System and method for network interfacing in a multiple network environment

• US 9,088,451 B2
• Filed: 01/13/2014
• Issued: 07/21/2015
• Est. Priority Date: 08/30/2002
• Status: Expired due to Fees

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Broadcom Corporation (Broadcom, Inc.)
• Inventors: Elzur, Uri, Fan, Frankie, Lindsay, Steven B., McDaniel, Scott
• Primary Examiner(s): HOANG, HIEU T
• Application Number:
  US14/153,206
• Publication Number:
  US 20140129737A1
• Time in Patent Office: 554 Days
• Field of Search: 709/250, 709/253
• US Class Current: 1/1
• CPC Class Codes: G06F 13/102 where the programme performs an interfacing function, e.g. device driver G06F13/105 takes precedence; scheduling within device drivers G06F9/52; contention policies within device drivers G06F9/4881
• CPC Class Codes: G06F 13/4027 using bus bridges G06F13/4022 takes precedence
• CPC Class Codes: G06F 2213/0024 Peripheral component interconnect [PCI]
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: H04L 69/161 Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
• CPC Class Codes: H04L 69/163 In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/18 Multiprotocol handlers, e.g. single devices capable of handling multiple protocols
• CPC Class Codes: H04L 69/22 Parsing or analysis of headers

Abstract

Systems and methods that network interface in a multiple network environment are provided. In one embodiment, the system includes, for example, a network connector, a processor, a peripheral component interface (PCI) bridge and a unified driver. The processor may be coupled to the network connector and to the PCI bridge. The processor may be adapted, for example, to process a plurality of different types of network traffic. The unified driver may be coupled to the PCI bridge and may be adapted to provide drivers associated with the plurality of different types of network traffic.

Claims

1. A server, comprising:

a network connector;

a processing circuit coupled to the network connector, the processing circuit processes a plurality of different types of network traffic communicated via the network connector, the plurality of different types of network traffic including at least two of common Ethernet traffic, storage traffic, or remote direct memory access (RDMA) traffic;

a peripheral component interface (PCI) bridge coupled to the processing circuit; and

a unified driver coupled to the PCI bridge, the unified driver interfaces with the plurality of different types of network traffic, wherein

the processing circuit determines the different types of network traffic that access software services via a single data path through a unified driver that interfaces with the different types of network traffic, and

the processing circuit dynamically allocates fixed resources among the different types of network traffic to provide access to the software services based on the determined different types of network traffic.

2. The server according to claim 1, wherein the network connector comprises an Ethernet connector.

3. The server according to claim 1, wherein the processing circuit comprises a single integrated chip.

4. The server according to claim 1, wherein the processing circuit includes a layer 2 network interface card (L2 NIC), a transmission control protocol (TCP) processor, and a ULP processor.

5. The server according to claim 4, wherein the TCP processor performs layer 3 processing and layer 4 processing.

6. The server according to claim 4, wherein the TCP processor is shared by at least two of TCP offload traffic, Internet small computer system interface (iSCSI) traffic, or RDMA traffic.

7. The server according to claim 4, wherein the ULP processor performs iSCSI processing.

8. The server according to claim 4, wherein the ULP processor performs RDMA processing.

9. The server according to claim 1, further comprising a server management agent coupled to the processing circuit.

10. The server according to claim 9, wherein the server management agent is coupled to a keyboard, video, or mouse service.

11. The server according to claim 1, further comprising a plurality of services coupled to the unified driver.

12. The server according to claim 1, wherein the processing circuit determines which of the different types of network traffic accesses a particular service provided by the server.

13. The server according to claim 1, wherein the processing circuit, the PCI bridge, or the unified driver provides a unified data and control path.

14. The server according to claim 1, wherein the processing circuit employs time division multiplexing to determine which of the different types of network traffic accesses the software services via the single data path.

15. A method for network interfacing, comprising:

receiving a plurality of different types of network traffic via a network connector, the plurality of different types of network traffic including at least two of common Ethernet traffic, storage traffic, or remote direct memory access (RDMA) traffic;

processing, by processing circuitry, the different types of network traffic communicated via the network connector;

determining, by the processing circuitry, which of the different types of network traffic accesses software services via a single data path through a unified driver that interfaces with the plurality of different types of network traffic; and

dynamically allocate fixed resources among the different types of network traffic to provide access to the software services based on the determined different types of network traffic.

16. The method according to claim 15, wherein the network connector is a single L2 connector.

17. The method according to claim 15, further comprising employing time division multiplexing, by the processing circuitry, to determine which of the different types of network traffic accesses the software services via the single data path.

18. The method according to claim 15, further comprising:

performing, by the processing circuitry, layer 3 processing and layer 4 processing.

19. A non-transitory computer readable medium having instructions for network interfacing, that when executed by processing circuitry, cause the processing circuitry to:

process different types of network traffic communicated via a network connector, the plurality of different types of network traffic including at least two of common Ethernet traffic, storage traffic, or remote direct memory access (RDMA) traffic;

determine the different types of network traffic that access software services via a single data path through a unified driver that interfaces with the different types of network traffic; and

dynamically allocate fixed resources among the different types of network traffic to provide access to the software services based on the determined different types of network traffic.

20. The non-transitory computer readable medium according to claim 19, wherein the processing circuitry is caused to employ time division multiplexing to determine which of the different types of network traffic accesses the software services via the single data path.