link, and wherein the plurality of switches are associated with a same media access control (MAC) address.
16. A method, comprising:
identifying, by a switch, a class of service associated with priority-based flow control configured for the switch;
identifying a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates the class of service associated with the priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first switch identifier identifying the switch in a routed network; and
generating a notification message comprising a second inner layer-2 header in response to identifying the class of service, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising a second switch identifier identifying a second switch in the routed network, and wherein the notification message specifies the class of service associated with the priority-based flow control configured for the switch;
wherein the switch and the remote switch are member switches of the network of interconnected switches.
17. The method of claim 16 , wherein the first inner layer-2 header is an Ethernet header and the first outer encapsulation header is forwardable in the routed network.
18. The method of claim 16 , wherein the switch is in a plurality of switches participating in a link aggregation, wherein the link aggregation includes a plurality of physical links operating as a single aggregated link, and wherein the plurality of switches are associated with a same media access control (MAC) address.
19. A computer system, comprising:
processing circuitry; and
a non-transitory computer-readable storage medium storing instructions which when executed by the processing circuitry cause the processing circuitry to perform a method, the method comprising:
identifying a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates a class of service associated with priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first identifier identifying the computer system and a second identifier identifying a second computer system in a routed network; and
in response to detecting a potential buffer overflow for the class of service, generating a pause frame comprising a second inner layer-2 header for the class of service associated with the priority-based flow control, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising the second identifier as a destination identifier, and wherein the first and second outer encapsulation headers are based on a same encapsulation protocol.
20. A computer system, comprising:
processing circuitry; and
a non-transitory computer-readable storage medium storing instructions which when executed by the processing circuitry cause the processing circuitry to perform a method, the method comprising:
identifying a class of service associated with priority-based flow control configured for the computer system;
identifying a priority value in a first inner layer-2 header of a packet encapsulated with a first outer encapsulation header, wherein the priority value indicates the class of service associated with the priority-based flow control for the packet, and wherein the first outer encapsulation header comprises a first identifier identifying the computer system in a routed network; and
generating a notification message comprising a second inner layer-2 header in response to identifying the class of service, wherein the second inner layer-2 header is encapsulated with a second outer encapsulation header comprising a second identifier identifying a second computer system in the routed network, and wherein the notification message specifies the class of service associated with the priority-based flow control configured for the computer system.