Network proxy for high-performance, low-power data center interconnect fabric

Patent metadata

Field	Value
Publication number	US-9311269-B2
Application number	US-201213692741-A
Country	US
Kind code	B2
Filing date	Dec 3, 2012
Priority date	Oct 30, 2009
Publication date	Apr 12, 2016
Grant date	Apr 12, 2016

Abstract

A system and method are provided for network proxying. The network proxying may occur in a node of a fabric or across nodes in the fabric. In the network proxying, the node has a processor with a low power mode and the system remaps, by a management processor of the node, a port identifier for a processor that is in a low power mode to the management processor. The management processor then processes a plurality of packets that contain the port identifier for the processor that is in the low power mode to maintain a network presence of the node.

First claim

The invention claimed is:

1. A node, comprising:
at least one processor associated with at least one first internal port, wherein the at least one first internal port has a first address;
a management processor associated with a second internal port, wherein the second internal port has a second address; and
a port remapping component configured to indicate that the first address is remapped to the second address, wherein the port remapping component is configured to activate a port remapping enable field, and wherein the port remapping enable field is specific to a given channel;
wherein the management processor is configured to disable a first-in first-out buffer of the at least one processor and to receive traffic destined for the at least one processor as a proxy of the at least one processor via the port remapping component and in response to the at least one processor being in a low power state.

2. The node of claim 1 , wherein the management processor is further configured to process an incoming packet that is to be remapped to the management processor.

3. The node of claim 2 , wherein the management processor is further configured to respond to the incoming packet if required for a particular protocol.

4. The node of claim 2 , wherein the management processor is further configured to ignore the incoming packet if destined for another node.

5. The node of claim 2 , wherein the management processor is further configured to wake up the at least one processor, if in the low power state, for the incoming packet that is to be processed by the at least one processor.

6. The node of claim 2 , wherein the incoming packet is a keep alive message, and wherein the management processor is further configured to respond to the keep alive message.

7. The node of claim 3 , wherein the incoming packet required for a protocol is an ARP packet, a NetBIOS datagram, or an ICMP ping.

8. The node of claim 4 , wherein the incoming packet destined for another node is a broadcast packet or a unicast packet.

9. The node of claim 5 , wherein the incoming packet that is to be processed by the at least one processor is a TCP SYN packet or a magic packet.

10. The node of claim 5 , wherein the management processor is further configured to:
reset the port remapping component to cancel the remapping; and
resend the incoming packet back to the at least one processor.

11. A method, comprising:
associating at least one processor in a node with at least one first internal port, wherein the at least one first internal port has a first address;
associating a management processor in the node with a second internal port, wherein the second port has a second address;
setting up a port remapping component which indicates that the first address is remapped to the second address, wherein the port remapping component is configured to activate a port remapping enable field, and wherein the port remapping enable field is specific to a given channel;
disabling, by the management processor, a first-in first-out buffer of the at least one processor; and
receiving, by the management processor as a proxy of the at least one processor, traffic destined for the at least one processor via the port remapping component and in response to the at least one processor being in a low power state.

12. The method of claim 11 , further comprising responding, by the management processor, to a packet remapped to the management processor if required for a particular protocol.

13. The method of claim 11 , further comprising ignoring, by the management processor, a packet remapped to the management processor if destined for another node.

14. The method of claim 11 , further comprising waking up the at least one processor, if in the low power state, for a packet that is to be processed by the at least one processor.

15. The method of claim 11 , further comprising responding, by the management processor, to a keep alive message that is remapped to the management processor.

16. The method of claim 12 , wherein the packet is an ARP packet, a NetBIOS datagram, or an ICMP ping.

17. The method of claim 13 , wherein the packet destined for another node is a broadcast packet or a unicast packet.

18. The method of claim 14 , wherein the packet that is to be processed by the at least one processor is a TCP SYN packet or a magic packet.

19. The method of claim 14 , further comprising:
resetting the port remapping component to cancel the remapping; and
resending a packet back to the at least one processor.

20. A fabric, comprising:
a plurality of nodes interconnected to each other, wherein each of the plurality of nodes includes:
at least one processor, wherein the at least one processor is associated with at least one internal port of a node in which the at least one processor is located, and wherein the at least one internal port has a first address in the fabric;
a management processor, wherein the management processor is associated with a second internal port of the node, and wherein the second internal port has a second address in the fabric; and
a port remapping component configured to indicate that the first address is remapped to the second address, wherein the port remapping component is configured to activate a port remapping enable field, and wherein the port remapping enable field is specific to a given channel;
wherein the management processor is configured to disable a first-in first-out buffer of the at least one processor and to receive traffic destined for the at least one processor as a proxy of the at least one processor via the port remapping component and in response to the at least one processor being in a low power state.

21. The fabric of claim 20 , wherein the management processor is further configured to process an incoming packet that is to be remapped to the management processor.

22. The fabric of claim 21 , wherein the management processor is further configured to respond to the incoming packet if required for a particular protocol.

23. The fabric of claim 21 , wherein the management processor is further configured to ignore the incoming packet if destined for another node.

24. The fabric of claim 21 , wherein the management processor is further configured to wake up the at least one processor, if in the low power state, for the incoming packet that is to be processed by the at least one processor.

25. The fabric of claim 21 , wherein the incoming packet is a keep alive message, and wherein the management processor is further configured to respond to the keep alive message.

26. The fabric of claim 22 , wherein the incoming packet for a protocol is an ARP packet, a NetBIOS datagram, or an ICMP ping.

27. The fabric of claim 23 , wherein the incoming packet destined for another node is a broadcast packet or a unicast packet.

28. The fabric of claim 24 , wherein the incoming packet that is to be processed by the at least one processor is a TCP SYN packet or a magic packet.

29. The fabric of claim 24 , wherein the management processor is configured to:
reset the port remapping component to cancel the remapping; and
resend the incoming packet back to the at least one processor.

30. An apparatus, comprising:
a plurality of nodes interconnected to each other to form a switching fabric, wherein each of the plurality of nodes is associated with a respe

Assignees

• Iii Holdings 2 Llc

Inventors

• Davis Mark B
• Borland David James
• Volpe Thomas A
• Goss Kenneth S

Classifications

• H04L47/10

  Flow control; Congestion control · CPC title

• H04L45/00

  Routing or path finding of packets in data switching networks (routing or path finding in wireless networks H04W40/00) · CPC title

• G06F15/177 Primary

  Initialisation or configuration control {(processor initialisation G06F9/4405)} · CPC title

• H04L49/356 Primary

  for storage area networks · CPC title

• H04L45/60

  Router architectures · CPC title