Two sets of performance metrics are closely monitored. The first set of performance metrics defines the performance experienced by end users of the application. One example of performance is average response times under peak load. The components of the set include load and response times.
The load is the volume of transactions processed by the application, e.g., transactions per second (tps), requests per second, pages per second. Without being loaded by computer-based demands for searches, calculations, transmissions, etc., most applications are fast enough, which is why programmers may not catch performance problems during development.
The response times are the times required for an application to respond to a user’s actions at such a load.
The second set of performance metrics measures the computational resources used by the application for the load, indicating whether there is adequate capacity to support the load, as well as possible locations of a performance bottleneck. Measurement of these quantities establishes an empirical performance baseline for the application. The baseline can then be used to detect changes in performance. Changes in performance can be correlated with external events and subsequently used to predict future changes in application performance.
Why Riverbed?
Get enterprise-scale visibility and diagnostics across your next-generation applications and infrastructure, both on and off the cloud. Riverbed gives you complete insight, with full details of every user transaction, from the user’s device through the back end. Apply advanced analytics and machine learning to APM big data to resolve issues before business is impacted.