System And Method for Lock-Less Multi-Core IP Forwarding

• US 20120210018A1
• Filed: 02/11/2011
• Published: 08/16/2012
• Est. Priority Date: 02/11/2011
• Status: Abandoned Application

• Current Assignee: Wind River Systems Incorporated (Aptiv PLC)
• Original Assignee: Wind River Systems Incorporated (Aptiv PLC)
• Inventors: Carlstedt, Markus, Wiles, Roger Keith, MENDEL, Rikard
• Application Number:
  US13/025,264
• Publication Number:
  US 20120210018A1
• Time in Patent Office: Days
• US Class Current: 709/242
• CPC Class Codes: G06F 15/17312 Routing techniques specific to parallel machines, e.g. wormhole, store and forward, shortest path problem congestion routing on a LAN H04L45/00
• CPC Class Codes: H04L 45/742 Route cache; Operation thereof

Abstract

Described herein are systems and methods using lock-less multi-core IP forwarding having dedicated forwarding cores. The exemplary embodiments may offer wire-rate on multiple gigabit links while guaranteeing packet order. One embodiment relates to a system including a plurality of forwarding cores within a network, and a routing table, wherein a first forwarding core of the plurality of forwarding cores polls data received from an input interface for routing information, references the routing table based on the routing information, determines a destination for the data based on the routing table, and transmits the data to the destination at a wire-rate, the wire-rate is independent from a further wire-rate corresponding to a further forwarding core of the plurality of forwarding cores.

Claims

1. A non-transitory computer readable storage medium including a set of instructions executable by a processor, the set of instructions operable to:

poll, by a forwarding core, data received from an input interface for routing information, wherein the forwarding core is one of a plurality of forwarding cores;

reference a routing table based on the routing information;

determine a destination for the data based on the routing table; and

transmit the data to the destination at a wire-rate, wherein the wire-rate is independent from a further wire-rate corresponding to a further forwarding core of the plurality of forwarding cores.

2. The non-transitory computer readable storage medium of claim 1, wherein the set of instructions are further operable to:

update the routing table by a network core.

3. The non-transitory computer readable storage medium of claim 1, wherein the forwarding core is a dedicated gigabit link.

4. The non-transitory computer readable storage medium of claim 1, wherein the transmitting of data to the destination is a lock-less transmission using a guaranteed packet order.

5. The non-transitory computer readable storage medium of claim 1, wherein the routing table includes a route cache of network destinations for the forwarding core.

6. The non-transitory computer readable storage medium of claim 1, wherein each of the plurality of forwarding cores includes an individual per-instance transmission queue to achieve multiple wire-rate flows to a plurality of destinations.

7. The non-transitory computer readable storage medium of claim 1, wherein the plurality of forwarding cores are components within a system utilizing one of a symmetric multiprocessing “

SMP”

architecture and an asymmetric multiprocessing “

AMP”

architecture.

8. A system, comprising:

a plurality of forwarding cores within a network; and

a routing table, wherein a first forwarding core of the plurality of forwarding cores polls data received from an input interface for routing information, references the routing table based on the routing information, determines a destination for the data based on the routing table, and transmits the data to the destination at a wire-rate, the wire-rate is independent from a further wire-rate corresponding to a further forwarding core of the plurality of forwarding cores.

9. The system of claim 8, further comprising:

a networking core updating the route table.

10. The system of claim 8, wherein the forwarding core is a dedicated gigabit link.

11. The system of claim 8, wherein the transmitting of data to the destination is a lock-less transmission using a guaranteed packet order.

12. The system of claim 8, wherein the routing table includes a route cache of network destinations for the forwarding core.

13. The system of claim 8, wherein each of the plurality of forwarding cores includes an individual per-instance transmission queue to achieve multiple wire-rate flows to a plurality of destinations.

14. The system of claim 8, wherein the plurality of forwarding cores are components within a system utilizing one of a symmetric multiprocessing “

SMP”

architecture and an asymmetric multiprocessing “

AMP”

architecture.

15. A data-forwarding system, comprising:

a polling means polling data received from an input interface for routing information;

a look-up means referencing a routing table based on the routing information;

a routing means determining a destination for the data based on the routing table; and

a transmitting means transmitting the data to the destination at a wire-rate, wherein the wire-rate is independent from a further wire-rate corresponding to a further transmitting means within the system.

16. The data-forwarding system of claim 15, further including:

an network updating means updating the routing table.

17. The data-forwarding system of claim 15, wherein the forwarding core is a dedicated gigabit link.

18. The data-forwarding system of claim 15, wherein the transmitting of data to the destination is a lock-less transmission using a guaranteed packet order.

19. The data-forwarding system of claim 15, wherein the routing table includes a route cache of network destinations for the forwarding core.

20. The data-forwarding system of claim 15, wherein each of the plurality of forwarding cores includes an individual per-instance transmission queue to achieve multiple wire-rate flows to a plurality of destinations.