Beanstalk Longshot test farm
Menu

Report rp_d16809a10e31f72a fail

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

windows+nvidia on thebasedpisces/agent-8d2999,

Machine

Commit
ef200041a7500f51d086fdf12c92b38243c71e65
Baseline
ed9495bbbed762e654bfa268214de8e10d03ec9a
App
nightly-206-d6e717d1, attempt 5
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 5 5600X3D 6-Core Processor
gpu
NVIDIA GeForce RTX 3070
tags
windowsnvidianvidia-proprietarydgpu
driver
621.24.0
ram_gb
32
vram_mb
8,017
gpu_vendor
nvidia
os_version
Windows 10.0.26200

Builds

main (baseline)

0 s warm

from 166ce0846b87

the PR's pack goes over the base this PC had (the PR's history holds it): no main build

PR

1,671.6 s warm

lift
118.3 s
read
0.7 s
finish
33.1 s
compile
1,513.3 s

Program cache: warm

Scenarios

field-and-market RX_VK_ACQUIRE_AHEAD=1 (PR only)

ok
Metric (median)switch offswitch onΔ
exit_code00±0%
field.fps_mean86.7185.48−1.4%
market.fps_mean60.7460.42−0.5%
run_hitch_count5147−7.8%
field.draws_mean826921.8+11.6%
field.hitch_count00±0%
market.draws_mean2,469.62,336.3−5.4%
log_forbidden_hits00±0%
market.hitch_count11±0%
field.stutter_count00±0%
log_expected_missing22±0%
market.stutter_count43−25%
run_frametime_max_ms6,077.536,203.65+2.1%
field.frametime_max_ms21.4522.61+5.4%
field.frametime_p50_ms11.3911.56+1.5%
field.frametime_p99_ms16.2115.35−5.3%
market.frametime_max_ms71.5275.18+5.1%
market.frametime_p50_ms16.216.29+0.6%
market.frametime_p99_ms21.5522.48+4.3%
field.frametime_1pct_low_ms17.5616.75−4.6%
market.frametime_1pct_low_ms29.6431.45+6.1%
screenshot_diff—0.27—

Pictures against the switch off: field diff 0.2729 (switch off against itself ), market diff 0 (switch off against itself )

Runs (2)
Metricoff 0on 1
hangnono
crashednono
exit_code00
field.fps_mean86.7185.48
market.fps_mean60.7460.42
run_hitch_count5147
field.draws_mean826921.8
field.hitch_count00
market.draws_mean2,469.62,336.3
log_forbidden_hits00
market.hitch_count11
field.stutter_count00
log_expected_missing22
market.stutter_count43
run_frametime_max_ms6,077.536,203.65
field.frametime_max_ms21.4522.61
field.frametime_p50_ms11.3911.56
field.frametime_p99_ms16.2115.35
market.frametime_max_ms71.5275.18
market.frametime_p50_ms16.216.29
market.frametime_p99_ms21.5522.48
field.frametime_1pct_low_ms17.5616.75
market.frametime_1pct_low_ms29.6431.45
screenshot_diff—0.27

Rules

ScenarioCellRuleLimitswitch offswitch onΔ %Status
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)crashFalse00—pass
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)field.fps_mean.min_delta_pct1086.7185.48−1.4%pass
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)market.fps_mean.min_delta_pct1060.7460.42−0.5%pass
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)screenshot.max_diff0.05—0.27—fail
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)field.frametime_p99_ms.max_delta_pct1016.2115.35−5.3%inconclusiveneed two usable starts per side (baseline: 1, PR: 1)
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)market.frametime_p99_ms.max_delta_pct1021.5522.48+4.3%inconclusiveneed two usable starts per side (baseline: 1, PR: 1)
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)log_forbidden_hits.max000—pass
field-and-marketRX_VK_ACQUIRE_AHEAD=1 (PR only)log_expected_missing.max022—fail

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-and-market-c0-field-main-failed.png
field-and-market-c0-field-main-failed.png
field-and-market-c0-field-pr-failed.png
field-and-market-c0-field-pr-failed.png

Log (PR side, end)

[hos host] vk: mirror syncs (600 submits): 3436 dirty pages from their submits' captures, 46694 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): 1024 dispatches, 37417 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5476 runs, 670.0 MB compared; 87 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9456 in captures, 1 only in the collection, 26 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 2340000 (1147681 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1001 of 3000 waited for their write-back, 0.05 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: 8507 kept their virtual core (nothing there to wait for), 3013 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: late pages' fix (600 recordings with one): of 668 captures with late pages 668 fixed (61.2 pages, 61.9 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 44 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 608 blocks (38912 KB); of the reads on the CPU, 1 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 0, of an earlier recording 43, not recorded yet 0, of this part 0; pages fixed from stamps 40049, from snapshots 863; the shadows: 139877 pages synced from captures, 138163 made known by it, 1714 left unknown because the replay or the collection wrote them since
[hos host] vk: replay reads of guest memory as submitted: 2360000 (1159534 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 890 ranges, 3351 MB), 227 pages written, 227 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 0.006, bytes copied 0.000; 24 kept (96 MB), 10 spare buffers, 7680 texture pages copied (30 MB)
[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: 2380000 (1171380 pages from the captures)
[hos host] vk: program picks: 3955719 kept (1358707 by the last picks' textures, a uniform buffer bound since), 3530 new, 1640750 with other textures (of 5600000)
[hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3732 dirty pages from their submits' captures, 46668 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): 1026 dispatches, 37618 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5599 runs, 687.6 MB compared; 85 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9220 in captures, 0 only in the collection, 28 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2400000 (1183217 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 17 pages in 17 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: a frame: 390 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 511.4 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 12262 ms in all, 413 jobs queued
[hos host] vk: a frame's replay time (ms): submit 14.02, present 0.20, draw 9.13, descriptors 3.26, texture lookups 0.08, uploads 0.01, pipelines 0.51, programs 1.63, commands 3.00, dispatch 0.92, memory sync 0.41, queue submit 0.00, slot wait 0.06
[hos host] vk: a frame: mirrors 220 (962 MB): 5.09 MB synced in 975.3 copies, 17.76 MB written back
[hos host] vk: 10920 presents, 61.6 fps; a frame: 2289 draws (0 skipped), 121 dispatches, 121 passes, 146 barriers, 6 submits, 0.1 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 1756 pipelines (378923 ms), 1394 programs (0 failed), 2375 textures (3333 MB)
[hos host] vk: host time in GPU resource waits: 1.05 ms a frame (fences 0.04, 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: 382.9 full barriers recorded, 220.6 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 37.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 137.2, an op 1971.0, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.2 ms a frame (the longest submission 2.4 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2420000 (1195098 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #120000: event 0x100c318048 mode 0 value 76325 (now 76306) (lr 0x806661f8)
[hos sead::MainThread] nvn: GPU waits in 5 s: 191 sync waits (199 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6104 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 2440000 (1206918 pages from the captures)
[hos host] vk: sparse mirrors: 76, 962 MB with memory of 1520 MB (557 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5442; 428 binds (147.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 109 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 35 spares now, 756 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 2665 dirty pages from their submits' captures, 48041 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): 1040 dispatches, 38081 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5614 runs, 687.0 MB compared; 82 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9480 in captures, 1 only in the collection, 25 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 2460000 (1218751 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2480000 (1230595 pages from the captures)
[hos host] vk: program picks: 4098545 kept (1415596 by the last picks' textures, a uniform buffer bound since), 3530 new, 1697924 with other textures (of 5800000)
[hos rmbl::VibrationThread] hid: 24576 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 889 ranges, 3353 MB), 227 pages written, 227 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 0.005, bytes copied 0.000; 25 kept (136 MB), 11 spare buffers, 7782 texture pages copied (30 MB)
[hos rmbl::VibrationThread] vcores: 143220 takes, 25612 waits (mean 93 us, longest 20.6 ms, 0 over HOS_VCORE_LOG_MS), 12622 kicks, 12730 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker2] nvn: 800000 recordings made, 69304 live copies (22.3 MB), 869 texture copies; 5 command buffers' segments (4.3 MB)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3013 dirty pages from their submits' captures, 46548 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): 1034 dispatches, 37063 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5489 runs, 670.7 MB compared; 91 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9440 in captures, 0 only in the collection, 33 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2500000 (1242447 pages from the captures)
[hos host] vk: in play: compute 09cc9a93a2d7dd81 (09cc9a93a2d7dd81 0000000000000000), inputs 0000000000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: in play: graphics 2617da75ccd7f311 (5f73d498e6000238 62a339dfd2622657), inputs 0000000000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[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: 2520000 (1254294 pages from the captures)
[hos host] vk: queues ordered by their events: 54000 submissions stopped at a wait, 53998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 121920, not met 0; captures at a CPU event's wait 6136, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 2540000 (1266147 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 999 of 3000 waited for their write-back, 0.04 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: 8289 kept their virtual core (nothing there to wait for), 2975 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: readback pages refreshed from guest memory: 1284010 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 248 KB; 0 made on demand (0 MB kept now); c1 stages: at most 68 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 77 sets (ub 1015, sb 446, cis 4152, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5904; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3799 dirty pages from their submits' captures, 47253 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): 1044 dispatches, 38059 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5628 runs, 687.4 MB compared; 136 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 156 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9212 in captures, 0 only in the collection, 26 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 2560000 (1277975 pages from the captures)
[hos host] vk: a frame: 393 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 487.9 draws left out (not ready), 0.01 waits for shaders or pipelines (0.0 ms); translation 12269 ms in all, 390 jobs queued
[hos host] vk: a frame's replay time (ms): submit 15.09, present 0.19, draw 9.68, descriptors 3.43, texture lookups 0.07, uploads 0.00, pipelines 0.53, programs 1.71, commands 3.21, dispatch 1.39, memory sync 0.41, queue submit 0.00, slot wait 0.06
[hos host] vk: a frame: mirrors 221 (962 MB): 5.10 MB synced in 975.4 copies, 17.76 MB written back
[hos host] vk: 11040 presents, 57.5 fps; a frame: 2310 draws (0 skipped), 122 dispatches, 121 passes, 147 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 1781 pipelines (387090 ms), 1396 programs (0 failed), 2384 textures (3335 MB)
[hos host] vk: host time in GPU resource waits: 1.51 ms a frame (fences 0.04, timelines 1.47, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 382.0 full barriers recorded, 221.5 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.5; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 138.0, an op 1970.6, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 2.4 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 4241502 kept (1472303 by the last picks' textures, a uniform buffer bound since), 3533 new, 1754964 with other textures (of 6000000)
[hos host] vk: replay reads of guest memory as submitted: 2580000 (1289841 pages from the captures)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 180000 so far (x1 0x117d028010 x2 0 x3 0x117d028000 x4 0x8b040)
[hos host] vk: late pages found at the replay (600 takes): 117 pages in 23 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 2600000 (1301667 pages from the captures)
[hos host] vk: in play: graphics 2ebad36173f70277 (e2c9665730ab4042 d82b787e5e29c74b), inputs 0000002000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: in play: graphics f86aa6df79157165 (b567f65880e1aa15 ef28db89e03b6ff0), inputs 0000002000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: in play: graphics 200b49bd1d4d9233 (0b6b3723991e3327 09fbfe9a98b5b3cc), inputs 0000002000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3260 dirty pages from their submits' captures, 46430 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): 1019 dispatches, 37141 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5527 runs, 671.3 MB compared; 84 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9564 in captures, 2 only in the collection, 25 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 889 ranges, 3359 MB), 225 pages written, 225 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.017; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 2375 texture pages copied (9 MB)
[hos host] vk: replay reads of guest memory as submitted: 2620000 (1313505 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5861 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: in play: graphics f6bbc92c351f76e7 (2e57b9d41de4deb2 c8ad2ce9a83b0aeb), inputs 0000002000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: in play: graphics f5880f9503ec3509 (3f6a861875fa344d d752a5fde10a1d1c), inputs 0000002000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants
[hos host] vk: replay reads of guest memory as submitted: 2640000 (1325373 pages from the captures)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 6354; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3165 dirty pages from their submits' captures, 45251 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): 986 dispatches, 36255 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5381 runs, 652.8 MB compared; 86 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 8850 in captures, 1 only in the collection, 26 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[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: 2660000 (1337213 pages from the captures)
[hos host] vk: program picks: 4384251 kept (1528806 by the last picks' textures, a uniform buffer bound since), 3544 new, 1812204 with other textures (of 6200000)
[hos host] vk: replay reads of guest memory as submitted: 2680000 (1349048 pages from the captures)
[hos Presentation Thread] vi: 11120 frames presented (59.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 60, 15.5-17.8 188, 17.8-22 43, 22-30 2, 30-40 1, over 40 2
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #80000: event 0x100c318008 mode 0 value 79995 (lr 0x80660f34)
[hos host] vk: replay reads of guest memory as submitted: 2700000 (1360913 pages from the captures)
[hos host] vk: pipeline cache: play file 14 saved (7972 KB): 80 pipelines, 35 from the driver's cache, 45 compiled; 0 more from the start's cache
[hos sead::MainThread] nvn: CommandBufferWaitEvent #125000: event 0x100c318048 mode 0 value 80125 (now 80106) (lr 0x806661f8)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4025 dirty pages from their submits' captures, 44698 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): 993 dispatches, 36255 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5362 runs, 653.0 MB compared; 80 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 156 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9030 in captures, 0 only in the collection, 21 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker2] barrier: 125490 looks: 27186 found the masks moved already, 93593 waited until they moved, 4711 for the whole 1 ms (a wait 270 us on average); 121701 wakes
[hos host] vk: replay reads of guest memory as submitted: 2720000 (1372735 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 889 ranges, 3363 MB), 234 pages written, 234 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.017; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 24 kept (86 MB), 12 spare buffers, 3911 texture pages copied (15 MB)
[hos host] vk: replay reads of guest memory as submitted: 2740000 (1384574 pages from the captures)
[hos host] vk: a frame: 400 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 458.4 draws left out (not ready), 0.04 waits for shaders or pipelines (0.4 ms); translation 12314 ms in all, 361 jobs queued
[hos host] vk: a frame's replay time (ms): submit 15.04, present 0.18, draw 9.89, descriptors 3.45, texture lookups 0.08, uploads 0.01, pipelines 0.52, programs 1.67, commands 3.12, dispatch 0.96, memory sync 0.39, queue submit 0.00, slot wait 0.07
[hos host] vk: a frame: mirrors 221 (962 MB): 5.12 MB synced in 978.8 copies, 17.79 MB written back
[hos host] vk: 11160 presents, 58.8 fps; a frame: 2349 draws (0 skipped), 122 dispatches, 122 passes, 147 barriers, 6 submits, 0.2 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 1816 pipelines (394746 ms), 1401 programs (0 failed), 2402 textures (3346 MB)
[hos host] vk: host time in GPU resource waits: 1.54 ms a frame (fences 0.04, timelines 1.50, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 386.1 full barriers recorded, 221.6 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.2; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 137.8, an op 1975.9, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.4 ms a frame (the longest submission 2.4 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.2 (0.1 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: readbacks of GPU results: 1008 of 3000 waited for their write-back, 0.04 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: 8483 kept their virtual core (nothing there to wait for), 3037 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 6804; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3505 dirty pages from their submits' captures, 46183 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): 1022 dispatches, 37087 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5488 runs, 670.7 MB compared; 92 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9235 in captures, 0 only in the collection, 24 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: vertex format NVN 0xe -> vk 17
[hos host] vk: replay reads of guest memory as submitted: 2760000 (1396432 pages from the captures)
[hos host] vk: program picks: 4527492 kept (1585558 by the last picks' textures, a uniform buffer bound since), 3544 new, 1868963 with other textures (of 6400000)
[hos host] vk: replay reads of guest memory as submitted: 2780000 (1408271 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 24 pages in 24 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos host] vk: replay reads of guest memory as submitted: 2800000 (1420139 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1357411 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 248 KB; 0 made on demand (0 MB kept now); c1 stages: at most 77 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 77 sets (ub 1015, sb 446, cis 4152, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 4088 dirty pages from their submits' captures, 44875 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): 995 dispatches, 36282 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5335 runs, 652.3 MB compared; 84 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9002 in captures, 0 only in the collection, 20 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 10714 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 2820000 (1431964 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 214 sync waits (352 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 2840000 (1443795 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 890 ranges, 3365 MB), 226 pages written, 226 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 0.006, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 4423 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 2860000 (1455659 pages from the captures)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 7254; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3559 dirty pages from their submits' captures, 46324 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): 1034 dispatches, 37257 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5473 runs, 670.1 MB compared; 81 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9465 in captures, 1 only in the collection, 21 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: program picks: 4670205 kept (1642153 by the last picks' textures, a uniform buffer bound since), 3544 new, 1926250 with other textures (of 6600000)
[hos host] vk: replay reads of guest memory as submitted: 2880000 (1467512 pages from the captures)
[hos NavMeshCAStepDepWorker1] vcores: 135017 takes, 23222 waits (mean 92 us, longest 20.7 ms, 0 over HOS_VCORE_LOG_MS), 11461 kicks, 11560 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2900000 (1479362 pages from the captures)
[hos host] vk: recorder: 9211101 packets run in 10.0 s (busy 2.82 s, spun idle 0.13 s, slept 11254 times, 2659 of them under 200 us), 0 calls made directly (no room); 18786 batches over 600 frames (31.3 a frame, 490 packets a batch), 9440 parts ended and submitted by it; the render thread (the replay lock's holder) waited for it 9 times, 1.87 ms (0.0 times, 0.00 ms a frame); every thread 225 times, 19.44 ms in all, the longest 1.83 ms; the queue's lock 126/12.37 ms (max 1.83), vmaDestroyBuffer 89/4.24 ms (max 1.78), vkDestroyImageView 7/1.61 ms (max 0.34), a part's submit 2/1.07 ms (max 0.95), vkQueueBindSparse 1/0.15 ms (max 0.15)
[hos host] vk: recorder: of its busy 2.82 s, 0.47 s in parts' ends and submits (the longest 3.04 ms), 0.00 s of that blocked on the queue's lock (0 times, the longest 0.00 ms), so 0.47 s in the ends, submits and holds; 2.35 s running the other packets; 15352 packets a frame
[hos host] vk: a frame: 404 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 299.7 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 12314 ms in all, 280 jobs queued
[hos host] vk: a frame's replay time (ms): submit 15.22, present 0.19, draw 10.22, descriptors 3.85, texture lookups 0.11, uploads 0.02, pipelines 0.53, programs 1.72, commands 3.36, dispatch 0.95, memory sync 0.42, queue submit 0.00, slot wait 0.06
[hos host] vk: a frame: mirrors 221 (962 MB): 5.14 MB synced in 979.0 copies, 17.76 MB written back
[hos host] vk: 11280 presents, 58.4 fps; a frame: 2503 draws (0 skipped), 121 dispatches, 122 passes, 147 barriers, 6 submits, 0.3 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 1897 pipelines (403907 ms), 1401 programs (0 failed), 2428 textures (3360 MB)
[hos host] vk: host time in GPU resource waits: 1.40 ms a frame (fences 0.04, timelines 1.36, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 389.1 full barriers recorded, 221.6 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.3; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 137.8, an op 1972.7, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.4 ms a frame (the longest submission 2.4 ms); 0.3 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.3 (0.1 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3716 dirty pages from their submits' captures, 46029 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): 1014 dispatches, 37157 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5472 runs, 670.0 MB compared; 82 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9006 in captures, 0 only in the collection, 20 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2920000 (1491189 pages from the captures)
[hos ModuleSystemWorker1] nvn: 850000 recordings made, 69636 live copies (22.6 MB), 869 texture copies; 5 command buffers' segments (4.4 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 2940000 (1503072 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 997 of 3000 waited for their write-back, 0.06 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: 8686 kept their virtual core (nothing there to wait for), 2834 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: 2960000 (1514907 pages from the captures)
[hos host] vk: program picks: 4813308 kept (1698877 by the last picks' textures, a uniform buffer bound since), 3544 new, 1983147 with other textures (of 6800000)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 7716; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3821 dirty pages from their submits' captures, 47319 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): 1036 dispatches, 38038 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5488 runs, 670.1 MB compared; 82 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9466 in captures, 1 only in the collection, 20 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #130000: event 0x100c318048 mode 0 value 83925 (now 83906) (lr 0x806661f8)
[hos host] vk: late pages found at the replay (600 takes): 21 pages in 21 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 2980000 (1526744 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 890 ranges, 3375 MB), 245 pages written, 245 copied (1.0 MB)
[hos host] vk: a capture taken (ms): all 0.024; 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 (158 MB), 8 spare buffers, 6733 texture pages copied (26 MB)
[hos host] vk: late pages' fix (600 recordings with one): of 631 captures with late pages 631 fixed (59.4 pages, 60.1 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 93 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 608 blocks (38912 KB); of the reads on the CPU, 8 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 0, of an earlier recording 85, not recorded yet 0, of this part 0; pages fixed from stamps 36725, from snapshots 783; the shadows: 110956 pages synced from captures, 109943 made known by it, 1013 left unknown because the replay or the collection wrote them since
[hos host] vk: replay reads of guest memory as submitted: 3000000 (1538597 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 16537 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos BaseProcExecutor5] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 43 made): 16907710 lookups, 168272 missed (1.00 %)
[hos host] vk: replay reads of guest memory as submitted: 3020000 (1550448 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3773 dirty pages from their submits' captures, 46134 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): 1029 dispatches, 37185 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5610 runs, 687.7 MB compared; 83 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9252 in captures, 1 only in the collection, 16 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3040000 (1562303 pages from the captures)
[hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #85000: event 0x100c31801c mode 0 value 84997 (lr 0x802911b8)
[hos host] vk: program picks: 4956187 kept (1755523 by the last picks' textures, a uniform buffer bound since), 3544 new, 2040268 with other textures (of 7000000)
[hos host] vk: replay reads of guest memory as submitted: 3060000 (1574159 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1430537 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 0.03, writes collected 0.04
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 248 KB; 0 made on demand (0 MB kept now); c1 stages: at most 77 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 77 sets (ub 1015, sb 446, cis 4152, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 8160; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 756, 3708.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3699 dirty pages from their submits' captures, 43914 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): 973 dispatches, 35442 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5223 runs, 635.3 MB compared; 75 pages read into the shadows; 352 MB of shadows (109 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9056 in captures, 1 only in the collection, 19 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: memory: working set 11591 MB (peak 12142), private 17643 MB, staging 176 MB in 11 arenas, 29 made so far (5 ms)
[hos host] vk: memory heaps: heap 0 (device): 198 blocks 5419 MB, 18669 allocations 5082 MB; used 5645 of 7213 MB; heap 1 (system): 17 blocks 884 MB, 41 allocations 834 MB; used 3141 of 15577 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): 16 blocks 256 MB, 124 images 141 MB; 64 free ranges, the largest 10 MB
[hos host] vk: image blocks (textures, compacted): 63 blocks 2016 MB, 2340 images 1942 MB; 1035 free ranges, the largest 13 MB
[hos host] vk: render target images: 641 reused from the pool, 923 made new, 792 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 5645 MB used of 7213 MB allowed (336 MB of it free in the blocks); textures 3383 MB (budget 3445 MB), 2479 textures
[hos host] vk: budget: VRAM 5419 of 7213 MB (5645 MB by the driver, 226 MB unaccounted): textures 3383, mirrors 962, shadows 352, blocks free 336, staging 176, other buffers 144, other images 63; RAM 3055 MB (the process's private memory 17643 MB): imports 2188, capture spares 704, captures 98, capture table 33, other buffers 32, others 0
[hos host] vk: textures: decoded ASTC 1455 MB, rendered 770 MB (48 drawn in one frame, kept: 25834 KB), other 767 MB; used in the last 8 presents 1311 MB
[hos host] vk: decoded ASTC used again: 51 textures (27 MB) copied from ones the game finalized, not decoded; 51 of those retired, 115 listed; 682 MB of blocks hashed in 74 ms
[hos host] vk:   288 MB: 0x114682a000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a4772c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 2826 presents ago
[hos host] vk:   214 MB: 0x10a0efa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 2826 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:   47 MB: 0x10c18e9000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 5760 presents ago
[hos host] vk:   47 MB: 0x10ae982400 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 5760 presents ago
[hos host] vk:   47 MB: 0x10ba6ea200 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 5760 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 69 (15329 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 35 (6158 KB); 262x104x1 NVN 0x1: 3 (79 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 419 waited for it, 1.48 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 75.2 ms; VRAM 5.5 of 7.0 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 0 program records loaded (0.0 ms), 1965 new graphics pipelines, pipelines from the driver's cache 643, from the start's cache 42, compiled 1201; 932733 draws and dispatches left out, 1259 waits (11160.5 ms)
[hos host] vk: program loads at create (play): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 8793 create calls with nothing kept for their stages, 0 before the index; units 8793 (0 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: program loads at create (play): 0 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them)
[hos host] vk: module identifiers (play): 0 known, 0 learned in this run; 0 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 407 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 244.6 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 12314 ms in all, 221 jobs queued
[hos host] vk: a frame's replay time (ms): submit 15.41, present 0.20, draw 10.31, descriptors 3.92, texture lookups 0.12, uploads 0.04, pipelines 0.52, programs 1.68, commands 3.43, dispatch 0.95, memory sync 0.43, queue submit 0.00, slot wait 0.06
[hos host] vk: a frame: mirrors 221 (962 MB): 5.13 MB synced in 978.4 copies, 17.77 MB written back
[hos host] vk: 11400 presents, 57.9 fps; a frame: 2558 draws (0 skipped), 122 dispatches, 122 passes, 147 barriers, 6 submits, 0.5 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 1956 pipelines (411835 ms), 1401 programs (0 failed), 2479 textures (3383 MB)
[hos host] vk: host time in GPU resource waits: 1.39 ms a frame (fences 0.04, timelines 1.35, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 389.8 full barriers recorded, 221.7 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.5; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 137.9, an op 1973.0, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.5 ms a frame (the longest submission 2.4 ms); 0.5 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.5 (0.2 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 17.00 ms a frame): its jobs 15.46 ms a frame (submits 4.76, presents 0.20, others 10.49), idle 1.54; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.24 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); 438 captures at a CPU signal; the submits' waits read in 0.059 ms a frame; readbacks: 2291 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 14.36 ms after its hand-over (72.18 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 1.38 + 0.17 (the window's copy is in the idle), after it 7.50 + 0.58; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.03 ms of GPU time), after its last that reads it 1.00 (0.03 ms)
[hos host] vk: frame ahead (600 presents): 9.13 parts a frame recorded in the signal's job, 66.7% of them took nothing that came with the signal; of the others, 3.04 a frame took pages of the signal's capture into a mirror (120.5 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 9 of 438 frames, its first three in 2
[hos host] vk: frame ahead, what came with the signal: 438 signals with a capture, each of 184.1 pages in 11.4 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: 1.59+0.18, 0.61+0.04, 1.14+0.07, 1.30+0.11, 0.39+0.05, 0.88+0.03, 1.34+0.03, 0.24+0.04, 0.01+0.02, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: replay reads of guest memory as submitted: 3080000 (1586004 pages from the captures)
[hos Presentation Thread] vi: 11413 frames presented (58.5 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 29, 15.5-17.8 191, 17.8-22 71, 22-30 2, 30-40 0, over 40 0
[hos host] vk: pipeline cache: play file 15 saved (6976 KB): 147 pipelines, 83 from the driver's cache, 64 compiled; 0 more from the start's cache
[hos host] vk: replay reads of guest memory as submitted: 3100000 (1597880 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 891 ranges, 3383 MB), 233 pages written, 233 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.019; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 24 kept (90 MB), 12 spare buffers, 7702 texture pages copied (30 MB)
[hos host] vk: replay reads of guest memory as submitted: 3120000 (1609711 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3371 dirty pages from their submits' captures, 47591 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): 1034 dispatches, 38179 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5682 runs, 688.4 MB compared; 85 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 156 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9348 in captures, 0 only in the collection, 21 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3140000 (1621559 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1009 of 3000 waited for their write-back, 0.07 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: 8555 kept their virtual core (nothing there to wait for), 3221 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: program picks: 5099144 kept (1812234 by the last picks' textures, a uniform buffer bound since), 3544 new, 2097311 with other textures (of 7200000)
[hos host] vk: render targets drawn over from another start, let go: 1275 so far (3505 MB), 1141 of them (3091 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 3160000 (1633424 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 27 pages in 27 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: sparse mirrors: 77, 962 MB with memory of 1524 MB (561 MB spared); blocks given memory later 4333, given back 10320; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 8622; 429 binds (147.2 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 110 taken from the spares, 111 made new; 144 kept as spares, 0 destroyed; 34 spares now, 752 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3242 dirty pages from their submits' captures, 46419 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): 1021 dispatches, 37234 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5553 runs, 671.8 MB compared; 94 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9338 in captures, 0 only in the collection, 23 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 141 live (2188 MB), 0 retired still imported (0 MB), 47 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 3180000 (1645256 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 13714 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3200000 (1657134 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: 3220000 (1668963 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 210 sync waits (267 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[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: 0 program records loaded (0.0 ms), 1965 new graphics pipelines, pipelines from the driver's cache 669, from the start's cache 42, compiled 1225; 957499 draws and dispatches left out, 1259 waits (11160.5 ms)
[hos host] vk: program loads at create (close): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 8793 create calls with nothing kept for their stages, 0 before the index; units 8793 (0 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: program loads at create (close): 0 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them)
[hos host] vk: module identifiers (close): 0 known, 0 learned in this run; 0 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: indexed descriptor arrays (close): 131 in 131 of 2717 program stages, 0 of them near a limit
[hos host] vk: indexed descriptor arrays (close), fragment stages: 131 texture (17-64: 131); the longest 64
[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 sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 892 ranges, 3387 MB), 235 pages written, 235 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.020; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 25 kept (80 MB), 11 spare buffers, 8065 texture pages copied (31 MB)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 3709 dirty pages from their submits' captures, 46231 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): 1013 dispatches, 37301 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5549 runs, 671.1 MB compared; 84 pages read into the shadows; 352 MB of shadows (110 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 9318 in captures, 1 only in the collection, 20 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3240000 (1680827 pages from the captures)
[hos host] vk: a frame: 407 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 225.3 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 12314 ms in all, 169 jobs queued
[hos host] vk: a frame's replay time (ms): submit 16.24, present 0.20, draw 10.89, descriptors 4.11, texture lookups 0.07, uploads 0.00, pipelines 0.55, programs 1.80, commands 3.62, dispatch 1.01, memory sync 0.41, queue submit 0.00, slot wait 0.07
[hos host] vk: a frame: mirrors 221 (962 MB): 5.12 MB synced in 980.5 copies, 17.79 MB written back
[hos host] vk: 11520 presents, 55.0 fps; a frame: 2574 draws (0 skipped), 124 dispatches, 122 passes, 148 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2008 pipelines (420631 ms), 1401 programs (0 failed), 2485 textures (3384 MB)
[hos host] vk: host time in GPU resource waits: 1.37 ms a frame (fences 0.04, timelines 1.33, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 385.8 full barriers recorded, 222.2 left out (nothing recorded since the one before), 14.2 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 39.1; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 38.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 138.6, an op 1973.4, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0;
[hos host] vk: GPU time 7.4 ms a frame (the longest submission 2.4 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: pipeline cache: play file 16 saved (4031 KB): 50 pipelines, 26 from the driver's cache, 24 compiled; 0 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)