Prototype performance measurements¶
- Kind: decision
- Date: 2026-10-13
- Source: moved from
how-it-works/plat/android/prototype-performance-measurement.md; #12139, #12187, #12345, #15562 - Shaped: Prototype performance measurement
Context¶
When the frame-time benchmark landed (#12187) no device baseline was recorded. #12139 asked whether
the up-front composition of a vertical scroll costs enough to justify deferring off-screen rows
behind same-size placeholders.
Options¶
- Keep composing every child up front (
Box(verticalScroll)). - Defer off-screen rows behind same-size placeholders.
- A
LazyColumn.
Decision¶
The owner decision is to keep every row findable: no LazyColumn. Any deferral waits for the
on-device figure for the benchmark list (scripts/android/prototype-frame-benchmark.sh --scenario
scroll), which was still owed.
Consequences¶
First-show measurement (#12345)¶
PrototypeScrollMeasurementTest under Robolectric, setContent through waitForIdle. Two runs, medians:
| Scenario | Render nodes | Semantics nodes | Median ms | p90 ms |
|---|---|---|---|---|
| trivial column (fixed overhead) | 2 | 3 | 6.4-7.6 | 7.7-9.6 |
| 87 rows (largest measured prototype) | 176 | 90 | 4.1-4.9 | 4.4-8.0 |
benchmark list (benchmark/prototype-frame) |
335 | 183 | 7.7-7.9 | 12.5-17.4 |
| 200 rows | 402 | 203 | 4.5-5.0 | 5.7 |
| 500 rows | 1002 | 503 | 17.6-17.9 | 31.9-35.8 |
Scenarios run in JUnit’s method-name-hash order (trivial, 500, benchmark list, 87, 200), not
the order above. The first two therefore carry more JIT/GC warm-up than the last two, and the trivial
case reads slower than 87 rows for that reason. The numbers exclude spec-to-render-model mapping
(the runtime’s cached render model is reused) and draw. Cost is not linear in rows. Going from 87 to 200
rows adds under 1 ms. Going from 200 to 500 rows adds roughly 13 ms (about 42-45 us per row, inflated by the
500-row case running early), and only 500 rows reaches a median of about 18 ms. Every row text is
present in the semantics tree in every scenario (asserted). Robolectric numbers are not device frame times.
The on-device figure for the benchmark list (scripts/android/prototype-frame-benchmark.sh
--scenario scroll) is still owed before any deferral is built.
Feed baseline¶
The feed baseline ran on 2026-10-26 with 1,000 rows, debug CtrlProxy on an API 37 arm64 emulator with
software rendering, and a host load average above 140. Results: feed-scroll-down p95 250 ms and
feed-fling-roundtrip p95 300 ms (about 98% janky), feed-idle no frames. This is a
smoke baseline, not a verdict: it misses the 16 ms target, but the debug build, software
GL and a saturated host dominate it. Re-measure a release build on an idle host or device.
iOS simulator (iPhone 17, iOS 26.5): six scripted swipes took 50.5 s wall time including
CLI overhead, which is not a frame-time measure.