Adaptive routing using inter-switch notifications

• US 9,014,006 B2
• Filed: 01/31/2013
• Issued: 04/21/2015
• Est. Priority Date: 01/31/2013
• Status: Active Grant

• Current Assignee: Mellanox Technologies Limited (NVIDIA Corporation)
• Original Assignee: Mellanox Technologies Limited (NVIDIA Corporation)
• Inventors: Haramaty, Zachy, Zahavi, Eitan, Gabbay, Freddy, Crupnicoff, Diego, Marelli, Amiad, Bloch, Gil
• Primary Examiner(s): Shah, Chirag
• Assistant Examiner(s): PERSAUD, AMARNAUTH G
• Application Number:
  US13/754,921
• Publication Number:
  US 20140211631A1
• Time in Patent Office: 810 Days
• Field of Search: None
• US Class Current: 370/237
• CPC Class Codes: H04L 47/122 by diverting traffic away from congested entities

Abstract

A method includes receiving in a network switch of a communication network communication traffic that originates from a source node and arrives over a route through the communication network traversing one or more preceding network switches, for forwarding to a destination node. In response to detecting in the network switch a compromised ability to forward the communication traffic to the destination node, a notification is sent to the preceding network switches. The notification is to be consumed by the preceding network switches and requests the preceding network switches to modify the route so as not to traverse the network switch.

Claims

1. A method, comprising:

in a network switch of a communication network, receiving communication traffic that originates from a source node and arrives over a route through the communication network traversing one or more preceding network switches, for forwarding to a destination node;

in response to detecting in the network switch a compromised ability to forward the communication traffic to the destination node, sending to the preceding network switches a notification, which is to be consumed by the preceding network switches and requests the preceding network switches to modify the route so as not to traverse the network switch;

receiving the notification in a preceding network switch, and modifying the route between the preceding network switch and the destination node in response to the notification;

evaluating in the preceding network switch a rule, which ensures that only one of the preceding network switches modifies the route, and modifying the route only when the rule is met; and

when the rule is not met, forwarding the notification to another of the preceding switches,

wherein forwarding the notification comprises extracting an address from the notification, caching an association between the address and a port over which the notification was received, and, upon receiving a packet from the cached address over a given port, forwarding the notification over the given port.

2. The method according to claim 1, wherein detecting the compromised ability comprises detecting one of a congestion on a network link leaving the network switch en-route to the destination node, a failure in the network link, and a head-of-line time-out at an input to the network link.

3. The method according to claim 1, wherein sending the notification comprises forwarding the notification in accordance with a forwarding rule that depends on a topology of the communication network.

4. The method according to claim 1, wherein detecting the compromised ability comprises identifying the compromised ability with respect to a packet having a source address and a destination address, and wherein sending the notification comprises substituting the source address of the packet to serve as the destination address of the notification, and substituting the destination address of the packet to serve as the source address of the notification.

5. The method according to claim 1, wherein sending the notification comprises indicating a cause of the compromised ability in the notification.

6. The method according to claim 1, wherein forwarding the notification comprises sending the notification using multicast.

7. The method according to claim 1, wherein the rule depends on a topology of the communication network.

8. The method according to claim 1, wherein the communication network has a Fat-Tree (FT) topology, and wherein evaluating the rule comprises comparing a level of the preceding network switch in the FT topology to the level of the network switch that sent the notification.

9. The method according to claim 1, wherein receiving the notification comprises extracting a source address from the notification, and wherein modifying the route comprises re-routing all the packets addressed to the extracted source address regardless of whether they are configured for adaptive routing.

10. The method according to claim 1, wherein sending the notification comprises routing the notification over an alternative route that differs from the route traversed by the communication traffic that caused the notification.

11. The method according to claim 1, wherein sending the notification comprises including in the notification a signature for checking by the preceding switches.

12. The method according to claim 1, wherein sending the notification comprises preempting processing of another packet in order to give precedence to the notification.

13. The method according to claim 1, wherein receiving the communication traffic comprises receiving in the communication traffic an indication of a preceding network switch that could have modified the route, and wherein sending the notification comprises addressing the notification to the preceding network switch in accordance with the indication.

14. A network switch, comprising:

multiple ports, which are configured to communicate with a communication network; and

switching circuitry, which is configured to receive communication traffic that originates from a source node and arrives over a route through the communication network traversing one or more preceding network switches, for forwarding to a destination node, and, in response to detecting a compromised ability to forward the communication traffic to the destination node, sending to the preceding network switches a notification, which is to be consumed by the preceding network switches and requests the preceding network switches to modify the route so as not to traverse the network switch,

wherein the switching circuitry is configured to evaluate a rule, which ensures that only one of multiple preceding network switches between the source node and the downstream network switch will modify the route, and to modify the route only when the rule is met,

wherein the switching circuitry is configured to forward the notification to another of the preceding switches when the rule is not met, and

wherein the switching circuitry is configured to extract an address from the notification, to cache an association between the address and a port over which the notification was received, and, upon receiving a packet from the cached address over a given port, to forward the notification over the given port.

15. The switch according to claim 14, wherein the switching circuitry is configured to detect the compromised ability by detecting one of a congestion on a network link leaving the network switch en-route to the destination node, a failure in the network link, and a head-of-line time-out at an input to the network link.

16. The switch according to claim 14, wherein the switching circuitry is configured to detect the compromised ability with respect to a packet having a source address and a destination address, to substitute the source address of the packet to serve as the destination address of the notification, and to substitute the destination address of the packet to serve as the source address of the notification.

17. The switch according to claim 14, wherein the switching circuitry is configured to indicate a cause of the compromised ability in the notification.

18. The switch according to claim 14, wherein the switching circuitry is configured to send the notification over an alternative route that differs from the route traversed by the communication traffic that caused the notification.

19. The switch according to claim 14, wherein the switching circuitry is configured to include in the notification a signature for checking by the preceding switches.

20. The switch according to claim 14, wherein the switching circuitry is configured to preempt processing of another packet in order to give precedence to the notification.

21. The switch according to claim 14, wherein the switching circuitry is configured to receive in the communication traffic an indication of a preceding network switch that could have modified the route, and to address the notification to the preceding network switch in accordance with the indication.

22. A network switch, comprising:

multiple ports, which are configured to communicate with a communication network; and

switching circuitry, which is configured to receive communication traffic that originates from a source node and arrives over a route through the communication network, to forward the traffic to a destination node via a downstream network switch, to receive from the downstream network switch a notification that indicates a compromised ability of the downstream network switch to forward the communication traffic to the destination node, and, in response to the notification, to modify the route so as not to traverse the downstream network switch,

wherein the switching circuitry is configured to evaluate a rule, which ensures that only one of multiple preceding network switches between the source node and the downstream network switch will modify the route, and to modify the route only when the rule is met,

wherein the switching circuitry is configured to forward the notification to another of the preceding switches when the rule is not met, and

wherein the switching circuitry is configured to extract an address from the notification, to cache an association between the address and a port over which the notification was received, and, upon receiving a packet from the cached address over a given port, to forward the notification over the given port.

23. The switch according to claim 22, wherein the compromised ability is caused by one of a congestion on a network link leaving the downstream network switch en-route to the destination node, a failure in the network link, and a head-of-line time-out at an input to the network link.

24. The switch according to claim 22, wherein the switching circuitry is configured to forward the notification in accordance with a forwarding rule that depends on a topology of the communication network.

25. The switch according to claim 22, wherein the switching circuitry is configured to forward the notification using multicast.

26. The switch according to claim 22, wherein the rule depends on a topology of the communication network.

27. The switch according to claim 22, wherein the communication network has a Fat-Tree (FT) topology, and wherein the switching circuitry is configured to evaluate the rule by comparing a level of the preceding network switch in the FT topology to the level of the network switch that sent the notification.

28. The switch according to claim 22, wherein the switching circuitry is configured to extract a source address from the notification, and to re-route all the packets addressed to the extracted source address regardless of whether they are configured for adaptive routing.

29. The switch according to claim 22, wherein the switching circuitry is configured to add to the communication traffic an indication of whether the switch is capable of modifying the route.