Beanstalk Longshot test farm
Menu

Report rp_c45a1107923a365f fail

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

windows+amd on Razytos/agent-d8f902,

Machine

Commit
3569b8da6a4f90bc036bbb40cb52993b865b0a39
Baseline
09cbdd979eacfbd0c83e27fad7e50380985af02d
App
nightly-172-736563c0, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
AMD Radeon RX 9070 XT
tags
windowsamdamd-proprietarydgpu
driver
2.0.416
ram_gb
32
vram_mb
16,304
gpu_vendor
amd
os_version
Windows 10.0.26300

Builds

main (baseline)

666.3 s warm

from 09cbdd979eac

lift
1.4 s
read
545.2 s
finish
87.7 s
compile
25.2 s

PR

172.9 s warm

Program cache: warm

Scenarios

forest-market RX_VK_PRESENT_THREAD=0

ok
Metric (median)mainPRΔ
exit_code00±0%
forest.fps_mean60.0259.77−0.4%
market.fps_mean59.9960.12+0.2%
forest.draws_mean672.4761.8+13.3%
market.draws_mean2,525.62,436.8−3.5%
forest.hitch_count00±0%
market.hitch_count00±0%
forest.stutter_count00±0%
market.stutter_count00±0%
forest.frametime_max_ms24.3122.51−7.4%
forest.frametime_p50_ms16.5116.64+0.8%
forest.frametime_p99_ms19.7918.6−6%
market.frametime_max_ms24.8922.89−8%
market.frametime_p50_ms16.5516.67+0.7%
market.frametime_p99_ms20.6720.73+0.3%
forest.frametime_1pct_low_ms21.9119.33−11.8%
market.frametime_1pct_low_ms21.9121.52−1.8%
screenshot_diff—0.71—

Pictures against main: forest diff 0.7096 (main against itself ), market diff 0.0858 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
forest.fps_mean60.0259.77
market.fps_mean59.9960.12
forest.draws_mean672.4761.8
market.draws_mean2,525.62,436.8
forest.hitch_count00
market.hitch_count00
forest.stutter_count00
market.stutter_count00
forest.frametime_max_ms24.3122.51
forest.frametime_p50_ms16.5116.64
forest.frametime_p99_ms19.7918.6
market.frametime_max_ms24.8922.89
market.frametime_p50_ms16.5516.67
market.frametime_p99_ms20.6720.73
forest.frametime_1pct_low_ms21.9119.33
market.frametime_1pct_low_ms21.9121.52
screenshot_diff—0.71

forest-market RX_VK_PRESENT_THREAD=1

ok
Metric (median)mainPRΔ
exit_code00±0%
forest.fps_mean59.5660.03+0.8%
market.fps_mean6060.02+0%
forest.draws_mean757.1757.1±0%
market.draws_mean2,540.22,505.7−1.4%
forest.hitch_count00±0%
market.hitch_count00±0%
forest.stutter_count00±0%
market.stutter_count00±0%
forest.frametime_max_ms20.2820.13−0.7%
forest.frametime_p50_ms16.6416.63−0.1%
forest.frametime_p99_ms19.0618.48−3%
market.frametime_max_ms24.2723.47−3.3%
market.frametime_p50_ms16.5816.6+0.1%
market.frametime_p99_ms20.720.74+0.2%
forest.frametime_1pct_low_ms19.4818.94−2.7%
market.frametime_1pct_low_ms21.6921.55−0.7%
screenshot_diff—0.15—

Pictures against main: forest diff 0.1547 (main against itself ), market diff 0.1314 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
forest.fps_mean59.5660.03
market.fps_mean6060.02
forest.draws_mean757.1757.1
market.draws_mean2,540.22,505.7
forest.hitch_count00
market.hitch_count00
forest.stutter_count00
market.stutter_count00
forest.frametime_max_ms20.2820.13
forest.frametime_p50_ms16.6416.63
forest.frametime_p99_ms19.0618.48
market.frametime_max_ms24.2723.47
market.frametime_p50_ms16.5816.6
market.frametime_p99_ms20.720.74
forest.frametime_1pct_low_ms19.4818.94
market.frametime_1pct_low_ms21.6921.55
screenshot_diff—0.15

Rules

ScenarioCellRuleLimitmainPRΔ %Status
forest-marketRX_VK_PRESENT_THREAD=0crashFalse00—pass
forest-marketRX_VK_PRESENT_THREAD=0forest.fps_mean.min_delta_pct1060.0259.77−0.4%pass
forest-marketRX_VK_PRESENT_THREAD=0market.fps_mean.min_delta_pct1059.9960.12+0.2%pass
forest-marketRX_VK_PRESENT_THREAD=0screenshot.max_diff0.1—0.71—fail
forest-marketRX_VK_PRESENT_THREAD=0forest.frametime_p99_ms.max_delta_pct1519.7918.6−6%pass
forest-marketRX_VK_PRESENT_THREAD=0market.frametime_p99_ms.max_delta_pct1520.6720.73+0.3%pass
forest-marketRX_VK_PRESENT_THREAD=1crashFalse00—pass
forest-marketRX_VK_PRESENT_THREAD=1forest.fps_mean.min_delta_pct1059.5660.03+0.8%pass
forest-marketRX_VK_PRESENT_THREAD=1market.fps_mean.min_delta_pct106060.02±0%pass
forest-marketRX_VK_PRESENT_THREAD=1screenshot.max_diff0.1—0.15—fail
forest-marketRX_VK_PRESENT_THREAD=1forest.frametime_p99_ms.max_delta_pct1519.0618.48−3%pass
forest-marketRX_VK_PRESENT_THREAD=1market.frametime_p99_ms.max_delta_pct1520.720.74+0.2%pass

Pictures of the failure

This report had 2 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: mirror of pool 0x7f9d400000 (12 MB) given back: idle, 6023 submissions since its sync
[hos host] vk: program picks: 2440623 kept (906090 by the last picks' textures, a uniform buffer bound since), 19581 new, 939795 with other textures (of 3400000)
[hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.00 since the last count
[hos host] vk: replay reads of guest memory as submitted: 1900000 (1108243 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 296 KB; 0 made on demand (0 MB kept now); c1 stages: at most 107 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 75, 974 MB with memory of 1464 MB (489 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 357 binds (24.9 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 48 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 29 spares now, 484 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 954 dirty pages from their submits' captures, 38075 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): 737 dispatches, 29436 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4213 runs, 561.3 MB compared; 57 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7380 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 1920000 (1121576 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 1940000 (1134927 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7817 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[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 host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 804 dirty pages from their submits' captures, 38593 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): 745 dispatches, 29958 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4311 runs, 576.4 MB compared; 56 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7379 in captures, 0 only in the collection, 32 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1960000 (1148261 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 1980000 (1161620 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 923 ranges, 3610 MB), 229 pages written, 229 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (124 MB), 11 spare buffers, 7917 texture pages copied (30 MB)
[hos NavMeshDepWorker2] vcores: 132515 takes, 22988 waits (mean 75 us, longest 17.5 ms, 0 over HOS_VCORE_LOG_MS), 11923 kicks, 11766 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 76, 975 MB with memory of 1468 MB (492 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 358 binds (25.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 49 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 28 spares now, 480 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1461 dirty pages from their submits' captures, 37557 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): 735 dispatches, 29426 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4218 runs, 558.2 MB compared; 64 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7396 in captures, 0 only in the collection, 29 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: readback pages refreshed from guest memory: 817156 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 2590169 kept (957449 by the last picks' textures, a uniform buffer bound since), 19588 new, 990242 with other textures (of 3600000)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #70000: event 0x100c31803c mode 0 value 48956 (now 48937) (lr 0x80662e5c)
[hos sead::MainThread] nvn: GPU waits in 5 s: 100 sync waits (107 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 2000000 (1174954 pages from the captures)
[hos host] vk: a frame: 392 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.63, present 0.12, draw 7.96, descriptors 3.01, texture lookups 0.10, uploads 0.03, pipelines 0.40, programs 1.17, commands 2.76, dispatch 0.77, memory sync 0.41, queue submit 0.71, slot wait 0.33
[hos host] vk: a frame: mirrors 153 (975 MB): 4.92 MB synced in 949.1 copies, 18.16 MB written back
[hos host] vk: 4560 presents, 60.0 fps; a frame: 2500 draws (0 skipped), 123 dispatches, 149 passes, 150 barriers, 6 submits, 0.7 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1352 textures (2572 MB)
[hos host] vk: host time in GPU resource waits: 1.30 ms a frame (fences 0.04, timelines 1.26, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 411.6 full barriers recorded, 202.8 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.8 ms a frame (the longest submission 2.7 ms); 0.7 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: 2020000 (1188241 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1154 dirty pages from their submits' captures, 37142 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): 734 dispatches, 28847 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4097 runs, 541.5 MB compared; 52 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7430 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2040000 (1201602 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 2060000 (1214950 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #50000: event 0x100c318034 mode 0 value 49999 (lr 0x806616b0)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1035 dirty pages from their submits' captures, 37273 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): 724 dispatches, 29082 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4269 runs, 562.8 MB compared; 59 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7210 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1149 of 3000 waited for their write-back, 0.11 ms each; 0 looked at the stopped queues first, 6 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: 8435 kept their virtual core (nothing there to wait for), 2829 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: 2080000 (1228265 pages from the captures)
[hos host] vk: program picks: 2740645 kept (1009888 by the last picks' textures, a uniform buffer bound since), 19589 new, 1039765 with other textures (of 3800000)
[hos host] vk: replay reads of guest memory as submitted: 2100000 (1241634 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4352 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: late pages found at the replay (600 takes): 3 pages in 3 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 923 ranges, 3616 MB), 221 pages written, 221 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 0.004, bytes copied 0.000; 25 kept (112 MB), 11 spare buffers, 7926 texture pages copied (30 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 296 KB; 0 made on demand (0 MB kept now); c1 stages: at most 107 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 969 dirty pages from their submits' captures, 37967 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): 737 dispatches, 29476 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4260 runs, 562.0 MB compared; 49 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7460 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2120000 (1254940 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2140000 (1268228 pages from the captures)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 784 dirty pages from their submits' captures, 38109 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): 739 dispatches, 29450 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4254 runs, 565.3 MB compared; 53 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7397 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 2160000 (1281534 pages from the captures)
[hos host] vk: a frame: 394 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.34, present 0.13, draw 7.50, descriptors 2.77, texture lookups 0.06, uploads 0.01, pipelines 0.39, programs 1.14, commands 2.60, dispatch 0.78, memory sync 0.43, queue submit 0.71, slot wait 0.33
[hos host] vk: a frame: mirrors 154 (986 MB): 4.99 MB synced in 949.1 copies, 18.27 MB written back
[hos host] vk: 4680 presents, 60.1 fps; a frame: 2500 draws (0 skipped), 124 dispatches, 148 passes, 150 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1371 textures (2579 MB)
[hos host] vk: host time in GPU resource waits: 1.08 ms a frame (fences 0.04, timelines 1.04, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 409.4 full barriers recorded, 203.0 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.7 ms); 0.2 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2180000 (1294876 pages from the captures)
[hos Presentation Thread] vi: 4699 frames presented (60.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 21, 15.5-17.8 263, 17.8-22 17, 22-30 0, 30-40 0, over 40 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 821 dirty pages from their submits' captures, 37947 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): 735 dispatches, 29403 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4232 runs, 563.7 MB compared; 45 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7406 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 889812 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 2890489 kept (1062176 by the last picks' textures, a uniform buffer bound since), 19589 new, 1089921 with other textures (of 4000000)
[hos host] vk: replay reads of guest memory as submitted: 2200000 (1308216 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2220000 (1321584 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 923 ranges, 3618 MB), 230 pages written, 230 copied (0.9 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 0.009, bytes copied 0.000; 25 kept (118 MB), 11 spare buffers, 8438 texture pages copied (32 MB)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1247 dirty pages from their submits' captures, 37580 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 738 dispatches, 29407 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4230 runs, 565.7 MB compared; 50 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7380 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 2240000 (1334846 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7417 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[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 ModuleSystemWorker1] nvn: 600000 recordings made, 78034 live copies (22.8 MB), 513 texture copies; 5 command buffers' segments (4.3 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #75000: event 0x100c31803c mode 0 value 52756 (now 52737) (lr 0x80662e5c)
[hos host] vk: replay reads of guest memory as submitted: 2260000 (1348190 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 872 dirty pages from their submits' captures, 37930 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): 738 dispatches, 29395 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4216 runs, 563.5 MB compared; 57 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7362 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: readbacks of GPU results: 1107 of 3000 waited for their write-back, 0.12 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: invalidates since the last readbacks line: 8919 kept their virtual core (nothing there to wait for), 3113 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: 2280000 (1361565 pages from the captures)
[hos host] vk: late pages' fix (600 recordings with one): of 768 captures with late pages 749 fixed (76.2 pages, 76.3 fixes a capture), waited as before: 0 no pool, 19 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; 38 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 99 blocks (6336 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 32, of an earlier recording 6, not recorded yet 0, of this part 0; pages fixed from stamps 56028, from snapshots 1066; the shadows: 633902 pages synced from captures, 619460 made known by it, 14375 left unknown because the replay or the collection wrote them since
[hos host] vk: program picks: 3040379 kept (1114528 by the last picks' textures, a uniform buffer bound since), 19589 new, 1140031 with other textures (of 4200000)
[hos host] vk: replay reads of guest memory as submitted: 2300000 (1374846 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 296 KB; 0 made on demand (0 MB kept now); c1 stages: at most 107 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 637 dirty pages from their submits' captures, 38065 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 737 dispatches, 29372 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4230 runs, 564.5 MB compared; 51 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7344 in captures, 1 only in the collection, 30 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: memory: working set 15893 MB (peak 15918), private 22156 MB, staging 224 MB in 14 arenas, 34 made so far (108 ms)
[hos host] vk: memory heaps: heap 0 (system): 15 blocks 912 MB, 39 allocations 850 MB; used 3084 of 15571 MB; heap 1 (device): 160 blocks 4779 MB, 17454 allocations 4279 MB; used 5980 of 15419 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): 15 blocks 480 MB, 100 images 235 MB; 56 free ranges, the largest 31 MB
[hos host] vk: image blocks (textures, compacted): 57 blocks 1824 MB, 1292 images 1805 MB; 225 free ranges, the largest 7 MB
[hos host] vk: render target images: 407 reused from the pool, 420 made new, 317 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 5980 MB used of 15419 MB allowed (500 MB of it free in the blocks); textures 2593 MB (budget 11000 MB), 1398 textures
[hos host] vk: budget: VRAM 4779 of 15419 MB (5980 MB by the driver, 1200 MB unaccounted): textures 2593, mirrors 986, blocks free 500, shadows 288, staging 224, other buffers 156, other images 31; RAM 3036 MB (the process's private memory 22156 MB): imports 1868, capture spares 724, retired imports 288, captures 118, capture table 30, other buffers 8, others 0
[hos host] vk: textures: decoded ASTC 1310 MB, rendered 778 MB (87 drawn in one frame, kept: 50355 KB), other 285 MB; used in the last 8 presents 2203 MB
[hos host] vk: decoded ASTC used again: 84 textures (168 MB) copied from ones the game finalized, not decoded; 84 of those retired, 0 listed; 875 MB of blocks hashed in 90 ms
[hos host] vk:   288 MB: 0x114682a000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x11361ac000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113b7bd000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   32 MB: 0x115882b000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   31 MB: 0x110a74ee00 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk:   23 MB: 0x111c0fb600 768x1536x1 x4 levels 11 NVN 0x7b ASTC, last used 19 presents ago
[hos host] vk:   21 MB: 0x10006f14600 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 17 (2817 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 16 (2815 KB);
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos Presentation Thread] vk: presents after the CPU's signal (600): 166 waited for it, 1.01 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: replay reads of guest memory as submitted: 2320000 (1388166 pages from the captures)
[hos host] vk: status: 600 frames, the slowest 23.3 ms; VRAM 5.8 of 15.1 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: 45 program records loaded (39.2 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5287 queued, 5287 loaded (median 0.68 ms, 99th percentile 8.12 ms, worst 25.96 ms, 6011 ms and 1201.4 MB read in all); 7325 programs (1466 of them compute variants without their code, 0 graphics programs no note names), 9581 graphics pipelines (0 not in a cache), 409 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 1 (2.1 ms); 1805 pipelines made at create taken by draws; 2961 create calls with nothing kept for their stages, 0 before the index; units 8248 (5287 ready, 0 loading), 14331 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 659 known, 0 learned in this run; 409 compute pipelines made by them at a create call, 250 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 390 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.43, present 0.12, draw 7.54, descriptors 2.78, texture lookups 0.06, uploads 0.01, pipelines 0.40, programs 1.10, commands 2.66, dispatch 0.80, memory sync 0.41, queue submit 0.71, slot wait 0.34
[hos host] vk: a frame: mirrors 154 (986 MB): 4.89 MB synced in 948.2 copies, 18.32 MB written back
[hos host] vk: 4800 presents, 60.0 fps; a frame: 2492 draws (0 skipped), 123 dispatches, 148 passes, 150 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1398 textures (2593 MB)
[hos host] vk: host time in GPU resource waits: 1.15 ms a frame (fences 0.04, timelines 1.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 408.6 full barriers recorded, 202.9 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.2 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 13.14 ms a frame (submits 9.28, presents 0.16, others 3.70), idle 3.53; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.32 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); 186 captures at a CPU signal; the submits' waits read in 0.062 ms a frame; readbacks: 1408 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 12.03 ms after its hand-over (17.75 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 2.73 + 0.19 (the window's copy is in the idle), after it 3.60 + 0.39; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 12.87 parts a frame recorded in the signal's job, 85.0% of them took nothing that came with the signal; of the others, 1.94 a frame took pages of the signal's capture into a mirror (91.7 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 3 of 186 frames, its first three in 3
[hos host] vk: frame ahead, what came with the signal: 186 signals with a capture, each of 154.6 pages in 10.4 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: 0.47+0.03, 0.45+0.02, 0.45+0.01, 0.63+0.03, 0.97+0.09, 0.24+0.03, 0.21+0.04, 0.03+0.02, 0.03+0.03, 0.03+0.03, 0.05+0.02, 0.03+0.03
[hos host] vk: replay reads of guest memory as submitted: 2340000 (1401482 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 871 dirty pages from their submits' captures, 37934 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 741 dispatches, 29378 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4232 runs, 565.4 MB compared; 50 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7378 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 923 ranges, 3618 MB), 223 pages written, 223 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 0.007, bytes copied 0.000; 24 kept (120 MB), 12 spare buffers, 2146 texture pages copied (8 MB)
[hos host] vk: replay reads of guest memory as submitted: 2360000 (1414827 pages from the captures)
[hos nn.npln.Worker] vcores: 131976 takes, 23255 waits (mean 72 us, longest 14.3 ms, 0 over HOS_VCORE_LOG_MS), 12088 kicks, 11940 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2380000 (1428166 pages from the captures)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1179 dirty pages from their submits' captures, 37468 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): 736 dispatches, 29265 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4126 runs, 554.9 MB compared; 61 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7376 in captures, 1 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: readback pages refreshed from guest memory: 963234 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 3190571 kept (1166936 by the last picks' textures, a uniform buffer bound since), 19589 new, 1189839 with other textures (of 4400000)
[hos host] vk: replay reads of guest memory as submitted: 2400000 (1441493 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 92 sync waits (76 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: recorder: 8705743 packets run in 10.0 s (busy 2.05 s, spun idle 5.51 s, slept 4205 times, 2239 of them under 200 us), 0 calls made directly (no room); the replay waited for it 30529 times, 139.78 ms in all, the longest 0.34 ms; vkResetDescriptorPool 11535/77.41 ms (max 0.26), vkEndCommandBuffer 11605/40.96 ms (max 0.34), replay_mu unlock 7376/21.31 ms (max 0.26), vkQueueBindSparse 3/0.09 ms (max 0.08), vmaInvalidateAllocation 10/0.02 ms (max 0.00)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #55000: event 0x100c318040 mode 0 value 54999 (lr 0x806621e8)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 21125 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[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 host] vk: replay reads of guest memory as submitted: 2420000 (1454893 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1095 dirty pages from their submits' captures, 36995 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): 733 dispatches, 28759 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4143 runs, 542.4 MB compared; 50 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7377 in captures, 1 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2440000 (1468262 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 2460000 (1481602 pages from the captures)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1227 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 8761 kept their virtual core (nothing there to wait for), 3015 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1151 dirty pages from their submits' captures, 37060 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): 724 dispatches, 29026 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4179 runs, 558.4 MB compared; 55 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7163 in captures, 0 only in the collection, 29 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: a frame: 406 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.44, present 0.13, draw 7.57, descriptors 2.81, texture lookups 0.05, uploads 0.00, pipelines 0.39, programs 1.13, commands 2.64, dispatch 0.78, memory sync 0.51, queue submit 0.71, slot wait 0.31
[hos host] vk: a frame: mirrors 154 (986 MB): 4.88 MB synced in 945.9 copies, 18.16 MB written back
[hos host] vk: 4920 presents, 60.0 fps; a frame: 2495 draws (0 skipped), 123 dispatches, 148 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1398 textures (2593 MB)
[hos host] vk: host time in GPU resource waits: 1.07 ms a frame (fences 0.04, timelines 1.04, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 407.6 full barriers recorded, 202.7 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.05 over 923 ranges, 3618 MB), 259 pages written, 259 copied (1.0 MB)
[hos host] vk: a capture taken (ms): all 0.038; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.031, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 9216 texture pages copied (36 MB)
[hos host] vk: replay reads of guest memory as submitted: 2480000 (1494965 pages from the captures)
[hos host] vk: program picks: 3340728 kept (1219359 by the last picks' textures, a uniform buffer bound since), 19589 new, 1239682 with other textures (of 4600000)
[hos host] vk: replay reads of guest memory as submitted: 2500000 (1508265 pages from the captures)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 120000 so far (x1 0x117a077030 x2 0 x3 0x117a077000 x4 0xf33080)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 296 KB; 0 made on demand (0 MB kept now); c1 stages: at most 107 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 919 dirty pages from their submits' captures, 37947 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): 736 dispatches, 29409 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4225 runs, 565.7 MB compared; 51 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7377 in captures, 1 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 622 so far (1489 MB), 568 of them (1346 MB) between the passes
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #80000: event 0x100c31803c mode 0 value 56556 (now 56537) (lr 0x80662e5c)
[hos host] vk: replay reads of guest memory as submitted: 2520000 (1521599 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2540000 (1535003 pages from the captures)
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 77 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 666 dirty pages from their submits' captures, 38286 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): 741 dispatches, 29489 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4216 runs, 559.4 MB compared; 64 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7368 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 2560000 (1548298 pages from the captures)
[hos host] vk: mirror of pool 0x103cc00000 (4 MB) given back: idle, 6037 submissions since its sync
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 11097 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1005a88004 mode 0 value 1 (lr 0x8348c78c)
[hos Presentation Thread] vi: 5000 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 20, 15.5-17.8 262, 17.8-22 19, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 2580000 (1561641 pages from the captures)
[hos host] vk: texture slots registered again at another size: 200000 (of 294859 registrations; slot 24332 64x36 -> 960x540)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 886 dirty pages from their submits' captures, 37984 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): 737 dispatches, 29479 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4156 runs, 556.5 MB compared; 58 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7353 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: readback pages refreshed from guest memory: 1035868 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 3490970 kept (1272111 by the last picks' textures, a uniform buffer bound since), 19589 new, 1289440 with other textures (of 4800000)
[hos host] vk: replay reads of guest memory as submitted: 2600000 (1574953 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 924 ranges, 3620 MB), 227 pages written, 227 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 0.006, bytes copied 0.000; 25 kept (112 MB), 10 spare buffers, 4523 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 2620000 (1588274 pages from the captures)
[hos host] vk: a frame: 390 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.38, present 0.12, draw 7.77, descriptors 2.91, texture lookups 0.09, uploads 0.02, pipelines 0.40, programs 1.12, commands 2.73, dispatch 0.77, memory sync 0.41, queue submit 0.72, slot wait 0.31
[hos host] vk: a frame: mirrors 154 (985 MB): 4.91 MB synced in 951.0 copies, 18.15 MB written back
[hos host] vk: 5040 presents, 60.0 fps; a frame: 2513 draws (0 skipped), 123 dispatches, 149 passes, 150 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1402 textures (2595 MB)
[hos host] vk: host time in GPU resource waits: 1.22 ms a frame (fences 0.04, timelines 1.18, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 408.8 full barriers recorded, 203.0 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.8 ms a frame (the longest submission 2.8 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 76, 985 MB with memory of 1476 MB (490 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 360 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 50 taken from the spares, 104 made new; 78 kept as spares, 0 destroyed; 28 spares now, 472 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1017 dirty pages from their submits' captures, 38102 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): 742 dispatches, 29535 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4091 runs, 555.0 MB compared; 67 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7376 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 2640000 (1601630 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2660000 (1614956 pages from the captures)
[hos sead::MainThread] vk: readbacks of GPU results: 1164 of 3000 waited for their write-back, 0.13 ms each; 0 looked at the stopped queues first, 5 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: 8819 kept their virtual core (nothing there to wait for), 2957 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1045 dirty pages from their submits' captures, 37327 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 732 dispatches, 28924 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4091 runs, 541.1 MB compared; 66 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7137 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2680000 (1628309 pages from the captures)
[hos host] vk: program picks: 3641187 kept (1325068 by the last picks' textures, a uniform buffer bound since), 19589 new, 1339223 with other textures (of 5000000)
[hos host] vk: replay reads of guest memory as submitted: 2700000 (1641655 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 296 KB; 0 made on demand (0 MB kept now); c1 stages: at most 107 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 361 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 51 taken from the spares, 104 made new; 78 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1056 dirty pages from their submits' captures, 37528 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): 738 dispatches, 29298 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4176 runs, 556.9 MB compared; 73 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7422 in captures, 0 only in the collection, 29 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos host] vk: replay reads of guest memory as submitted: 2720000 (1655121 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 14530 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[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: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 925 ranges, 3630 MB), 241 pages written, 241 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.021; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.014, bytes copied 0.000; 25 kept (112 MB), 11 spare buffers, 5377 texture pages copied (21 MB)
[hos host] vk: replay reads of guest memory as submitted: 2740000 (1668630 pages from the captures)
[hos ModuleSystemWorker3] nvn: 650000 recordings made, 78321 live copies (23.5 MB), 513 texture copies; 5 command buffers' segments (4.3 MB)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 656 dirty pages from their submits' captures, 38294 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): 738 dispatches, 29518 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4175 runs, 556.9 MB compared; 71 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7429 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #60000: event 0x100c31800c mode 0 value 60002 (lr 0x80660adc)
[hos host] vk: replay reads of guest memory as submitted: 2760000 (1682119 pages from the captures)
[hos nn.npln.Worker] vcores: 133422 takes, 23348 waits (mean 73 us, longest 12.8 ms, 0 over HOS_VCORE_LOG_MS), 12169 kicks, 12005 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2780000 (1695599 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #85000: event 0x100c31803c mode 0 value 60356 (now 60337) (lr 0x80662e5c)
[hos host] vk: a frame: 390 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 74 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 12.36, present 0.12, draw 7.68, descriptors 2.91, texture lookups 0.11, uploads 0.03, pipelines 0.40, programs 1.13, commands 2.66, dispatch 0.75, memory sync 0.42, queue submit 0.71, slot wait 0.31
[hos host] vk: a frame: mirrors 155 (986 MB): 4.92 MB synced in 952.7 copies, 18.07 MB written back
[hos host] vk: 5160 presents, 60.0 fps; a frame: 2513 draws (0 skipped), 124 dispatches, 148 passes, 150 barriers, 6 submits, 0.3 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42904 pipelines (23540 ms), 0 programs (10 failed), 1415 textures (2610 MB)
[hos host] vk: host time in GPU resource waits: 1.13 ms a frame (fences 0.04, timelines 1.09, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 409.3 full barriers recorded, 202.7 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: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.8 ms a frame (the longest submission 2.8 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: sparse mirrors: 77, 986 MB with memory of 1480 MB (493 MB spared); blocks given memory later 1894, given back 5482; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 361 binds (25.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 51 taken from the spares, 104 made new; 78 kept as spares, 0 destroyed; 27 spares now, 468 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1011 dirty pages from their submits' captures, 37951 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): 737 dispatches, 29498 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4173 runs, 556.8 MB compared; 79 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7386 in captures, 0 only in the collection, 31 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 112 live (1868 MB), 19 retired still imported (288 MB), 13 retired given back (328 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 84 sync waits (90 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: readback pages refreshed from guest memory: 1108853 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 2800000 (1709054 pages from the captures)
[hos host] vk: program picks: 3791396 kept (1378202 by the last picks' textures, a uniform buffer bound since), 19589 new, 1389014 with other textures (of 5200000)
[hos host] vk: replay reads of guest memory as submitted: 2820000 (1722469 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 918 dirty pages from their submits' captures, 38170 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): 737 dispatches, 29552 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4138 runs, 555.5 MB compared; 74 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 7373 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2840000 (1735932 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: slow present: 16.5 ms:
[hos host] vk: present 5200 written to <home>\AppData\Local\<user>\data\jobs\jb_9465ac03f6c5dcbb\runs\forest-market-g1-01-pr\shots/forest-market-c1-pr-01-market.png (the control bridge)
[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: 45 program records loaded (39.2 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (close): 5287 queued, 5287 loaded (median 0.68 ms, 99th percentile 8.12 ms, worst 25.96 ms, 6011 ms and 1201.4 MB read in all); 7325 programs (1466 of them compute variants without their code, 0 graphics programs no note names), 9581 graphics pipelines (0 not in a cache), 409 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 1 (2.1 ms); 1805 pipelines made at create taken by draws; 2961 create calls with nothing kept for their stages, 0 before the index; units 8248 (5287 ready, 0 loading), 14331 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (close): 659 known, 0 learned in this run; 409 compute pipelines made by them at a create call, 250 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 (4263 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)