TCP segmentation offload (TSO)

TCP segmentation offload (TSO)
This is a technology that shift the data segmentation effort from CPU to NIC-CPU. So the checksum will also generated by the NIC-CPU.

In Linux OS, we can disable this function by issue the following command:
# ethtool -K eth0 tso off

show all the offload information for a specified interface
# ethtool -k eth0

Large segment offload
http://en.wikipedia.org/wiki/TCP_segmentation_offloading

In computer networking, large segment offload (LSO) is a technique for increasing outbound throughput of high-bandwidth network connections by reducing CPU overhead. It works by queuing up large buffers and letting the NIC split them into separate packets. The technique is also called TCP segmentation offload (TSO) when applied to TCP, or generic segmentation offload (GSO).

When large chunks of data are to be sent over a computer network, they need to be first broken down to smaller segments that can pass through all the network elements like routers and switches between the source and destination computers. This process is referred to as segmentation. Segmentation is often done by the TCP protocol in the host computer. Offloading this work to the network card is called TCP segmentation offload (TSO).

For example, a unit of 64KB (65,536 bytes) of data is usually segmented to 46 segments of 1448 bytes each before it is sent over the network through the network interface controller (NIC). With some intelligence in the NIC, the host CPU can hand over the 64 KB of data to the NIC in a single transmit request, the NIC can break that data down into smaller segments of 1448 bytes, add the TCP, IP, and data link layer protocol headers -- according to a template provided by the host's TCP/IP stack -- to each segment, and send the resulting frames over the network. This significantly reduces the work done by the CPU. Many new NICs on the market today support TSO.

Some network cards implement TSO generically enough that it can be used for offloading fragmentation of other transport layer protocols, or by doing IP fragmentation for protocols that don't support fragmentation by themselves, such as UDP. This is not as useful, though, as other protocols aren't commonly used for transmitting large amounts of data.

TCP checksum offload (