1. The notion of known-knowns, known-unknowns and unknown-unknowns is important for the field of performance:
a) Known-knowns: These are things you know;
b) Known-unknowns: These are things you know that you do not know;
c) Unknown-unknowns: These are things you do not know you do not know.
2. Performance metrics are statistics generated by the system, applications or additional tools that measure activity of interest. They are studied for performance analysis or monitoring, either numerically at the command line or graphically using visualization. Common types of performance metrics include IOPS(I/O operations per second), throughput(either operations or volume per second), utilization and latency.
Performance metrics are not free; at some point, CPU cycles must be spent on to gather and store them. This cause overhead, which can negatively affect the performance of the target of measurement. This is called observer effect.
3. Utilization is often used for operating system to describe device usage, such as for the CPU and disk devices. Utilization can be time-based or capacity-based.
(a) Time-based utilization is formally defined in queueing theory: the average amount of time the system or resource was busy along with the ratio U=B/T, where U = utilization, B = total time the system was busy during T, the observation period.
(b) Capacity-based utilization: A system or component (such as a disk drive) is able to deliver a certain amount of throughput. At any level of performance, the system or component is working at some proportion of its capacity. That proportion is called utilization. This defines utilization in terms of capacity instead of time.