Direct answer
An average MSPT can hide brief severe stalls. Median and high-percentile MSPT describe typical ticks and worst-end behavior more clearly than an average alone.
How to check it
- Collect a spark report during peak activity and compare its tick time distribution, not just the TPS displayed when you happen to look. Note whether spikes line up with backups, saves, logins or chunk generation.
- Record the original configuration or test conditions, capture a profile or a repeatable observation, and identify the affected world or player group.
- Make the measurement under the same player count and workload you will later use to verify the change.
What to change
For example, most ticks may finish in 12 ms while a small fraction pause for 250 ms: the average can remain acceptable even though players feel freezes. Investigate the time-consuming events and compare the same percentile after a fix.
Do not treat a single outlier in an otherwise smooth session as proof of an ongoing CPU bottleneck.
Software and version notes
Check the active version and generated configuration before copying paths or values. Different forks and mod loaders may implement this behavior differently.
This article is written for Paper / compatible servers. Configuration keys and defaults can move between versions. The source material checked for this page includes PaperMC profiling guide. If your server is Folia, Leaf, Purpur, Fabric, Forge, NeoForge, or another fork/loader, do not assume a Paper-only setting exists or behaves identically.
Verify the result
Repeat the same test with the same software build, player count and world activity. Compare the targeted symptom and any spark measurements, then check that intended game mechanics still work. If the change does not produce a reproducible improvement, revert to the recorded baseline.