Connection latency.

Connection latency refers to the delay or lag in establishing a connection between a client and a server. It is the time taken for the initial request to reach the server and for the server's response to reach back to the client.

One way to reduce connection latency is by using the Keep-Alive feature in HTTP. Keep-Alive allows multiple requests to be sent over the same TCP connection, eliminating the need to establish a new connection for each request. This can result in a significant speedup in latency times, especially for HTML documents with many images.

To enable Keep-Alive connections in HTTP/1.1, you can set the "KeepAlive" directive to "On" in your server configuration. This will allow the server to keep the connection open for multiple requests.

However, it's important to note that setting a high value for the KeepAliveTimeout may cause performance problems in heavily loaded servers. The KeepAliveTimeout specifies the maximum time a connection can remain idle before it is closed. If this value is set too high, it can result in server processes being occupied waiting on connections with idle clients, leading to decreased performance.

In summary, using Keep-Alive connections can help reduce connection latency by allowing multiple requests to be sent over the same TCP connection. However, it's important to balance the KeepAliveTimeout value to avoid performance issues in heavily loaded servers.