Bandwidth and Latency
Bandwidth and latency are
the
two
most fundamental measures of network performance. Relating these
concepts to the performance terms we use in this book, bandwidth is
similar to network capacity as measured in bits (or sometimes bytes)
per second, while latency is a measure of network response time. In
this section, we look at how to measure network utilization, the most
common measure of bandwidth. We also look at how to measure network
response time and round trip time, the two most important measures of
network latency.
Latency is primarily a function of distance, so it is especially important in wide area networking. Counterintuitively, perhaps, even when the bandwidth of a long-distance connection link is limited, network latency is usually a more important consideration in long-distance communication than bandwidth. On the other hand, bandwidth considerations tend to dominate performance in LAN traffic where the typical latency is minimal, frequently 10 μsecs (microseconds) or less. Of course, there are some networked applications where both latency and bandwidth are significant. Examples include almost any high-volume data-intensive operations like bulk file copies, disk backup, or digital video processing. When both are necessary for adequate performance, it is customary to represent network capacity as Latency x Bandwidth.
Bandwidth
Bandwidth refers to the data rate of the data communications transmission, usually measured in bits per second. It is ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access