The first three layers of the OSI Reference Model—the physical layer, data link layer and network layer—are very important layers for understanding how networks function. The physical layer moves bits over wires; the data link layer moves frames on a network; the network layer moves datagrams on an internetwork. Taken as a whole, they are the parts of a protocol stack that are responsible for the actual “nuts and bolts” of getting data from one place to another.

Immediately above these we have the fourth layer of the OSI Reference Model: the transport layer, called the host-to-host transport layer in the TCP/IP model. This layer is interesting in that it resides in the very architectural center of the model. Accordingly, it represents an important transition point between the hardware-associated layers below it that do the “grunt work”, and the layers above that are more software-oriented and abstract.

Protocols running at the transport layer are charged with providing several important services to enable software applications in higher layers to work over an internetwork. They are typically responsible for allowing connections to be established and maintained between software services on possibly distant machines. Perhaps most importantly, they serve as the bridge between the needs of many higher-layer applications to send data in a reliable way without needing to worry about error correction, lost data or flow management, and network-layer protocols, which are often unreliable and unacknowledged. Transport layer protocols are often very tightly-tied to the network layer protocols directly below them, and designed specifically to take care of functions that they do not deal with.

In this section I describe transport layer protocols and related technologies used in the TCP/IP protocol There are two main protocols at this layer; the Transmission Control Protocol (TCP) and the User Datagram Protocol (UDP). I also discuss how transport-layer addressing is done in TCP/IP in the form of ports and sockets.