Ludovic Marie
50 lines
2.9 KiB
Markdown
50 lines
2.9 KiB
Markdown
# Measuring resident process memory
|
|
|
|
Horizon Lab 0.6.0 records process RSS alongside JVM heap and nonheap pools. RSS
|
|
counts resident pages belonging to the Minecraft process, including native
|
|
allocations and mapped pages. It helps detect cases where reducing heap use
|
|
merely moves memory elsewhere. It is not unique physical-memory ownership or
|
|
a complete accounting of GPU allocations, shared pages, compressed memory,
|
|
swap, or Apple Silicon unified memory. Do not add heap to RSS: heap pages can
|
|
already be included in it.
|
|
|
|
Minecraft 26.3 already ships OSHI 6.9.0 and JNA on both client and server. The
|
|
original mod uses those dependencies without embedding them. Native reader
|
|
initialization and refresh happen on a low-priority daemon thread, never on
|
|
the render or server-tick thread. One reader serves overlapping frame and
|
|
tick recordings. Reads run about once per second only while recordings are
|
|
active; the scheduler stops polling when the last recording finishes. Ordinary
|
|
gameplay without a benchmark performs no resident-memory reads.
|
|
|
|
Reports include these optional schema-1 fields:
|
|
|
|
| Field | Meaning |
|
|
| --- | --- |
|
|
| `process_rss_peak_sampled_bytes` | Largest successful resident-memory sample during this recording |
|
|
| `process_rss_last_sampled_bytes` | Last successful sample, which can precede recording completion |
|
|
| `process_rss_samples` | Number of successful samples delivered to this recording |
|
|
| `process_rss_sample_interval_ms` | Requested 1,000 ms interval; reads can take longer |
|
|
| `process_rss_last_sample_age_ms` | Time from the last successful sample to report completion |
|
|
|
|
Unsupported or failed reads leave these fields absent if no sample succeeded;
|
|
zero is not used as a substitute. Frames and ticks continue recording. A read
|
|
that completes after a recording finishes is ignored. Sampled peaks can miss
|
|
brief spikes, and the initial read can be delayed by native-library startup.
|
|
|
|
The offline viewer compares RSS separately from heap/nonheap and warns about
|
|
stale resident samples. Keep recording duration, workload and warm-up matched
|
|
when comparing peaks. Process CPU counters cover the whole process over the
|
|
recording wall time, including native work and the integrated server; they do
|
|
not identify which thread or mod caused CPU use.
|
|
|
|
`gc_time_ms` sums collector MXBean collection-time counters. With concurrent
|
|
collectors these can include cycle duration and overlapping phases; it is not a
|
|
direct stop-the-world pause measurement. The viewer calls it collection time.
|
|
Use [JFR pause events](profiling.md) when investigating GC-induced stalls.
|
|
|
|
The native-read test exercises the real library, overlapping recordings,
|
|
background execution, idle cancellation and unavailable-reader behavior on
|
|
the build platform. This validates measurement availability, not an FPS or
|
|
RAM optimization result. Real game integration and platform results are
|
|
recorded in the release validation document after they finish.
|