I was curious why “disabling nagle’s” to improve performance is such a popular fix these days…

Nagle’s algorithm is a means of improving the efficiency of TCP/IP networks by reducing the number of packets that need to be sent over the network. It is named after John Nagle, then at Ford Aerospace and lately at Animats.

Nagle’s document, Congestion Control in IP/TCP Internetworks (RFC896) describes what he called the ’small packet problem’, where an application repeatedly emits data in small chunks, frequently only 1 byte in size. Since TCP packets have a 40 byte header, this results in a 41 byte packet for 1 byte of useful information, a huge overhead. This situation occurs in Telnet sessions, where keypresses generate a single byte of data which is transmitted immediately. Worse, over slow links, many such packets can be in transit at the same time, potentially leading to congestion collapse.

The Nagle algorithm works by coalescing a number of small outgoing messages, and sending them all at once. Specifically, as long as there is a sent packet for which the sender has received no acknowledgement, the sender should keep buffering its output until it has a full packet’s worth of output, so that output can be sent all at once.

In the Java world, java.net.Socket.setTcpNoDelay() is used to enable/disable TCP_NODELAY which disables/enables Nagle’s algorithm.