perf(vk): the recorder thread spins 5 ms before it sleeps on Intel CPUs, which keeps their clock up #1745

Closed
HumanBean wants to merge 3 commits from HumanBean/Longshot:perf/recorder-spin into main
Owner

Type: perf · Risk: medium · Tested on: Linux, RX 580 (RADV), i7-9700K; Linux, RTX 3090, Ryzen 9 7900X · Needs: Windows and other Intel CPUs (the Test Farm)

TL;DR

On a CPU with 6 or more cores, threaded rendering's recorder thread went to sleep many times a frame. On an Intel i7-9700K those tiny sleeps made the CPU lower its own clock to 1-3 GHz instead of 4.5, and the whole game ran about 2.5 times slower on the CPU. The recorder now keeps going for up to 5 ms before it sleeps, which keeps the clock up. In three interleaved runs each, Kokiri Forest went from 15-34 fps to 48 standing and from 24 to 42 turning, and the Market from 28 to 44 turning, with far fewer stutters.

Breakdown

  • Who it helps: players with an Intel CPU of 6 or more cores (where Auto turns the recorder thread on), measured on an i7-9700K. Other CPUs keep the adaptive spin: on a Ryzen 9 7900X the 5 ms spin cost 6-11% in Hyrule Field and 3-5% in the Market.
  • What was wrong: the recorder's short idle spin (20-200 us) ended in a sleep many times a frame, and those sleeps let the CPU's clock control lower the clock that all its cores share.
  • What changes: on an Intel CPU (cpuid's brand string), with nothing to run, the recorder spins 5 ms before it sleeps, so it sleeps about once a frame, in the frame wait; elsewhere the adaptive 20-200 us spin, as before.
  • What does not change: which PCs get the recorder thread (Auto's tiers), the recorder's work and its ordering; the adaptive spin stays as RX_VK_RECORDER_SPIN_US=0.
  • How it was checked: three interleaved runs each against main in three scenes on the lab PC; test_recorder_sync.py and test_recorder_own_idle.py pass.
  • What is still open: Windows, and Intel CPUs other than the i7-9700K (hybrid ones, laptops): the Test Farm. The structural fix, fewer hand-offs to the recorder so it idles less often, would help without a spin and is for later.
  • Risk: medium: the recorder's core stays busy through gaps of up to 5 ms, so a little more power is used where it is on.

Why

Kokiri Forest and the Market played at 15-30 fps with constant hitches on an i7-9700K with an RX 580 at 1080p, with the GPU a third to half idle. Tracy showed the game's own update (the actor batch) taking longer; the scheduler's per-thread counters (/proc/<pid>/task/*/schedstat) showed every game thread using about 2.5 times its CPU time a frame, with little time waiting for a core. Sampling the CPU's clock showed why: 0.8-3.1 GHz with the recorder thread on, against 3.2-4.3 GHz with it off and 4.4-4.6 GHz with a long recorder spin, at 38-57 °C, so not heat. On this CPU all cores share one clock, and the recorder's frequent short sleeps (about 20-25 a frame) let Intel's clock control (HWP, under Linux's powersave governor) pull it down for every core.

The spin length was chosen from an A/B of RX_VK_RECORDER_SPIN_US (two runs each): 1 ms was too short (Kokiri Forest turning 29.9 fps, the clock 2.1-4.3 GHz), 5 ms and 20 ms were alike (42.1 and 43.0 fps), and both beat the recorder thread off (37.8 fps). See #1407 (riqmarmes), which saw worse 1% lows under threaded rendering on the same CPU, and #1664, which set Auto's tiers on a Ryzen 9 9950X3D.

What changed

The recorder's default idle spin is a fixed 5 ms instead of the adaptive 20-200 us.

  • vk: gpu/vk/vk_recorder.h: kSpinDefault (5 ms) is g_spin_ns's default; RX_VK_RECORDER_SPIN_US=0 now gives the adaptive spin (before, 0 read as 1 us); the comment holds the measurements. g_spin_long (set by vk_replay.cpp's recorder_long_spin, an Intel CPU) chooses the 5 ms spin by default; other CPUs get the adaptive one.
  • switches: gpu/vk/switches.def: RX_VK_RECORDER_SPIN_US's row has the new default and the meaning of 0.
  • docs: docs/development.md, the recorder's row names the spin and its default; docs/tested/2026-11-19-recorder-spin-humanbean-*.md, the six runs.

Measurements

Verdict: a large gain on the i7-9700K in every scene and phase, the runs of the two sides far apart: Kokiri Forest 15.4 → 48.1 fps standing and 24.0 → 42.2 turning (frames over 50 ms 320 → 16), the Market 28.2 → 43.8 turning (279 → 14), Hyrule Field 35.1 → 48.4 turning.

Hardware: CachyOS Linux (kernel 7.3.3), RX 580 8 GB, Mesa RADV 26.2.6, Intel Core i7-9700K (8 cores, no SMT; intel_pstate, powersave governor, balance_performance), 15 GB
Scene: the kokiri-start repo save: Kokiri Forest, then teleports to Hyrule Field and the Market. 1920x1080, Render resolution 100%, upscaling, DLSS and frame generation off, quality preset 6, from one pinned options file; HOS_FPS_MAX=1000. Threaded rendering Auto: "on, the render thread and the recorder thread (7 cores of 7 logical processors)" in both arms
Method: in each scene 10 s settle, then 15 s standing still and 20 s turning with the right stick held (longshot_ctl.py sequence); fps (frames over time) and frames over 50 ms from RX_VK_FRAME_LOG; GPU busy from gpu_busy_percent and the CPU's clock from /proc/cpuinfo, every 100 ms. One warm-up run of the pack, then three runs a side, interleaved main, change; the median
How to reproduce: dev_packs.py pack <base> spin5 --tree <this branch>, a runtime with and one without the pack, the same options file; RX_VK_RECORDER_SPIN_US=0 on this branch gives main's spin

Baseline: the base is main 9b82abf6 (adopted from a full build on the lab PC), and the change ran as a pack over it. This branch is rebased onto 868f6be8; the commits between change how a few switches are read (env_on_or) and touch nothing in the recorder, threaded rendering or the virtual cores.

fps (frames over 50 ms) Before: main @ 9b82abf6 After: this PR @ 39b70e45
Kokiri Forest, standing 33.6 / 15.4 / 15.0, median 15.4 (222) 48.6 / 48.1 / 47.4, median 48.1 (0)
Kokiri Forest, turning 25.0 / 20.7 / 24.0, median 24.0 (320) 42.8 / 42.2 / 41.8, median 42.2 (16)
Hyrule Field, standing 40.8 / 41.1 / 38.0, median 40.8 (2) 43.3 / 43.2 / 43.3, median 43.3 (0)
Hyrule Field, turning 35.1 / 37.8 / 33.4, median 35.1 (45) 48.5 / 48.4 / 46.1, median 48.4 (2)
Market, standing 28.9 / 26.8 / 27.9, median 27.9 (3) 33.8 / 32.2 / 32.4, median 32.4 (1)
Market, turning 29.5 / 28.2 / 25.4, median 28.2 (279) 44.6 / 43.8 / 43.3, median 43.8 (14)
frame time p99, Market turning 82.5 ms 42.0 ms
GPU busy, Market turning 56% 76%
CPU clock, all phases 0.8-3.1 GHz 4.4-4.6 GHz
main:    vk: Threaded rendering: Auto: on, the render thread and the recorder thread (7 cores of 7 logical processors)
         vk: RX_VK_RECORDER=thread: ... ring 8192 KB, spin adaptive 20-200 us
this PR: vk: Threaded rendering: Auto: on, the render thread and the recorder thread (7 cores of 7 logical processors)
         vk: RX_VK_RECORDER=thread: ... ring 8192 KB, spin 5000 us

The spin-length A/B behind the choice (same PC and method, two runs each, the switch on main's build; fps, frames over 50 ms):

main (adaptive) recorder off 1 ms 5 ms 20 ms
Kokiri Forest, standing 20.7 40.6 33.7 48.4 48.1
Kokiri Forest, turning 24.0 (395) 37.8 (42) 29.9 (186) 42.1 (18) 43.0 (16)
Market, turning 27.4 (228) 33.4 (165) 30.0 (240) 40.3 (22) 45.4 (10)
Hyrule Field, turning 40.8 (14) 41.8 (22) 44.7 (6) 48.1 (2) 47.5 (3)
CPU clock 1.1-3.1 GHz 3.2-4.3 GHz 2.1-4.3 GHz 4.4-4.6 GHz 4.6 GHz

On a Ryzen 9 7900X

(HumanBean, 2026-11-19.) CachyOS Linux, RTX 3090, Ryzen 9 7900X (12 cores, 24 threads), Threaded rendering Auto (both threads on), 2560x1440 DLSS Quality, uncapped, Reflex on: main against main with RX_VK_RECORDER_SPIN_US=5000, a warm-up each, then 2 interleaved timed sessions each on the PC's timing queue; 15 s still, 5 s walking, 20 s turning in each area; fps from the renderer's vk: N presents lines, the median (each run in brackets).

main (adaptive) 5 ms spin
Kokiri still / walk / turn 63.6 [59,69] / 70.7 [68,73] / 70.5 [67,74] 66.8 [64,69] / 71.1 [67,75] / 70.9 [69,73]
Hyrule Field still / walk / turn 90.2 [89,91] / 88.6 [87,90] / 88.5 [86,91] 80.3 [76,84] / 82.3 [86,79] / 83.5 [85,82]
Market still / walk / turn 75.7 [74,77] / 73.6 [71,77] / 88.8 [85,93] 71.9 [75,69] / 69.9 [73,67] / 86.2 [90,82]

So the long spin is the default on Intel CPUs only; on this PC the PR now runs main's adaptive spin.

Flags and settings

RX_VK_RECORDER_SPIN_US's default changes, and its 0 now means the old adaptive spin.

Flag What it is Before this PR After this PR Effect Helps / doesn't help / untested Recommendation
RX_VK_RECORDER_SPIN_US how long the recorder thread spins with nothing to run before it sleeps unset: adaptive 20-200 us; 0 read as 1 us unset: 5000 us on an Intel CPU, adaptive 20-200 us on others; 0: adaptive the recorder sleeps about once a frame instead of many times helps on an i7-9700K (Linux); untested on Windows and on Ryzen 5000 us for everyone, pending the Test Farm

Testing

Tested: in the game on Linux, RX 580, Mesa RADV 26.2.6, i7-9700K: Kokiri Forest, Hyrule Field and the Market, standing and turning, three runs each against main as in Measurements; the log names the 5000 us spin; no device lost, nothing looked wrong in the end-of-run screenshots. Game-free: tests/run_all.py --changed on that PC: test_recorder_sync.py, test_recorder_own_idle.py, test_threaded_rendering.py and the rest pass; test_dev_packs.py ("a game patch shows in the objects") and test_switch_table.py (switches read in host/ and vk_replay.cpp with no row) fail the same way on main there. test_tested_configurations.py passes with the six files.

Not tested: Windows, where the scheduler and the power plan are not Linux's; AMD Ryzen CPUs, whose cores have clocks of their own (Auto's tiers were measured on one); laptops on battery.

Must be tested:

  • Windows, any GPU, a CPU of 6 or more cores (Threaded rendering Auto): the Market, standing and turning, this PR against main, expecting fps no lower and frames over 50 ms no more (Test Farm: @Beanstalk windows)
  • Linux, a Ryzen CPU of 6 or more cores: the same, expecting no loss (Test Farm: @Beanstalk linux amd)

Risks

What could break: nothing in what is drawn: only how long the recorder thread waits before it sleeps. A PC could use a little more power, and with more threads than cores the spinning recorder could take time from a game thread (here the scheduler's counters show the game's threads waiting less for a core, not more).

Turning it off: RX_VK_RECORDER_SPIN_US=0 gives main's adaptive spin; RX_VK_RECORDER=off turns the recorder thread off.

Compatibility: Nothing changes: no cache, option or save is touched.

Checklist

Everyone

  • One topic.
  • The title is a Conventional Commit (type(scope): description) of the status line's type.
  • Why gives the reason plainly and links the issues that fit (the tracker searched).
  • Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what
    can't be run by hand is in Testing's Not testable by hand, with why.
  • Measurements has a verdict, or one line saying why there is nothing to measure.
  • Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and
    in Risks.
  • Testing names what was tested, what wasn't, and what must still be tested, where and how.
  • Rebased on current main.
  • python -I -B tests/run_all.py passes (any failure that also fails on main is named).
  • No game files, dumps, build output or generated files.
  • third_party/ untouched (a new folder with a PROVENANCE.md instead).
  • The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled.

When it applies

  • AI assistance recorded with Assisted-by: / Co-Authored-By: trailers.
  • Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported.
  • Switches documented (docs/development.md; the README for a menu row) and shipped at their recommended value.
  • A file in docs/tested/ for each new measured run (format in docs/tested-configurations.md).
  • Docs updated.

🤖 Generated with Claude Code

https://claude.ai/code/session_016o1k1NeAdSovkHa9ukS7YM

**Type:** perf · **Risk:** medium · **Tested on:** Linux, RX 580 (RADV), i7-9700K; Linux, RTX 3090, Ryzen 9 7900X · **Needs:** Windows and other Intel CPUs (the Test Farm) ## TL;DR On a CPU with 6 or more cores, threaded rendering's recorder thread went to sleep many times a frame. On an Intel i7-9700K those tiny sleeps made the CPU lower its own clock to 1-3 GHz instead of 4.5, and the whole game ran about 2.5 times slower on the CPU. The recorder now keeps going for up to 5 ms before it sleeps, which keeps the clock up. In three interleaved runs each, Kokiri Forest went from 15-34 fps to 48 standing and from 24 to 42 turning, and the Market from 28 to 44 turning, with far fewer stutters. ## Breakdown - **Who it helps:** players with an Intel CPU of 6 or more cores (where Auto turns the recorder thread on), measured on an i7-9700K. Other CPUs keep the adaptive spin: on a Ryzen 9 7900X the 5 ms spin cost 6-11% in Hyrule Field and 3-5% in the Market. - **What was wrong:** the recorder's short idle spin (20-200 us) ended in a sleep many times a frame, and those sleeps let the CPU's clock control lower the clock that all its cores share. - **What changes:** on an Intel CPU (cpuid's brand string), with nothing to run, the recorder spins 5 ms before it sleeps, so it sleeps about once a frame, in the frame wait; elsewhere the adaptive 20-200 us spin, as before. - **What does not change:** which PCs get the recorder thread (Auto's tiers), the recorder's work and its ordering; the adaptive spin stays as `RX_VK_RECORDER_SPIN_US=0`. - **How it was checked:** three interleaved runs each against `main` in three scenes on the lab PC; `test_recorder_sync.py` and `test_recorder_own_idle.py` pass. - **What is still open:** Windows, and Intel CPUs other than the i7-9700K (hybrid ones, laptops): the Test Farm. The structural fix, fewer hand-offs to the recorder so it idles less often, would help without a spin and is for later. - **Risk:** medium: the recorder's core stays busy through gaps of up to 5 ms, so a little more power is used where it is on. ## Why Kokiri Forest and the Market played at 15-30 fps with constant hitches on an i7-9700K with an RX 580 at 1080p, with the GPU a third to half idle. Tracy showed the game's own update (the actor batch) taking longer; the scheduler's per-thread counters (`/proc/<pid>/task/*/schedstat`) showed every game thread using about 2.5 times its CPU time a frame, with little time waiting for a core. Sampling the CPU's clock showed why: 0.8-3.1 GHz with the recorder thread on, against 3.2-4.3 GHz with it off and 4.4-4.6 GHz with a long recorder spin, at 38-57 °C, so not heat. On this CPU all cores share one clock, and the recorder's frequent short sleeps (about 20-25 a frame) let Intel's clock control (HWP, under Linux's powersave governor) pull it down for every core. The spin length was chosen from an A/B of `RX_VK_RECORDER_SPIN_US` (two runs each): 1 ms was too short (Kokiri Forest turning 29.9 fps, the clock 2.1-4.3 GHz), 5 ms and 20 ms were alike (42.1 and 43.0 fps), and both beat the recorder thread off (37.8 fps). See #1407 (riqmarmes), which saw worse 1% lows under threaded rendering on the same CPU, and #1664, which set Auto's tiers on a Ryzen 9 9950X3D. ## What changed The recorder's default idle spin is a fixed 5 ms instead of the adaptive 20-200 us. - vk: `gpu/vk/vk_recorder.h`: `kSpinDefault` (5 ms) is `g_spin_ns`'s default; `RX_VK_RECORDER_SPIN_US=0` now gives the adaptive spin (before, 0 read as 1 us); the comment holds the measurements. `g_spin_long` (set by `vk_replay.cpp`'s `recorder_long_spin`, an Intel CPU) chooses the 5 ms spin by default; other CPUs get the adaptive one. - switches: `gpu/vk/switches.def`: `RX_VK_RECORDER_SPIN_US`'s row has the new default and the meaning of 0. - docs: `docs/development.md`, the recorder's row names the spin and its default; `docs/tested/2026-11-19-recorder-spin-humanbean-*.md`, the six runs. ## Measurements **Verdict:** a large gain on the i7-9700K in every scene and phase, the runs of the two sides far apart: Kokiri Forest 15.4 → 48.1 fps standing and 24.0 → 42.2 turning (frames over 50 ms 320 → 16), the Market 28.2 → 43.8 turning (279 → 14), Hyrule Field 35.1 → 48.4 turning. Hardware: CachyOS Linux (kernel 7.3.3), RX 580 8 GB, Mesa RADV 26.2.6, Intel Core i7-9700K (8 cores, no SMT; intel_pstate, powersave governor, balance_performance), 15 GB Scene: the `kokiri-start` repo save: Kokiri Forest, then teleports to Hyrule Field and the Market. 1920x1080, Render resolution 100%, upscaling, DLSS and frame generation off, quality preset 6, from one pinned options file; `HOS_FPS_MAX=1000`. Threaded rendering Auto: "on, the render thread and the recorder thread (7 cores of 7 logical processors)" in both arms Method: in each scene 10 s settle, then 15 s standing still and 20 s turning with the right stick held (`longshot_ctl.py sequence`); fps (frames over time) and frames over 50 ms from `RX_VK_FRAME_LOG`; GPU busy from `gpu_busy_percent` and the CPU's clock from `/proc/cpuinfo`, every 100 ms. One warm-up run of the pack, then three runs a side, interleaved main, change; the median How to reproduce: `dev_packs.py pack <base> spin5 --tree <this branch>`, a runtime with and one without the pack, the same options file; `RX_VK_RECORDER_SPIN_US=0` on this branch gives main's spin Baseline: the base is main 9b82abf6 (adopted from a full build on the lab PC), and the change ran as a pack over it. This branch is rebased onto 868f6be8; the commits between change how a few switches are read (`env_on_or`) and touch nothing in the recorder, threaded rendering or the virtual cores. | fps (frames over 50 ms) | Before: main @ 9b82abf6 | After: this PR @ 39b70e45 | |---|---|---| | Kokiri Forest, standing | 33.6 / 15.4 / 15.0, median **15.4** (222) | 48.6 / 48.1 / 47.4, median **48.1** (0) | | Kokiri Forest, turning | 25.0 / 20.7 / 24.0, median **24.0** (320) | 42.8 / 42.2 / 41.8, median **42.2** (16) | | Hyrule Field, standing | 40.8 / 41.1 / 38.0, median **40.8** (2) | 43.3 / 43.2 / 43.3, median **43.3** (0) | | Hyrule Field, turning | 35.1 / 37.8 / 33.4, median **35.1** (45) | 48.5 / 48.4 / 46.1, median **48.4** (2) | | Market, standing | 28.9 / 26.8 / 27.9, median **27.9** (3) | 33.8 / 32.2 / 32.4, median **32.4** (1) | | Market, turning | 29.5 / 28.2 / 25.4, median **28.2** (279) | 44.6 / 43.8 / 43.3, median **43.8** (14) | | frame time p99, Market turning | 82.5 ms | 42.0 ms | | GPU busy, Market turning | 56% | 76% | | CPU clock, all phases | 0.8-3.1 GHz | 4.4-4.6 GHz | ``` main: vk: Threaded rendering: Auto: on, the render thread and the recorder thread (7 cores of 7 logical processors) vk: RX_VK_RECORDER=thread: ... ring 8192 KB, spin adaptive 20-200 us this PR: vk: Threaded rendering: Auto: on, the render thread and the recorder thread (7 cores of 7 logical processors) vk: RX_VK_RECORDER=thread: ... ring 8192 KB, spin 5000 us ``` The spin-length A/B behind the choice (same PC and method, two runs each, the switch on main's build; fps, frames over 50 ms): | | main (adaptive) | recorder off | 1 ms | 5 ms | 20 ms | |---|---|---|---|---|---| | Kokiri Forest, standing | 20.7 | 40.6 | 33.7 | 48.4 | 48.1 | | Kokiri Forest, turning | 24.0 (395) | 37.8 (42) | 29.9 (186) | 42.1 (18) | 43.0 (16) | | Market, turning | 27.4 (228) | 33.4 (165) | 30.0 (240) | 40.3 (22) | 45.4 (10) | | Hyrule Field, turning | 40.8 (14) | 41.8 (22) | 44.7 (6) | 48.1 (2) | 47.5 (3) | | CPU clock | 1.1-3.1 GHz | 3.2-4.3 GHz | 2.1-4.3 GHz | 4.4-4.6 GHz | 4.6 GHz | ### On a Ryzen 9 7900X (HumanBean, 2026-11-19.) CachyOS Linux, RTX 3090, Ryzen 9 7900X (12 cores, 24 threads), Threaded rendering Auto (both threads on), 2560x1440 DLSS Quality, uncapped, Reflex on: main against main with `RX_VK_RECORDER_SPIN_US=5000`, a warm-up each, then 2 interleaved timed sessions each on the PC's timing queue; 15 s still, 5 s walking, 20 s turning in each area; fps from the renderer's `vk: N presents` lines, the median (each run in brackets). | | main (adaptive) | 5 ms spin | |---|---|---| | Kokiri still / walk / turn | 63.6 [59,69] / 70.7 [68,73] / 70.5 [67,74] | 66.8 [64,69] / 71.1 [67,75] / 70.9 [69,73] | | Hyrule Field still / walk / turn | 90.2 [89,91] / 88.6 [87,90] / 88.5 [86,91] | 80.3 [76,84] / 82.3 [86,79] / 83.5 [85,82] | | Market still / walk / turn | 75.7 [74,77] / 73.6 [71,77] / 88.8 [85,93] | 71.9 [75,69] / 69.9 [73,67] / 86.2 [90,82] | So the long spin is the default on Intel CPUs only; on this PC the PR now runs main's adaptive spin. ### Flags and settings `RX_VK_RECORDER_SPIN_US`'s default changes, and its 0 now means the old adaptive spin. | Flag | What it is | Before this PR | After this PR | Effect | Helps / doesn't help / untested | Recommendation | |---|---|---|---|---|---|---| | `RX_VK_RECORDER_SPIN_US` | how long the recorder thread spins with nothing to run before it sleeps | unset: adaptive 20-200 us; `0` read as 1 us | unset: 5000 us on an Intel CPU, adaptive 20-200 us on others; `0`: adaptive | the recorder sleeps about once a frame instead of many times | helps on an i7-9700K (Linux); untested on Windows and on Ryzen | 5000 us for everyone, pending the Test Farm | ## Testing **Tested:** in the game on Linux, RX 580, Mesa RADV 26.2.6, i7-9700K: Kokiri Forest, Hyrule Field and the Market, standing and turning, three runs each against main as in Measurements; the log names the 5000 us spin; no device lost, nothing looked wrong in the end-of-run screenshots. Game-free: `tests/run_all.py --changed` on that PC: `test_recorder_sync.py`, `test_recorder_own_idle.py`, `test_threaded_rendering.py` and the rest pass; `test_dev_packs.py` ("a game patch shows in the objects") and `test_switch_table.py` (switches read in host/ and vk_replay.cpp with no row) fail the same way on main there. `test_tested_configurations.py` passes with the six files. **Not tested:** Windows, where the scheduler and the power plan are not Linux's; AMD Ryzen CPUs, whose cores have clocks of their own (Auto's tiers were measured on one); laptops on battery. **Must be tested:** - Windows, any GPU, a CPU of 6 or more cores (Threaded rendering Auto): the Market, standing and turning, this PR against main, expecting fps no lower and frames over 50 ms no more (Test Farm: @Beanstalk windows) - Linux, a Ryzen CPU of 6 or more cores: the same, expecting no loss (Test Farm: @Beanstalk linux amd) ## Risks **What could break:** nothing in what is drawn: only how long the recorder thread waits before it sleeps. A PC could use a little more power, and with more threads than cores the spinning recorder could take time from a game thread (here the scheduler's counters show the game's threads waiting less for a core, not more). **Turning it off:** `RX_VK_RECORDER_SPIN_US=0` gives main's adaptive spin; `RX_VK_RECORDER=off` turns the recorder thread off. **Compatibility:** Nothing changes: no cache, option or save is touched. ## Checklist ### Everyone - [x] One topic. - [x] The title is a Conventional Commit (`type(scope): description`) of the status line's type. - [x] Why gives the reason plainly and links the issues that fit (the tracker searched). - [x] Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what can't be run by hand is in Testing's Not testable by hand, with why. - [x] Measurements has a verdict, or one line saying why there is nothing to measure. - [x] Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and in Risks. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`. - [x] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). - [x] No game files, dumps, build output or generated files. - [x] `third_party/` untouched (a new folder with a `PROVENANCE.md` instead). - [x] The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled. ### When it applies - [x] AI assistance recorded with `Assisted-by:` / `Co-Authored-By:` trailers. - [x] Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported. - [x] Switches documented (docs/development.md; the README for a menu row) and shipped at their recommended value. - [x] A file in `docs/tested/` for each new measured run (format in `docs/tested-configurations.md`). - [x] Docs updated. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_016o1k1NeAdSovkHa9ukS7YM
With nothing to run, the recorder thread spun an adaptive 20-200 us and
then slept, many times a frame. On an i7-9700K (RX 580, RADV, Linux's
powersave governor) those short sleeps let the CPU's own clock control
lower every core's clock to 1.1-3.1 GHz, against 4.4-4.6 with a spin
that lasts through the frame's recording gaps, and the game's threads
took about 2.5 times their CPU time a frame. A 5 ms spin is now the
default (RX_VK_RECORDER_SPIN_US=0 gives the adaptive spin back): the
recorder sleeps about once a frame, in the frame wait.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1NeAdSovkHa9ukS7YM
docs(tested): the recorder thread's 5 ms spin against main on an i7-9700K with an RX 580, three runs each
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 12s
Website / Website on Cloudflare (pull_request_target) Has been skipped
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 18s
CI / Workflow lint (actionlint) (pull_request) Successful in 21s
Third-party parts / As their notes say (pull_request) Successful in 21s
PR description / Description follows the template (pull_request_target) Successful in 8s
beanstalk/windows 0/1 pass, 0 running, 0 queued
beanstalk/linux+amd+cpu-ryzen-* 0/1 pass, 0 running, 0 queued
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/linux+amd 0/1 pass, 2 running, 0 queued
beanstalk/linux+nvidia 0/1 pass, 2 running, 0 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
e855d37ac9
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1NeAdSovkHa9ukS7YM
Author
Owner

Tested in game: Linux (CachyOS, kernel 7.3.3), RX 580, Mesa RADV 26.2.6, i7-9700K, 1080p native, no upscaler or frame generation: Kokiri Forest, Hyrule Field and the Market, standing and turning, three interleaved runs each against main. 15.4 -> 48.1 fps standing in Kokiri Forest, 28.2 -> 43.8 turning in the Market, frames over 50 ms 279 -> 14 there; the CPU's clock 4.4-4.6 GHz instead of 0.8-3.1. No device lost, nothing wrong on screen.

Tested in game: Linux (CachyOS, kernel 7.3.3), RX 580, Mesa RADV 26.2.6, i7-9700K, 1080p native, no upscaler or frame generation: Kokiri Forest, Hyrule Field and the Market, standing and turning, three interleaved runs each against main. 15.4 -> 48.1 fps standing in Kokiri Forest, 28.2 -> 43.8 turning in the Market, frames over 50 ms 279 -> 14 there; the CPU's clock 4.4-4.6 GHz instead of 0.8-3.1. No device lost, nothing wrong on screen.
Author
Owner

@Beanstalk windows: on a PC with a CPU of 6 or more cores (Threaded rendering on Auto, so the recorder thread is on), compare this PR against main in the Market, standing still and turning the camera. Expect fps no lower and no more frames over 50 ms than main. Also, if available, the same on Linux with an AMD Ryzen CPU of 6 or more cores (linux, amd).

@Beanstalk windows: on a PC with a CPU of 6 or more cores (Threaded rendering on Auto, so the recorder thread is on), compare this PR against main in the Market, standing still and turning the camera. Expect fps no lower and no more frames over 50 ms than main. Also, if available, the same on Linux with an AMD Ryzen CPU of 6 or more cores (linux, amd).
Member
Beanstalk test farm · an earlier run: commit e855d37 (the newer results are in a comment below)

Commit e855d37 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

On Windows and Linux AMD Ryzen targets, the plan compares main and the PR in the Market, with Threaded rendering left on Auto and the recorder thread verified in the log. It measures FPS and frames over 50 ms while standing still and after a scripted camera turn, and compares Market screenshots. Each target takes about 21 minutes; lower FPS, more hitches, a crash, or a substantial screenshot difference fails the PR. The farm cannot measure during the scripted stick input or filter targets by core count, so the log check verifies that Auto enabled the recorder.

  • Where: windows (1-2 reports), linux+amd+cpu-ryzen-* (CPU "ryzen *", 1-2 reports).
  • market-recorder: from the repository's save kokiri-start, then teleport to Market, measure standing for 15 s (after 10 s warm-up), take the picture market-standing to compare with main, move the stick, measure after-turn for 20 s (after 0 s warm-up), take the picture market-after-turn to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, memory and CPU time.
  • The PR fails if: it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 10%; or hitches over 50 ms is more than 0% above main.
  • Time: about 23 min of game runs per tester (4 game starts), plus the two builds.

Started at 14:58 UTC.

Estimate: done in about 50 min, from the queue and the testers online now; some jobs can't start yet.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 1/1 1 none — — running
linux+amd+cpu-ryzen-* 0/1 — — — running

Measurements · windows

Verdict: running on windows (1/1 report).

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM
Scene: market-recorder, from the repository's save kokiri-start; each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); market-recorder: 2 game starts a side, standing 15 s after 10 s warm-up, after-turn 20 s after 0 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Nothing was measured: no metric came back.

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** running on windows (1/1 report).

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`  
Scene: market-recorder, from the repository's save kokiri-start; each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); market-recorder: 2 game starts a side, standing 15 s after 10 s warm-up, after-turn 20 s after 0 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

Nothing was measured: no metric came back.

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>e855d37</code> (the newer results are in a comment below)</summary> Commit `e855d37` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1745) **What will be tested** · AI plan (`gpt-6.1-terra`) On Windows and Linux AMD Ryzen targets, the plan compares main and the PR in the Market, with Threaded rendering left on Auto and the recorder thread verified in the log. It measures FPS and frames over 50 ms while standing still and after a scripted camera turn, and compares Market screenshots. Each target takes about 21 minutes; lower FPS, more hitches, a crash, or a substantial screenshot difference fails the PR. The farm cannot measure during the scripted stick input or filter targets by core count, so the log check verifies that Auto enabled the recorder. - **Where:** windows (1-2 reports), linux+amd+cpu-ryzen-* (CPU "ryzen *", 1-2 reports). - **market-recorder:** from the repository's save `kokiri-start`, then teleport to Market, measure standing for 15 s (after 10 s warm-up), take the picture market-standing to compare with main, move the stick, measure after-turn for 20 s (after 0 s warm-up), take the picture market-after-turn to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, memory and CPU time. - **The PR fails if:** it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 10%; or hitches over 50 ms is more than 0% above main. - **Time:** about 23 min of game runs per tester (4 game starts), plus the two builds. Started at 14:58 UTC. **Estimate:** done in about 50 min, from the queue and the testers online now; some jobs can't start yet. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_4a0a8ec6755f62f8) | none | — | — | running | | linux+amd+cpu-ryzen-* | 0/1 | — | — | — | running | #### Measurements · windows **Verdict:** running on windows (1/1 report). Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM` Scene: market-recorder, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); market-recorder: 2 game starts a side, standing 15 s after 10 s warm-up, after-turn 20 s after 0 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** running on windows (1/1 report). Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM` Scene: market-recorder, from the repository's save kokiri-start; each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); market-recorder: 2 game starts a side, standing 15 s after 10 s warm-up, after-turn 20 s after 0 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> </details>
HumanBean changed title from WIP: perf(vk): the recorder thread spins 5 ms before it sleeps, which keeps an Intel CPU's clock up to perf(vk): the recorder thread spins 5 ms before it sleeps, which keeps an Intel CPU's clock up 2026-11-19 14:57:38 +00:00
Member

Possibly related, for context:

  • PR #389 docs(tested): the recorder thread in the Market while moving, interleaved off and on — Open recorder-thread Market measurements; relevant context, not overlapping code.
  • PR #753 docs(tested): RX_VK_WB_MAX_KB=1024 and RX_VK_RECORDER_OWN=1 measured on an RX 9070 XT with a Ryzen 9 7900X — Open recorder behavior measurements on Ryzen; informs cross-CPU impact.
  • issue #402 Deck: the frame is CPU-bound in the submission path, not GPU-bound (16 fps at 50% internal, GPU-bound wait 0.4 ms) — Open CPU-side rendering performance discussion; related symptom, but different Deck bottleneck.
Possibly related, for context: - PR #389 docs(tested): the recorder thread in the Market while moving, interleaved off and on — Open recorder-thread Market measurements; relevant context, not overlapping code. - PR #753 docs(tested): RX_VK_WB_MAX_KB=1024 and RX_VK_RECORDER_OWN=1 measured on an RX 9070 XT with a Ryzen 9 7900X — Open recorder behavior measurements on Ryzen; informs cross-CPU impact. - issue #402 Deck: the frame is CPU-bound in the submission path, not GPU-bound (16 fps at 50% internal, GPU-bound wait 0.4 ms) — Open CPU-side rendering performance discussion; related symptom, but different Deck bottleneck.
Author
Owner

@Beanstalk please test this PR against main on Linux PCs whose CPU has 6 or more cores (Threaded rendering's Auto turns the recorder thread on there): linux+amd, linux+nvidia, linux+intel. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the kokiri-start save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side. Expect fps no lower than main and fewer frames over 50 ms; the log should show spin 5000 us (PR) against spin adaptive 20-200 us (main) in the RX_VK_RECORDER=thread line. Windows waits for #1729 (main doesn't build on Windows until it merges).

@Beanstalk please test this PR against main on Linux PCs whose CPU has 6 or more cores (Threaded rendering's Auto turns the recorder thread on there): linux+amd, linux+nvidia, linux+intel. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the `kokiri-start` save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side. Expect fps no lower than main and fewer frames over 50 ms; the log should show `spin 5000 us` (PR) against `spin adaptive 20-200 us` (main) in the `RX_VK_RECORDER=thread` line. Windows waits for #1729 (main doesn't build on Windows until it merges).
Member
Beanstalk test farm · an earlier run: commit e855d37, run 2 (the newer results are in a comment below)

Commit e855d37 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Linux AMD, NVIDIA and Intel GPU targets will compare the PR with main over two starts per side, using the Kokiri save and visiting Kokiri Forest, Hyrule Field and Market; the Intel target waits for a matching tester. Each visit measures 15 seconds standing, turns the camera, then measures another 10 seconds; the farm cannot measure concurrently with the stick input. The run takes roughly 25 minutes per tester, with V-Sync off and the frame rate uncapped. Crashes, lower FPS, increased over-50-ms hitch counts, visual differences or a missing PR spin log fail the plan; the recorder Auto log also gates both sides. CPU core count cannot be selected directly, but the Auto log requires the recorder thread to be active. No tester online now matches linux+intel: that target waits for one.

  • Where: linux+amd (1-2 reports), linux+nvidia (1-2 reports), linux+intel (1-2 reports).
  • recorder-scenes: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 10 s warm-up), move the stick, measure forest-after-turn for 10 s (after 0 s warm-up), take the picture forest to compare with main, teleport to Hyrule Field, measure field-standing for 15 s (after 10 s warm-up), measure field-after-turn for 10 s (after 0 s warm-up), take the picture field to compare with main, teleport to Market, measure market-standing for 15 s (after 10 s warm-up), measure market-after-turn for 10 s (after 0 s warm-up), take the picture market to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 5%; or hitches over 50 ms is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0.
  • Time: about 27 min of game runs per tester (4 game starts), plus the two builds.

Started at 15:03 UTC. Run 2: re-planned by HumanBean.

Estimate: done in about 55 min, from the queue and the testers online now; some jobs can't start yet.

⚠ No tester has a PC for linux+intel (none seen in 14 days): it waits until one signs in.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
linux+amd 0/1 — — — running
linux+nvidia 0/1 — — — running
linux+intel 0/1 — — — queued
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>e855d37</code>, run 2 (the newer results are in a comment below)</summary> Commit `e855d37` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1745) **What will be tested** · AI plan (`gpt-6.1-terra`) Linux AMD, NVIDIA and Intel GPU targets will compare the PR with main over two starts per side, using the Kokiri save and visiting Kokiri Forest, Hyrule Field and Market; the Intel target waits for a matching tester. Each visit measures 15 seconds standing, turns the camera, then measures another 10 seconds; the farm cannot measure concurrently with the stick input. The run takes roughly 25 minutes per tester, with V-Sync off and the frame rate uncapped. Crashes, lower FPS, increased over-50-ms hitch counts, visual differences or a missing PR spin log fail the plan; the recorder Auto log also gates both sides. CPU core count cannot be selected directly, but the Auto log requires the recorder thread to be active. No tester online now matches linux+intel: that target waits for one. - **Where:** linux+amd (1-2 reports), linux+nvidia (1-2 reports), linux+intel (1-2 reports). - **recorder-scenes:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 10 s warm-up), move the stick, measure forest-after-turn for 10 s (after 0 s warm-up), take the picture forest to compare with main, teleport to Hyrule Field, measure field-standing for 15 s (after 10 s warm-up), measure field-after-turn for 10 s (after 0 s warm-up), take the picture field to compare with main, teleport to Market, measure market-standing for 15 s (after 10 s warm-up), measure market-after-turn for 10 s (after 0 s warm-up), take the picture market to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 5%; or hitches over 50 ms is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0. - **Time:** about 27 min of game runs per tester (4 game starts), plus the two builds. Started at 15:03 UTC. Run 2: re-planned by HumanBean. **Estimate:** done in about 55 min, from the queue and the testers online now; some jobs can't start yet. ⚠ No tester has a PC for `linux+intel` (none seen in 14 days): it waits until one signs in. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | linux+amd | 0/1 | — | — | — | running | | linux+nvidia | 0/1 | — | — | — | running | | linux+intel | 0/1 | — | — | — | queued | </details>
HumanBean force-pushed perf/recorder-spin from e855d37ac9
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 12s
Website / Website on Cloudflare (pull_request_target) Has been skipped
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 18s
CI / Workflow lint (actionlint) (pull_request) Successful in 21s
Third-party parts / As their notes say (pull_request) Successful in 21s
PR description / Description follows the template (pull_request_target) Successful in 8s
beanstalk/windows 0/1 pass, 0 running, 0 queued
beanstalk/linux+amd+cpu-ryzen-* 0/1 pass, 0 running, 0 queued
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/linux+amd 0/1 pass, 2 running, 0 queued
beanstalk/linux+nvidia 0/1 pass, 2 running, 0 queued
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
to bd4df97921
Some checks failed
PR description / Description follows the template (pull_request_target) Successful in 9s
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 9s
CI / Workflow lint (actionlint) (pull_request) Successful in 11s
Third-party parts / As their notes say (pull_request) Successful in 10s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/linux+intel 0/1 pass, 0 running, 2 queued
beanstalk/linux+cpu-ryzen-* 2/1 fail
beanstalk/windows+amd 0/1 pass, 0 running, 1 queued
beanstalk/windows+nvidia 1/1 fail
beanstalk/windows+intel 0/1 pass, 0 running, 2 queued
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/linux+amd 2/1 fail
beanstalk/linux+nvidia 1/1 fail
2026-11-19 15:04:38 +00:00
Compare
Member
Beanstalk test farm · an earlier run: commit bd4df97 (the newer results are in a comment below)

Commit bd4df97 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Two starts per side compare the PR with main from the Kokiri save through Kokiri Forest, Hyrule Field and Market, with uncapped frame rate and V-Sync off. Each scene measures 15 seconds standing and then turns the camera for 600 frames; the plan cannot time or separately measure the turn while applying stick input. FPS, standing hitches, whole-run hitches, screenshots and the PR’s recorder log are checked; a crash, lower standing FPS, more hitches, a materially different image or a missing 5000 us recorder line fails the PR. The six OS/GPU targets and an additional Linux Ryzen target are requested; Intel GPU targets may wait for a matching tester. The schema cannot filter by CPU core count, so the recorder log verifies that the changed path is active rather than enforcing the requested six-core minimum; each tester’s game runs take roughly 23 minutes plus camera-turn time. No tester online now matches linux+intel, windows+intel: those targets wait for one.

  • Where: linux+amd (1-2 reports), linux+nvidia (1-2 reports), linux+intel (1-2 reports), linux+cpu-ryzen-* (CPU "ryzen *", 1-2 reports), windows+amd (1-2 reports), windows+nvidia (1-2 reports), windows+intel (1-2 reports).
  • three-scenes: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 10 s warm-up), take the picture forest to compare with main, move the stick, teleport to Hyrule Field, measure field-standing for 15 s (after 10 s warm-up), take the picture field to compare with main, teleport to Market, measure market-standing for 15 s (after 10 s warm-up), take the picture market to compare with main; 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 5%; or hitches over 50 ms is more than 0% above main; or hitches over 50 ms in the whole run is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0.
  • Time: about 25 min of game runs per tester (4 game starts), plus the two builds.

Started at 15:05 UTC.

Estimate: done in about 35 min, from the queue and the testers online now; some jobs can't start yet.

⚠ No tester has a PC for linux+intel (none seen in 14 days): it waits until one signs in.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
linux+amd · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7; 2: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 2/1 1 2 none 33.8 vs 39.1 (−14%) — fail ⚠ outlier
linux+nvidia · 1: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4070, 615.71.9 1/1 1 none 13.7 vs 12.4 (+10%) — fail
linux+intel 0/1 — — — queued
linux+cpu-ryzen-* · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7; 2: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 5070, 620.70.6 2/1 1 2 none 12.0 vs 12.6 (−5%) — fail ⚠ outlier
windows+amd · 1: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 1/1 1 none — — queued
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 2/1 1 2 none 15.0 vs 15.1 (−1%) — fail
windows+intel 0/1 — — — queued

Measurements · linux+amd

Verdict: fail on linux+amd (2/1 report): three-scenes forest-standing.fps_mean.min_delta_pct (+0.0%); three-scenes field-standing.fps_mean.min_delta_pct (-5.1%); three-scenes screenshot.max_diff failed.

Hardware: 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM; 2: linux+amd+radv+igpu+handheld AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99 AMD Custom APU 0405, 12 GB RAM
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ bd4df97
three-scenes · field-standing · frame rate 63.5 60.9 (−4%)
three-scenes · forest-standing · frame rate 52.6 52.1 (−1%)
three-scenes · market-standing · frame rate 11.4 13.5 (+18%)
three-scenes · field-standing · hitches over 50 ms 89.5 96.0 (+7%)
three-scenes · forest-standing · hitches over 50 ms 5.0 36.8 (+635%)
three-scenes · market-standing · hitches over 50 ms 114.5 119.2 (+4%)
three-scenes · hitches over 50 ms in the whole run 836.8 807.5 (−3%)
three-scenes · forbidden log lines 0.0 0.0
three-scenes · expected log lines missing 1.0 0.5 (−50%)
three-scenes · field-standing · frame time (p99) (ms) 39.1 33.8 (−14%)
three-scenes · forest-standing · frame time (p99) (ms) 32.9 33.6 (+2%)
three-scenes · market-standing · frame time (p99) (ms) 561.7 544.7 (−3%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on linux+amd (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (+0.0%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-5.1%)`; `three-scenes screenshot.max_diff` failed.

Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM`  
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ bd4df97 |
|---|---|---|
| three-scenes · field-standing · frame rate | 63.5 | 60.9 (−4%) |
| three-scenes · forest-standing · frame rate | 52.6 | 52.1 (−1%) |
| three-scenes · market-standing · frame rate | 11.4 | 13.5 (+18%) |
| three-scenes · field-standing · hitches over 50 ms | 89.5 | 96.0 (+7%) |
| three-scenes · forest-standing · hitches over 50 ms | 5.0 | 36.8 (+635%) |
| three-scenes · market-standing · hitches over 50 ms | 114.5 | 119.2 (+4%) |
| three-scenes · hitches over 50 ms in the whole run | 836.8 | 807.5 (−3%) |
| three-scenes · forbidden log lines | 0.0 | 0.0 |
| three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) |
| three-scenes · field-standing · frame time (p99) (ms) | 39.1 | 33.8 (−14%) |
| three-scenes · forest-standing · frame time (p99) (ms) | 32.9 | 33.6 (+2%) |
| three-scenes · market-standing · frame time (p99) (ms) | 561.7 | 544.7 (−3%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · linux+nvidia

Verdict: fail on linux+nvidia (1/1 report): three-scenes field-standing.fps_mean.min_delta_pct (-2.5%); three-scenes screenshot.max_diff; three-scenes market-standing.hitch_count.max_delta_pct failed.

Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4070, 615.71.9 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ bd4df97
three-scenes · field-standing · frame rate 104.9 102.3 (−3%)
three-scenes · forest-standing · frame rate 101.7 105.4 (+4%)
three-scenes · market-standing · frame rate 75.2 79.9 (+6%)
three-scenes · field-standing · hitches over 50 ms 0.0 0.0
three-scenes · forest-standing · hitches over 50 ms 0.0 0.0
three-scenes · market-standing · hitches over 50 ms 0.0 1.0
three-scenes · hitches over 50 ms in the whole run 28.5 32.5 (+14%)
three-scenes · forbidden log lines 0.0 0.0
three-scenes · expected log lines missing 1.0 0.0 (−100%)
three-scenes · field-standing · frame time (p99) (ms) 12.4 13.7 (+10%)
three-scenes · forest-standing · frame time (p99) (ms) 13.0 13.2 (+2%)
three-scenes · market-standing · frame time (p99) (ms) 21.1 19.8 (−6%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on linux+nvidia (1/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-2.5%)`; `three-scenes screenshot.max_diff`; `three-scenes market-standing.hitch_count.max_delta_pct` failed.

Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070, 615.71.9` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`  
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ bd4df97 |
|---|---|---|
| three-scenes · field-standing · frame rate | 104.9 | 102.3 (−3%) |
| three-scenes · forest-standing · frame rate | 101.7 | 105.4 (+4%) |
| three-scenes · market-standing · frame rate | 75.2 | 79.9 (+6%) |
| three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · market-standing · hitches over 50 ms | 0.0 | 1.0 |
| three-scenes · hitches over 50 ms in the whole run | 28.5 | 32.5 (+14%) |
| three-scenes · forbidden log lines | 0.0 | 0.0 |
| three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) |
| three-scenes · field-standing · frame time (p99) (ms) | 12.4 | 13.7 (+10%) |
| three-scenes · forest-standing · frame time (p99) (ms) | 13.0 | 13.2 (+2%) |
| three-scenes · market-standing · frame time (p99) (ms) | 21.1 | 19.8 (−6%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · linux+cpu-ryzen-*

Verdict: fail on linux+cpu-ryzen-* (2/1 report): three-scenes forest-standing.fps_mean.min_delta_pct (-0.1%); three-scenes field-standing.fps_mean.min_delta_pct (-1.3%); three-scenes market-standing.hitch_count.max_delta_pct (+3.7%) failed.

Hardware: 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM; 2: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 5070, 620.70.6 AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ bd4df97
three-scenes · field-standing · frame rate 102.6 102.3 (−0%)
three-scenes · forest-standing · frame rate 89.2 89.8 (+1%)
three-scenes · market-standing · frame rate 43.3 44.6 (+3%)
three-scenes · field-standing · hitches over 50 ms 0.5 0.5 (+0%)
three-scenes · forest-standing · hitches over 50 ms 0.0 0.0
three-scenes · market-standing · hitches over 50 ms 6.8 7.0 (+4%)
three-scenes · hitches over 50 ms in the whole run 47.2 45.2 (−4%)
three-scenes · forbidden log lines 0.0 0.0
three-scenes · expected log lines missing 1.0 0.5 (−50%)
three-scenes · field-standing · frame time (p99) (ms) 12.6 12.0 (−5%)
three-scenes · forest-standing · frame time (p99) (ms) 14.8 14.6 (−2%)
three-scenes · market-standing · frame time (p99) (ms) 514.5 513.6 (−0%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on linux+cpu-ryzen-* (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (-0.1%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-1.3%)`; `three-scenes market-standing.hitch_count.max_delta_pct (+3.7%)` failed.

Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM`  
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ bd4df97 |
|---|---|---|
| three-scenes · field-standing · frame rate | 102.6 | 102.3 (−0%) |
| three-scenes · forest-standing · frame rate | 89.2 | 89.8 (+1%) |
| three-scenes · market-standing · frame rate | 43.3 | 44.6 (+3%) |
| three-scenes · field-standing · hitches over 50 ms | 0.5 | 0.5 (+0%) |
| three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · market-standing · hitches over 50 ms | 6.8 | 7.0 (+4%) |
| three-scenes · hitches over 50 ms in the whole run | 47.2 | 45.2 (−4%) |
| three-scenes · forbidden log lines | 0.0 | 0.0 |
| three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) |
| three-scenes · field-standing · frame time (p99) (ms) | 12.6 | 12.0 (−5%) |
| three-scenes · forest-standing · frame time (p99) (ms) | 14.8 | 14.6 (−2%) |
| three-scenes · market-standing · frame time (p99) (ms) | 514.5 | 513.6 (−0%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · windows+amd

Verdict: queued on windows+amd (1/1 report).

Hardware: 1: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Nothing was measured: no metric came back.

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** queued on windows+amd (1/1 report).

Hardware: 1: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM`  
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

Nothing was measured: no metric came back.

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · windows+nvidia

Verdict: fail on windows+nvidia (2/1 report): three-scenes field-standing.fps_mean.min_delta_pct (-0.6%); three-scenes market-standing.fps_mean.min_delta_pct (-0.7%); three-scenes run_hitch_count.max_delta_pct (+12.2%) failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0 AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3090, 621.24.0 AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ bd4df97
three-scenes · field-standing · frame rate 82.1 81.7 (−1%)
three-scenes · forest-standing · frame rate 78.9 81.0 (+3%)
three-scenes · market-standing · frame rate 63.0 62.6 (−1%)
three-scenes · field-standing · hitches over 50 ms 0.0 0.0
three-scenes · forest-standing · hitches over 50 ms 0.0 0.0
three-scenes · market-standing · hitches over 50 ms 0.0 0.0
three-scenes · hitches over 50 ms in the whole run 20.5 23.0 (+12%)
three-scenes · forbidden log lines 0.0 0.0
three-scenes · expected log lines missing 1.0 0.0 (−100%)
three-scenes · field-standing · frame time (p99) (ms) 15.1 15.0 (−1%)
three-scenes · forest-standing · frame time (p99) (ms) 17.2 15.0 (−13%)
three-scenes · market-standing · frame time (p99) (ms) 21.5 21.3 (−1%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on windows+nvidia (2/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-0.6%)`; `three-scenes market-standing.fps_mean.min_delta_pct (-0.7%)`; `three-scenes run_hitch_count.max_delta_pct (+12.2%)` failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM`  
Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ bd4df97 |
|---|---|---|
| three-scenes · field-standing · frame rate | 82.1 | 81.7 (−1%) |
| three-scenes · forest-standing · frame rate | 78.9 | 81.0 (+3%) |
| three-scenes · market-standing · frame rate | 63.0 | 62.6 (−1%) |
| three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · market-standing · hitches over 50 ms | 0.0 | 0.0 |
| three-scenes · hitches over 50 ms in the whole run | 20.5 | 23.0 (+12%) |
| three-scenes · forbidden log lines | 0.0 | 0.0 |
| three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) |
| three-scenes · field-standing · frame time (p99) (ms) | 15.1 | 15.0 (−1%) |
| three-scenes · forest-standing · frame time (p99) (ms) | 17.2 | 15.0 (−13%) |
| three-scenes · market-standing · frame time (p99) (ms) | 21.5 | 21.3 (−1%) |

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:previous --> <details><summary>Beanstalk test farm · an earlier run: commit <code>bd4df97</code> (the newer results are in a comment below)</summary> Commit `bd4df97` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1745) **What will be tested** · AI plan (`gpt-6.1-terra`) Two starts per side compare the PR with main from the Kokiri save through Kokiri Forest, Hyrule Field and Market, with uncapped frame rate and V-Sync off. Each scene measures 15 seconds standing and then turns the camera for 600 frames; the plan cannot time or separately measure the turn while applying stick input. FPS, standing hitches, whole-run hitches, screenshots and the PR’s recorder log are checked; a crash, lower standing FPS, more hitches, a materially different image or a missing 5000 us recorder line fails the PR. The six OS/GPU targets and an additional Linux Ryzen target are requested; Intel GPU targets may wait for a matching tester. The schema cannot filter by CPU core count, so the recorder log verifies that the changed path is active rather than enforcing the requested six-core minimum; each tester’s game runs take roughly 23 minutes plus camera-turn time. No tester online now matches linux+intel, windows+intel: those targets wait for one. - **Where:** linux+amd (1-2 reports), linux+nvidia (1-2 reports), linux+intel (1-2 reports), linux+cpu-ryzen-* (CPU "ryzen *", 1-2 reports), windows+amd (1-2 reports), windows+nvidia (1-2 reports), windows+intel (1-2 reports). - **three-scenes:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure forest-standing for 15 s (after 10 s warm-up), take the picture forest to compare with main, move the stick, teleport to Hyrule Field, measure field-standing for 15 s (after 10 s warm-up), take the picture field to compare with main, teleport to Market, measure market-standing for 15 s (after 10 s warm-up), take the picture market to compare with main; 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 0% below main; or a picture differs from main by more than 5%; or hitches over 50 ms is more than 0% above main; or hitches over 50 ms in the whole run is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0. - **Time:** about 25 min of game runs per tester (4 game starts), plus the two builds. Started at 15:05 UTC. **Estimate:** done in about 35 min, from the queue and the testers online now; some jobs can't start yet. ⚠ No tester has a PC for `linux+intel` (none seen in 14 days): it waits until one signs in. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | linux+amd · 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_abf028383aacba39) [2](https://beanstalk.magicbean.dev/reports/rp_d072671692b40a29) | none | 33.8 vs 39.1 (−14%) | — | fail ⚠ outlier | | linux+nvidia · 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070, 615.71.9` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_a2dd0e666d132822) | none | 13.7 vs 12.4 (+10%) | — | fail | | linux+intel | 0/1 | — | — | — | queued | | linux+cpu-ryzen-* · 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_0aea16740f59b27f) [2](https://beanstalk.magicbean.dev/reports/rp_70fef5f97c75247a) | none | 12.0 vs 12.6 (−5%) | — | fail ⚠ outlier | | windows+amd · 1: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` | 1/1 [1](https://beanstalk.magicbean.dev/reports/rp_892184c638a55487) | none | — | — | queued | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_0a924842278c9849) [2](https://beanstalk.magicbean.dev/reports/rp_261b1e9d7ad5d411) | none | 15.0 vs 15.1 (−1%) | — | fail | | windows+intel | 0/1 | — | — | — | queued | #### Measurements · linux+amd **Verdict:** fail on linux+amd (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (+0.0%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-5.1%)`; `three-scenes screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 63.5 | 60.9 (−4%) | | three-scenes · forest-standing · frame rate | 52.6 | 52.1 (−1%) | | three-scenes · market-standing · frame rate | 11.4 | 13.5 (+18%) | | three-scenes · field-standing · hitches over 50 ms | 89.5 | 96.0 (+7%) | | three-scenes · forest-standing · hitches over 50 ms | 5.0 | 36.8 (+635%) | | three-scenes · market-standing · hitches over 50 ms | 114.5 | 119.2 (+4%) | | three-scenes · hitches over 50 ms in the whole run | 836.8 | 807.5 (−3%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) | | three-scenes · field-standing · frame time (p99) (ms) | 39.1 | 33.8 (−14%) | | three-scenes · forest-standing · frame time (p99) (ms) | 32.9 | 33.6 (+2%) | | three-scenes · market-standing · frame time (p99) (ms) | 561.7 | 544.7 (−3%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+amd (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (+0.0%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-5.1%)`; `three-scenes screenshot.max_diff` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+igpu+handheld `AMD Custom GPU 0405 (RADV VANGOGH), 26.1.99` `AMD Custom APU 0405, 12 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 63.5 | 60.9 (−4%) | | three-scenes · forest-standing · frame rate | 52.6 | 52.1 (−1%) | | three-scenes · market-standing · frame rate | 11.4 | 13.5 (+18%) | | three-scenes · field-standing · hitches over 50 ms | 89.5 | 96.0 (+7%) | | three-scenes · forest-standing · hitches over 50 ms | 5.0 | 36.8 (+635%) | | three-scenes · market-standing · hitches over 50 ms | 114.5 | 119.2 (+4%) | | three-scenes · hitches over 50 ms in the whole run | 836.8 | 807.5 (−3%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) | | three-scenes · field-standing · frame time (p99) (ms) | 39.1 | 33.8 (−14%) | | three-scenes · forest-standing · frame time (p99) (ms) | 32.9 | 33.6 (+2%) | | three-scenes · market-standing · frame time (p99) (ms) | 561.7 | 544.7 (−3%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · linux+nvidia **Verdict:** fail on linux+nvidia (1/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-2.5%)`; `three-scenes screenshot.max_diff`; `three-scenes market-standing.hitch_count.max_delta_pct` failed. Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070, 615.71.9` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 104.9 | 102.3 (−3%) | | three-scenes · forest-standing · frame rate | 101.7 | 105.4 (+4%) | | three-scenes · market-standing · frame rate | 75.2 | 79.9 (+6%) | | three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 0.0 | 1.0 | | three-scenes · hitches over 50 ms in the whole run | 28.5 | 32.5 (+14%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) | | three-scenes · field-standing · frame time (p99) (ms) | 12.4 | 13.7 (+10%) | | three-scenes · forest-standing · frame time (p99) (ms) | 13.0 | 13.2 (+2%) | | three-scenes · market-standing · frame time (p99) (ms) | 21.1 | 19.8 (−6%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+nvidia (1/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-2.5%)`; `three-scenes screenshot.max_diff`; `three-scenes market-standing.hitch_count.max_delta_pct` failed. Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070, 615.71.9` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 104.9 | 102.3 (−3%) | | three-scenes · forest-standing · frame rate | 101.7 | 105.4 (+4%) | | three-scenes · market-standing · frame rate | 75.2 | 79.9 (+6%) | | three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 0.0 | 1.0 | | three-scenes · hitches over 50 ms in the whole run | 28.5 | 32.5 (+14%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) | | three-scenes · field-standing · frame time (p99) (ms) | 12.4 | 13.7 (+10%) | | three-scenes · forest-standing · frame time (p99) (ms) | 13.0 | 13.2 (+2%) | | three-scenes · market-standing · frame time (p99) (ms) | 21.1 | 19.8 (−6%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · linux+cpu-ryzen-* **Verdict:** fail on linux+cpu-ryzen-* (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (-0.1%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-1.3%)`; `three-scenes market-standing.hitch_count.max_delta_pct (+3.7%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 102.6 | 102.3 (−0%) | | three-scenes · forest-standing · frame rate | 89.2 | 89.8 (+1%) | | three-scenes · market-standing · frame rate | 43.3 | 44.6 (+3%) | | three-scenes · field-standing · hitches over 50 ms | 0.5 | 0.5 (+0%) | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 6.8 | 7.0 (+4%) | | three-scenes · hitches over 50 ms in the whole run | 47.2 | 45.2 (−4%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) | | three-scenes · field-standing · frame time (p99) (ms) | 12.6 | 12.0 (−5%) | | three-scenes · forest-standing · frame time (p99) (ms) | 14.8 | 14.6 (−2%) | | three-scenes · market-standing · frame time (p99) (ms) | 514.5 | 513.6 (−0%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+cpu-ryzen-* (2/1 report): `three-scenes forest-standing.fps_mean.min_delta_pct (-0.1%)`; `three-scenes field-standing.fps_mean.min_delta_pct (-1.3%)`; `three-scenes market-standing.hitch_count.max_delta_pct (+3.7%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 102.6 | 102.3 (−0%) | | three-scenes · forest-standing · frame rate | 89.2 | 89.8 (+1%) | | three-scenes · market-standing · frame rate | 43.3 | 44.6 (+3%) | | three-scenes · field-standing · hitches over 50 ms | 0.5 | 0.5 (+0%) | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 6.8 | 7.0 (+4%) | | three-scenes · hitches over 50 ms in the whole run | 47.2 | 45.2 (−4%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.5 (−50%) | | three-scenes · field-standing · frame time (p99) (ms) | 12.6 | 12.0 (−5%) | | three-scenes · forest-standing · frame time (p99) (ms) | 14.8 | 14.6 (−2%) | | three-scenes · market-standing · frame time (p99) (ms) | 514.5 | 513.6 (−0%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · windows+amd **Verdict:** queued on windows+amd (1/1 report). Hardware: 1: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** queued on windows+amd (1/1 report). Hardware: 1: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 1 report How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) Nothing was measured: no metric came back. ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · windows+nvidia **Verdict:** fail on windows+nvidia (2/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-0.6%)`; `three-scenes market-standing.fps_mean.min_delta_pct (-0.7%)`; `three-scenes run_hitch_count.max_delta_pct (+12.2%)` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 82.1 | 81.7 (−1%) | | three-scenes · forest-standing · frame rate | 78.9 | 81.0 (+3%) | | three-scenes · market-standing · frame rate | 63.0 | 62.6 (−1%) | | three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · hitches over 50 ms in the whole run | 20.5 | 23.0 (+12%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) | | three-scenes · field-standing · frame time (p99) (ms) | 15.1 | 15.0 (−1%) | | three-scenes · forest-standing · frame time (p99) (ms) | 17.2 | 15.0 (−13%) | | three-scenes · market-standing · frame time (p99) (ms) | 21.5 | 21.3 (−1%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+nvidia (2/1 report): `three-scenes field-standing.fps_mean.min_delta_pct (-0.6%)`; `three-scenes market-standing.fps_mean.min_delta_pct (-0.7%)`; `three-scenes run_hitch_count.max_delta_pct (+12.2%)` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3050 Ti Laptop GPU, 621.24.0` `AMD Ryzen 7 5800H with Radeon Graphics, 16 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3090, 621.24.0` `AMD Ryzen 9 5900X 12-Core Processor, 128 GB RAM` Scene: three-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); three-scenes: 2 game starts a side, forest-standing 15 s after 10 s warm-up, field-standing 15 s after 10 s warm-up, market-standing 15 s after 10 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ bd4df97 | |---|---|---| | three-scenes · field-standing · frame rate | 82.1 | 81.7 (−1%) | | three-scenes · forest-standing · frame rate | 78.9 | 81.0 (+3%) | | three-scenes · market-standing · frame rate | 63.0 | 62.6 (−1%) | | three-scenes · field-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · forest-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · market-standing · hitches over 50 ms | 0.0 | 0.0 | | three-scenes · hitches over 50 ms in the whole run | 20.5 | 23.0 (+12%) | | three-scenes · forbidden log lines | 0.0 | 0.0 | | three-scenes · expected log lines missing | 1.0 | 0.0 (−100%) | | three-scenes · field-standing · frame time (p99) (ms) | 15.1 | 15.0 (−1%) | | three-scenes · forest-standing · frame time (p99) (ms) | 17.2 | 15.0 (−13%) | | three-scenes · market-standing · frame time (p99) (ms) | 21.5 | 21.3 (−1%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> </details>
Author
Owner

@Beanstalk #1729 is merged and this PR is rebased on it, so Windows builds again. Please add Windows to the test: windows+amd, windows+nvidia and windows+intel PCs whose CPU has 6 or more cores (Threaded rendering's Auto turns the recorder thread on there), as well as the Linux targets asked for above. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the kokiri-start save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side, this PR against main. Expect fps no lower than main and no more frames over 50 ms; the log shows spin 5000 us (PR) against spin adaptive 20-200 us (main) in the RX_VK_RECORDER=thread line.

@Beanstalk #1729 is merged and this PR is rebased on it, so Windows builds again. Please add Windows to the test: windows+amd, windows+nvidia and windows+intel PCs whose CPU has 6 or more cores (Threaded rendering's Auto turns the recorder thread on there), as well as the Linux targets asked for above. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the `kokiri-start` save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side, this PR against main. Expect fps no lower than main and no more frames over 50 ms; the log shows `spin 5000 us` (PR) against `spin adaptive 20-200 us` (main) in the `RX_VK_RECORDER=thread` line.
Author
Owner

Measured on a Ryzen 9 7900X (12 cores, 24 threads, each core its own clock) with an RTX 3090 on CachyOS Linux: main against main with RX_VK_RECORDER_SPIN_US=5000 (the same spin as this PR's default), Threaded rendering Auto (render and recorder threads on), 2560x1440 DLSS Quality, uncapped, Reflex on; a warm-up of each, then 2 timed sessions each, interleaved, on the PC's timing queue. Kokiri Forest, then Hyrule Field and the Market by teleport: 15 s still, 5 s walking, 20 s turning. fps (frames over time from the renderer's vk: N presents lines), the median of the two (each run in brackets):

main (adaptive spin) 5 ms spin
Kokiri still / walk / turn 63.6 [59,69] / 70.7 [68,73] / 70.5 [67,74] 66.8 [64,69] / 71.1 [67,75] / 70.9 [69,73]
Hyrule Field still / walk / turn 90.2 [89,91] / 88.6 [87,90] / 88.5 [86,91] 80.3 [76,84] / 82.3 [86,79] / 83.5 [85,82]
Market still / walk / turn 75.7 [74,77] / 73.6 [71,77] / 88.8 [85,93] 71.9 [75,69] / 69.9 [73,67] / 86.2 [90,82]
p99 (ms), Field still / Market walk 14.2 / 20.6 18.4 / 24.0
frames over 50 ms, whole session 24.0 25.5

So the 5 ms spin costs 6-11% in Hyrule Field and 3-5% in the Market on this CPU, with a higher p99; Kokiri Forest is about even. Here each core sets its own clock, so the short sleeps cost nothing, and a recorder core kept spinning likely shares a physical core with one of the game's threads. As the default for every CPU this would be a loss on Ryzen; suggestion: the 5 ms spin by default only where the cores share one clock (Intel desktop CPUs like the i7-9700K), the adaptive spin elsewhere, until a structural fix (the recorder sleeping at the frame's end rather than after a fixed time, or fewer, larger hand-offs to it) can be measured on both kinds of CPU. The Test Farm runs asked for above will show Windows and other CPUs.

Measured on a Ryzen 9 7900X (12 cores, 24 threads, each core its own clock) with an RTX 3090 on CachyOS Linux: main against main with `RX_VK_RECORDER_SPIN_US=5000` (the same spin as this PR's default), Threaded rendering Auto (render and recorder threads on), 2560x1440 DLSS Quality, uncapped, Reflex on; a warm-up of each, then 2 timed sessions each, interleaved, on the PC's timing queue. Kokiri Forest, then Hyrule Field and the Market by teleport: 15 s still, 5 s walking, 20 s turning. fps (frames over time from the renderer's `vk: N presents` lines), the median of the two (each run in brackets): | | main (adaptive spin) | 5 ms spin | |---|---|---| | Kokiri still / walk / turn | 63.6 [59,69] / 70.7 [68,73] / 70.5 [67,74] | 66.8 [64,69] / 71.1 [67,75] / 70.9 [69,73] | | Hyrule Field still / walk / turn | 90.2 [89,91] / 88.6 [87,90] / 88.5 [86,91] | 80.3 [76,84] / 82.3 [86,79] / 83.5 [85,82] | | Market still / walk / turn | 75.7 [74,77] / 73.6 [71,77] / 88.8 [85,93] | 71.9 [75,69] / 69.9 [73,67] / 86.2 [90,82] | | p99 (ms), Field still / Market walk | 14.2 / 20.6 | 18.4 / 24.0 | | frames over 50 ms, whole session | 24.0 | 25.5 | So the 5 ms spin costs 6-11% in Hyrule Field and 3-5% in the Market on this CPU, with a higher p99; Kokiri Forest is about even. Here each core sets its own clock, so the short sleeps cost nothing, and a recorder core kept spinning likely shares a physical core with one of the game's threads. As the default for every CPU this would be a loss on Ryzen; suggestion: the 5 ms spin by default only where the cores share one clock (Intel desktop CPUs like the i7-9700K), the adaptive spin elsewhere, until a structural fix (the recorder sleeping at the frame's end rather than after a fixed time, or fewer, larger hand-offs to it) can be measured on both kinds of CPU. The Test Farm runs asked for above will show Windows and other CPUs.
perf(vk): the recorder's 5 ms spin on Intel CPUs only; adaptive elsewhere, where it cost fps on a Ryzen
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 11s
Third-party parts / As their notes say (pull_request) Successful in 11s
PR description / Description follows the template (pull_request_target) Successful in 4s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+intel 0/1 pass, 0 running, 0 queued
beanstalk/linux+intel 0/1 pass, 0 running, 0 queued
beanstalk/windows+nvidia 1/1 fail
beanstalk/windows+amd 1/1 fail
beanstalk/linux+amd 2/1 fail
beanstalk/linux+nvidia 2/1 fail
78d325922c
On a Ryzen 9 7900X with an RTX 3090 (Linux, two interleaved runs each after a warm-up), the 5 ms spin lost 6-11% in
Hyrule Field (90.2 -> 80.3 fps standing, 88.6 -> 82.3 walking) and 3-5% in the Market, with a higher p99; Kokiri
Forest was even. Each core there sets its own clock, so the adaptive spin's short sleeps cost nothing, and a core kept
spinning takes power or a physical core from the game's threads. The long spin stays the default on Intel CPUs (the
i7-9700K it was measured on); RX_VK_RECORDER_SPIN_US still chooses over either.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_016o1k1PazAdTJxQQWQBksW2
Member

Beanstalk test farm

Commit 78d3259 · tier reviewed · approved by HumanBean · dashboard

What will be tested · AI plan (gpt-6.1-terra)

Two starts per side compare main and the PR in Kokiri Forest, Hyrule Field and the Market, with V-Sync off and the frame-rate cap uncapped. Each scene is measured for 15 seconds standing and 10 seconds after a camera turn; the plan cannot measure while the stick input is running. Lower FPS, more frames over 50 ms, a missing recorder-spin log or a crash fails the PR. CPU core count and vendor cannot be targeted directly, and the shared log rule accepts either spin rather than enforcing the CPU-specific choice. The requested Intel-GPU targets have no matching online hardware listed and will remain pending until matching hardware is available. No tester online now matches windows+intel, linux+intel: those targets wait for one.

  • Where: windows+intel (1-2 reports), linux+intel (1-2 reports), windows+nvidia (1-2 reports), windows+amd (1-2 reports), linux+amd (1-2 reports), linux+nvidia (1-2 reports).
  • recorder-scenes: from the repository's save kokiri-start (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-still for 15 s (after 10 s warm-up), move the stick, measure kokiri-after-turn for 10 s (after 0 s warm-up), teleport to Hyrule Field, measure field-still for 15 s (after 10 s warm-up), measure field-after-turn for 10 s (after 0 s warm-up), teleport to Market, measure market-still for 15 s (after 10 s warm-up), measure market-after-turn for 10 s (after 0 s warm-up); 2 runs on each side.
  • Measured: crashes, frame times, stutters and hitches, draws and frame rate, the game's log.
  • The PR fails if: it crashes; or frame rate is more than 0% below main; or hitches over 50 ms is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0.
  • Time: about 27 min of game runs per tester (4 game starts), plus the two builds.

Done (started 16:18 UTC, last report 21:37 UTC). Comment @Beanstalk to run it again.

Target Reports Crash Frame p99 (ms) vs main VRAM peak (MB) vs main Result
windows+intel 0/1 — — — queued
linux+intel 0/1 — — — queued
windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4070 Ti, 621.14.0; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3070, 621.24.0 2/1 1 2 1 PR run 12.5 vs 12.4 (+1%) — fail
windows+amd · 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 7900 XTX, 2.0.416; 2: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 2/1 1 2 none 10.6 vs 10.9 (−2%) — fail
linux+amd · 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7; 2: linux+amd+radv+dgpu AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6 2/1 1 2 none 15.2 vs 14.5 (+5%) — fail ⚠ outlier
linux+nvidia · 1: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4090, 590.48.1; 2: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 5070, 620.70.6 2/1 1 2 1 PR run 11.0 vs 12.1 (−9%) — fail

Run by hand on PCs that don't match their target (not counted toward it):

Target Ran on Result
linux+intel off target (ran on linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 5070, 620.70.6) fail

Measurements · windows+nvidia

Verdict: fail on windows+nvidia (2/1 report): recorder-scenes crash; recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-0.2%); recorder-scenes field-after-turn.fps_mean.min_delta_pct (-3.2%) failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4070 Ti, 621.14.0 AMD Ryzen 9 5900X 12-Core Processor, 64 GB RAM; 2: windows+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 3070, 621.24.0 AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ 78d3259
recorder-scenes · field-still · frame rate 95.6 96.4 (+1%)
recorder-scenes · kokiri-still · frame rate 87.7 90.1 (+3%)
recorder-scenes · market-still · frame rate 68.5 68.4 (−0%)
recorder-scenes · field-after-turn · frame rate 104.8 101.5 (−3%)
recorder-scenes · kokiri-after-turn · frame rate 88.6 88.4 (−0%)
recorder-scenes · market-after-turn · frame rate 89.8 88.8 (−1%)
recorder-scenes · field-still · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-still · hitches over 50 ms 0.0 0.0
recorder-scenes · market-still · hitches over 50 ms 0.0 0.0
recorder-scenes · field-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · market-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · forbidden log lines 0.0 0.0
recorder-scenes · expected log lines missing 0.0 0.0
recorder-scenes · field-still · frame time (p99) (ms) 12.4 12.5 (+1%)
recorder-scenes · kokiri-still · frame time (p99) (ms) 16.0 13.7 (−14%)
recorder-scenes · market-still · frame time (p99) (ms) 19.5 20.9 (+7%)
recorder-scenes · field-after-turn · frame time (p99) (ms) 12.4 12.4 (−0%)
recorder-scenes · kokiri-after-turn · frame time (p99) (ms) 15.4 14.5 (−6%)
recorder-scenes · market-after-turn · frame time (p99) (ms) 14.7 15.0 (+3%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on windows+nvidia (2/1 report): `recorder-scenes crash`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-0.2%)`; `recorder-scenes field-after-turn.fps_mean.min_delta_pct (-3.2%)` failed.

Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070 Ti, 621.14.0` `AMD Ryzen 9 5900X 12-Core Processor, 64 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM`  
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ 78d3259 |
|---|---|---|
| recorder-scenes · field-still · frame rate | 95.6 | 96.4 (+1%) |
| recorder-scenes · kokiri-still · frame rate | 87.7 | 90.1 (+3%) |
| recorder-scenes · market-still · frame rate | 68.5 | 68.4 (−0%) |
| recorder-scenes · field-after-turn · frame rate | 104.8 | 101.5 (−3%) |
| recorder-scenes · kokiri-after-turn · frame rate | 88.6 | 88.4 (−0%) |
| recorder-scenes · market-after-turn · frame rate | 89.8 | 88.8 (−1%) |
| recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · forbidden log lines | 0.0 | 0.0 |
| recorder-scenes · expected log lines missing | 0.0 | 0.0 |
| recorder-scenes · field-still · frame time (p99) (ms) | 12.4 | 12.5 (+1%) |
| recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.0 | 13.7 (−14%) |
| recorder-scenes · market-still · frame time (p99) (ms) | 19.5 | 20.9 (+7%) |
| recorder-scenes · field-after-turn · frame time (p99) (ms) | 12.4 | 12.4 (−0%) |
| recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 15.4 | 14.5 (−6%) |
| recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.7 | 15.0 (+3%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · windows+amd

Verdict: fail on windows+amd (2/1 report): recorder-scenes kokiri-still.fps_mean.min_delta_pct (-5.3%); recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-19.2%); recorder-scenes field-still.fps_mean.min_delta_pct (-0.8%) failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu AMD Radeon RX 7900 XTX, 2.0.416 AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM; 2: windows+amd+amd-proprietary+igpu AMD Radeon(TM) 880M Graphics, 2.0.416 AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ 78d3259
recorder-scenes · field-still · frame rate 121.4 120.4 (−1%)
recorder-scenes · kokiri-still · frame rate 111.1 105.2 (−5%)
recorder-scenes · market-still · frame rate 77.9 77.9 (−0%)
recorder-scenes · field-after-turn · frame rate 132.7 126.9 (−4%)
recorder-scenes · kokiri-after-turn · frame rate 112.5 90.8 (−19%)
recorder-scenes · market-after-turn · frame rate 81.4 85.3 (+5%)
recorder-scenes · field-still · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-still · hitches over 50 ms 0.0 0.0
recorder-scenes · market-still · hitches over 50 ms 0.0 0.0
recorder-scenes · field-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · market-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · forbidden log lines 0.0 0.0
recorder-scenes · expected log lines missing 0.0 0.0
recorder-scenes · field-still · frame time (p99) (ms) 10.9 10.6 (−2%)
recorder-scenes · kokiri-still · frame time (p99) (ms) 11.5 11.9 (+3%)
recorder-scenes · market-still · frame time (p99) (ms) 18.0 17.7 (−2%)
recorder-scenes · field-after-turn · frame time (p99) (ms) 9.7 10.1 (+5%)
recorder-scenes · kokiri-after-turn · frame time (p99) (ms) 11.6 13.9 (+20%)
recorder-scenes · market-after-turn · frame time (p99) (ms) 17.0 16.4 (−4%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on windows+amd (2/1 report): `recorder-scenes kokiri-still.fps_mean.min_delta_pct (-5.3%)`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-19.2%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-0.8%)` failed.

Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM`  
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ 78d3259 |
|---|---|---|
| recorder-scenes · field-still · frame rate | 121.4 | 120.4 (−1%) |
| recorder-scenes · kokiri-still · frame rate | 111.1 | 105.2 (−5%) |
| recorder-scenes · market-still · frame rate | 77.9 | 77.9 (−0%) |
| recorder-scenes · field-after-turn · frame rate | 132.7 | 126.9 (−4%) |
| recorder-scenes · kokiri-after-turn · frame rate | 112.5 | 90.8 (−19%) |
| recorder-scenes · market-after-turn · frame rate | 81.4 | 85.3 (+5%) |
| recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · forbidden log lines | 0.0 | 0.0 |
| recorder-scenes · expected log lines missing | 0.0 | 0.0 |
| recorder-scenes · field-still · frame time (p99) (ms) | 10.9 | 10.6 (−2%) |
| recorder-scenes · kokiri-still · frame time (p99) (ms) | 11.5 | 11.9 (+3%) |
| recorder-scenes · market-still · frame time (p99) (ms) | 18.0 | 17.7 (−2%) |
| recorder-scenes · field-after-turn · frame time (p99) (ms) | 9.7 | 10.1 (+5%) |
| recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.6 | 13.9 (+20%) |
| recorder-scenes · market-after-turn · frame time (p99) (ms) | 17.0 | 16.4 (−4%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · linux+amd

Verdict: fail on linux+amd (2/1 report): recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-1.5%); recorder-scenes field-still.fps_mean.min_delta_pct (-14.9%); recorder-scenes market-still.fps_mean.min_delta_pct (-46.4%) failed.

Hardware: 1: linux+amd+radv+dgpu AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7 AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM; 2: linux+amd+radv+dgpu AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6 11th Gen Intel(R) Core(TM) i9-11900KB @ 3.30GHz, 32 GB RAM
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ 78d3259
recorder-scenes · field-still · frame rate 89.8 81.8 (−9%)
recorder-scenes · kokiri-still · frame rate 74.4 79.2 (+6%)
recorder-scenes · market-still · frame rate 26.3 23.3 (−11%)
recorder-scenes · field-after-turn · frame rate 85.6 85.7 (+0%)
recorder-scenes · kokiri-after-turn · frame rate 76.2 77.3 (+2%)
recorder-scenes · market-after-turn · frame rate 78.6 77.8 (−1%)
recorder-scenes · field-still · hitches over 50 ms 0.2 1.5 (+500%)
recorder-scenes · kokiri-still · hitches over 50 ms 0.0 0.0
recorder-scenes · market-still · hitches over 50 ms 8.2 9.0 (+9%)
recorder-scenes · field-after-turn · hitches over 50 ms 0.2 0.2 (+0%)
recorder-scenes · kokiri-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · market-after-turn · hitches over 50 ms 0.2 0.5 (+100%)
recorder-scenes · forbidden log lines 0.0 0.0
recorder-scenes · expected log lines missing 0.0 0.0
recorder-scenes · field-still · frame time (p99) (ms) 14.5 15.2 (+5%)
recorder-scenes · kokiri-still · frame time (p99) (ms) 16.8 15.6 (−7%)
recorder-scenes · market-still · frame time (p99) (ms) 517.1 628.4 (+22%)
recorder-scenes · field-after-turn · frame time (p99) (ms) 14.4 14.7 (+2%)
recorder-scenes · kokiri-after-turn · frame time (p99) (ms) 17.5 16.8 (−4%)
recorder-scenes · market-after-turn · frame time (p99) (ms) 16.4 16.6 (+1%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on linux+amd (2/1 report): `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-1.5%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-14.9%)`; `recorder-scenes market-still.fps_mean.min_delta_pct (-46.4%)` failed.

Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+dgpu `AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6` `11th Gen Intel(R) Core(TM) i9-11900KB @ 3.30GHz, 32 GB RAM`  
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ 78d3259 |
|---|---|---|
| recorder-scenes · field-still · frame rate | 89.8 | 81.8 (−9%) |
| recorder-scenes · kokiri-still · frame rate | 74.4 | 79.2 (+6%) |
| recorder-scenes · market-still · frame rate | 26.3 | 23.3 (−11%) |
| recorder-scenes · field-after-turn · frame rate | 85.6 | 85.7 (+0%) |
| recorder-scenes · kokiri-after-turn · frame rate | 76.2 | 77.3 (+2%) |
| recorder-scenes · market-after-turn · frame rate | 78.6 | 77.8 (−1%) |
| recorder-scenes · field-still · hitches over 50 ms | 0.2 | 1.5 (+500%) |
| recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-still · hitches over 50 ms | 8.2 | 9.0 (+9%) |
| recorder-scenes · field-after-turn · hitches over 50 ms | 0.2 | 0.2 (+0%) |
| recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-after-turn · hitches over 50 ms | 0.2 | 0.5 (+100%) |
| recorder-scenes · forbidden log lines | 0.0 | 0.0 |
| recorder-scenes · expected log lines missing | 0.0 | 0.0 |
| recorder-scenes · field-still · frame time (p99) (ms) | 14.5 | 15.2 (+5%) |
| recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.8 | 15.6 (−7%) |
| recorder-scenes · market-still · frame time (p99) (ms) | 517.1 | 628.4 (+22%) |
| recorder-scenes · field-after-turn · frame time (p99) (ms) | 14.4 | 14.7 (+2%) |
| recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 17.5 | 16.8 (−4%) |
| recorder-scenes · market-after-turn · frame time (p99) (ms) | 16.4 | 16.6 (+1%) |

### Flags and settings

None: the plan varied no setting, switch or build option.

Measurements · linux+nvidia

Verdict: fail on linux+nvidia (2/1 report): recorder-scenes log_expected_missing.max; recorder-scenes crash; recorder-scenes market-still.fps_mean.min_delta_pct (-0.4%) failed.

Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 4090, 590.48.1 AMD Ryzen 7 5700X3D 8-Core Processor, 128 GB RAM; 2: linux+nvidia+nvidia-proprietary+dgpu NVIDIA GeForce RTX 5070, 620.70.6 AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports
How to reproduce: the farm's plan above (@Beanstalk on this PR runs it again)

Before: main @ d5794c8 After: this PR @ 78d3259
recorder-scenes · field-still · frame rate 107.7 110.6 (+3%)
recorder-scenes · kokiri-still · frame rate 100.4 108.3 (+8%)
recorder-scenes · market-still · frame rate 86.4 86.1 (−0%)
recorder-scenes · field-after-turn · frame rate 110.2 119.8 (+9%)
recorder-scenes · kokiri-after-turn · frame rate 107.0 117.7 (+10%)
recorder-scenes · market-after-turn · frame rate 91.3 93.2 (+2%)
recorder-scenes · field-still · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-still · hitches over 50 ms 0.0 0.0
recorder-scenes · market-still · hitches over 50 ms 0.0 0.0
recorder-scenes · field-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · kokiri-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · market-after-turn · hitches over 50 ms 0.0 0.0
recorder-scenes · forbidden log lines 0.0 0.5
recorder-scenes · expected log lines missing 1.0 1.0 (+0%)
recorder-scenes · field-still · frame time (p99) (ms) 12.1 11.0 (−9%)
recorder-scenes · kokiri-still · frame time (p99) (ms) 13.5 11.6 (−14%)
recorder-scenes · market-still · frame time (p99) (ms) 15.7 16.1 (+3%)
recorder-scenes · field-after-turn · frame time (p99) (ms) 11.6 10.3 (−11%)
recorder-scenes · kokiri-after-turn · frame time (p99) (ms) 11.7 11.1 (−5%)
recorder-scenes · market-after-turn · frame time (p99) (ms) 14.4 14.3 (−1%)

Flags and settings

None: the plan varied no setting, switch or build option.

Markdown for the PR description
## Measurements

**Verdict:** fail on linux+nvidia (2/1 report): `recorder-scenes log_expected_missing.max`; `recorder-scenes crash`; `recorder-scenes market-still.fps_mean.min_delta_pct (-0.4%)` failed.

Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4090, 590.48.1` `AMD Ryzen 7 5700X3D 8-Core Processor, 128 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM`  
Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them  
Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports  
How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again)

| | Before: main @ d5794c8 | After: this PR @ 78d3259 |
|---|---|---|
| recorder-scenes · field-still · frame rate | 107.7 | 110.6 (+3%) |
| recorder-scenes · kokiri-still · frame rate | 100.4 | 108.3 (+8%) |
| recorder-scenes · market-still · frame rate | 86.4 | 86.1 (−0%) |
| recorder-scenes · field-after-turn · frame rate | 110.2 | 119.8 (+9%) |
| recorder-scenes · kokiri-after-turn · frame rate | 107.0 | 117.7 (+10%) |
| recorder-scenes · market-after-turn · frame rate | 91.3 | 93.2 (+2%) |
| recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 |
| recorder-scenes · forbidden log lines | 0.0 | 0.5 |
| recorder-scenes · expected log lines missing | 1.0 | 1.0 (+0%) |
| recorder-scenes · field-still · frame time (p99) (ms) | 12.1 | 11.0 (−9%) |
| recorder-scenes · kokiri-still · frame time (p99) (ms) | 13.5 | 11.6 (−14%) |
| recorder-scenes · market-still · frame time (p99) (ms) | 15.7 | 16.1 (+3%) |
| recorder-scenes · field-after-turn · frame time (p99) (ms) | 11.6 | 10.3 (−11%) |
| recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.7 | 11.1 (−5%) |
| recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.4 | 14.3 (−1%) |

### Flags and settings

None: the plan varied no setting, switch or build option.
<!-- beanstalk:sticky --> ### Beanstalk test farm Commit `78d3259` · tier **reviewed** · approved by HumanBean · [dashboard](https://beanstalk.magicbean.dev/prs/1745) **What will be tested** · AI plan (`gpt-6.1-terra`) Two starts per side compare main and the PR in Kokiri Forest, Hyrule Field and the Market, with V-Sync off and the frame-rate cap uncapped. Each scene is measured for 15 seconds standing and 10 seconds after a camera turn; the plan cannot measure while the stick input is running. Lower FPS, more frames over 50 ms, a missing recorder-spin log or a crash fails the PR. CPU core count and vendor cannot be targeted directly, and the shared log rule accepts either spin rather than enforcing the CPU-specific choice. The requested Intel-GPU targets have no matching online hardware listed and will remain pending until matching hardware is available. No tester online now matches windows+intel, linux+intel: those targets wait for one. - **Where:** windows+intel (1-2 reports), linux+intel (1-2 reports), windows+nvidia (1-2 reports), windows+amd (1-2 reports), linux+amd (1-2 reports), linux+nvidia (1-2 reports). - **recorder-scenes:** from the repository's save `kokiri-start` (settings vsync=2, frame_rate_cap=6), then teleport to Kokiri Forest, measure kokiri-still for 15 s (after 10 s warm-up), move the stick, measure kokiri-after-turn for 10 s (after 0 s warm-up), teleport to Hyrule Field, measure field-still for 15 s (after 10 s warm-up), measure field-after-turn for 10 s (after 0 s warm-up), teleport to Market, measure market-still for 15 s (after 10 s warm-up), measure market-after-turn for 10 s (after 0 s warm-up); 2 runs on each side. - **Measured:** crashes, frame times, stutters and hitches, draws and frame rate, the game's log. - **The PR fails if:** it crashes; or frame rate is more than 0% below main; or hitches over 50 ms is more than 0% above main; or forbidden log lines is above 0; or expected log lines missing is above 0. - **Time:** about 27 min of game runs per tester (4 game starts), plus the two builds. Done (started 16:18 UTC, last report 21:37 UTC). Comment `@Beanstalk` to run it again. | Target | Reports | Crash | Frame p99 (ms) vs main | VRAM peak (MB) vs main | Result | | --- | --- | --- | --- | --- | --- | | windows+intel | 0/1 | — | — | — | queued | | linux+intel | 0/1 | — | — | — | queued | | windows+nvidia · 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070 Ti, 621.14.0`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_a5c5dfc05e8a05cc) [2](https://beanstalk.magicbean.dev/reports/rp_a81c68523b1b6758) | 1 PR run | 12.5 vs 12.4 (+1%) | — | fail | | windows+amd · 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_8a67295ba5184901) [2](https://beanstalk.magicbean.dev/reports/rp_5a1191aa883ea965) | none | 10.6 vs 10.9 (−2%) | — | fail | | linux+amd · 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7`; 2: linux+amd+radv+dgpu `AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_ca4244d1242f55af) [2](https://beanstalk.magicbean.dev/reports/rp_a87bd3941b74d4d5) | none | 15.2 vs 14.5 (+5%) | — | fail ⚠ outlier | | linux+nvidia · 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4090, 590.48.1`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` | 2/1 [1](https://beanstalk.magicbean.dev/reports/rp_108e7eeb0cbf0c4e) [2](https://beanstalk.magicbean.dev/reports/rp_d485034ddb4f5826) | 1 PR run | 11.0 vs 12.1 (−9%) | — | fail | Run by hand on PCs that don't match their target (not counted toward it): | Target | Ran on | Result | | --- | --- | --- | | linux+intel | off target (ran on linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6`) | [fail](https://beanstalk.magicbean.dev/reports/rp_a0498857d73064d9) | #### Measurements · windows+nvidia **Verdict:** fail on windows+nvidia (2/1 report): `recorder-scenes crash`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-0.2%)`; `recorder-scenes field-after-turn.fps_mean.min_delta_pct (-3.2%)` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070 Ti, 621.14.0` `AMD Ryzen 9 5900X 12-Core Processor, 64 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 95.6 | 96.4 (+1%) | | recorder-scenes · kokiri-still · frame rate | 87.7 | 90.1 (+3%) | | recorder-scenes · market-still · frame rate | 68.5 | 68.4 (−0%) | | recorder-scenes · field-after-turn · frame rate | 104.8 | 101.5 (−3%) | | recorder-scenes · kokiri-after-turn · frame rate | 88.6 | 88.4 (−0%) | | recorder-scenes · market-after-turn · frame rate | 89.8 | 88.8 (−1%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 12.4 | 12.5 (+1%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.0 | 13.7 (−14%) | | recorder-scenes · market-still · frame time (p99) (ms) | 19.5 | 20.9 (+7%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 12.4 | 12.4 (−0%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 15.4 | 14.5 (−6%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.7 | 15.0 (+3%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+nvidia (2/1 report): `recorder-scenes crash`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-0.2%)`; `recorder-scenes field-after-turn.fps_mean.min_delta_pct (-3.2%)` failed. Hardware: 1: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4070 Ti, 621.14.0` `AMD Ryzen 9 5900X 12-Core Processor, 64 GB RAM`; 2: windows+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 3070, 621.24.0` `AMD Ryzen 5 5600X3D 6-Core Processor, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 95.6 | 96.4 (+1%) | | recorder-scenes · kokiri-still · frame rate | 87.7 | 90.1 (+3%) | | recorder-scenes · market-still · frame rate | 68.5 | 68.4 (−0%) | | recorder-scenes · field-after-turn · frame rate | 104.8 | 101.5 (−3%) | | recorder-scenes · kokiri-after-turn · frame rate | 88.6 | 88.4 (−0%) | | recorder-scenes · market-after-turn · frame rate | 89.8 | 88.8 (−1%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 12.4 | 12.5 (+1%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.0 | 13.7 (−14%) | | recorder-scenes · market-still · frame time (p99) (ms) | 19.5 | 20.9 (+7%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 12.4 | 12.4 (−0%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 15.4 | 14.5 (−6%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.7 | 15.0 (+3%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · windows+amd **Verdict:** fail on windows+amd (2/1 report): `recorder-scenes kokiri-still.fps_mean.min_delta_pct (-5.3%)`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-19.2%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-0.8%)` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 121.4 | 120.4 (−1%) | | recorder-scenes · kokiri-still · frame rate | 111.1 | 105.2 (−5%) | | recorder-scenes · market-still · frame rate | 77.9 | 77.9 (−0%) | | recorder-scenes · field-after-turn · frame rate | 132.7 | 126.9 (−4%) | | recorder-scenes · kokiri-after-turn · frame rate | 112.5 | 90.8 (−19%) | | recorder-scenes · market-after-turn · frame rate | 81.4 | 85.3 (+5%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 10.9 | 10.6 (−2%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 11.5 | 11.9 (+3%) | | recorder-scenes · market-still · frame time (p99) (ms) | 18.0 | 17.7 (−2%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 9.7 | 10.1 (+5%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.6 | 13.9 (+20%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 17.0 | 16.4 (−4%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on windows+amd (2/1 report): `recorder-scenes kokiri-still.fps_mean.min_delta_pct (-5.3%)`; `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-19.2%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-0.8%)` failed. Hardware: 1: windows+amd+amd-proprietary+dgpu `AMD Radeon RX 7900 XTX, 2.0.416` `AMD Ryzen 7 5800X3D 8-Core Processor, 32 GB RAM`; 2: windows+amd+amd-proprietary+igpu `AMD Radeon(TM) 880M Graphics, 2.0.416` `AMD Ryzen AI 9 365 w/ Radeon 880M, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 121.4 | 120.4 (−1%) | | recorder-scenes · kokiri-still · frame rate | 111.1 | 105.2 (−5%) | | recorder-scenes · market-still · frame rate | 77.9 | 77.9 (−0%) | | recorder-scenes · field-after-turn · frame rate | 132.7 | 126.9 (−4%) | | recorder-scenes · kokiri-after-turn · frame rate | 112.5 | 90.8 (−19%) | | recorder-scenes · market-after-turn · frame rate | 81.4 | 85.3 (+5%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 10.9 | 10.6 (−2%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 11.5 | 11.9 (+3%) | | recorder-scenes · market-still · frame time (p99) (ms) | 18.0 | 17.7 (−2%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 9.7 | 10.1 (+5%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.6 | 13.9 (+20%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 17.0 | 16.4 (−4%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · linux+amd **Verdict:** fail on linux+amd (2/1 report): `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-1.5%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-14.9%)`; `recorder-scenes market-still.fps_mean.min_delta_pct (-46.4%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+dgpu `AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6` `11th Gen Intel(R) Core(TM) i9-11900KB @ 3.30GHz, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 89.8 | 81.8 (−9%) | | recorder-scenes · kokiri-still · frame rate | 74.4 | 79.2 (+6%) | | recorder-scenes · market-still · frame rate | 26.3 | 23.3 (−11%) | | recorder-scenes · field-after-turn · frame rate | 85.6 | 85.7 (+0%) | | recorder-scenes · kokiri-after-turn · frame rate | 76.2 | 77.3 (+2%) | | recorder-scenes · market-after-turn · frame rate | 78.6 | 77.8 (−1%) | | recorder-scenes · field-still · hitches over 50 ms | 0.2 | 1.5 (+500%) | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 8.2 | 9.0 (+9%) | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.2 | 0.2 (+0%) | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.2 | 0.5 (+100%) | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 14.5 | 15.2 (+5%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.8 | 15.6 (−7%) | | recorder-scenes · market-still · frame time (p99) (ms) | 517.1 | 628.4 (+22%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 14.4 | 14.7 (+2%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 17.5 | 16.8 (−4%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 16.4 | 16.6 (+1%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+amd (2/1 report): `recorder-scenes kokiri-after-turn.fps_mean.min_delta_pct (-1.5%)`; `recorder-scenes field-still.fps_mean.min_delta_pct (-14.9%)`; `recorder-scenes market-still.fps_mean.min_delta_pct (-46.4%)` failed. Hardware: 1: linux+amd+radv+dgpu `AMD Radeon RX 7900 XTX (RADV NAVI31), 26.2.7` `AMD Ryzen 7 5800X3D 8-Core Processor, 64 GB RAM`; 2: linux+amd+radv+dgpu `AMD Radeon RX 9070 XT (RADV GFX1201), 26.2.6` `11th Gen Intel(R) Core(TM) i9-11900KB @ 3.30GHz, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 89.8 | 81.8 (−9%) | | recorder-scenes · kokiri-still · frame rate | 74.4 | 79.2 (+6%) | | recorder-scenes · market-still · frame rate | 26.3 | 23.3 (−11%) | | recorder-scenes · field-after-turn · frame rate | 85.6 | 85.7 (+0%) | | recorder-scenes · kokiri-after-turn · frame rate | 76.2 | 77.3 (+2%) | | recorder-scenes · market-after-turn · frame rate | 78.6 | 77.8 (−1%) | | recorder-scenes · field-still · hitches over 50 ms | 0.2 | 1.5 (+500%) | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 8.2 | 9.0 (+9%) | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.2 | 0.2 (+0%) | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.2 | 0.5 (+100%) | | recorder-scenes · forbidden log lines | 0.0 | 0.0 | | recorder-scenes · expected log lines missing | 0.0 | 0.0 | | recorder-scenes · field-still · frame time (p99) (ms) | 14.5 | 15.2 (+5%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 16.8 | 15.6 (−7%) | | recorder-scenes · market-still · frame time (p99) (ms) | 517.1 | 628.4 (+22%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 14.4 | 14.7 (+2%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 17.5 | 16.8 (−4%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 16.4 | 16.6 (+1%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details> #### Measurements · linux+nvidia **Verdict:** fail on linux+nvidia (2/1 report): `recorder-scenes log_expected_missing.max`; `recorder-scenes crash`; `recorder-scenes market-still.fps_mean.min_delta_pct (-0.4%)` failed. Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4090, 590.48.1` `AMD Ryzen 7 5700X3D 8-Core Processor, 128 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 107.7 | 110.6 (+3%) | | recorder-scenes · kokiri-still · frame rate | 100.4 | 108.3 (+8%) | | recorder-scenes · market-still · frame rate | 86.4 | 86.1 (−0%) | | recorder-scenes · field-after-turn · frame rate | 110.2 | 119.8 (+9%) | | recorder-scenes · kokiri-after-turn · frame rate | 107.0 | 117.7 (+10%) | | recorder-scenes · market-after-turn · frame rate | 91.3 | 93.2 (+2%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.5 | | recorder-scenes · expected log lines missing | 1.0 | 1.0 (+0%) | | recorder-scenes · field-still · frame time (p99) (ms) | 12.1 | 11.0 (−9%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 13.5 | 11.6 (−14%) | | recorder-scenes · market-still · frame time (p99) (ms) | 15.7 | 16.1 (+3%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 11.6 | 10.3 (−11%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.7 | 11.1 (−5%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.4 | 14.3 (−1%) | ### Flags and settings None: the plan varied no setting, switch or build option. <details><summary>Markdown for the PR description</summary> ```markdown ## Measurements **Verdict:** fail on linux+nvidia (2/1 report): `recorder-scenes log_expected_missing.max`; `recorder-scenes crash`; `recorder-scenes market-still.fps_mean.min_delta_pct (-0.4%)` failed. Hardware: 1: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 4090, 590.48.1` `AMD Ryzen 7 5700X3D 8-Core Processor, 128 GB RAM`; 2: linux+nvidia+nvidia-proprietary+dgpu `NVIDIA GeForce RTX 5070, 620.70.6` `AMD Ryzen 5 9600X 6-Core Processor, 32 GB RAM` Scene: recorder-scenes, from the repository's save kokiri-start (vsync=2, frame_rate_cap=6); each cell's settings and switches as the table names them Method: the Beanstalk test farm: main and this PR built and run on the same PC in one session, game starts alternating (ABBA); recorder-scenes: 2 game starts a side, kokiri-still 15 s after 10 s warm-up, kokiri-after-turn 10 s after 0 s warm-up, field-still 15 s after 10 s warm-up, field-after-turn 10 s after 0 s warm-up, market-still 15 s after 10 s warm-up, market-after-turn 10 s after 0 s warm-up; each number the median of the runs, then of 2 reports How to reproduce: the farm's plan above (`@Beanstalk` on this PR runs it again) | | Before: main @ d5794c8 | After: this PR @ 78d3259 | |---|---|---| | recorder-scenes · field-still · frame rate | 107.7 | 110.6 (+3%) | | recorder-scenes · kokiri-still · frame rate | 100.4 | 108.3 (+8%) | | recorder-scenes · market-still · frame rate | 86.4 | 86.1 (−0%) | | recorder-scenes · field-after-turn · frame rate | 110.2 | 119.8 (+9%) | | recorder-scenes · kokiri-after-turn · frame rate | 107.0 | 117.7 (+10%) | | recorder-scenes · market-after-turn · frame rate | 91.3 | 93.2 (+2%) | | recorder-scenes · field-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-still · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · field-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · kokiri-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · market-after-turn · hitches over 50 ms | 0.0 | 0.0 | | recorder-scenes · forbidden log lines | 0.0 | 0.5 | | recorder-scenes · expected log lines missing | 1.0 | 1.0 (+0%) | | recorder-scenes · field-still · frame time (p99) (ms) | 12.1 | 11.0 (−9%) | | recorder-scenes · kokiri-still · frame time (p99) (ms) | 13.5 | 11.6 (−14%) | | recorder-scenes · market-still · frame time (p99) (ms) | 15.7 | 16.1 (+3%) | | recorder-scenes · field-after-turn · frame time (p99) (ms) | 11.6 | 10.3 (−11%) | | recorder-scenes · kokiri-after-turn · frame time (p99) (ms) | 11.7 | 11.1 (−5%) | | recorder-scenes · market-after-turn · frame time (p99) (ms) | 14.4 | 14.3 (−1%) | ### Flags and settings None: the plan varied no setting, switch or build option. ``` </details>
HumanBean changed title from perf(vk): the recorder thread spins 5 ms before it sleeps, which keeps an Intel CPU's clock up to perf(vk): the recorder thread spins 5 ms before it sleeps on Intel CPUs, which keeps their clock up 2026-11-19 16:17:46 +00:00
Author
Owner

@Beanstalk the PR changed: the 5 ms spin is now the default on Intel CPUs only (AMD CPUs keep main's adaptive spin; it cost 3-11% on a Ryzen 9 7900X). Please test this PR against main on PCs whose CPU has 6 or more cores, preferring Intel CPUs: windows+intel, linux+intel, and windows+nvidia / windows+amd / linux+amd / linux+nvidia testers with an Intel CPU where there are some; on an AMD CPU expect no change. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the kokiri-start save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side. Expect fps no lower than main and no more frames over 50 ms; the log's RX_VK_RECORDER=thread line shows spin 5000 us on Intel and spin adaptive 20-200 us on AMD.

@Beanstalk the PR changed: the 5 ms spin is now the default on Intel CPUs only (AMD CPUs keep main's adaptive spin; it cost 3-11% on a Ryzen 9 7900X). Please test this PR against main on PCs whose CPU has 6 or more cores, preferring Intel CPUs: windows+intel, linux+intel, and windows+nvidia / windows+amd / linux+amd / linux+nvidia testers with an Intel CPU where there are some; on an AMD CPU expect no change. Settings vsync=2 (Off) and frame_rate_cap=6 (Uncapped), defaults otherwise. From the `kokiri-start` save: Kokiri Forest, Hyrule Field and Castle Town Market, in each 15 s standing then 10 s turning the camera, two game starts a side. Expect fps no lower than main and no more frames over 50 ms; the log's `RX_VK_RECORDER=thread` line shows `spin 5000 us` on Intel and `spin adaptive 20-200 us` on AMD.
Contributor

Windows 11, i7-13700K / RTX 5090, Balanced, uncapped and windowed behind other windows. I tested bd4df979 in one binary: default 5 ms spin vs RX_VK_RECORDER_SPIN_US=0 (adaptive 20–200 µs). Both render and recorder threads were on.

The 5 ms spin didn’t meet the requested ‘FPS no lower’ result in the Market. In pairs 1/2/3, FPS was lower by 5.7/6.0/0.7% standing and 7.0/9.1/1.3% turning. Market-turn p99 was also higher in all three. Kokiri and Field FPS went both ways. Market frames over 50 ms: one with 5 ms, none with adaptive; across all scenes: three vs zero (18 windows per arm).

Game CPU share was higher in all 18 comparisons (+0.7 to +2.5 percentage points), without a consistent rise in the machine-wide clock estimate. Non-game CPU was higher in all six fixed-spin Market windows; pair 3 was a separate, quieter attempt after a launcher failure. Three pairs on this PC don’t isolate the cause or establish a general Windows regression.

Windows 11, i7-13700K / RTX 5090, Balanced, uncapped and windowed behind other windows. I tested `bd4df979` in one binary: default 5 ms spin vs `RX_VK_RECORDER_SPIN_US=0` (adaptive 20–200 µs). Both render and recorder threads were on. The 5 ms spin didn’t meet the requested ‘FPS no lower’ result in the Market. In pairs 1/2/3, FPS was lower by 5.7/6.0/0.7% standing and 7.0/9.1/1.3% turning. Market-turn p99 was also higher in all three. Kokiri and Field FPS went both ways. Market frames over 50 ms: one with 5 ms, none with adaptive; across all scenes: three vs zero (18 windows per arm). Game CPU share was higher in all 18 comparisons (+0.7 to +2.5 percentage points), without a consistent rise in the machine-wide clock estimate. Non-game CPU was higher in all six fixed-spin Market windows; pair 3 was a separate, quieter attempt after a launcher failure. Three pairs on this PC don’t isolate the cause or establish a general Windows regression.
Author
Owner

Replaced by #1763: it removes the recorder thread entirely (the game's thread records its own work and the render thread replays it), so there is no recorder left to spin, and Intel's clock drop from its 20-25 wake-ups a frame goes with it. Closing this one so there is a single PR.

Replaced by [#1763](https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/1763): it removes the recorder thread entirely (the game's thread records its own work and the render thread replays it), so there is no recorder left to spin, and Intel's clock drop from its 20-25 wake-ups a frame goes with it. Closing this one so there is a single PR.
HumanBean closed this pull request 2026-11-19 22:12:54 +00:00
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
Website / Website on Cloudflare (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Successful in 7s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 10s
CI / Workflow lint (actionlint) (pull_request) Successful in 11s
Third-party parts / As their notes say (pull_request) Successful in 11s
PR description / Description follows the template (pull_request_target) Successful in 4s
Website / Website on Cloudflare (pull_request_target) Has been skipped
beanstalk/approval approved by HumanBean (reviewed)
beanstalk/windows+intel 0/1 pass, 0 running, 0 queued
beanstalk/linux+intel 0/1 pass, 0 running, 0 queued
beanstalk/windows+nvidia 1/1 fail
beanstalk/windows+amd 1/1 fail
beanstalk/linux+amd 2/1 fail
beanstalk/linux+nvidia 2/1 fail

Pull request closed

Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
4 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
MagicBeanDev/Longshot!1745
No description provided.