Jumbo frame

From Wikipedia, the free encyclopedia

In computer networking, jumbo frames are Ethernet frames with more than 1,500 bytes of payload (MTU). Conventionally, jumbo frames can carry up to 9,000 bytes of payload, but variations exist and some care must be taken when using the term. Many, but not all, Gigabit Ethernet switches and Gigabit Ethernet network interface cards support jumbo frames, but all Fast Ethernet switches and Fast Ethernet network interface cards support only standard-sized frames. Most national research and education networks (such as Internet2/NLR, ESnet, GEANT and AARNet) support jumbo frames, but most commercial Internet service providers do not support jumbo frames.

1 Inception
2 Adoption
3 Super jumbo frame
4 See also
5 References
6 External websites

[edit] Inception

The original 1,518-byte MTU for Ethernet was used because of the high error rates and low speed of communications. Thus, if one receives a corrupted packet, only 1,518 bytes must be re-sent to correct the error. However, each frame requires that the network hardware and software process it. If the frame size is increased, the same amount of data can be transferred with less effort. This reduces CPU utilization (mostly due to interrupt reduction) and increases throughput (5-10%) by allowing the system to concentrate on the data in the frames, instead of the frames around the data. At the sender, a similar reduction in CPU utilization can be achieved by using TCP segmentation offloading, although this does not reduce the receiver CPU load. Interrupt-combining Ethernet chipsets, however, do provide most of the same gain for the receiver, and work without special consideration without requiring all stations to support jumbo frames. Zero-copy NICs and device drivers, when combined with interrupt combining, can provide effectively all the gains of Jumbo Frames without the re-send costs, and without requiring any changes to other stations on the network.

Jumbo frames gained initial prominence when Alteon WebSystems introduced them in their ACEnic Gigabit Ethernet adapters.^{[citation needed]} Many other vendors also created proprietary implementations, however they did not become part of the official IEEE 802.3 Ethernet standard.

[edit] Adoption

The IEEE 802 standards committee does not recognize jumbo frames, as doing so would remove interoperability with other 802 protocols, including 802.5 Token Ring and 802.11 Wireless LAN. The use of 9,000 bytes as preferred size for jumbo frames arose from discussions within the Joint Engineering Team of Internet2 and the U.S. federal government networks. Their recommendation has been adopted by all other national research and education networks. In order to meet this mandatory purchasing criterion, manufacturers have in turn adopted 9,000 bytes as the conventional jumbo frame size.

Internet Protocol subnetworks require that all hosts in a subnet have an identical MTU. As a result, interfaces using the standard frame size and interfaces using the jumbo frame size should not be in the same subnet. To reduce interoperability issues, network interface cards capable of jumbo frames require explicit configuration to use jumbo frames.

[edit] Super jumbo frame

Super jumbo frames (SJFs) are generally considered to be Internet packets which have a payload in excess of the tacitly accepted jumbo frame size of 9000 bytes. The relative scalability of network data throughput as a function of packet transfer rates is related in a complex manner ^[1] to payload size per packet. Generally, as line bit rate increases, the packet payload size should increase in direct proportion to maintain equivalent timing parameters. This however implies the covariant scaling of numerous intermediating logic circuits along the network path, to accommodate the maximum transmission unit (MTU), required. As it has been a relatively difficult, and somewhat lengthy, process to increase the path MTU, of high performance national research and education networks, from 1518 bytes to 9000 bytes or so, an increase to significantly over 9000 bytes, possibly 64000 bytes for example, may take some time.

The main factor involved with an increase in the maximum segment size (MSS) is an increase in the available memory buffer size in all of the intervening persistence mechanisms along the path. The main benefit of this is the reduction of the packet rate, both at end nodes and intermediate transit nodes. As the nodes in general use reciprocating logic to handle the packets, the number of machine cycles spent parsing packet headers decreases as the average MSS per packet increases. This relationship becomes increasingly important as average network line bit rate increases to 10 gigabits per second, and above.