Method and apparatus for distributed data network traffic optimization
Embodiments disclosed include a method and apparatus for global traffic control and optimization for software-defined networks. In an embodiment, data traffic is optimized by distributing predefined metrics (data traffic information) to all controllers in the network. The predefined metrics are specific to local network switches and controllers, but are distributed to all peers at configurable intervals. “Local” as used herein implies one POP and its associated switch and controller. The method of distribution of local POP metrics is strictly in band using a packet as defined by the protocol used by the data network.
1. A method for data network traffic optimization, the method comprising:
a first network controller interpreting local data traffic information, wherein local data traffic information comprises at least latency, packet loss, and link utilization associated with a network switch local to the first network controller, wherein the first network controller comprises a processor;
the first network controller creating an information packet;
the first network controller directing its associated network switch to send the information packet to all network links connected to other switches in the same network;
a second network controller in the same network receiving the information packet; and
the second network controller forming on-the-fly data routing decisions based on the information packet.
2. The method of claim 1 , wherein data in the information packet comprises:
a device ID for the network switch;
link utilization data related to the device;
latency experienced by the device; and
packet loss experienced by the device.
3. The method of claim 1 , wherein the first network controller and the network switch belong to a first point of presence (POP) at a first geographic location.
4. The method of claim 3 , wherein the second network controller belongs to a second POP at a second geographic location.
5. The method of claim 1 , wherein a plurality of additional network controllers in the same network receive the information packet.
6. The method of claim 5 , wherein the plurality of additional network controllers also form on-the-fly routing decisions based on the information packet.
7. The method of claim 5 , wherein the first network controller is connected to the second network controller and to each of the additional network controllers via different network links.
8. The method of claim 1 , wherein the first network controller receives the local data traffic information from the network switch.
9. The method of claim 1 , wherein the first network controller is associated with a first distributed feedback database that is updated with the local data traffic information.
10. The method of claim 2 , wherein the second network controller is associated with a second distributed feedback database that is updated based on the received information packet.
11. A non-transitory machine readable medium storing a first network controller program which when executed by a processor performs data network traffic optimization, the first network controller program comprising sets of instructions for:
interpreting local data traffic information, wherein local data traffic information comprises at least latency, packet loss, and link utilization associated with a network switch local to the first network controller;
creating an information packet; and
directing the associated network switch to send the information packet to all network links connected to other switches in the same network,
wherein a second network controller in the same network receives the information packet and forms on-the-fly data routing decisions based on the information packet.
12. The non-transitory machine readable medium of claim 11 , wherein data in the information packet comprises:
a device ID for the network switch;
link utilization data related to the device;
latency experienced by the device; and
packet loss experienced by the device.
13. The non-transitory machine readable medium of claim 11 , wherein the first network controller and the network switch belong to a first point of presence (POP) at a first geographic location.
14. The non-transitory machine readable medium of claim 13 , wherein the second network controller belongs to a second POP at a second geographic location.
15. The non-transitory machine readable medium of claim 11 , wherein a plurality of additional network controllers in the same network receive the information packet.
16. The non-transitory machine readable medium of claim 15 , wherein the plurality of additional network controllers also form on-the-fly routing decisions based on the information packet.
17. The non-transitory machine readable medium of claim 15 , wherein the first network controller is connected to the second network controller and to each of the additional network controllers via different network links.
18. The non-transitory machine readable medium of claim 11 , wherein the first network controller receives the local data traffic information from the network switch.
19. The non-transitory machine readable medium of claim 11 , wherein the first network controller is associated with a first distributed feedback database that is updated with the local data traffic information.
20. The non-transitory machine readable medium of claim 12 , wherein the second network controller is associated with a second distributed feedback database that is updated based on the received information packet.