Beanstalk Longshot test farm
Menu

Report rp_a168d2e42dd7b0b4 fail

#1574 perf(vk): ask for the window's next image on the presenter thread right after a present, so the render thread stops waiting for it

linux+nvidia on Hidden tester,

This report disagrees with its peers.

hyrule-field run_frametime_max_ms: -1.2% against peers' +28.0%
hyrule-field run_hitch_count: -5.0% against peers' +25.0%
hyrule-field#1 field.fps_mean: -29.7% against peers' -1.5%
hyrule-field#1 field.frametime_1pct_low_ms: +1575.5% against peers' +12.8%
hyrule-field#1 field.frametime_max_ms: +8996.1% against peers' +11.8%
hyrule-field#1 field.frametime_p50_ms: +30.9% against peers' +0.6%
hyrule-field#1 field.frametime_p99_ms: +33.2% against peers' +9.7%
hyrule-field#1 field.stutter_count: +1000.0% against peers' +0.0%
hyrule-field#1 run_frametime_max_ms: +6413.6% against peers' -11.1%
hyrule-field#1 run_hitch_count: +190.9% against peers' -8.3%

Machine

Commit
2f24a499ca2a8fc708008cdb350c09fea17e9ea0
Baseline
430eef4f2cc94e398b06d0daeb585a679d3ebcda
App
nightly-191-38dff5fc, attempt 1
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 5 9600X 6-Core Processor
gpu
NVIDIA GeForce RTX 5070
tags
linuxnvidianvidia-proprietarydgpu
driver
620.70.6
ram_gb
32
vram_mb
12,227
gpu_vendor
nvidia
os_version
CachyOS (kernel 7.3.5)

Builds

main (baseline)

920.9 s warm

from 430eef4f2cc9

lift
54.8 s
read
1.4 s
finish
11.2 s
compile
771 s
shaders
78 s

PR

51.1 s warm

Program cache: warm

Scenarios

hyrule-field RX_VK_ACQUIRE_AHEAD=0 (PR only)

ok
Metric (median)switch offswitch onΔ
exit_code00±0%
field.fps_mean98.1298.25+0.1%
run_hitch_count109.5−5%
field.draws_mean1,192.61,192.15−0%
field.hitch_count00±0%
field.stutter_count0.50.5±0%
run_frametime_max_ms1,777.181,756.27−1.2%
field.frametime_max_ms21.0518.18−13.6%
field.frametime_p50_ms9.939.9−0.2%
field.frametime_p99_ms14.1914.07−0.8%
field.frametime_1pct_low_ms15.3814.81−3.7%
screenshot_diff—0.08—

Pictures against the switch off: field diff 0.1138 (switch off against itself 0.0897)

Runs (4)
Metricoff 0on 1on 2off 3
hangnononono
crashednononono
exit_code0000
field.fps_mean97.7595.33101.1698.5
run_hitch_count161544
field.draws_mean1,187.11,192.71,191.61,198.1
field.hitch_count0000
field.stutter_count0101
run_frametime_max_ms3,410.413,335.04177.5143.95
field.frametime_max_ms17.9320.7315.6324.16
field.frametime_p50_ms9.8310.049.7710.03
field.frametime_p99_ms15.2915.812.3413.09
field.frametime_1pct_low_ms16.3616.7312.8914.41
screenshot_diff—0.040.11—

hyrule-field RX_VK_ACQUIRE_AHEAD=1 (PR only)

ok
Metric (median)switch offswitch onΔ
exit_code00±0%
field.fps_mean99.369.78−29.7%
run_hitch_count5.516+190.9%
field.draws_mean1,196.11,173.2−1.9%
field.hitch_count03—
field.stutter_count0.55.5+1000%
run_frametime_max_ms151.619,875.49+6413.6%
field.frametime_max_ms19.161,742.44+8996.1%
field.frametime_p50_ms9.9513.03+30.9%
field.frametime_p99_ms12.8117.07+33.2%
field.frametime_1pct_low_ms13.75230.43+1575.5%
screenshot_diff—0.03—

Pictures against the switch off: field diff 0.0381 (switch off against itself 0.0316)

Runs (4)
Metricoff 0on 1on 2off 3
hangnononono
crashednononono
exit_code0000
field.fps_mean98.4396.8442.72100.17
run_hitch_count46267
field.draws_mean1,188.71,193.71,152.71,203.5
field.hitch_count0150
field.stutter_count1290
run_frametime_max_ms158.38161.0519,589.92144.85
field.frametime_max_ms21.4664.043,420.8416.85
field.frametime_p50_ms10.0410.2315.839.86
field.frametime_p99_ms12.9913.6120.5312.63
field.frametime_1pct_low_ms14.0116.74444.1313.49
screenshot_diff—0.020.04—

Rules

ScenarioCellRuleLimitswitch offswitch onΔ %Status
hyrule-fieldRX_VK_ACQUIRE_AHEAD=0 (PR only)crashFalse00—pass
hyrule-fieldRX_VK_ACQUIRE_AHEAD=0 (PR only)screenshot.max_diff0.050.090.11—passover the limit, but main differs from itself by 0.0897 here: no more than 1.5x that is the scene, not the PR
hyrule-fieldRX_VK_ACQUIRE_AHEAD=1 (PR only)crashFalse00—pass
hyrule-fieldRX_VK_ACQUIRE_AHEAD=1 (PR only)screenshot.max_diff0.050.030.04—pass
hyrule-fieldRX_VK_ACQUIRE_AHEAD=1 (PR only)field.fps_mean: RX_VK_ACQUIRE_AHEAD=1 vs RX_VK_ACQUIRE_AHEAD=0 (PR)598.2569.78−29%failthe PR's own cells: RX_VK_ACQUIRE_AHEAD=1 against RX_VK_ACQUIRE_AHEAD=0 (RX_VK_ACQUIRE_AHEAD=0 (PR only))
hyrule-fieldRX_VK_ACQUIRE_AHEAD=1 (PR only)field.frametime_p99_ms: RX_VK_ACQUIRE_AHEAD=1 vs RX_VK_ACQUIRE_AHEAD=0 (PR)1514.0717.07+21.3%failthe PR's own cells: RX_VK_ACQUIRE_AHEAD=1 against RX_VK_ACQUIRE_AHEAD=0 (RX_VK_ACQUIRE_AHEAD=0 (PR only))

Log (PR side, end)

[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 3000 of 3000 waited for their write-back, 0.09 ms each; 161 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 1537 kept their virtual core (nothing there to wait for), 3327 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: program picks: 583259 kept (237135 by the last picks' textures, a uniform buffer bound since), 2844 new, 213896 with other textures (of 800000)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4397 dirty pages from their submits' captures, 77204 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1242 dispatches, 51791 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5427 runs, 185.8 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32973 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 360000 (154373 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 280 pages written, 280 copied (1.1 MB)
[hos sead::MainThread] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (248 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 260 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: sparse mirrors: 76, 1035 MB with memory of 1428 MB (392 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 185 binds (14.2 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 34 kept as spares, 1 destroyed; 16 spares now, 612 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4605 dirty pages from their submits' captures, 79064 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1265 dispatches, 53053 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5492 runs, 187.4 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33606 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos sead::MainThread] vk: mirror of pool 0x7f64c00000 (4 MB) given back: idle, 6059 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f61c00000 (4 MB) given back: idle, 6059 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f58c00000 (12 MB) given back: idle, 6057 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f5ac00000 (4 MB) given back: idle, 6055 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f62000000 (4 MB) given back: idle, 6055 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f62400000 (4 MB) given back: idle, 6055 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f57c00000 (16 MB) given back: idle, 6054 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f59c00000 (16 MB) given back: idle, 6054 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f5bc00000 (4 MB) given back: idle, 6054 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f61000000 (4 MB) given back: idle, 6054 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f63c00000 (12 MB) given back: idle, 6054 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f61800000 (4 MB) given back: idle, 6053 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f64800000 (4 MB) given back: idle, 6053 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f61400000 (4 MB) given back: idle, 6053 submissions since its sync
[hos sead::MainThread] vk: mirror of pool 0x7f5b400000 (8 MB) given back: idle, 6053 submissions since its sync
[hos sead::MainThread] vk: 49 mirrors given back (840 MB in all); 990 MB of mirrors now, 36 MB of them idle and kept for what the GPU wrote there alone
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.44, present 0.13, draw 3.19, descriptors 0.99, texture lookups 0.05, uploads 0.00, pipelines 0.11, programs 0.46, commands 1.33, dispatch 0.78, memory sync 0.30, queue submit 0.16, slot wait 0.01
[hos Presentation Thread] vk: a frame: mirrors 110 (990 MB): 7.26 MB synced in 1166.4 copies, 18.46 MB written back
[hos Presentation Thread] vk: 4680 presents, 62.1 fps; a frame: 1193 draws (0 skipped), 148 dispatches, 146 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3515999 ms), 0 programs (0 failed), 658 textures (1907 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.89 ms a frame (fences 0.01, timelines 4.88, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 413.2 full barriers recorded, 174.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.8 ms a frame (the longest submission 9.3 ms); 0.1 textures made a frame
[hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 380000 (161554 pages from the captures)
[hos host] vk: queues ordered by their events: 18000 submissions stopped at a wait, 17886 went on once it was reached, 112 waits gone past; made to go by presents 481, releases 0, waits for the replay 0, 50 ms 8 (stopped 1000.95 ms at most); waits met 33421, not met 0; captures at a CPU event's wait 1055, 37 of them at a wait met on arrival
[hos Presentation Thread] vk: mirror of pool 0x7f65000000 (8 MB) given back: idle, 6027 submissions since its sync
[hos Presentation Thread] vk: mirror of pool 0x7fd3c00000 (48 MB) given back: idle, 6027 submissions since its sync
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4417 dirty pages from their submits' captures, 76900 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1245 dispatches, 51782 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5259 runs, 182.9 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32706 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos host] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 276 pages written, 276 copied (1.1 MB)
[hos host] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (234 MB), 12 spare buffers, 4480 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 400000 (168720 pages from the captures)
[hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 262 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #35000: event 0x100d6c8030 mode 0 value 18478 (now 18459) (lr 0x806614d8)
[hos Presentation Thread] vk: readback pages refreshed from guest memory: 244804 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4480 dirty pages from their submits' captures, 78771 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): 1261 dispatches, 52829 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5335 runs, 184.7 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33355 in captures, 0 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos Presentation Thread] vk: 7 textures retired (651 left, 1904 MB): budget 7, drawn over 0, dead targets 0
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 40000 so far (x1 0x117cf20000 x2 0x2 x3 0x117cf20000 x4 0x9b040)
[hos ModuleSystemWorker2] vcores: 165842 takes, 14170 waits (mean 30 us, longest 1.4 ms, 0 over HOS_VCORE_LOG_MS), 5980 kicks, 6074 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: program picks: 735968 kept (304128 by the last picks' textures, a uniform buffer bound since), 2844 new, 261187 with other textures (of 1000000)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 3000 of 3000 waited for their write-back, 0.08 ms each; 155 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 1312 kept their virtual core (nothing there to wait for), 2784 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: texture #11 0x10000348400 2560x1440x1 x1 NVN 0x38 the GPU drew goes with no copy of its texels (live, unused for 3605 frames, over the budget): made again over this storage, it starts empty
[hos Presentation Thread] vk: 1 textures retired (650 left, 1889 MB): budget 1, drawn over 0, dead targets 0; GPU-drawn with no copy kept: 1 live, 0 finalized, 14 MB
[hos host] vk: replay reads of guest memory as submitted: 420000 (175879 pages from the captures)
[hos Presentation Thread] vk: memory: working set 17966 MB (peak 18168), private 9666 MB, staging 128 MB in 8 arenas, 44 made so far (74 ms)
[hos Presentation Thread] vk: memory heaps: heap 0 (device): 126 blocks 3981 MB, 16196 allocations 3292 MB; used 5010 of 10576 MB; heap 1 (system): 34 blocks 1034 MB, 44 allocations 955 MB; used 2694 of 23390 MB;
[hos Presentation Thread] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB
[hos Presentation Thread] vk: image blocks (render targets): 15 blocks 480 MB, 106 images 214 MB; 48 free ranges, the largest 26 MB
[hos Presentation Thread] vk: image blocks (textures, compacted): 21 blocks 672 MB, 514 images 628 MB; 174 free ranges, the largest 19 MB
[hos Presentation Thread] vk: render target images: 247 reused from the pool, 392 made new, 284 destroyed from it; it holds 0 (0 MB)
[hos Presentation Thread] vk: VRAM: 5010 MB used of 10576 MB allowed (688 MB of it free in the blocks); textures 1892 MB (budget 1054 MB), 657 textures
[hos Presentation Thread] vk: textures: decoded ASTC 715 MB, rendered 778 MB (112 drawn in one frame, kept: 51967 KB), other 217 MB; used in the last 8 presents 1321 MB
[hos Presentation Thread] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 0 listed; 927 MB of blocks hashed in 44 ms
[hos Presentation Thread] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 888 presents ago
[hos Presentation Thread] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos Presentation Thread] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos Presentation Thread] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos Presentation Thread] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos Presentation Thread] vk:   54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos Presentation Thread] vk:   37 MB: 0x110a311a00 1800x1380x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos Presentation Thread] vk:   32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 888 presents ago
[hos Presentation Thread] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos Presentation Thread] vk: status: 600 frames, the slowest 19544.7 ms; VRAM 4.9 of 10.3 GB
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.41, present 0.12, draw 3.07, descriptors 0.88, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.45, commands 1.32, dispatch 0.76, memory sync 0.30, queue submit 0.15, slot wait 0.01
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.23 MB synced in 1164.0 copies, 18.40 MB written back
[hos Presentation Thread] vk: 4800 presents, 62.3 fps; a frame: 1193 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3515999 ms), 0 programs (0 failed), 657 textures (1892 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.86 ms a frame (fences 0.01, timelines 4.85, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 409.8 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.8 ms a frame (the longest submission 9.4 ms); 0.1 textures made a frame
[hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: the recording streams: 48 of 2 MB, the most one held 380 KB; 0 made on demand (0 MB kept now); c1 stages: at most 94 a recording; 0 descriptor pools made when a recording's own ran out
[hos sead::MainThread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos sead::MainThread] vk: mirror syncs (600 submits): 4448 dirty pages from their submits' captures, 77268 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 sead::MainThread] vk: mirror syncs' pass (600 submits): 1242 dispatches, 51904 chunks; 0 syncs as copies (no table room)
[hos sead::MainThread] vk: write-back diff (600 submits): 5262 runs, 183.1 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32707 in captures, 0 only in the collection, 45 only by the replay itself
[hos sead::MainThread] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 279 pages written, 279 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (234 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #20000: event 0x100d6c8034 mode 0 value 19999 (lr 0x806616b0)
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 257 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 440000 (183047 pages from the captures)
[hos host] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4489 dirty pages from their submits' captures, 77655 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): 1253 dispatches, 52202 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5238 runs, 181.8 MB compared; 71 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32588 in captures, 0 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 313 sync waits (1367 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos Presentation Thread] vi: 4858 frames presented (62.5 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 141, 15.5-17.8 163, 17.8-22 7, 22-30 0, 30-40 0, over 40 2
[hos Presentation Thread] vk: 7 textures retired (651 left, 1889 MB): budget 7, drawn over 0, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 279 pages written, 279 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (234 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos host] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4452 dirty pages from their submits' captures, 78100 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): 1250 dispatches, 52541 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5356 runs, 184.9 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33469 in captures, 0 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 460000 (190619 pages from the captures)
[hos Presentation Thread] vk: render targets drawn over from another start, let go: 445 so far (1269 MB), 406 of them (1162 MB) between the passes
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos ModuleSystemWorker1] nvn: 300000 recordings made, 38618 live copies (14.9 MB), 453 texture copies; 3 command buffers' segments (4.1 MB)
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 260 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.50, present 0.12, draw 3.17, descriptors 0.92, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.45, commands 1.37, dispatch 0.76, memory sync 0.31, queue submit 0.14, slot wait 0.02
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.21 MB synced in 1163.7 copies, 18.40 MB written back
[hos Presentation Thread] vk: 4920 presents, 63.7 fps; a frame: 1193 draws (0 skipped), 145 dispatches, 146 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); 32425 pipelines (3515999 ms), 0 programs (0 failed), 651 textures (1889 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.47 ms a frame (fences 0.01, timelines 4.46, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 409.7 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.9 ms a frame (the longest submission 9.5 ms); 0.0 textures made a frame
[hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: program picks: 888205 kept (371388 by the last picks' textures, a uniform buffer bound since), 2844 new, 308950 with other textures (of 1200000)
[hos Presentation Thread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4277 dirty pages from their submits' captures, 76393 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1238 dispatches, 51527 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5236 runs, 182.8 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32627 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #40000: event 0x100d6c8030 mode 0 value 22278 (now 22259) (lr 0x806614d8)
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 480000 (197970 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 3000 of 3000 waited for their write-back, 0.07 ms each; 149 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 1313 kept their virtual core (nothing there to wait for), 2783 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: readback pages refreshed from guest memory: 312402 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 278 pages written, 278 copied (1.1 MB)
[hos sead::MainThread] vk: a capture taken (ms): all 0.022; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (248 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4658 dirty pages from their submits' captures, 78262 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1261 dispatches, 52783 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5354 runs, 184.9 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33355 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 262 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 500000 (205336 pages from the captures)
[hos Presentation Thread] vk: 1 textures retired (652 left, 1890 MB): budget 1, drawn over 0, dead targets 0
[hos Presentation Thread] vk: the recording streams: 48 of 2 MB, the most one held 380 KB; 0 made on demand (0 MB kept now); c1 stages: at most 94 a recording; 0 descriptor pools made when a recording's own ran out
[hos Presentation Thread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4425 dirty pages from their submits' captures, 76466 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1245 dispatches, 51610 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5277 runs, 183.3 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32677 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.61, present 0.13, draw 3.16, descriptors 0.88, texture lookups 0.06, uploads 0.00, pipelines 0.15, programs 0.45, commands 1.38, dispatch 0.79, memory sync 0.32, queue submit 0.15, slot wait 0.02
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.19 MB synced in 1160.5 copies, 18.41 MB written back
[hos Presentation Thread] vk: 5040 presents, 63.4 fps; a frame: 1194 draws (0 skipped), 145 dispatches, 146 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); 32425 pipelines (3515999 ms), 0 programs (0 failed), 652 textures (1890 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.35 ms a frame (fences 0.01, timelines 4.34, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 409.9 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.8 ms a frame (the longest submission 9.3 ms); 0.0 textures made a frame
[hos Presentation Thread] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 275 pages written, 275 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.020; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (248 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 520000 (212692 pages from the captures)
[hos sead::MainThread] vk: late pages' fix (600 recordings with one): of 600 captures with late pages 600 fixed (137.3 pages, 138.3 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; 599 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 95 blocks (6080 KB); of the reads on the CPU, 0 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 592, of an earlier recording 7, not recorded yet 0, of this part 0; pages fixed from stamps 79377, from snapshots 3000; the shadows: 447101 pages synced from captures, 446478 made known by it, 623 left unknown because the replay or the collection wrote them since
[hos host] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4510 dirty pages from their submits' captures, 78150 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): 1260 dispatches, 52714 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5390 runs, 185.6 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33578 in captures, 0 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 259 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 1041110 kept (438573 by the last picks' textures, a uniform buffer bound since), 2844 new, 356045 with other textures (of 1400000)
[hos BaseProcExecutor1] vcores: 159609 takes, 14466 waits (mean 29 us, longest 1.4 ms, 0 over HOS_VCORE_LOG_MS), 6029 kicks, 6187 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #25000: event 0x100d6c8040 mode 0 value 24999 (lr 0x806621e8)
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos sead::MainThread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos sead::MainThread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos sead::MainThread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos sead::MainThread] vk: mirror syncs (600 submits): 4384 dirty pages from their submits' captures, 77269 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 sead::MainThread] vk: mirror syncs' pass (600 submits): 1246 dispatches, 51757 chunks; 0 syncs as copies (no table room)
[hos sead::MainThread] vk: write-back diff (600 submits): 5291 runs, 183.4 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32933 in captures, 0 only in the collection, 45 only by the replay itself
[hos sead::MainThread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos host] vk: replay reads of guest memory as submitted: 540000 (220054 pages from the captures)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 3000 of 3000 waited for their write-back, 0.07 ms each; 153 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: 1428 kept their virtual core (nothing there to wait for), 3180 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 279 pages written, 279 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.019; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (242 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos Presentation Thread] vk: 4 textures retired (650 left, 1889 MB): budget 4, drawn over 0, dead targets 0
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #45000: event 0x100d6c8030 mode 0 value 26078 (now 26059) (lr 0x806614d8)
[hos rmbl::VibrationThread] hid: 24576 vibration values, strongest 0.00 since the last count
[hos sead::MainThread] nvn: GPU waits in 5 s: 301 sync waits (1739 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos Presentation Thread] vi: 5152 frames presented (56.9 fps over the last 5.2 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 124, 15.5-17.8 160, 17.8-22 8, 22-30 0, 30-40 1, over 40 1
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 60000 so far (x1 0x117a4f2040 x2 0x6001d40 x3 0x117a4f2000 x4 0xf33080)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4561 dirty pages from their submits' captures, 77296 from earlier ones', 24 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1255 dispatches, 52111 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5241 runs, 181.8 MB compared; 71 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32738 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 24;
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.65, present 0.13, draw 3.23, descriptors 0.93, texture lookups 0.06, uploads 0.01, pipelines 0.11, programs 0.47, commands 1.40, dispatch 0.78, memory sync 0.30, queue submit 0.14, slot wait 0.02
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.20 MB synced in 1161.6 copies, 18.41 MB written back
[hos Presentation Thread] vk: 5160 presents, 49.4 fps; a frame: 1195 draws (0 skipped), 146 dispatches, 146 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3515999 ms), 0 programs (0 failed), 658 textures (1915 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 8.74 ms a frame (fences 0.01, timelines 8.73, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 411.1 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.9 ms a frame (the longest submission 9.3 ms); 0.1 textures made a frame
[hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 560000 (227658 pages from the captures)
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 260 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 380378 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos Presentation Thread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4456 dirty pages from their submits' captures, 78404 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1251 dispatches, 52342 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5386 runs, 185.2 MB compared; 74 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33677 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos Presentation Thread] vk: 8 textures retired (652 left, 1890 MB): budget 8, drawn over 0, dead targets 0
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 580000 (234811 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 279 pages written, 279 copied (1.1 MB)
[hos sead::MainThread] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (248 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos host] vk: program picks: 1194261 kept (505921 by the last picks' textures, a uniform buffer bound since), 2844 new, 402894 with other textures (of 1600000)
[hos Presentation Thread] vk: the recording streams: 48 of 2 MB, the most one held 380 KB; 0 made on demand (0 MB kept now); c1 stages: at most 94 a recording; 0 descriptor pools made when a recording's own ran out
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4568 dirty pages from their submits' captures, 76824 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1238 dispatches, 51675 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5287 runs, 183.5 MB compared; 71 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32862 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 260 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 600000 (241982 pages from the captures)
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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 Presentation Thread] vk: a frame's replay time (ms): submit 5.67, present 0.13, draw 3.13, descriptors 0.90, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.46, commands 1.35, dispatch 0.78, memory sync 0.32, queue submit 0.14, slot wait 0.02
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.25 MB synced in 1162.3 copies, 18.41 MB written back
[hos Presentation Thread] vk: 5280 presents, 62.6 fps; a frame: 1193 draws (0 skipped), 146 dispatches, 146 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); 32425 pipelines (3515999 ms), 0 programs (0 failed), 655 textures (1892 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.56 ms a frame (fences 0.01, timelines 4.55, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 410.3 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.9 ms a frame (the longest submission 9.3 ms); 0.0 textures made a frame
[hos Presentation Thread] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4492 dirty pages from their submits' captures, 79150 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1263 dispatches, 52887 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5390 runs, 185.5 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33666 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos sead::MainThread] vk: readbacks of GPU results: 3000 of 3000 waited for their write-back, 0.07 ms each; 157 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: 1391 kept their virtual core (nothing there to wait for), 2961 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: 3 textures retired (652 left, 1890 MB): budget 3, drawn over 0, dead targets 0
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37173): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5310 (texture frame 5311), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 276 pages written, 276 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.020; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (234 MB), 12 spare buffers, 4480 texture pages copied (17 MB)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37257): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5322 (texture frame 5323), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 620000 (249194 pages from the captures)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37341): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5334 (texture frame 5335), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4373 dirty pages from their submits' captures, 77150 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1243 dispatches, 51597 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5244 runs, 182.9 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32617 in captures, 0 only in the collection, 45 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37355): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5336 (texture frame 5337), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: 2 textures retired (650 left, 1889 MB): budget 2, drawn over 0, dead targets 0
[hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 262 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37439): uploaded again
[hos Presentation Thread] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5348 (texture frame 5349), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #50000: event 0x100d6c8030 mode 0 value 29878 (now 29859) (lr 0x806614d8)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #30000: event 0x100d6c8000 mode 0 value 29999 (lr 0x80291440)
[hos Presentation Thread] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37523): uploaded again
[hos Presentation Thread] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5360 (texture frame 5361), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos BaseProcExecutor1] vcores: 146570 takes, 12692 waits (mean 30 us, longest 1.5 ms, 0 over HOS_VCORE_LOG_MS), 5322 kicks, 5398 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37621): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5374 (texture frame 5375), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: sparse mirrors: 59, 954 MB with memory of 1268 MB (313 MB spared); blocks given memory later 1938, given back 4366; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 187 binds (14.3 ms); 1 made whole for want of memory
[hos Presentation Thread] vk: sparse mirrors' buffers: 18 taken from the spares, 93 made new; 51 kept as spares, 1 destroyed; 33 spares now, 772 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos Presentation Thread] vk: write-backs left out (600 submits): 1080, 4916.4 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos Presentation Thread] vk: mirror syncs (600 submits): 4569 dirty pages from their submits' captures, 78297 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1260 dispatches, 52748 chunks; 0 syncs as copies (no table room)
[hos Presentation Thread] vk: write-back diff (600 submits): 5347 runs, 184.9 MB compared; 72 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 33465 in captures, 0 only in the collection, 44 only by the replay itself
[hos Presentation Thread] vk:   read live, by pool:
[hos Presentation Thread] vk: imports: 91 live (1640 MB), 0 retired still imported (0 MB), 24 retired given back (812 MB)
[hos Presentation Thread] vk: replay reads of guest memory as submitted: 640000 (256362 pages from the captures)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37705): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5386 (texture frame 5387), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos ModuleSystemWorker1] nvn: 350000 recordings made, 38547 live copies (13.2 MB), 453 texture copies; 6 command buffers' segments (4.3 MB)
[hos Presentation Thread] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37789): uploaded again
[hos Presentation Thread] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5398 (texture frame 5399), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: memory: working set 17966 MB (peak 18168), private 9666 MB, staging 64 MB in 4 arenas, 44 made so far (74 ms)
[hos Presentation Thread] vk: memory heaps: heap 0 (device): 126 blocks 3981 MB, 16185 allocations 3225 MB; used 5010 of 10576 MB; heap 1 (system): 34 blocks 1034 MB, 44 allocations 955 MB; used 2694 of 23390 MB;
[hos Presentation Thread] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB
[hos Presentation Thread] vk: image blocks (render targets): 15 blocks 480 MB, 106 images 214 MB; 48 free ranges, the largest 26 MB
[hos Presentation Thread] vk: image blocks (textures, compacted): 21 blocks 672 MB, 507 images 625 MB; 174 free ranges, the largest 19 MB
[hos Presentation Thread] vk: render target images: 247 reused from the pool, 392 made new, 284 destroyed from it; it holds 0 (0 MB)
[hos Presentation Thread] vk: VRAM: 5010 MB used of 10576 MB allowed (756 MB of it free in the blocks); textures 1889 MB (budget 1054 MB), 650 textures
[hos Presentation Thread] vk: textures: decoded ASTC 712 MB, rendered 778 MB (112 drawn in one frame, kept: 51967 KB), other 217 MB; used in the last 8 presents 1321 MB
[hos Presentation Thread] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 0 listed; 932 MB of blocks hashed in 44 ms
[hos Presentation Thread] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1488 presents ago
[hos Presentation Thread] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos Presentation Thread] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos Presentation Thread] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos Presentation Thread] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos Presentation Thread] vk:   54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos Presentation Thread] vk:   37 MB: 0x110a311a00 1800x1380x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos Presentation Thread] vk:   32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1488 presents ago
[hos Presentation Thread] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos host] vk: malloc: 10905 MB in arenas (10052 MB in use, 852 MB free, 0 MB of it at the tops), 6 MB mapped
[hos Presentation Thread] vk: status: 600 frames, the slowest 529.2 ms; VRAM 4.9 of 10.3 GB
[hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos Presentation Thread] 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, 1 jobs queued
[hos Presentation Thread] vk: a frame's replay time (ms): submit 5.59, present 0.13, draw 3.15, descriptors 0.97, texture lookups 0.06, uploads 0.01, pipelines 0.11, programs 0.45, commands 1.31, dispatch 0.75, memory sync 0.32, queue submit 0.21, slot wait 0.02
[hos Presentation Thread] vk: a frame: mirrors 110 (954 MB): 7.22 MB synced in 1161.9 copies, 18.40 MB written back
[hos Presentation Thread] vk: 5400 presents, 63.2 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.1 uploads (0.1 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3515999 ms), 0 programs (0 failed), 650 textures (1889 MB)
[hos Presentation Thread] vk: host time in GPU resource waits: 4.44 ms a frame (fences 0.01, timelines 4.43, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos Presentation Thread] vk: a frame: 409.8 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos Presentation Thread] 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 Presentation Thread] vk: GPU time 12.9 ms a frame (the longest submission 9.4 ms); 0.0 textures made a frame
[hos Presentation Thread] vk: a frame: 0.15 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: malloc_trim: 852 MB free in the arenas now, the process's private memory 9666 -> 9495 MB (22 ms)
[hos Presentation Thread] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37803): uploaded again
[hos Presentation Thread] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5400 (texture frame 5401), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: program picks: 1346336 kept (573038 by the last picks' textures, a uniform buffer bound since), 2844 new, 450819 with other textures (of 1800000)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.03 over 847 ranges, 4191 MB), 279 pages written, 279 copied (1.1 MB)
[hos Presentation Thread] vk: a capture taken (ms): all 0.020; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (234 MB), 12 spare buffers, 4478 texture pages copied (17 MB)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37887): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5412 (texture frame 5413), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos Presentation Thread] vk: readback pages refreshed from guest memory: 447606 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 37971): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5424 (texture frame 5425), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos sead::MainThread] vk: write-backs left out (600 submits): 1056, 4807.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos sead::MainThread] vk: mirror syncs (600 submits): 4539 dirty pages from their submits' captures, 77327 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 sead::MainThread] vk: mirror syncs' pass (600 submits): 1243 dispatches, 51840 chunks; 0 syncs as copies (no table room)
[hos sead::MainThread] vk: write-back diff (600 submits): 5250 runs, 182.9 MB compared; 73 pages read into the shadows; 144 MB of shadows; pages the shadows knew that the CPU wrote: 32676 in captures, 0 only in the collection, 45 only by the replay itself
[hos sead::MainThread] vk:   read live, by pool:
[hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 257 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: texture #3443 0x100010e0400 960x540 NVN 0x3f: the GPU wrote its storage (submission 38069): uploaded again
[hos host] vk: upload over a drawn image: #3443 0x100010e0400 960x540x1 x1 NVN 0x3f at present 5438 (texture frame 5439), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: replay reads of guest memory as submitted: 660000 (263609 pages from the captures)
[hos host] vk: present 5439 written to /<user>/<user>/Beanstalk/jobs/jb_9b9182dee33aa156/runs/hyrule-field-g1-02-pr/shots/hyrule-field-c1-pr-02-field.png (the control bridge)
[hos host] control: quit asked by a client
[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)