Network interface controller

"Network card" redirects here. For the British Rail discount card, see Network Railcard.
Network interface controller

A 1990s Ethernet network interface controller card which connects to the motherboard via the now-obsolete ISA bus. This combination card features both a BNC connector (left) for use in (now obsolete) 10BASE2 networks and an 8P8C connector (right) for use in 10BASE-T networks.
Connects to

Motherboard via one of:

Network via one of:

Speeds 10 Mbit/s
100 Mbit/s
1 Gbit/s
10 Gbit/s
up to 160 Gbit/s
Common manufacturers Intel
Realtek
Broadcom
Marvell Technology Group
QLogic

A network interface controller (NIC, also known as a network interface card, network adapter, LAN adapter, physical network interface[1] and by similar terms) is a computer hardware component that connects a computer to a computer network.[2]

Early network interface controllers were commonly implemented on expansion cards that plugged into a computer bus. The low cost and ubiquity of the Ethernet standard means that most newer computers have a network interface built into the motherboard.

Modern NICs offer advanced features such as interrupt and DMA interfaces to the host processors, support for multiple receive and transmit queues and network processing such as TCP offload engine.

Purpose

A Madge 4/16 Mbit/s Token Ring ISA-16 NIC

The network controller implements the electronic circuitry required to communicate using a specific physical layer and data link layer standard such as Ethernet, Fibre Channel, Wi-Fi or Token Ring. This provides a base for a full network protocol stack, allowing communication among small groups of computers on the same local area network (LAN) and large-scale network communications through routable protocols, such as Internet Protocol (IP).

The NIC allows computers to communicate over a computer network, either by using cables or wirelessly. The NIC is both a physical layer and data link layer device, as it provides physical access to a networking medium and, for IEEE 802 and similar networks, provides a low-level addressing system through the use of MAC addresses that are uniquely assigned to network interfaces.

Implementation

An ATM network interface.

Whereas network controllers used to operate on expansion cards that plugged into a computer bus, the low cost and ubiquity of the Ethernet standard means that most new computers have a network interface built into the motherboard. Newer server motherboards may even have dual network interfaces built-in. The Ethernet capabilities are either integrated into the motherboard chipset or implemented via a low-cost dedicated Ethernet chip, connected through the PCI (or the newer PCI Express) bus. A separate network card is not required unless additional interfaces are needed or some other type of network is used.

The NIC may use one or more of two techniques to indicate the availability of packets to transfer:

and may use one or more of two techniques to transfer packet data:

An Ethernet network controller typically has an 8P8C socket where the network cable is connected. Older NICs also supplied BNC, or AUI connections. A few LEDs inform the user of whether the network is active, and whether or not data transmission occurs. Ethernet network controllers typically support 10 Mbit/s Ethernet, 100 Mbit/s Ethernet, and 1000 Mbit/s Ethernet varieties. Such controllers are designated 10/100/1000 - this means they can support a notional maximum transfer rate of 10, 100 or 1000 Megabits per second. Standalone 10 Gigabit Ethernet NICs are also available and 10 Gigabit Ethernet is becoming readily available om motherboards.[3]

Performance and advanced functionality

An Intel 82574L Gigabit Ethernet NIC, PCI Express x1 card; it provides two hardware receive queues[4]

Multiqueue NICs provide multiple transmit and receive queues, allowing packets received by the NIC to be assigned to one of its receive queues. Each receive queue is assigned to a separate interrupt; by routing each of those interrupts to different CPUs/cores, processing of the interrupt requests triggered by the network traffic received by a single NIC can be distributed among multiple cores, bringing additional performance improvements in interrupt handling. Usually, a NIC distributes incoming traffic between the receive queues using a hash function, while separate interrupts can be routed to different CPUs/cores either automatically by the operating system, or manually by configuring the IRQ affinity.[5][6]

The hardware-based distribution of the interrupts, described above, is referred to as receive-side scaling (RSS).[7]:82 Purely software implementations also exist, such as the receive packet steering (RPS) and receive flow steering (RFS).[5] Further performance improvements can be achieved by routing the interrupt requests to the CPUs/cores executing the applications which are actually the ultimate destinations for network packets that generated the interrupts. That way, taking the application locality into account results in higher overall performance, reduced latency and better hardware utilization, resulting from the higher utilization of CPU caches and fewer required context switches. Examples of such implementations are the RFS[5] and Intel's Flow Director.[7]:98,99[8][9]

With multiqueue NICs, additional performance improvements can be achieved by distributing outgoing traffic among different transmit queues. By assigning different transmit queues to different CPUs/cores, various operating system's internal contentions can be avoided; this approach is usually referred to as transmit packet steering (XPS).[5]

Some products feature NIC partitioning (NPAR), which divides a single 10 Gigabit Ethernet NIC into multiple discrete virtual NICs with dedicated bandwidth, presented to the firmware and operating system as separate PCI device functions.[10]

TCP offload engine is a technology used in NICs to offload processing of the entire TCP/IP stack to the network controller. It is primarily used with high-speed network interfaces, such as Gigabit Ethernet and 10 Gigabit Ethernet, where processing overhead of the network stack becomes significant.

Some NICs offer integrated field-programmable gate arrays (FPGAs) for user-programmable processing of network traffic before it reaches the host computer, allowing for significantly reduced latencies in time-sensitive workloads. Moreover, some NICs offer complete low-latency TCP/IP stacks running on integrated FPGAs in combination with userspace libraries that intercept networking operations usually performed by the operating system kernel; Solarflare's open-source OpenOnload network stack that runs on Linux is an example. This kind of functionality is usually referred to as user-level networking.[11][12][13]

See also

References

  1. ↑ "Physical Network Interface". Microsoft. January 7, 2009.
  2. ↑ Posey, Brien M. (2006). "Networking Basics: Part 1 - Networking Hardware". Windowsnetworking.com. TechGenix Ltd. Retrieved 2012-06-09.
  3. ↑ Jim O'Reilly (2014-01-22). "Will 2014 Be The Year Of 10 Gigabit Ethernet?". Network Computing. Retrieved 2015-04-29.
  4. ↑ "Intel 82574 Gigabit Ethernet Controller Family Datasheet" (PDF). Intel. June 2014. p. 1. Retrieved November 16, 2014.
  5. ↑ 5.0 5.1 5.2 5.3 Tom Herbert; Willem de Bruijn (May 9, 2014). "Linux kernel documentation: Documentation/networking/scaling.txt". kernel.org. Retrieved November 16, 2014.
  6. ↑ "Intel Ethernet Controller i210 Family Product Brief" (PDF). Intel. 2012. Retrieved November 16, 2014.
  7. ↑ 7.0 7.1 "Intel Look Inside: Intel Ethernet" (PDF). Intel. November 27, 2014. Retrieved March 26, 2015.
  8. ↑ "Linux kernel documentation: Documentation/networking/ixgbe.txt". kernel.org. December 15, 2014. Retrieved March 26, 2015.
  9. ↑ "Intel Ethernet Flow Director". Intel. February 16, 2015. Retrieved March 26, 2015.
  10. ↑ "Enhancing Scalability Through Network Interface Card Partitioning" (PDF). Dell. April 2011. Retrieved 2014-05-12.
  11. ↑ Timothy Prickett Morgan (2012-02-08). "Solarflare turns network adapters into servers: When a CPU just isn't fast enough". The Register. Retrieved 2014-05-08.
  12. ↑ "OpenOnload". openonload.org. 2013-12-03. Retrieved 2014-05-08.
  13. ↑ Steve Pope; David Riddoch (2008-03-21). "OpenOnload: A user-level network stack" (PDF). openonload.org. Retrieved 2014-05-08.

External links