Perfcounter (Performance Metrics) - (Operational|Machine) data
Table of Contents
1 - About
This section is about machine data:
- performance counter
Performance metrics known also as Perfcounter (generally on Windows) are counter produced by application (OS and every other app) in order to:
- infer their performance
- find performance bottlenecks (i.e. performance analysis)
- predict future system load (i.e. capacity planning).
See also: Observablity
(Counter|Metrics|Monitoring) data are of the time serie data type.
These (counter|numbers) are or we will derive averages from them. There is no way to figure out from the data, if you got from one point to another in an horizontal and constant line.
2 - Steps / Lifecycle
Merge with monitoring lifecycle ??
3 - Counter Category
Machine data counter example:
3.1 - Sensor
- number of printouts
3.2 - Service Metrics
3.3 - Event
Some monitoring systems can also capture events:
- Changes: Internal code releases, builds, and build failures
- Alerts: Internally generated alerts or third-party notifications
- Scaling events: Adding or subtracting hosts
4 - Property
4.1 - Increasing
Increasing counter starts at zero, increasing when an action occurs. This type of counter will probably have a maximum value. If this value is reached, the counter starts over at zero. This is the same as many counters in the world such as the mileage counter in a car.
4.2 - Scale and Persistence
- last 2 hours at 1 minute resolution,
- last 24 hours at 10 minute resolution,
- last 3 days with 1 hour resolution,
- last 7 days at 2 hours resolution
5 - Reference
- CSE 141 - Performance I and II