Beanstalk Longshot test farm
Menu

Report rp_5072ab1c444a542a pass

#1776 fix(host): the render thread's reserved core is one the game may run on, under a launcher's or Process Lasso's affinity mask too

windows+vram-ge6gb on Flashman4/agent-de36c5,

This report disagrees with its peers.

hyrule-field field.frametime_1pct_low_ms: -2.7% against peers' -35.5%
hyrule-field field.frametime_max_ms: -14.3% against peers' -88.2%
hyrule-field run_frametime_max_ms: -4.5% against peers' -44.1%
hyrule-field run_hitch_count: -29.2% against peers' -72.2%

Machine

Commit
7949fcc74d0f1c6f54f8985a1bdbd3c1d24a3c0d
Baseline
89c3d21ea169ed46124e6c97acd90587f660b75a
App
nightly-195-f9b6d598, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 9 5900X 12-Core Processor
gpu
NVIDIA GeForce RTX 3090
tags
windowsnvidianvidia-proprietarydgpu
driver
621.1.0
ram_gb
128
vram_mb
24,322
gpu_vendor
nvidia
os_version
Windows 10.0.26200

Builds

main (baseline)

0 s warm

from 89c3d21ea169

the base was built already

PR

699.4 s warm

lift
98.8 s
read
0.8 s
finish
27.3 s
compile
565.4 s

Program cache: warm

Scenarios

hyrule-field

ok
Metric (median)mainPRΔ
exit_code00±0%
field.fps_mean90.4190.58+0.2%
run_hitch_count128.5−29.2%
field.draws_mean1,510.051,508.3−0.1%
field.hitch_count00±0%
log_forbidden_hits00±0%
field.stutter_count00±0%
log_expected_missing00±0%
run_frametime_max_ms418.27399.48−4.5%
field.frametime_max_ms17.514.99−14.3%
field.frametime_p50_ms1110.97−0.3%
field.frametime_p99_ms13.6213.45−1.3%
field.frametime_1pct_low_ms14.3413.95−2.7%
Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0000
field.fps_mean90.4990.490.7590.32
run_hitch_count151169
field.draws_mean1,508.21,516.11,500.51,511.9
field.hitch_count0000
log_forbidden_hits0000
field.stutter_count0000
log_expected_missing0000
run_frametime_max_ms596.48586.02212.93240.06
field.frametime_max_ms15.5415.2514.7419.46
field.frametime_p50_ms10.9810.9710.9711.02
field.frametime_p99_ms13.713.3713.5213.55
field.frametime_1pct_low_ms14.2913.914.0114.38

Rules

ScenarioCellRuleLimitmainPRΔ %Status
hyrule-fieldcrashFalse00—pass
hyrule-fieldfield.fps_mean.min_delta_pct1090.4190.58+0.2%pass
hyrule-fieldfield.frametime_p99_ms.max_delta_pct1513.6213.45−1.3%pass

Log (PR side, end)

[hos host] vk: frame ahead, what came with the signal: 404 signals with a capture, each of 62.7 pages in 7.1 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.97+0.19, 0.15+0.10, 0.25+0.10, 0.01+0.02, 0.01+0.02, 0.02+0.02, 0.02+0.02, 0.02+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 976, 4339.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1555 dirty pages from their submits' captures, 46993 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 866 dispatches, 37696 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7889 runs, 693.6 MB compared; 99 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15990 in captures, 0 only in the collection, 180 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: replay reads of guest memory as submitted: 1920000 (828248 pages from the captures)
[hos host] vk: program picks: 3950500 kept (1886701 by the last picks' textures, a uniform buffer bound since), 1535 new, 1447964 with other textures (of 5400000)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (246 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 270 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 487 sets (ub 5566, sb 2442, cis 41090, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1532 dirty pages from their submits' captures, 46994 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37677 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7877 runs, 693.5 MB compared; 96 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16113 in captures, 1 only in the collection, 175 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1940000 (836270 pages from the captures)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1420 dirty pages from their submits' captures, 47020 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37641 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7875 runs, 693.5 MB compared; 102 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15889 in captures, 0 only in the collection, 175 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos sead::MainThread] vk: readbacks of GPU results: 1091 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: invalidates since the last readbacks line: 1309 kept their virtual core (nothing there to wait for), 3299 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: replay reads of guest memory as submitted: 1960000 (844736 pages from the captures)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.10, present 0.28, draw 3.97, descriptors 1.56, texture lookups 0.05, uploads 0.00, pipelines 0.18, programs 0.67, commands 1.24, dispatch 0.78, memory sync 0.37, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.86 MB synced in 964.3 copies, 17.78 MB written back
[hos host] vk: 9720 presents, 91.4 fps; a frame: 1501 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.33 ms a frame (fences 0.03, timelines 0.30, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.7 full barriers recorded, 175.6 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.1 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1266616 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1285 dirty pages from their submits' captures, 47163 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37642 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7875 runs, 693.6 MB compared; 92 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16055 in captures, 0 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vi: 9740 frames presented (91.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 456, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (246 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1980000 (852571 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos ModuleSystemWorker3] nvn: 650000 recordings made, 41615 live copies (14.2 MB), 490 texture copies; 3 command buffers' segments (4.1 MB)
[hos host] vk: program picks: 4102307 kept (1961510 by the last picks' textures, a uniform buffer bound since), 1535 new, 1496157 with other textures (of 5600000)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 999, 4447.1 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1429 dirty pages from their submits' captures, 48275 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 880 dispatches, 38625 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7905 runs, 693.7 MB compared; 91 pages read into the shadows; 316 MB of shadows (99 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16475 in captures, 0 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos ModuleSystemWorker2] nvn: CommandBufferWaitEvent #120000: event 0x10103c8020 mode 0 value 79142 (now 79123) (lr 0x80664f90)
[hos host] vk: render targets drawn over from another start, let go: 415 so far (2168 MB), 364 of them (1903 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 2000000 (860578 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1259 dirty pages from their submits' captures, 47248 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 868 dispatches, 37699 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8044 runs, 711.1 MB compared; 88 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16078 in captures, 0 only in the collection, 181 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: CommandBufferSignalEvent #80000: event 0x10103c8028 mode 0 value 79999 (lr 0x80667410)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (246 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2020000 (868454 pages from the captures)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.17, present 0.25, draw 3.95, descriptors 1.54, texture lookups 0.06, uploads 0.00, pipelines 0.18, programs 0.67, commands 1.23, dispatch 0.79, memory sync 0.40, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.85 MB synced in 964.3 copies, 17.78 MB written back
[hos host] vk: 9840 presents, 90.6 fps; a frame: 1502 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.34 ms a frame (fences 0.03, timelines 0.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.3 full barriers recorded, 175.5 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.2 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 270 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 487 sets (ub 5566, sb 2442, cis 41090, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 976, 4339.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1167 dirty pages from their submits' captures, 47277 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 867 dispatches, 37665 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7883 runs, 693.6 MB compared; 101 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15981 in captures, 1 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.00 since the last count
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1094 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 1158 kept their virtual core (nothing there to wait for), 2682 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: replay reads of guest memory as submitted: 2040000 (876441 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 300 sync waits (145 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: write-backs left out (600 submits): 999, 4447.1 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1264 dirty pages from their submits' captures, 48404 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 882 dispatches, 38621 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8065 runs, 711.3 MB compared; 91 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16442 in captures, 0 only in the collection, 177 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 4254081 kept (2036475 by the last picks' textures, a uniform buffer bound since), 1535 new, 1544383 with other textures (of 5800000)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos host] vk: late pages' fix (600 recordings with one): of 681 captures with late pages 681 fixed (138.0 pages, 138.9 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 2 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 640 blocks (40960 KB); of the reads on the CPU, 1 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 0, of an earlier recording 1, not recorded yet 0, of this part 0; pages fixed from stamps 92768, from snapshots 1194; the shadows: 288430 pages synced from captures, 282052 made known by it, 6378 left unknown because the replay or the collection wrote them since
[hos host] vk: replay reads of guest memory as submitted: 2060000 (884324 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 194 pages written, 194 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (224 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1334225 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 976, 4339.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1345 dirty pages from their submits' captures, 47097 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 866 dispatches, 37654 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7884 runs, 693.6 MB compared; 92 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15999 in captures, 1 only in the collection, 180 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.11, present 0.25, draw 4.00, descriptors 1.58, texture lookups 0.05, uploads 0.00, pipelines 0.18, programs 0.69, commands 1.23, dispatch 0.79, memory sync 0.39, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.85 MB synced in 964.3 copies, 17.78 MB written back
[hos host] vk: 9960 presents, 91.1 fps; a frame: 1503 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.38 ms a frame (fences 0.03, timelines 0.36, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.6 full barriers recorded, 175.5 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.2 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2080000 (892239 pages from the captures)
[hos sead::MainThread] nvn: DrawMeshTasksIndirect: 200000 so far (x1 0x1186908030 x2 0 x3 0x1186908000 x4 0x9b040)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1456 dirty pages from their submits' captures, 47050 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37652 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7881 runs, 693.6 MB compared; 101 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16047 in captures, 1 only in the collection, 180 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #125000: event 0x10103c8020 mode 0 value 82942 (now 82923) (lr 0x80664f90)
[hos sead::MainThread] nvn: QueueSubmitCommands #60000: queue 00001010103BF020 (its #10000), 1 handles (lr 0x80666be0)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos sead::MainThread] nvn: EventSignal (CPU) #20000: event 0x1009b38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: replay reads of guest memory as submitted: 2100000 (900561 pages from the captures)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1159 dirty pages from their submits' captures, 47382 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 864 dispatches, 37647 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7873 runs, 693.5 MB compared; 98 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16021 in captures, 0 only in the collection, 177 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos nn.npln.Shared] vcores: 218161 takes, 22663 waits (mean 40 us, longest 5.2 ms, 0 over HOS_VCORE_LOG_MS), 10631 kicks, 10529 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (244 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 4405731 kept (2111200 by the last picks' textures, a uniform buffer bound since), 1535 new, 1592733 with other textures (of 6000000)
[hos sead::MainThread] vk: readbacks of GPU results: 1099 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: invalidates since the last readbacks line: 1343 kept their virtual core (nothing there to wait for), 3265 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 2120000 (908625 pages from the captures)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 270 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 487 sets (ub 5566, sb 2442, cis 41090, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 999, 4447.1 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1398 dirty pages from their submits' captures, 48316 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 884 dispatches, 38616 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7903 runs, 693.7 MB compared; 100 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16428 in captures, 1 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.07, present 0.25, draw 3.95, descriptors 1.56, texture lookups 0.06, uploads 0.00, pipelines 0.18, programs 0.69, commands 1.20, dispatch 0.79, memory sync 0.39, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.86 MB synced in 964.3 copies, 17.78 MB written back
[hos host] vk: 10080 presents, 91.3 fps; a frame: 1502 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.35 ms a frame (fences 0.03, timelines 0.32, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.8 full barriers recorded, 175.6 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.2 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2140000 (916636 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #85000: event 0x10103c8034 mode 0 value 84999 (lr 0x806616b0)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1308 dirty pages from their submits' captures, 47189 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 864 dispatches, 37676 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8038 runs, 711.1 MB compared; 102 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16040 in captures, 1 only in the collection, 175 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 194 pages written, 194 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (260 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1401399 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 976, 4339.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1472 dirty pages from their submits' captures, 46976 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 866 dispatches, 37660 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7887 runs, 693.6 MB compared; 97 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16032 in captures, 0 only in the collection, 182 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2160000 (924778 pages from the captures)
[hos host] vk: program picks: 4557206 kept (2185946 by the last picks' textures, a uniform buffer bound since), 1535 new, 1641258 with other textures (of 6200000)
[hos host] vk: queues ordered by their events: 54000 submissions stopped at a wait, 53998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 129427, not met 0; captures at a CPU event's wait 6607, 0 of them at a wait met on arrival
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1439 dirty pages from their submits' captures, 47111 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37678 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7878 runs, 693.6 MB compared; 93 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16067 in captures, 0 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: replay reads of guest memory as submitted: 2180000 (932790 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #130000: event 0x10103c8020 mode 0 value 86742 (now 86723) (lr 0x80664f90)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1099 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 1197 kept their virtual core (nothing there to wait for), 2899 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 190 pages written, 190 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (250 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 10196 frames presented (91.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 456, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: memory: working set 21712 MB (peak 21736), private 32071 MB, staging 32 MB in 2 arenas, 22 made so far (3 ms)
[hos host] vk: memory heaps: heap 0 (device): 241 blocks 8059 MB, 17378 allocations 7038 MB; used 9130 of 23554 MB; heap 1 (system): 27 blocks 1016 MB, 38 allocations 895 MB; used 2734 of 104029 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB
[hos host] vk: image blocks (render targets): 23 blocks 736 MB, 110 images 401 MB; 52 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 116 blocks 3712 MB, 2263 images 3688 MB; 1069 free ranges, the largest 20 MB
[hos host] vk: render target images: 276 reused from the pool, 376 made new, 259 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 9130 MB used of 23554 MB allowed (1020 MB of it free in the blocks); textures 5598 MB (budget 11000 MB), 2389 textures
[hos host] vk: budget: VRAM 8059 of 23554 MB (9130 MB by the driver, 1071 MB unaccounted): textures 5598, blocks free 1020, mirrors 886, shadows 316, other buffers 146, other images 60, staging 32; RAM 2547 MB (the process's private memory 32071 MB): imports 1624, capture spares 656, captures 230, capture table 28, other buffers 9, others 0
[hos host] vk: textures: decoded ASTC 3429 MB, rendered 1226 MB (108 drawn in one frame, kept: 65294 KB), other 614 MB; used in the last 8 presents 1635 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 11 listed; 640 MB of blocks hashed in 60 ms
[hos host] vk:   288 MB: 0x1150c06000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 3572 presents ago
[hos host] vk:   214 MB: 0x10aea22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10ab1aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x114045c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x1145b99000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x114045c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 4611 presents ago
[hos host] vk:   54 MB: 0x10005f65c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x1000657e400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3220 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 3 (353 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 2 (351 KB);
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos Presentation Thread] vk: presents after the CPU's signal (600): 374 waited for it, 0.53 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 14.5 ms; VRAM 8.9 of 23.0 GB
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.05, present 0.25, draw 4.02, descriptors 1.58, texture lookups 0.06, uploads 0.00, pipelines 0.18, programs 0.69, commands 1.24, dispatch 0.78, memory sync 0.38, queue submit 0.46, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.86 MB synced in 964.3 copies, 17.78 MB written back
[hos host] vk: 10200 presents, 91.7 fps; a frame: 1505 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.36 ms a frame (fences 0.03, timelines 0.33, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 412.0 full barriers recorded, 175.7 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.2 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 10.96 ms a frame): its jobs 7.85 ms a frame (submits 3.16, presents 0.27, others 4.43), idle 3.11; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 2.46 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 396 captures at a CPU signal; the submits' waits read in 0.033 ms a frame; readbacks: 2776 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 6.98 ms after its hand-over (10.55 at most)
[hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 0.67 + 0.17 (the window's copy is in the idle), after it 1.44 + 0.51; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 8.63 parts a frame recorded in the signal's job, 68.7% of them took nothing that came with the signal; of the others, 2.70 a frame took pages of the signal's capture into a mirror (50.6 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 24 of 396 frames, its first three in 24
[hos host] vk: frame ahead, what came with the signal: 396 signals with a capture, each of 58.6 pages in 6.7 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.95+0.19, 0.16+0.10, 0.25+0.10, 0.01+0.02, 0.01+0.02, 0.02+0.02, 0.02+0.02, 0.02+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: write-backs left out (600 submits): 974, 4335.9 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1633 dirty pages from their submits' captures, 46922 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 861 dispatches, 37692 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7863 runs, 693.5 MB compared; 93 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16066 in captures, 0 only in the collection, 176 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2200000 (940809 pages from the captures)
[hos ModuleSystemWorker2] nvn: 700000 recordings made, 41551 live copies (13.4 MB), 490 texture copies; 5 command buffers' segments (4.3 MB)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 270 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 487 sets (ub 5566, sb 2442, cis 41090, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 976, 4339.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1142 dirty pages from their submits' captures, 47278 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 865 dispatches, 37644 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7888 runs, 693.6 MB compared; 100 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16040 in captures, 0 only in the collection, 179 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: replay reads of guest memory as submitted: 2220000 (948860 pages from the captures)
[hos host] vk: program picks: 4708676 kept (2260827 by the last picks' textures, a uniform buffer bound since), 1535 new, 1689788 with other textures (of 6400000)
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (254 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1385 dirty pages from their submits' captures, 47026 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 863 dispatches, 37638 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7875 runs, 693.5 MB compared; 106 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 139 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15865 in captures, 1 only in the collection, 176 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 2240000 (957451 pages from the captures)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.06, present 0.26, draw 3.85, descriptors 1.47, texture lookups 0.06, uploads 0.00, pipelines 0.18, programs 0.68, commands 1.20, dispatch 0.78, memory sync 0.40, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.86 MB synced in 964.5 copies, 17.78 MB written back
[hos host] vk: 10320 presents, 91.5 fps; a frame: 1503 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.36 ms a frame (fences 0.03, timelines 0.33, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.9 full barriers recorded, 175.7 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.2 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 1468983 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1422 dirty pages from their submits' captures, 47204 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 864 dispatches, 37714 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7878 runs, 693.6 MB compared; 92 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 15988 in captures, 1 only in the collection, 177 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1096 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 1270 kept their virtual core (nothing there to wait for), 3082 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos sead::MainThread] nvn: GPU waits in 5 s: 313 sync waits (148 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 2260000 (965365 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #90000: event 0x10103c8040 mode 0 value 89999 (lr 0x806621e8)
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 220000 so far (x1 0x1182746000 x2 0 x3 0x1182746000 x4 0x654040)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1288 dirty pages from their submits' captures, 47901 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 879 dispatches, 38162 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7882 runs, 693.6 MB compared; 115 pages read into the shadows; 316 MB of shadows (99 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16267 in captures, 0 only in the collection, 178 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (242 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker2] nvn: CommandBufferWaitEvent #135000: event 0x10103c8020 mode 0 value 90542 (now 90523) (lr 0x80664f90)
[hos host] vk: replay reads of guest memory as submitted: 2280000 (973218 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 415 so far (2168 MB), 364 of them (1903 MB) between the passes
[hos host] vk: program picks: 4860265 kept (2335606 by the last picks' textures, a uniform buffer bound since), 1535 new, 1738199 with other textures (of 6600000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1000, 4449.1 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1317 dirty pages from their submits' captures, 47736 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 869 dispatches, 38217 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8068 runs, 711.3 MB compared; 88 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16042 in captures, 0 only in the collection, 181 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: replay reads of guest memory as submitted: 2300000 (981053 pages from the captures)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.10, present 0.25, draw 3.98, descriptors 1.55, texture lookups 0.06, uploads 0.00, pipelines 0.18, programs 0.68, commands 1.25, dispatch 0.79, memory sync 0.40, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 159 (886 MB): 4.86 MB synced in 965.5 copies, 17.78 MB written back
[hos host] vk: 10440 presents, 90.9 fps; a frame: 1502 draws (0 skipped), 159 dispatches, 139 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37474 pipelines (6945926 ms), 0 programs (0 failed), 2389 textures (5598 MB)
[hos host] vk: host time in GPU resource waits: 0.32 ms a frame (fences 0.03, timelines 0.29, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.6 full barriers recorded, 175.5 left out (nothing recorded since the one before), 15.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.1 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 270 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 487 sets (ub 5566, sb 2442, cis 41090, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1205 dirty pages from their submits' captures, 47360 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 868 dispatches, 37755 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7877 runs, 693.6 MB compared; 105 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16004 in captures, 1 only in the collection, 179 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 688 ranges, 1857 MB), 192 pages written, 192 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (230 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 2320000 (988976 pages from the captures)
[hos tera::FileResourceMgr] vcores: 218808 takes, 22120 waits (mean 40 us, longest 5.4 ms, 0 over HOS_VCORE_LOG_MS), 10284 kicks, 10217 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 63, 886 MB with memory of 1148 MB (261 MB spared); blocks given memory later 2347, given back 4543; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 268 binds (31.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 30 taken from the spares, 129 made new; 96 kept as spares, 0 destroyed; 66 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 975, 4337.8 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1450 dirty pages from their submits' captures, 47704 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 874 dispatches, 38140 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7922 runs, 694.2 MB compared; 100 pages read into the shadows; 316 MB of shadows (99 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16458 in captures, 0 only in the collection, 177 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 110 live (1624 MB), 0 retired still imported (0 MB), 53 retired given back (788 MB)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1095 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 1289 kept their virtual core (nothing there to wait for), 3063 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: recorder: 8427830 packets run in 10.0 s (busy 2.07 s, spun idle 4.89 s, slept 3685 times, 1524 of them under 200 us), 0 calls made directly (no room); the replay waited for it 39477 times, 148.46 ms in all, the longest 0.72 ms; vkEndCommandBuffer 13973/80.87 ms (max 0.72), replay_mu unlock 11558/34.55 ms (max 0.20), vkResetDescriptorPool 13945/33.04 ms (max 0.11), vmaInvalidateAllocation 1/0.00 ms (max 0.00)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos host] vk: replay reads of guest memory as submitted: 2340000 (996870 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1536166 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 1000, 4449.1 MB; 35 bindings followed, 51 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1280 dirty pages from their submits' captures, 47759 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 868 dispatches, 38255 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8108 runs, 711.9 MB compared; 98 pages read into the shadows; 316 MB of shadows (100 MB of pages known, in 140 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 16022 in captures, 0 only in the collection, 179 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 5012019 kept (2410379 by the last picks' textures, a uniform buffer bound since), 1535 new, 1786445 with other textures (of 6800000)
[hos host] vk: replay reads of guest memory as submitted: 2360000 (1004726 pages from the captures)
[hos host] control: quit asked by a client
[hos host] vk: indexed descriptor arrays (close): 2661 in 2661 of 52288 program stages, 0 of them near a limit
[hos host] vk: indexed descriptor arrays (close), fragment stages: 2661 texture (17-64: 2661); the longest 64
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4302 pools in the table now)
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)