Beanstalk Longshot test farm
Menu

Report rp_6f75df0f318b29e5 fail

#1702 perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; after #1121

windows+nvidia on Flashman4/agent-de36c5,

Machine

Commit
3569b8da6a4f90bc036bbb40cb52993b865b0a39
Baseline
09cbdd979eacfbd0c83e27fad7e50380985af02d
App
nightly-177-99542c21, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 9 5900X 12-Core Processor
gpu
NVIDIA GeForce RTX 3090
tags
windowsnvidianvidia-proprietarydgpu
driver
621.24.0
ram_gb
128
vram_mb
24,322
gpu_vendor
nvidia
os_version
Windows 10.0.26200

Builds

main (baseline)

691 s warm

from 09cbdd979eac

lift
0.3 s
read
573.3 s
finish
75.3 s
compile
11 s

PR

152.7 s warm

Program cache: warm

Scenarios

default-presenter

error

the game refused a step: refused: the game refused the teleport: an event is playing (a cutscene, a map change's)

Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count813+62.5%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms461.01356.16−22.7%
kokiri-standing.fps_mean73.5576+3.3%
market-standing.fps_mean61.9664.03+3.3%
kokiri-standing.draws_mean862.55823.6−4.5%
market-standing.draws_mean2,578.62,521.7−2.2%
kokiri-standing.hitch_count0.50−100%
market-standing.hitch_count00±0%
kokiri-after-motion.fps_mean79.6877.62−2.6%
market-after-motion.fps_mean66.5967.56+1.5%
kokiri-standing.stutter_count72−71.4%
market-standing.stutter_count22±0%
kokiri-after-motion.draws_mean752.05781.8+4%
market-after-motion.draws_mean1,717.11,740.65+1.4%
kokiri-after-motion.hitch_count00±0%
market-after-motion.hitch_count00±0%
kokiri-standing.frametime_max_ms50.4837.66−25.4%
kokiri-standing.frametime_p50_ms12.7412.76+0.1%
kokiri-standing.frametime_p99_ms23.3116.66−28.5%
market-standing.frametime_max_ms36.0634.92−3.2%
market-standing.frametime_p50_ms15.9215.43−3.1%
market-standing.frametime_p99_ms20.8420.22−3%
kokiri-after-motion.stutter_count32−33.3%
market-after-motion.stutter_count22±0%
kokiri-after-motion.frametime_max_ms30.8830.93+0.1%
kokiri-after-motion.frametime_p50_ms12.4212.66+1.9%
kokiri-after-motion.frametime_p99_ms17.2615.63−9.4%
market-after-motion.frametime_max_ms35.2535.68+1.2%
market-after-motion.frametime_p50_ms14.8714.69−1.2%
market-after-motion.frametime_p99_ms19.419.16−1.2%
kokiri-standing.frametime_1pct_low_ms29.420.61−29.9%
market-standing.frametime_1pct_low_ms24.824.22−2.3%
kokiri-after-motion.frametime_1pct_low_ms21.7920.32−6.8%
market-after-motion.frametime_1pct_low_ms23.823.88+0.3%
screenshot_diff—0.94—

Pictures against main: kokiri-standing 5 s diff 0.6244 (main against itself 0.622), kokiri-standing 9 s diff 0.6318 (main against itself 0.6323), kokiri-after-motion 5 s diff 0.8367 (main against itself 0.8392), kokiri-after-motion 9 s diff 0.9396 (main against itself 0.9365), market-standing 5 s diff 0.9085 (main against itself ), market-standing 9 s diff 0.9061 (main against itself ), market-after-motion 5 s diff 0.9345 (main against itself ), market-after-motion 9 s diff 0.9328 (main against itself ), kokiri-standing diff 0.626 (main against itself 0.6262), kokiri-after-motion diff 0.9365 (main against itself 0.9359), market-standing diff 0.9058 (main against itself ), market-after-motion diff 0.9361 (main against itself )

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code000—
run_hitch_count1212144
log_forbidden_hits0000
log_expected_missing0000
run_frametime_max_ms444.36316.7395.62477.67
kokiri-standing.fps_mean67.5476.8575.1679.55
market-standing.fps_mean61.9663.9864.07—
kokiri-standing.draws_mean819.3821.6825.6905.8
market-standing.draws_mean2,578.62,551.52,491.9—
kokiri-standing.hitch_count1000
market-standing.hitch_count000—
kokiri-after-motion.fps_mean76.3177.7777.4783.05
market-after-motion.fps_mean66.5968.0567.07—
kokiri-standing.stutter_count6228
market-standing.stutter_count222—
kokiri-after-motion.draws_mean842729834.6662.1
market-after-motion.draws_mean1,717.11,637.51,843.8—
kokiri-after-motion.hitch_count0000
market-after-motion.hitch_count000—
kokiri-standing.frametime_max_ms65.735.6539.6635.26
kokiri-standing.frametime_p50_ms13.7212.712.8211.77
kokiri-standing.frametime_p99_ms24.4115.717.6322.21
market-standing.frametime_max_ms36.0635.0234.82—
market-standing.frametime_p50_ms15.9215.4415.41—
market-standing.frametime_p99_ms20.8420.3620.09—
kokiri-after-motion.stutter_count2224
market-after-motion.stutter_count222—
kokiri-after-motion.frametime_max_ms30.9430.8730.9830.82
kokiri-after-motion.frametime_p50_ms12.8312.612.7212.01
kokiri-after-motion.frametime_p99_ms16.9815.271617.53
market-after-motion.frametime_max_ms35.2532.0339.32—
market-after-motion.frametime_p50_ms14.8714.6214.76—
market-after-motion.frametime_p99_ms19.419.0219.3—
kokiri-standing.frametime_1pct_low_ms33.6519.6421.5925.16
market-standing.frametime_1pct_low_ms24.82424.45—
kokiri-after-motion.frametime_1pct_low_ms20.9619.7520.8922.63
market-after-motion.frametime_1pct_low_ms23.82324.76—
screenshot_diff—0.940.94—

forced-presenter RX_VK_PRESENT_THREAD=1 (PR only)

error

the game refused a step: refused: the game refused the teleport: an event is playing (a cutscene, a map change's)

Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count10.58−23.8%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms203.44434.12+113.4%
kokiri-standing.fps_mean78.0679.17+1.4%
market-standing.fps_mean62.7763.93+1.8%
kokiri-standing.draws_mean868872.45+0.5%
market-standing.draws_mean2,506.42,570.1+2.5%
kokiri-standing.hitch_count00±0%
market-standing.hitch_count00±0%
kokiri-after-motion.fps_mean79.7280.67+1.2%
market-after-motion.fps_mean68.1564.85−4.8%
kokiri-standing.stutter_count24+100%
market-standing.stutter_count21−50%
kokiri-after-motion.draws_mean773.5789.2+2%
market-after-motion.draws_mean1,638.82,142.2+30.7%
kokiri-after-motion.hitch_count00±0%
market-after-motion.hitch_count00±0%
kokiri-standing.frametime_max_ms37.2239.67+6.6%
kokiri-standing.frametime_p50_ms12.411.9−4%
kokiri-standing.frametime_p99_ms17.4720.52+17.5%
market-standing.frametime_max_ms34.5832.86−5%
market-standing.frametime_p50_ms15.6315.57−0.4%
market-standing.frametime_p99_ms20.7120.42−1.4%
kokiri-after-motion.stutter_count33.5+16.7%
market-after-motion.stutter_count22±0%
kokiri-after-motion.frametime_max_ms32.7131.17−4.7%
kokiri-after-motion.frametime_p50_ms12.412.37−0.3%
kokiri-after-motion.frametime_p99_ms17.3217.05−1.5%
market-after-motion.frametime_max_ms35.8935.5−1.1%
market-after-motion.frametime_p50_ms14.6815.3+4.3%
market-after-motion.frametime_p99_ms18.7720.91+11.4%
kokiri-standing.frametime_1pct_low_ms21.5324.1+11.9%
market-standing.frametime_1pct_low_ms24.1623.38−3.2%
kokiri-after-motion.frametime_1pct_low_ms22.7922.48−1.4%
market-after-motion.frametime_1pct_low_ms24.2425.36+4.6%
screenshot_diff—0.52—

Pictures against main: kokiri-standing 5 s diff 0.1221 (main against itself 0.6272), kokiri-standing 9 s diff 0.1056 (main against itself 0.6241), kokiri-after-motion 5 s diff 0.3322 (main against itself 0.859), kokiri-after-motion 9 s diff 0.3308 (main against itself 0.94), market-standing 5 s diff 0.0377 (main against itself ), market-standing 9 s diff 0.0364 (main against itself ), market-after-motion 5 s diff 0.8597 (main against itself ), market-after-motion 9 s diff 0.8494 (main against itself ), kokiri-standing diff 0.1043 (main against itself 0.6218), kokiri-after-motion diff 0.3342 (main against itself 0.9437), market-standing diff 0.0382 (main against itself ), market-after-motion diff 0.8562 (main against itself )

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code——00
run_hitch_count851113
log_forbidden_hits0000
log_expected_missing0000
run_frametime_max_ms123.56515.43352.82283.32
kokiri-standing.fps_mean82.984.4673.8773.23
kokiri-standing.draws_mean919925.4819.5817
kokiri-standing.hitch_count0000
kokiri-after-motion.fps_mean83.1786.6474.7176.26
kokiri-standing.stutter_count2532
kokiri-after-motion.draws_mean653.2636.4942893.8
kokiri-after-motion.hitch_count0000
kokiri-standing.frametime_max_ms34.6633.6945.6539.77
kokiri-standing.frametime_p50_ms11.610.912.913.2
kokiri-standing.frametime_p99_ms14.6319.0621.9820.3
kokiri-after-motion.stutter_count4522
kokiri-after-motion.frametime_max_ms33.5430.0232.3231.88
kokiri-after-motion.frametime_p50_ms1211.5213.2112.79
kokiri-after-motion.frametime_p99_ms17.9616.6817.4316.67
kokiri-standing.frametime_1pct_low_ms17.9822.525.725.08
kokiri-after-motion.frametime_1pct_low_ms24.3423.6321.3321.24
screenshot_diff—0.170.86—
market-standing.fps_mean——63.9362.77
market-standing.draws_mean——2,570.12,506.4
market-standing.hitch_count——00
market-after-motion.fps_mean——64.8568.15
market-standing.stutter_count——12
market-after-motion.draws_mean——2,142.21,638.8
market-after-motion.hitch_count——00
market-standing.frametime_max_ms——32.8634.58
market-standing.frametime_p50_ms——15.5715.63
market-standing.frametime_p99_ms——20.4220.71
market-after-motion.stutter_count——22
market-after-motion.frametime_max_ms——35.535.89
market-after-motion.frametime_p50_ms——15.314.68
market-after-motion.frametime_p99_ms——20.9118.77
market-standing.frametime_1pct_low_ms——23.3824.16
market-after-motion.frametime_1pct_low_ms——25.3624.24

Rules

ScenarioCellRuleLimitmainPRΔ %Status
default-presentercrashFalse00—pass
default-presenterkokiri-standing.fps_mean.min_delta_pct1573.5576+3.3%pass
default-presenterkokiri-after-motion.fps_mean.min_delta_pct1579.6877.62−2.6%pass
default-presentermarket-standing.fps_mean.min_delta_pct1561.9664.03+3.3%pass
default-presentermarket-after-motion.fps_mean.min_delta_pct1566.5967.56+1.5%pass
default-presenterscreenshot.max_diff0.40.940.94—fail
default-presenterkokiri-standing.frametime_p99_ms.max_delta_pct2023.3116.66−28.5%pass
default-presenterkokiri-after-motion.frametime_p99_ms.max_delta_pct2017.2615.63−9.4%pass
default-presentermarket-standing.frametime_p99_ms.max_delta_pct2020.8420.22−3%pass
default-presentermarket-after-motion.frametime_p99_ms.max_delta_pct2019.419.16−1.2%pass
default-presenterlog_forbidden_hits.max000—pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)crashFalse00—pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-standing.fps_mean.min_delta_pct1578.0679.17+1.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.fps_mean.min_delta_pct1579.7280.67+1.2%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.fps_mean.min_delta_pct1562.7763.93+1.8%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.fps_mean.min_delta_pct1568.1564.85−4.8%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)screenshot.max_diff0.40.940.86—fail
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-standing.frametime_p99_ms.max_delta_pct2017.4720.52+17.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.frametime_p99_ms.max_delta_pct2017.3217.05−1.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.frametime_p99_ms.max_delta_pct2020.7120.42−1.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.frametime_p99_ms.max_delta_pct2018.7720.91+11.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)log_forbidden_hits.max000—pass

Pictures of the failure

This report had 3 pictures of its failure (the last frame of a stuck step, or main's and the PR's picture where they differed too much). The farm keeps those for a day: they were deleted.

Log (PR side, end)

[hos host] vk:   read live, by pool: 0x104c000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 122 live (1796 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: texture slots registered again at another size: 400000 (of 496463 registrations; slot 11524 512x512 -> 256x256)
[hos host] vk: late pages found at the replay (600 takes): 2 pages in 2 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 180000 so far (x1 0x11872d8020 x2 0 x3 0x11872d8000 x4 0x8b040)
[hos host] vk: replay reads of guest memory as submitted: 4100000 (2600121 pages from the captures)
[hos host] vk: pool 0x101ebb2600+0x960000 imported in 4.2 ms as 0x101e800000..0x101f800000 (137 imports, 169 ms in all)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.07
[hos host] vk: 11 textures retired (3387 left, 6363 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: replay reads of guest memory as submitted: 4120000 (2614804 pages from the captures)
[hos host] vk: 3 textures retired (3387 left, 6364 MB): budget 0, drawn over 0, dead targets 3
[hos ModuleSystemWorker1] nvn: 900000 recordings made, 83373 live copies (22.0 MB), 1698 texture copies; 4 command buffers' segments (4.2 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 11091 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #135000: event 0x10103c8000 mode 0 value 89216 (now 89197) (lr 0x82c0301c)
[hos host] vk: a frame: 180 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 8.69, present 0.44, draw 5.19, descriptors 2.07, texture lookups 0.42, uploads 0.05, pipelines 0.21, programs 0.90, commands 1.66, dispatch 0.74, memory sync 0.52, queue submit 0.55, slot wait 0.05
[hos host] vk: a frame: mirrors 182 (991 MB): 4.83 MB synced in 937.7 copies, 17.20 MB written back
[hos host] vk: 10920 presents, 67.5 fps; a frame: 1354 draws (0 skipped), 124 dispatches, 148 passes, 151 barriers, 6 submits, 0.2 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3390 textures (6367 MB)
[hos host] vk: host time in GPU resource waits: 0.65 ms a frame (fences 0.03, timelines 0.62, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 390.9 full barriers recorded, 195.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 39.8; 0x12: 79.0; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 2.7 ms); 2.6 textures made a frame
[hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: write-backs left out (600 submits): 1056, 5038.7 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 325 dirty pages from their submits' captures, 57222 from earlier ones', 16 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): 1151 dispatches, 44415 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6535 runs, 819.3 MB compared; 110 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 16640 in captures, 3 only in the collection, 386 only by the replay itself
[hos host] vk:   read live, by pool: 0x105f800000 (4 MB, captured, state 2): 10; 0x7f69c00000 (4 MB, captured, state 2): 6;
[hos host] vk: replay reads of guest memory as submitted: 4140000 (2629314 pages from the captures)
[hos sead::MainThread] vk: readbacks of GPU results: 1045 of 3000 waited for their write-back, 0.07 ms each; 0 looked at the stopped queues first, 13 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: 7466 kept their virtual core (nothing there to wait for), 3030 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: 4160000 (2643308 pages from the captures)
[hos host] vk: 11 textures retired (3407 left, 6357 MB): budget 0, drawn over 0, dead targets 11
[hos host] vk: program picks: 5106193 kept (2065731 by the last picks' textures, a uniform buffer bound since), 1935 new, 2091871 with other textures (of 7200000)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #90000: event 0x10103c8014 mode 0 value 90000 (lr 0x80660bcc)
[hos host] vk: replay reads of guest memory as submitted: 4180000 (2656574 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.00, scan 0.07 over 1161 ranges, 3494 MB), 228 pages written, 228 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.013; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 25 kept (100 MB), 10 spare buffers, 6690 texture pages copied (26 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 297 KB; 0 made on demand (0 MB kept now); c1 stages: at most 89 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 109, 1004 MB with memory of 1604 MB (599 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 367 binds (65.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 68 taken from the spares, 116 made new; 75 kept as spares, 0 destroyed; 7 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 901, 4301.9 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 366 dirty pages from their submits' captures, 49020 from earlier ones', 15 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): 966 dispatches, 37604 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5523 runs, 702.0 MB compared; 84 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 13476 in captures, 1 only in the collection, 331 only by the replay itself
[hos host] vk:   read live, by pool: 0x1067400000 (4 MB, captured, state 2): 14; 0x1066c00000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos BaseProcExecutor0] vcores: 157983 takes, 32075 waits (mean 86 us, longest 16.3 ms, 0 over HOS_VCORE_LOG_MS), 15952 kicks, 15801 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 4200000 (2669193 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 host] vk: recorder: 9889054 packets run in 10.0 s (busy 2.00 s, spun idle 5.30 s, slept 4430 times, 2253 of them under 200 us), 0 calls made directly (no room); the replay waited for it 29724 times, 124.47 ms in all, the longest 1.41 ms; vkEndCommandBuffer 11149/61.83 ms (max 0.17), vkResetDescriptorPool 11091/34.35 ms (max 1.41), replay_mu unlock 7432/27.85 ms (max 1.28), vkQueueBindSparse 31/0.28 ms (max 0.04), vmaInvalidateAllocation 21/0.16 ms (max 0.09)
[hos host] vk: replay reads of guest memory as submitted: 4220000 (2681739 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 749, 3571.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 467 dirty pages from their submits' captures, 43135 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): 888 dispatches, 32397 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4556 runs, 582.9 MB compared; 80 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11279 in captures, 0 only in the collection, 276 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 0.01, writes collected 0.07
[hos sead::MainThread] nvn: GPU waits in 5 s: 16 sync waits (31 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 4240000 (2694340 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2777 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1655463 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4260000 (2706944 pages from the captures)
[hos host] vk: sparse mirrors: 109, 1004 MB with memory of 1604 MB (599 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 367 binds (65.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 68 taken from the spares, 116 made new; 75 kept as spares, 0 destroyed; 7 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 542 dirty pages from their submits' captures, 43786 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): 900 dispatches, 32861 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4434 runs, 577.4 MB compared; 67 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11670 in captures, 2 only in the collection, 271 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: a frame: 328 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 10.18, present 0.32, draw 6.05, descriptors 2.27, texture lookups 0.18, uploads 0.02, pipelines 0.27, programs 1.03, commands 2.04, dispatch 0.70, memory sync 0.53, queue submit 0.60, slot wait 0.06
[hos host] vk: a frame: mirrors 184 (1004 MB): 5.03 MB synced in 944.1 copies, 17.08 MB written back
[hos host] vk: 11040 presents, 64.5 fps; a frame: 2001 draws (0 skipped), 114 dispatches, 149 passes, 150 barriers, 6 submits, 0.6 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3422 textures (6354 MB)
[hos host] vk: host time in GPU resource waits: 0.75 ms a frame (fences 0.03, timelines 0.72, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 392.5 full barriers recorded, 198.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 40.1; 0x12: 78.1; 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 2.5 ms); 0.8 textures made a frame
[hos host] vk: a frame: 0.06 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: program picks: 5251439 kept (2111830 by the last picks' textures, a uniform buffer bound since), 1943 new, 2146617 with other textures (of 7400000)
[hos host] vk: replay reads of guest memory as submitted: 4280000 (2719508 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1157 ranges, 3088 MB), 240 pages written, 240 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.012; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 6013 texture pages copied (23 MB)
[hos host] vk: replay reads of guest memory as submitted: 4300000 (2732097 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 770, 3674.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 627 dirty pages from their submits' captures, 43828 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): 896 dispatches, 33101 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4547 runs, 593.7 MB compared; 70 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11337 in captures, 0 only in the collection, 284 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1113 of 3000 waited for their write-back, 0.08 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: 7240 kept their virtual core (nothing there to wait for), 3000 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: 4320000 (2744676 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 host] vk: replay reads of guest memory as submitted: 4340000 (2757294 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.07
[hos host] vk: sparse mirrors: 109, 1004 MB with memory of 1604 MB (599 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 367 binds (65.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 68 taken from the spares, 116 made new; 75 kept as spares, 0 destroyed; 7 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 770, 3674.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 483 dirty pages from their submits' captures, 44338 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): 913 dispatches, 33323 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4555 runs, 593.9 MB compared; 79 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11612 in captures, 0 only in the collection, 275 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: replay reads of guest memory as submitted: 4360000 (2769872 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #140000: event 0x10103c8000 mode 0 value 93016 (now 92997) (lr 0x82c0301c)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7545 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vi: 11124 frames presented (65.6 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 217, 15.5-17.8 98, 17.8-22 12, 22-30 1, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 4380000 (2782494 pages from the captures)
[hos host] vk: program picks: 5396520 kept (2157856 by the last picks' textures, a uniform buffer bound since), 1947 new, 2201532 with other textures (of 7600000)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 297 KB; 0 made on demand (0 MB kept now); c1 stages: at most 89 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 575 dirty pages from their submits' captures, 43706 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): 900 dispatches, 32803 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4455 runs, 577.8 MB compared; 69 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11690 in captures, 0 only in the collection, 277 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4400000 (2795119 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.16 ms (lock 0.00, scan 0.06 over 1156 ranges, 3052 MB), 248 pages written, 248 copied (1.0 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 0.011, bytes copied 0.000; 25 kept (88 MB), 11 spare buffers, 6412 texture pages copied (25 MB)
[hos host] vk: a frame: 336 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 10.38, present 0.32, draw 6.23, descriptors 2.38, texture lookups 0.13, uploads 0.01, pipelines 0.28, programs 1.07, commands 2.04, dispatch 0.69, memory sync 0.53, queue submit 0.64, slot wait 0.06
[hos host] vk: a frame: mirrors 184 (1004 MB): 5.02 MB synced in 953.6 copies, 16.98 MB written back
[hos host] vk: 11160 presents, 65.1 fps; a frame: 2169 draws (0 skipped), 112 dispatches, 152 passes, 151 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3439 textures (6356 MB)
[hos host] vk: host time in GPU resource waits: 0.86 ms a frame (fences 0.03, timelines 0.83, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 392.4 full barriers recorded, 200.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 40.1; 0x12: 78.5; 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 2.4 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4420000 (2807805 pages from the captures)
[hos host] vk: sparse mirrors: 109, 1004 MB with memory of 1604 MB (599 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 367 binds (65.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 68 taken from the spares, 116 made new; 75 kept as spares, 0 destroyed; 7 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 770, 3674.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 569 dirty pages from their submits' captures, 43761 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): 896 dispatches, 33071 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4551 runs, 594.5 MB compared; 81 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11250 in captures, 0 only in the collection, 296 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: replay reads of guest memory as submitted: 4440000 (2820437 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1104 of 3000 waited for their write-back, 0.09 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 6972 kept their virtual core (nothing there to wait for), 3012 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: mirror of pool 0x7f72400000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: mirror of pool 0x7fdb800000 (12 MB) given back: idle, 6064 submissions since its sync
[hos host] vk: mirror of pool 0x7fa6800000 (8 MB) given back: idle, 6050 submissions since its sync
[hos host] vk: mirror of pool 0x7fc2000000 (8 MB) given back: idle, 6032 submissions since its sync
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.07
[hos host] vk: render targets drawn over from another start, let go: 2379 so far (13010 MB), 2174 of them (11730 MB) between the passes
[hos host] vk: readback pages refreshed from guest memory: 1740235 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4460000 (2832989 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 770, 3674.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 425 dirty pages from their submits' captures, 44438 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): 914 dispatches, 33348 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4562 runs, 593.8 MB compared; 71 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11662 in captures, 0 only in the collection, 289 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: mirror of pool 0x7fddc00000 (4 MB) given back: idle, 6042 submissions since its sync
[hos host] vk: mirror of pool 0x1066800000 (4 MB) given back: idle, 6025 submissions since its sync
[hos host] vk: mirror of pool 0x7fab400000 (4 MB) given back: idle, 6025 submissions since its sync
[hos host] vk: mirror of pool 0x7f86000000 (4 MB) given back: idle, 6025 submissions since its sync
[hos host] vk: 83 mirrors given back (710 MB in all); 983 MB of mirrors now, 100 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: mirror of pool 0x7fe2800000 (8 MB) given back: idle, 6018 submissions since its sync
[hos host] vk: mirror of pool 0x7fe1400000 (4 MB) given back: idle, 6055 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4480000 (2845560 pages from the captures)
[hos host] vk: mirror of pool 0x7f58000000 (4 MB) given back: idle, 6061 submissions since its sync
[hos host] vk: mirror of pool 0x7f7bc00000 (4 MB) given back: idle, 6013 submissions since its sync
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #95000: event 0x10103c8020 mode 0 value 95000 (lr 0x80664f14)
[hos host] vk: program picks: 5541645 kept (2203937 by the last picks' textures, a uniform buffer bound since), 1948 new, 2256406 with other textures (of 7800000)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9463 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4500000 (2858157 pages from the captures)
[hos host] vk: sparse mirrors: 99, 976 MB with memory of 1544 MB (567 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 375 binds (66.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 87 kept as spares, 0 destroyed; 17 spares now, 360 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 779 dirty pages from their submits' captures, 42997 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): 892 dispatches, 32505 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4428 runs, 576.9 MB compared; 77 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11280 in captures, 0 only in the collection, 272 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: mirror of pool 0x7f72800000 (8 MB) given back: idle, 6035 submissions since its sync
[hos host] vk: mirror of pool 0x7f69c00000 (4 MB) given back: idle, 6012 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4520000 (2870768 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1157 ranges, 3030 MB), 239 pages written, 239 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (86 MB), 11 spare buffers, 4909 texture pages copied (19 MB)
[hos host] vk: mirror of pool 0x7f69800000 (4 MB) given back: idle, 6012 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4540000 (2883340 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 515 dirty pages from their submits' captures, 43923 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): 929 dispatches, 32952 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4466 runs, 581.0 MB compared; 77 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11598 in captures, 1 only in the collection, 260 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: mirror of pool 0x7f7a800000 (8 MB) given back: idle, 6016 submissions since its sync
[hos host] vk: mirror of pool 0x104bc00000 (4 MB) given back: idle, 6013 submissions since its sync
[hos host] vk: slow present: 18.7 ms:
[hos host] vk: late pages' fix (600 recordings with one): of 1067 captures with late pages 1041 fixed (39.3 pages, 39.3 fixes a capture), waited as before: 0 no pool, 26 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; 68 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 105 blocks (6720 KB); of the reads on the CPU, 3 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 43, of an earlier recording 22, not recorded yet 0, of this part 0; pages fixed from stamps 40213, from snapshots 703; the shadows: 1830488 pages synced from captures, 1780753 made known by it, 48996 left unknown because the replay or the collection wrote them since
[hos host] vk: present 11277 written to <home>\AppData\Local\<user>\data\jobs\jb_23d863037c761b45\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion_5s.png (the control bridge)
[hos host] vk: a frame: 337 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 10.36, present 0.41, draw 6.32, descriptors 2.35, texture lookups 0.08, uploads 0.00, pipelines 0.29, programs 1.08, commands 2.13, dispatch 0.68, memory sync 0.51, queue submit 0.61, slot wait 0.06
[hos host] vk: a frame: mirrors 186 (968 MB): 5.04 MB synced in 955.3 copies, 17.01 MB written back
[hos host] vk: 11280 presents, 64.5 fps; a frame: 2173 draws (0 skipped), 112 dispatches, 152 passes, 151 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3442 textures (6357 MB)
[hos host] vk: host time in GPU resource waits: 0.91 ms a frame (fences 0.03, timelines 0.88, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 392.6 full barriers recorded, 200.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 40.1; 0x12: 78.5; 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 2.4 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: mirror of pool 0x7fd7400000 (4 MB) given back: idle, 6014 submissions since its sync
[hos host] vk: mirror of pool 0x7f99400000 (16 MB) given back: idle, 6064 submissions since its sync
[hos host] vk: mirror of pool 0x7f9c000000 (8 MB) given back: idle, 6062 submissions since its sync
[hos host] vk: mirror of pool 0x7f73800000 (4 MB) given back: idle, 6006 submissions since its sync
[hos host] vk: 96 mirrors given back (743 MB in all); 952 MB of mirrors now, 100 MB of them idle and kept for what the GPU wrote there alone
[hos ModuleSystemWorker1] nvn: 950000 recordings made, 83922 live copies (25.6 MB), 1698 texture copies; 3 command buffers' segments (4.6 MB)
[hos host] vk: replay reads of guest memory as submitted: 4560000 (2895942 pages from the captures)
[hos host] vk: mirror of pool 0x7fb2000000 (8 MB) given back: idle, 6036 submissions since its sync
[hos ModuleSystemWorker1] vcores: 159486 takes, 30623 waits (mean 79 us, longest 18.6 ms, 0 over HOS_VCORE_LOG_MS), 15605 kicks, 15443 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker1] tex: the game's texture heap: 92 compaction rounds asked for in 10800 frames without one running
[hos host] vk: late pages found at the replay (600 takes): 77 pages in 4 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 0.07
[hos host] vk: mirror of pool 0x7f9ac00000 (4 MB) given back: idle, 6010 submissions since its sync
[hos host] vk: mirror of pool 0x7fde000000 (4 MB) given back: idle, 6006 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4580000 (2908514 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 297 KB; 0 made on demand (0 MB kept now); c1 stages: at most 89 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 87, 940 MB with memory of 1468 MB (527 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 383 binds (67.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 99 kept as spares, 0 destroyed; 29 spares now, 436 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 769, 3672.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 689 dirty pages from their submits' captures, 43604 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): 895 dispatches, 33029 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4563 runs, 596.8 MB compared; 84 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11119 in captures, 0 only in the collection, 276 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: program picks: 5686905 kept (2249832 by the last picks' textures, a uniform buffer bound since), 1948 new, 2311146 with other textures (of 8000000)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #145000: event 0x10103c8000 mode 0 value 96816 (now 96797) (lr 0x82c0301c)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1081 of 3000 waited for their write-back, 0.09 ms each; 0 looked at the stopped queues first, 2 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: 7221 kept their virtual core (nothing there to wait for), 3019 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: 4600000 (2921078 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4768 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] nvn: GPU waits in 5 s: 11 sync waits (28 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 4620000 (2933714 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 749, 3571.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 533 dirty pages from their submits' captures, 43760 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): 905 dispatches, 32813 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4431 runs, 577.0 MB compared; 71 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11667 in captures, 1 only in the collection, 290 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.00, scan 0.06 over 1152 ranges, 3026 MB), 249 pages written, 249 copied (1.0 MB)
[hos host] vk: a capture taken (ms): all 0.017; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.013, bytes copied 0.000; 25 kept (80 MB), 10 spare buffers, 4467 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 4640000 (2946447 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1825706 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4660000 (2958965 pages from the captures)
[hos host] vk: sparse mirrors: 87, 940 MB with memory of 1468 MB (527 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 383 binds (67.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 99 kept as spares, 0 destroyed; 29 spares now, 436 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 769, 3672.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 554 dirty pages from their submits' captures, 43920 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): 892 dispatches, 33066 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4554 runs, 596.1 MB compared; 71 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11306 in captures, 0 only in the collection, 273 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: replay reads of guest memory as submitted: 4680000 (2971611 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.07
[hos host] vk: memory: working set 13296 MB (peak 13304), private 22638 MB, staging 32 MB in 2 arenas, 35 made so far (5 ms)
[hos host] vk: memory heaps: heap 0 (device): 256 blocks 8295 MB, 18786 allocations 7833 MB; used 8755 of 23554 MB; heap 1 (system): 14 blocks 656 MB, 39 allocations 566 MB; used 2566 of 104029 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 5 images 16 MB; 1 free ranges, the largest 15 MB
[hos host] vk: image blocks (render targets): 22 blocks 704 MB, 108 images 396 MB; 48 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 141 blocks 4512 MB, 3343 images 4477 MB; 1681 free ranges, the largest 7 MB
[hos host] vk: render target images: 1588 reused from the pool, 1128 made new, 1015 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 8755 MB used of 23554 MB allowed (461 MB of it free in the blocks); textures 6364 MB (budget 11000 MB), 3467 textures
[hos host] vk: budget: VRAM 8295 of 23554 MB (8755 MB by the driver, 460 MB unaccounted): textures 6364, mirrors 940, blocks free 461, shadows 308, other buffers 156, staging 32, other images 31; RAM 2418 MB (the process's private memory 22638 MB): imports 1820, capture spares 468, captures 88, capture table 32, other buffers 10, others 0
[hos host] vk: textures: decoded ASTC 4099 MB, rendered 1109 MB (49 drawn in one frame, kept: 49593 KB), other 718 MB; used in the last 8 presents 2466 MB
[hos host] vk: decoded ASTC used again: 161 textures (223 MB) copied from ones the game finalized, not decoded; 161 of those retired, 393 listed; 883 MB of blocks hashed in 101 ms
[hos host] vk:   288 MB: 0x1150c06000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10aea22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 3557 presents ago
[hos host] vk:   214 MB: 0x10ab1aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 3557 presents ago
[hos host] vk:   64 MB: 0x114045c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 6220 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 0x34 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10005b2da00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2159 presents ago
[hos host] vk:   54 MB: 0x1000558d800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6207 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 56 (12391 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 64x62x1 NVN 0x25: 1 (15 KB); 73x33x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 128x126x1 NVN 0x1: 1 (15 KB); 137x97x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB);
[hos host] vk: late pages found at the replay (600 takes): 1 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: presents after the CPU's signal (600): 36 waited for it, 1.31 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: program picks: 5832095 kept (2295765 by the last picks' textures, a uniform buffer bound since), 1948 new, 2365956 with other textures (of 8200000)
[hos host] vk: status: 600 frames, the slowest 29.2 ms; VRAM 8.6 of 23.0 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 135 program records loaded (34.2 ms), 1 new graphics pipelines, pipelines from the driver's cache 1, from the start's cache 0, compiled 20; 324 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5348 queued, 5348 loaded (median 4.67 ms, 99th percentile 21.51 ms, worst 39.76 ms, 31181 ms and 1253.6 MB read in all); 7771 programs (1639 of them compute variants without their code, 0 graphics programs no note names), 9503 graphics pipelines (0 not in a cache), 372 compute pipelines (297 not in a cache); a first use ran 35 itself and waited for 0 (107.1 ms); 1671 pipelines made at create taken by draws; 2900 create calls with nothing kept for their stages, 0 before the index; units 8248 (5348 ready, 0 loading), 14342 programs alive; 45 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 670 known, 0 learned in this run; 372 compute pipelines made by them at a create call, 297 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 340 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 10.50, present 0.29, draw 6.32, descriptors 2.39, texture lookups 0.15, uploads 0.04, pipelines 0.29, programs 1.07, commands 2.09, dispatch 0.69, memory sync 0.52, queue submit 0.62, slot wait 0.06
[hos host] vk: a frame: mirrors 186 (940 MB): 5.02 MB synced in 954.0 copies, 17.01 MB written back
[hos host] vk: 11400 presents, 64.8 fps; a frame: 2174 draws (0 skipped), 112 dispatches, 152 passes, 151 barriers, 6 submits, 0.4 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3467 textures (6364 MB)
[hos host] vk: host time in GPU resource waits: 0.79 ms a frame (fences 0.03, timelines 0.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 393.6 full barriers recorded, 200.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 40.2; 0x12: 78.5; 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 2.4 ms); 0.4 textures made a frame
[hos host] vk: a frame: 0.04 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 15.32 ms a frame): its jobs 11.00 ms a frame (submits 9.82, presents 0.37, others 0.81), idle 4.33; the game waited for room at 1 presents, 13.16 ms each (0.02 a frame; 1.59 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); 42 captures at a CPU signal; the submits' waits read in 0.061 ms a frame; readbacks: 768 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 9.76 ms after its hand-over (29.54 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 4.01 + 0.28 (the window's copy is in the idle), after it 2.50 + 0.52; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.03 ms of GPU time), after its last that reads it 1.00 (0.03 ms)
[hos host] vk: frame ahead (600 presents): 10.69 parts a frame recorded in the signal's job, 78.8% of them took nothing that came with the signal; of the others, 2.26 a frame took pages of the signal's capture into a mirror (45.3 pages a frame) and 0.02 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 8 of 42 frames, its first three in 8
[hos host] vk: frame ahead, what came with the signal: 42 signals with a capture, each of 132.2 pages in 10.2 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: 0.46+0.06, 0.37+0.05, 0.34+0.05, 0.58+0.09, 0.36+0.08, 0.15+0.05, 0.13+0.04, 0.02+0.03, 0.03+0.02, 0.03+0.02, 0.02+0.02, 0.01+0.01
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 200000 so far (x1 0x1182746000 x2 0 x3 0x1182746000 x4 0x654040)
[hos host] vk: replay reads of guest memory as submitted: 4700000 (2984236 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 749, 3571.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 404 dirty pages from their submits' captures, 43216 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): 887 dispatches, 32437 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4472 runs, 578.0 MB compared; 67 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11354 in captures, 1 only in the collection, 288 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4720000 (2996816 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9118 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4740000 (3009402 pages from the captures)
[hos host] vk: sparse mirrors: 87, 940 MB with memory of 1468 MB (527 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 383 binds (67.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 99 kept as spares, 0 destroyed; 29 spares now, 436 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 770, 3674.0 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 405 dirty pages from their submits' captures, 44428 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): 914 dispatches, 33331 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4567 runs, 594.6 MB compared; 73 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11637 in captures, 2 only in the collection, 290 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1117 of 3000 waited for their write-back, 0.08 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: 7006 kept their virtual core (nothing there to wait for), 2978 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vi: 11448 frames presented (64.7 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 194, 15.5-17.8 124, 17.8-22 5, 22-30 1, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1148 ranges, 3024 MB), 237 pages written, 237 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.006, bytes copied 0.000; 25 kept (94 MB), 12 spare buffers, 4464 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 4760000 (3022119 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4780000 (3034678 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 297 KB; 0 made on demand (0 MB kept now); c1 stages: at most 89 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 376 dirty pages from their submits' captures, 43323 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): 890 dispatches, 32498 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4403 runs, 575.6 MB compared; 77 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11264 in captures, 2 only in the collection, 283 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #100000: event 0x10103c8028 mode 0 value 99999 (lr 0x80667410)
[hos host] vk: program picks: 5977174 kept (2341633 by the last picks' textures, a uniform buffer bound since), 1948 new, 2420877 with other textures (of 8400000)
[hos host] vk: replay reads of guest memory as submitted: 4800000 (3047204 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.07
[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: 4820000 (3059812 pages from the captures)
[hos host] vk: sparse mirrors: 87, 940 MB with memory of 1468 MB (527 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 383 binds (67.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 99 kept as spares, 0 destroyed; 29 spares now, 436 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 730 dirty pages from their submits' captures, 43045 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): 889 dispatches, 32525 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4449 runs, 581.1 MB compared; 68 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11255 in captures, 1 only in the collection, 278 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos ModuleSystemWorker2] nvn: CommandBufferWaitEvent #150000: event 0x10103c8000 mode 0 value 100616 (now 100597) (lr 0x82c0301c)
[hos host] vk: a frame: 340 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 10.40, present 0.28, draw 6.26, descriptors 2.38, texture lookups 0.17, uploads 0.04, pipelines 0.29, programs 1.04, commands 2.09, dispatch 0.69, memory sync 0.54, queue submit 0.62, slot wait 0.06
[hos host] vk: a frame: mirrors 186 (940 MB): 5.02 MB synced in 954.6 copies, 17.00 MB written back
[hos host] vk: 11520 presents, 65.0 fps; a frame: 2175 draws (0 skipped), 112 dispatches, 152 passes, 151 barriers, 6 submits, 0.4 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 43826 pipelines (4906794 ms), 0 programs (0 failed), 3483 textures (6371 MB)
[hos host] vk: host time in GPU resource waits: 0.82 ms a frame (fences 0.03, timelines 0.78, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 393.6 full barriers recorded, 200.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 40.1; 0x12: 78.5; 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 2.4 ms); 0.4 textures made a frame
[hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: replay reads of guest memory as submitted: 4840000 (3072357 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7639 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: slow present: 18.1 ms:
[hos host] vk: present 11536 written to <home>\AppData\Local\<user>\data\jobs\jb_23d863037c761b45\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion_9s.png (the control bridge)
[hos host] vk: readback pages refreshed from guest memory: 1910801 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 4860000 (3084928 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 748, 3569.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 768 dirty pages from their submits' captures, 43321 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): 897 dispatches, 32710 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4439 runs, 579.5 MB compared; 95 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 10975 in captures, 1 only in the collection, 275 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.16 ms (lock 0.00, scan 0.06 over 1149 ranges, 3032 MB), 257 pages written, 257 copied (1.0 MB)
[hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.019, bytes copied 0.000; 25 kept (88 MB), 11 spare buffers, 7000 texture pages copied (27 MB)
[hos host] vk: replay reads of guest memory as submitted: 4880000 (3097585 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1099 of 3000 waited for their write-back, 0.08 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: 7335 kept their virtual core (nothing there to wait for), 3161 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: program picks: 6122662 kept (2387417 by the last picks' textures, a uniform buffer bound since), 1950 new, 2475387 with other textures (of 8600000)
[hos host] vk: replay reads of guest memory as submitted: 4900000 (3110161 pages from the captures)
[hos host] vk: sparse mirrors: 87, 940 MB with memory of 1468 MB (527 MB spared); blocks given memory later 1953, given back 5471; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 383 binds (67.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 70 taken from the spares, 116 made new; 99 kept as spares, 0 destroyed; 29 spares now, 436 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 769, 3672.1 MB; 32 bindings followed, 48 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 517 dirty pages from their submits' captures, 43929 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): 895 dispatches, 33108 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4572 runs, 595.4 MB compared; 75 pages read into the shadows; 308 MB of shadows; pages the shadows knew that the CPU wrote: 11610 in captures, 1 only in the collection, 279 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 125 live (1820 MB), 0 retired still imported (0 MB), 14 retired given back (344 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.07
[hos host] vk: queues ordered by their events: 60000 submissions stopped at a wait, 59999 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 152049, not met 0; captures at a CPU event's wait 5080, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 4920000 (3122704 pages from the captures)
[hos host] vk: slow present: 18.0 ms:
[hos host] vk: present 11601 written to <home>\AppData\Local\<user>\data\jobs\jb_23d863037c761b45\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion.png (the control bridge)
[hos host] vk: late pages found at the replay (600 takes): 156 pages in 3 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] control: quit asked by a client
[hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 135 program records loaded (34.2 ms), 1 new graphics pipelines, pipelines from the driver's cache 1, from the start's cache 0, compiled 20; 324 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (close): 5348 queued, 5348 loaded (median 4.67 ms, 99th percentile 21.51 ms, worst 39.76 ms, 31181 ms and 1253.6 MB read in all); 7771 programs (1639 of them compute variants without their code, 0 graphics programs no note names), 9503 graphics pipelines (0 not in a cache), 372 compute pipelines (297 not in a cache); a first use ran 35 itself and waited for 0 (107.1 ms); 1672 pipelines made at create taken by draws; 2900 create calls with nothing kept for their stages, 0 before the index; units 8248 (5348 ready, 0 loading), 14342 programs alive; 45 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (close): 670 known, 0 learned in this run; 372 compute pipelines made by them at a create call, 297 asked that way were in no cache (their code read, as before)
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4310 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)