Operations | Monitoring | ITSM | DevOps | Cloud

Average response time has become the default metric on many dashboards. It's easy to compute, easy to explain, and provides a single number to track over time. Of all the metrics available in application monitoring, this one feels closest to the actual user experience. But this simplicity can create a trap if you treat the average as a complete picture of system health. In fact, it’s really the starting point for a deeper investigation.

Regular monitoring practices can emphasize application response time, but queue time is also often an early and important warning sign. If it rises, you’ll quickly see downstream effects: tail latency, timeouts, and error spikes. This means that this metric can give you a head start tackling app issues before they become user problems. In this post, we’ll discuss queue time, how things can go off track, and practical steps to turn it around.

Throughput is one of the most foundational metrics in application performance monitoring. It tells you how many requests your app is handling over time and offers a direct look at system load, responsiveness, and scalability. But throughput rarely speaks for itself. The key is knowing how to interpret it, and when to act. In this post, we’ll look at how throughput works in the real world: what healthy looks like, what broken looks like, and what lives in between.

Your app feels slow, users complain… but your dashboard says response time is totally fine! But the real pain is revealed when looking at percentiles. In this post, we’ll break down why the 95th percentile response time metric is useful, plus how to work with it in practice. ‍