ISPs and the FCC use the terms 'bandwidth' and 'speed' interchangeably, and they shouldn't. ISPs claim to deliver blazing speeds if you buy their highest bandwidth services. This misleads consumers into assuming that a higher bandwidth connection will automatically deliver a faster user experience. In fact, bandwidth is but one of a half dozen factors that affect user response time (a.k.a. speed).
As we mentioned in last week's posting, the correct way to refer to the bandwidth is as capacity, NOT speed. Here is a simple equation we developed to explain this. You can see who/what is responsible for each factor in this "speed" equation. Your ISP is responsible for just one factor, and it is not among the mathematically most important factors that affect the user's experience.
Task response time (R) is the most useful measure of the speed of a user's experience. A task is each user interaction with the application during a session or process. Task time is measured from the time the user enters an application query, command, function, etc. requiring a server response, to the moment the user receives the response and can proceed. Some call this "user wait time" -- or in the case of the Web, "page load time" (PLT). The aggregation of these individual task completion times defines application "responsiveness" perceived by the user.
Payload is information content (in bytes x 8 or bits) that must be delivered to/from the user's device. It is determined by the application or website developer.
Bandwidth is the minimum capacity (in bits per second) across all network links between the user and the application server. The slowest link is typically the user's access line to the Internet. Useable link bandwidth may be reduced by congestion and protocol inefficiency (e.g., small TCP window size).
AppTurns are the application client-server software interactions (turn count) needed to generate a user-level system response or task. Turns are determined by those who program an application or website. They do not include two-way TCP interactions (e.g., ACKs).
RTT is the round-trip-time (in seconds) between the user and the application server. This is determined by physics, which we'll call 'Mother Nature' for this discussion.
Cc (Compute Client) is the total processing time (in seconds) required by the client device.
Cs (Compute Server) is the total processing time (seconds) required by the server(s).
Note that the AppTurn-RTT product is the most important factor affecting response time and your broadband ISP has absolutely no control over it. Today's typical web pages often require more than 100 AppTurns to load.
It is unhelpful, confusing, and (may we be so bold as to suggest) just plain wrong to use bandwidth and speed interchangeably. We suggest that the FCC and ISPs begin referring to bandwidth as capacity, and to define it is one of many factors that can contribute to a faster user experience. Truth in advertising would have ISPs tout "high capacity" rather than "high speed" Internet connections.