Beanstalk Longshot test farm
Menu

Report rp_bc0d17a3bdb9533a error

#1681 perf(vk): render targets take a pooled image's memory by size, and the pool holds longer on integrated GPUs

linux+nvidia on Floppy/agent-06957c,

This report disagrees with its peers.

field-turn-and-stand run_hitch_count: +100.0% against peers' -40.0%
field-turn-and-stand#1 run_hitch_count: -100.0% against peers' +0.0%
no scenario could be judged: a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)

Machine

Commit
742b053ae6b0a34dca75a574db424c559f22850f
Baseline
068fb8ebe232d455ef48e817702b03ccc62d8520
App
nightly-211-845707b2, attempt 1
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 7 7800X3D 8-Core Processor
gpu
NVIDIA GeForce RTX 5080
tags
linuxnvidianvidia-proprietarydgpu
driver
620.73.4
ram_gb
32
vram_mb
16,303
gpu_vendor
nvidia
os_version
CachyOS (kernel 7.3.5)

Builds

main (baseline)

1,292.6 s warm

from 068fb8ebe232

lift
74.2 s
read
2.5 s
finish
11.3 s
compile
887.2 s
shaders
316.6 s

PR

27.2 s warm

Program cache: warm

Scenarios

field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=0 (PR only)

timeout

a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)

Metric (median)mainPRΔ
value_pool_mb00±0%
run_hitch_count12+100%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms647.72652.24+0.7%
value_reused_by_size—0—
Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code——
value_pool_mb00
run_hitch_count12
log_forbidden_hits00
log_expected_missing00
run_frametime_max_ms647.72652.24
value_reused_by_size—0

field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=1 (PR only)

timeout

a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)

Metric (median)mainPRΔ
value_pool_mb00±0%
run_hitch_count10−100%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms50.8146.68−8.1%
value_reused_by_size—12—
Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code——
value_pool_mb00
run_hitch_count10
log_forbidden_hits00
log_expected_missing00
run_frametime_max_ms50.8146.68
value_reused_by_size—12

field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=2 (PR only)

timeout

a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)

Metric (median)mainPRΔ
value_pool_mb00±0%
run_hitch_count01—
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms46.8470.6+50.7%
value_reused_by_size—9—
Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code——
value_pool_mb00
run_hitch_count01
log_forbidden_hits00
log_expected_missing00
run_frametime_max_ms46.8470.6
value_reused_by_size—9

Rules

ScenarioCellRuleLimitmainPRΔ %Status
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=0 (PR only)crashFalse00—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=0 (PR only)screenshot.max_diff0.15———skippedthe plan has no screenshot probe
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=0 (PR only)log_forbidden_hits.max000—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=1 (PR only)crashFalse00—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=1 (PR only)screenshot.max_diff0.15———skippedthe plan has no screenshot probe
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=1 (PR only)log_forbidden_hits.max000—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=2 (PR only)crashFalse00—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=2 (PR only)screenshot.max_diff0.15———skippedthe plan has no screenshot probe
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=2 (PR only)log_forbidden_hits.max000—pass
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=1 (PR only)standing.frametime_p99_ms: RX_VK_TARGET_REUSE_MEMORY=1 vs RX_VK_TARGET_REUSE_MEMORY=0 (PR)20———skippedthe metric was not measured in both cells
field-turn-and-standRX_VK_TARGET_REUSE_MEMORY=2 (PR only)standing.frametime_p99_ms: RX_VK_TARGET_REUSE_MEMORY=2 vs RX_VK_TARGET_REUSE_MEMORY=0 (PR)20———skippedthe metric was not measured in both cells

Pictures of the failure

The last frame of a step that got stuck, or main's and the PR's picture where they differed more than the plan allows; shrunk, and kept a day: until .

field-turn-and-stand-c0-baseline0-last-frame.png
field-turn-and-stand-c0-baseline0-last-frame.png
field-turn-and-stand-c0-pr1-last-frame.png
field-turn-and-stand-c0-pr1-last-frame.png

Log (PR side, end)

[hos sead::MainThread] barrier: 75400 looks: 26248 found the masks moved already, 35726 waited until they moved, 13426 for the whole 1 ms (a wait 456 us on average); 25492 wakes
[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: queues ordered by their events: 24000 submissions stopped at a wait, 23992 went on once it was reached, 4 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.05 ms at most); waits met 73159, not met 0; captures at a CPU event's wait 267, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 1380000 (705756 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 13 dirty pages from their submits' captures, 72078 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): 1372 dispatches, 56247 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6795 runs, 1050.2 MB compared; 283 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23594 in captures, 0 only in the collection, 63 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: replay reads of guest memory as submitted: 1400000 (716151 pages from the captures)
[hos host] vk: a frame: 53 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 2.76, present 0.08, draw 1.56, descriptors 0.68, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.26, commands 0.45, dispatch 0.33, memory sync 0.22, queue submit 0.10, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.54 MB synced in 906.9 copies, 16.92 MB written back
[hos host] vk: 4440 presents, 60.0 fps; a frame: 677 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 0.96 ms a frame (fences 0.01, timelines 0.96, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.5 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #75000: event 0x100d6c8038 mode 0 value 53495 (now 53476) (lr 0x80661a48)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 11 spare buffers, 0 texture pages copied (0 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 96 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 10 dirty pages from their submits' captures, 72020 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): 1371 dispatches, 56165 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6808 runs, 1049.2 MB compared; 286 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23629 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 120000 so far (x1 0x117a4f2010 x2 0 x3 0x117a4f2000 x4 0xf33080)
[hos host] vk: replay reads of guest memory as submitted: 1420000 (726576 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 ModuleSystemWorker1] vk: readbacks of GPU results: 1355 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 ModuleSystemWorker1] vk: invalidates since the last readbacks line: 4690 kept their virtual core (nothing there to wait for), 3246 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: readback pages refreshed from guest memory: 639628 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos BaseProcExecutor1] vcores: 73290 takes, 11388 waits (mean 49 us, longest 3.2 ms, 0 over HOS_VCORE_LOG_MS), 4286 kicks, 4161 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1440000 (736992 pages from the captures)
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 44 dirty pages from their submits' captures, 72202 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): 1372 dispatches, 56411 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6834 runs, 1051.5 MB compared; 275 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23647 in captures, 1 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #55000: event 0x100d6c8044 mode 0 value 54999 (lr 0x802742f0)
[hos host] vk: recorder: 3488325 packets run in 10.0 s (busy 0.68 s, spun idle 1.33 s, slept 4834 times, 637 of them under 200 us), 0 calls made directly (no room); the replay waited for it 18730 times, 59.35 ms in all, the longest 0.22 ms; vkEndCommandBuffer 5782/24.60 ms (max 0.06), replay_mu unlock 7203/23.32 ms (max 0.21), vkResetDescriptorPool 5745/11.43 ms (max 0.22)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (244 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1460000 (747415 pages from the captures)
[hos host] vk: a frame: 54 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 2.76, present 0.07, draw 1.54, descriptors 0.67, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.26, commands 0.45, dispatch 0.34, memory sync 0.21, queue submit 0.09, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.55 MB synced in 908.0 copies, 16.94 MB written back
[hos host] vk: 4560 presents, 60.0 fps; a frame: 678 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 1.05 ms a frame (fences 0.01, 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: 340.5 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: write-backs left out (600 submits): 1386, 5809.5 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 18 dirty pages from their submits' captures, 73241 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): 1391 dispatches, 57186 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6809 runs, 1049.2 MB compared; 295 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23977 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 1272308 kept (393772 by the last picks' textures, a uniform buffer bound since), 745 new, 926946 with other textures (of 2200000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: replay reads of guest memory as submitted: 1480000 (757796 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 Presentation Thread] vi: 4625 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 1500000 (768306 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #80000: event 0x100d6c8038 mode 0 value 57295 (now 57276) (lr 0x80661a48)
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 18 dirty pages from their submits' captures, 72401 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): 1376 dispatches, 56424 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6904 runs, 1065.1 MB compared; 283 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23619 in captures, 1 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 207 pages written, 207 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (254 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker2] nvn: 500000 recordings made, 43072 live copies (11.8 MB), 310 texture copies; 3 command buffers' segments (4.1 MB)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1348 of 3000 waited for their write-back, 0.13 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: 4443 kept their virtual core (nothing there to wait for), 2981 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: 1520000 (778603 pages from the captures)
[hos host] vk: a frame: 53 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 2.82, present 0.07, draw 1.60, descriptors 0.69, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.26, commands 0.47, dispatch 0.34, memory sync 0.21, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.55 MB synced in 909.3 copies, 16.92 MB written back
[hos host] vk: 4680 presents, 60.0 fps; a frame: 677 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 1.08 ms a frame (fences 0.01, timelines 1.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.6 full barriers recorded, 182.1 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.00 since the last count
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 34 dirty pages from their submits' captures, 72051 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): 1372 dispatches, 56287 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6798 runs, 1050.2 MB compared; 278 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23687 in captures, 1 only in the collection, 63 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1540000 (788867 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 sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1560000 (799179 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 96 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 17 dirty pages from their submits' captures, 72089 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): 1371 dispatches, 56251 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6807 runs, 1049.8 MB compared; 280 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23647 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: 1 textures retired (1223 left, 3288 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferSignalEvent #60000: event 0x100d6c8004 mode 0 value 59999 (lr 0x80291504)
[hos host] vk: replay reads of guest memory as submitted: 1580000 (809472 pages from the captures)
[hos host] vk: memory: working set 19329 MB (peak 20288), private 11940 MB, staging 32 MB in 2 arenas, 27 made so far (9 ms)
[hos host] vk: memory heaps: heap 0 (device): 157 blocks 4994 MB, 14126 allocations 4614 MB; used 5770 of 14230 MB; heap 1 (system): 28 blocks 832 MB, 38 allocations 701 MB; used 1942 of 23769 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB
[hos host] vk: image blocks (render targets): 14 blocks 448 MB, 100 images 237 MB; 24 free ranges, the largest 29 MB
[hos host] vk: image blocks (textures, compacted): 57 blocks 1824 MB, 1112 images 1792 MB; 469 free ranges, the largest 17 MB
[hos host] vk: render target images: 54 reused from the pool, 242 made new, 138 destroyed from it, 9 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=2), 2 missed after their image was taken by size; it holds 0 (0 MB)
[hos host] vk: render targets not reused by size: 198 with the pool empty (0 of them with targets still in the dead queue), 12 with none in it a present yet, 0 with none of a kind they can use, 1 with all smaller (the largest 8% short on average), 12 with all bigger (over 1.5 times), 19 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 138 idle
[hos host] vk: VRAM: 5770 MB used of 14230 MB allowed (379 MB of it free in the blocks); textures 3288 MB (budget 10829 MB), 1223 textures
[hos host] vk: budget: VRAM 4994 of 14230 MB (5770 MB by the driver, 776 MB unaccounted): textures 3288, mirrors 792, blocks free 379, shadows 320, other buffers 153, staging 32, other images 28; RAM 1815 MB (the process's private memory 11940 MB): imports 1088, capture spares 466, captures 226, capture table 26, other buffers 9, others 0
[hos host] vk: textures: decoded ASTC 1864 MB, rendered 850 MB (103 drawn in one frame, kept: 47857 KB), other 346 MB; used in the last 8 presents 2206 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 3 listed; 387 MB of blocks hashed in 18 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 3074 presents ago
[hos host] vk:   54 MB: 0x10002ac7800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3063 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: presents after the CPU's signal (600): 1 waited for it, 0.08 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.6 ms; VRAM 5.6 of 13.9 GB
[hos host] vk: a frame: 53 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 2.82, present 0.08, draw 1.63, descriptors 0.72, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.27, commands 0.47, dispatch 0.34, memory sync 0.23, queue submit 0.10, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.54 MB synced in 907.5 copies, 16.93 MB written back
[hos host] vk: 4800 presents, 60.0 fps; a frame: 676 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1223 textures (3288 MB)
[hos host] vk: host time in GPU resource waits: 1.06 ms a frame (fences 0.01, timelines 1.05, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.5 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 3.10 ms a frame (submits 2.93, presents 0.08, others 0.09), idle 13.57; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.23 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); 6 captures at a CPU signal; the submits' waits read in 0.023 ms a frame; readbacks: 2990 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 2.65 ms after its hand-over (4.31 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 11.16 + 0.50 (the window's copy is in the idle), after it 0.12 + 0.28; 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): 3.67 parts a frame recorded in the signal's job, 90.9% of them took nothing that came with the signal; of the others, 0.33 a frame took pages of the signal's capture into a mirror (0.5 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 5 of 6 frames, its first three in 5
[hos host] vk: frame ahead, what came with the signal: 6 signals with a capture, each of 1.0 pages in 0.8 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: 0.09+0.18, 0.01+0.04, 0.01+0.05, 0.01+0.02, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: readback pages refreshed from guest memory: 710344 pages so far (0 held: may be written ahead in their submission)
[hos BaseProcExecutor3] vcores: 74356 takes, 11664 waits (mean 52 us, longest 3.7 ms, 0 over HOS_VCORE_LOG_MS), 4368 kicks, 4262 yields, 0 starved grants, 0 escapes in 5 s
[hos sead::MainThread] vk: readbacks of GPU results: 1353 of 3000 waited for their write-back, 0.13 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: 4250 kept their virtual core (nothing there to wait for), 2918 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: 1600000 (819735 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1386, 5809.5 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 27 dirty pages from their submits' captures, 73264 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): 1391 dispatches, 57247 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6802 runs, 1049.2 MB compared; 282 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 24021 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: CommandBufferWaitEvent #85000: event 0x100d6c8038 mode 0 value 61095 (now 61076) (lr 0x80661a48)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 204 pages written, 204 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (236 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 1387590 kept (429818 by the last picks' textures, a uniform buffer bound since), 745 new, 1011664 with other textures (of 2400000)
[hos host] vk: replay reads of guest memory as submitted: 1620000 (830018 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 5 dirty pages from their submits' captures, 72057 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): 1375 dispatches, 56234 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6914 runs, 1066.1 MB compared; 284 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23671 in captures, 0 only in the collection, 63 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: replay reads of guest memory as submitted: 1640000 (840339 pages from the captures)
[hos host] vk: a frame: 53 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 2.84, present 0.09, draw 1.59, descriptors 0.69, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.26, commands 0.46, dispatch 0.34, memory sync 0.21, queue submit 0.12, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.55 MB synced in 909.0 copies, 16.93 MB written back
[hos host] vk: 4920 presents, 60.0 fps; a frame: 678 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1223 textures (3288 MB)
[hos host] vk: host time in GPU resource waits: 1.03 ms a frame (fences 0.01, timelines 1.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.5 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 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] vi: 4926 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker3] nvn: DrawMeshTasksIndirect: 140000 so far (x1 0x117e463060 x2 0 x3 0x117e463040 x4 0x8b040)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 207 pages written, 207 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1660000 (850907 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 41 dirty pages from their submits' captures, 72488 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): 1374 dispatches, 56479 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6823 runs, 1050.4 MB compared; 276 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23672 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[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 ModuleSystemWorker5] vk: readbacks of GPU results: 1356 of 3000 waited for their write-back, 0.13 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: 4442 kept their virtual core (nothing there to wait for), 2982 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: 1680000 (861330 pages from the captures)
[hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 25 dirty pages from their submits' captures, 72506 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): 1385 dispatches, 56514 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6805 runs, 1049.2 MB compared; 264 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23731 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: replay reads of guest memory as submitted: 1700000 (871714 pages from the captures)
[hos host] vk: a frame: 53 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 2.82, present 0.07, draw 1.58, descriptors 0.69, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.26, commands 0.45, dispatch 0.34, memory sync 0.22, queue submit 0.09, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.54 MB synced in 907.8 copies, 16.93 MB written back
[hos host] vk: 5040 presents, 60.0 fps; a frame: 677 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 1.11 ms a frame (fences 0.01, timelines 1.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.4 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker5] nvn: 550000 recordings made, 43079 live copies (11.4 MB), 310 texture copies; 2 command buffers' segments (4.1 MB)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #90000: event 0x100d6c8038 mode 0 value 64895 (now 64876) (lr 0x80661a48)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (242 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #65000: event 0x100d6c8014 mode 0 value 65000 (lr 0x802915c8)
[hos host] vk: replay reads of guest memory as submitted: 1720000 (882100 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 96 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1386, 5809.5 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 19 dirty pages from their submits' captures, 72801 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): 1378 dispatches, 56940 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6885 runs, 1064.7 MB compared; 287 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 24031 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[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 0.00, writes collected 0.03
[hos aal::LowPrioWorkerThread] vcores: 73488 takes, 12044 waits (mean 49 us, longest 3.4 ms, 0 over HOS_VCORE_LOG_MS), 4517 kicks, 4315 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1740000 (892513 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 781770 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: recorder: 3489298 packets run in 10.0 s (busy 0.68 s, spun idle 1.34 s, slept 4846 times, 645 of them under 200 us), 0 calls made directly (no room); the replay waited for it 18728 times, 59.27 ms in all, the longest 0.22 ms; vkEndCommandBuffer 5782/25.17 ms (max 0.22), replay_mu unlock 7204/22.96 ms (max 0.20), vkResetDescriptorPool 5742/11.14 ms (max 0.12)
[hos host] vk: program picks: 1502828 kept (465788 by the last picks' textures, a uniform buffer bound since), 745 new, 1096426 with other textures (of 2600000)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1355 of 3000 waited for their write-back, 0.13 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: 4211 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: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 15 dirty pages from their submits' captures, 72110 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): 1374 dispatches, 56312 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6825 runs, 1050.5 MB compared; 282 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23658 in captures, 0 only in the collection, 63 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1760000 (902924 pages from the captures)
[hos host] vk: a frame: 53 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 2.82, present 0.08, draw 1.60, descriptors 0.68, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.28, commands 0.47, dispatch 0.34, memory sync 0.21, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.54 MB synced in 908.0 copies, 16.92 MB written back
[hos host] vk: 5160 presents, 60.0 fps; a frame: 676 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 1.03 ms a frame (fences 0.01, timelines 1.03, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.4 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 1780000 (913319 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 25 dirty pages from their submits' captures, 72089 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): 1372 dispatches, 56319 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6805 runs, 1049.2 MB compared; 273 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23686 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vi: 5227 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29994 went on once it was reached, 4 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.05 ms at most); waits met 94567, not met 0; captures at a CPU event's wait 274, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 1800000 (923961 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #95000: event 0x100d6c8038 mode 0 value 68695 (now 68676) (lr 0x80661a48)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 207 pages written, 207 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1386, 5809.5 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 32 dirty pages from their submits' captures, 73501 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): 1392 dispatches, 57343 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6800 runs, 1049.2 MB compared; 282 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23961 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: replay reads of guest memory as submitted: 1820000 (934207 pages from the captures)
[hos host] vk: a frame: 53 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 2.84, present 0.09, draw 1.62, descriptors 0.70, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.27, commands 0.48, dispatch 0.35, memory sync 0.22, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.55 MB synced in 909.4 copies, 16.92 MB written back
[hos host] vk: 5280 presents, 60.0 fps; a frame: 676 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1224 textures (3294 MB)
[hos host] vk: host time in GPU resource waits: 1.04 ms a frame (fences 0.01, timelines 1.03, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.6 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1351 of 3000 waited for their write-back, 0.13 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: 4470 kept their virtual core (nothing there to wait for), 2954 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: 1840000 (944501 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #70000: event 0x100d6c8020 mode 0 value 70000 (lr 0x80667410)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 22 dirty pages from their submits' captures, 72029 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): 1374 dispatches, 56214 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6919 runs, 1066.8 MB compared; 271 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23637 in captures, 3 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[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: present 5342 written to /<user>/<user>/Beanstalk/jobs/jb_bf65fab375c3c465/runs/field-turn-and-stand-g2-01-pr/shots/field-turn-and-stand-pr-01-last-frame.png (the control bridge)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.001; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (238 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1860000 (954778 pages from the captures)
[hos host] vk: 1 textures retired (1223 left, 3288 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 1880000 (965065 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 96 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 55, 792 MB with memory of 1016 MB (223 MB spared); blocks given memory later 93, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 89 binds (12.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 4 taken from the spares, 66 made new; 15 kept as spares, 0 destroyed; 11 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 6 dirty pages from their submits' captures, 72147 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): 1372 dispatches, 56314 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6823 runs, 1050.2 MB compared; 282 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23632 in captures, 0 only in the collection, 63 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 63 live (1088 MB), 0 retired still imported (0 MB), 9 retired given back (248 MB)
[hos host] vk: memory: working set 19370 MB (peak 20288), private 11948 MB, staging 32 MB in 2 arenas, 27 made so far (9 ms)
[hos host] vk: memory heaps: heap 0 (device): 157 blocks 4994 MB, 14127 allocations 4618 MB; used 5770 of 14230 MB; heap 1 (system): 29 blocks 848 MB, 39 allocations 704 MB; used 1958 of 23769 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): 14 blocks 448 MB, 100 images 237 MB; 24 free ranges, the largest 29 MB
[hos host] vk: image blocks (textures, compacted): 57 blocks 1824 MB, 1112 images 1792 MB; 469 free ranges, the largest 17 MB
[hos host] vk: render target images: 54 reused from the pool, 243 made new, 139 destroyed from it, 9 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=2), 2 missed after their image was taken by size; it holds 0 (0 MB)
[hos host] vk: render targets not reused by size: 199 with the pool empty (0 of them with targets still in the dead queue), 12 with none in it a present yet, 0 with none of a kind they can use, 1 with all smaller (the largest 8% short on average), 12 with all bigger (over 1.5 times), 19 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 139 idle
[hos host] vk: VRAM: 5770 MB used of 14230 MB allowed (375 MB of it free in the blocks); textures 3288 MB (budget 10829 MB), 1223 textures
[hos host] vk: budget: VRAM 4994 of 14230 MB (5770 MB by the driver, 776 MB unaccounted): textures 3288, mirrors 792, blocks free 375, shadows 320, other buffers 153, staging 32, other images 31; RAM 1818 MB (the process's private memory 11948 MB): imports 1088, capture spares 452, captures 230, capture table 26, other buffers 22, others 0
[hos host] vk: textures: decoded ASTC 1864 MB, rendered 850 MB (103 drawn in one frame, kept: 47857 KB), other 346 MB; used in the last 8 presents 2211 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 3 listed; 387 MB of blocks hashed in 18 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 3674 presents ago
[hos host] vk:   54 MB: 0x10002ac7800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3663 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos host] vk: malloc: 12867 MB in arenas (11516 MB in use, 1351 MB free, 13 MB of it at the tops), 8 MB mapped
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.03
[hos Presentation Thread] vk: presents after the CPU's signal (600): 2 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 19.0 ms; VRAM 5.6 of 13.9 GB
[hos host] vk: a frame: 53 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, 1 jobs queued
[hos host] vk: a frame's replay time (ms): submit 2.85, present 0.19, draw 1.61, descriptors 0.71, texture lookups 0.03, uploads 0.00, pipelines 0.07, programs 0.27, commands 0.46, dispatch 0.35, memory sync 0.22, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 70 (792 MB): 4.54 MB synced in 907.3 copies, 16.94 MB written back
[hos host] vk: 5400 presents, 60.0 fps; a frame: 676 draws (0 skipped), 98 dispatches, 141 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (3630737 ms), 0 programs (0 failed), 1223 textures (3288 MB)
[hos host] vk: host time in GPU resource waits: 1.08 ms a frame (fences 0.01, timelines 1.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 340.4 full barriers recorded, 182.2 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 4.6 ms a frame (the longest submission 2.2 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 16.67 ms a frame): its jobs 3.17 ms a frame (submits 2.99, presents 0.11, others 0.08), idle 13.49; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.26 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); 4 captures at a CPU signal; the submits' waits read in 0.024 ms a frame; readbacks: 2995 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 2.72 ms after its hand-over (11.76 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 11.15 + 0.50 (the window's copy is in the idle), after it 0.12 + 0.28; 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): 3.25 parts a frame recorded in the signal's job, 76.9% of them took nothing that came with the signal; of the others, 0.75 a frame took pages of the signal's capture into a mirror (5.0 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 1 of 4 frames, its first three in 1
[hos host] vk: frame ahead, what came with the signal: 4 signals with a capture, each of 6.0 pages in 3.0 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: 0.09+0.18, 0.01+0.04, 0.01+0.05, 0.01+0.02, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: malloc_trim: 1337 MB free in the arenas now, the process's private memory 11948 -> 11929 MB (12 ms)
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x117a4f2030 x2 0 x3 0x117a4f2000 x4 0xf33080)
[hos host] vk: program picks: 1618029 kept (501689 by the last picks' textures, a uniform buffer bound since), 745 new, 1181225 with other textures (of 2800000)
[hos ModuleSystemWorker4] vcores: 74026 takes, 11952 waits (mean 49 us, longest 3.5 ms, 0 over HOS_VCORE_LOG_MS), 4505 kicks, 4320 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: readback pages refreshed from guest memory: 853186 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 1900000 (975336 pages from the captures)
[hos sead::MainThread] nvn: 600000 recordings made, 42989 live copies (11.4 MB), 310 texture copies; 5 command buffers' segments (4.2 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #100000: event 0x100d6c8038 mode 0 value 72495 (now 72476) (lr 0x80661a48)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.05 over 1284 ranges, 1844 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.002; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (230 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: write-backs left out (600 submits): 1364, 5717.3 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 3 dirty pages from their submits' captures, 72047 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): 1372 dispatches, 56277 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6801 runs, 1049.1 MB compared; 263 pages read into the shadows; 320 MB of shadows; pages the shadows knew that the CPU wrote: 23699 in captures, 0 only in the collection, 62 only by the replay itself
[hos host] vk:   read live, by pool:
[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)