Comparisons
Two tools, two questions. Neither column wins — what decides is which question you actually have in front of you.
Metrics vs TracesTracing vs ProfilingUtilization vs Saturationp50 (median) vs p99 (tail)Add capacity vs Fix the bottleneckLoad test vs Production telemetryCause-based alerts vs Symptom-based alertsMicrobenchmark vs End-to-end benchmark
Utilization vs Saturation
Utilization is how busy a resource is. Saturation is how much work is waiting for it. The first is comfortable to look at; the second is what your users feel.
UtilizationOpen lesson →
Best for
Capacity trending and cost decisions
Blind to
Queueing — 80% utilization says nothing about how deep the queue is
Costs
Trivially available from every host dashboard
Answers
"How much of what we pay for are we using?"
SaturationOpen lesson →
Best for
Explaining current latency and predicting the cliff
Blind to
Efficiency — a saturated resource may be saturated by wasted work
Costs
Requires instrumenting the wait: queue depth, pool wait, run queue
Answers
"Is anything waiting, and for how long?"
| Dimension | Utilization | Saturation |
|---|---|---|
| Typical signal | CPU %, memory % | Run queue, pool wait, queue depth |
| At 100% | Fully used — could be fine | Unbounded queue growth — never fine |
| Predicts latency | Poorly, and not at all below the knee | Directly |