16.1. Metrics
Our first concern is performance metrics that drive server selection algorithms.[2] Three main groups of metrics are used: the proximity metrics that measure proximity of servers to a client, the server load metrics that measure the load of servers or network paths to the servers, and the aggregate metrics that implicitly measure the effects of both load and proximity.
[2] Following a general practice in experimental computer science, we use the term metric to mean a measure of performance. This usage is different from mathematics, where metrics are assumed to satisfy specific mathematical properties.
Metrics are also distinguished based on the measurement method. Passive measurements obtain metrics by simply observing the normal ...
Get Web Caching and Replication now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
