Beanstalk Longshot test farm
Menu

Report rp_a65df7e54289f5a3 fail

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

windows+amd on Hidden tester,

Machine

Commit
3569b8da6a4f90bc036bbb40cb52993b865b0a39
Baseline
09cbdd979eacfbd0c83e27fad7e50380985af02d
App
nightly-172-736563c0, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 9 5900X 12-Core Processor
gpu
AMD Radeon RX 9070 XT
tags
windowsamdamd-proprietarydgpu
driver
2.0.416
ram_gb
32
vram_mb
16,304
gpu_vendor
amd
os_version
Windows 10.0.26300

Builds

main (baseline)

620.5 s warm

from 09cbdd979eac

lift
0.5 s
read
511.7 s
finish
85.4 s
compile
15.8 s

PR

164.5 s warm

Program cache: warm

Scenarios

forest-market

ok
Metric (median)mainPRΔ
exit_code00±0%
forest.fps_mean73.7580.45+9.1%
market.fps_mean66.3773.5+10.7%
forest.draws_mean673.3665.85−1.1%
market.draws_mean2,027.11,954.8−3.6%
forest.hitch_count00±0%
log_forbidden_hits00±0%
market.hitch_count00±0%
forest.stutter_count33±0%
log_expected_missing00±0%
market.stutter_count3.54+14.3%
forest.frametime_max_ms30.2831.24+3.2%
forest.frametime_p50_ms13.6112.5−8.2%
forest.frametime_p99_ms15.6714.06−10.3%
market.frametime_max_ms33.5431.78−5.2%
market.frametime_p50_ms14.9513.42−10.2%
market.frametime_p99_ms19.9217.48−12.2%
forest.frametime_1pct_low_ms19.9317.47−12.3%
market.frametime_1pct_low_ms24.9321.73−12.8%
screenshot_diff—0.58—

Pictures against main: forest 5 s diff 0.0146 (main against itself 0.0273), forest 10 s diff 0.0288 (main against itself 0.0309), forest 15 s diff 0.0346 (main against itself 0.0402), forest 19 s diff 0.0318 (main against itself 0.0262), market 5 s diff 0.5742 (main against itself 0.3712), market 10 s diff 0.5822 (main against itself 0.3802), market 15 s diff 0.5846 (main against itself 0.3785), market 19 s diff 0.5873 (main against itself 0.3798), forest diff 0.0295 (main against itself 0.0375), market diff 0.5893 (main against itself 0.3867)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0000
forest.fps_mean73.4780.0380.8774.04
market.fps_mean64.0473.173.968.7
forest.draws_mean674.7665.7666671.9
market.draws_mean2,168.91,946.61,9631,885.3
forest.hitch_count0000
log_forbidden_hits0000
market.hitch_count0000
forest.stutter_count3333
log_expected_missing0000
market.stutter_count3444
forest.frametime_max_ms30.5929.8232.6629.97
forest.frametime_p50_ms13.6812.5212.4713.54
forest.frametime_p99_ms15.8414.114.0215.49
market.frametime_max_ms34.0231.4832.0933.06
market.frametime_p50_ms15.4713.4713.3714.43
market.frametime_p99_ms21.0817.3417.6218.75
forest.frametime_1pct_low_ms19.8317.4717.4820.03
market.frametime_1pct_low_ms26.4421.4522.0223.42
screenshot_diff—0.590.58—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
forest-marketcrashFalse00—pass
forest-marketforest.fps_mean.min_delta_pct1073.7580.45+9.1%pass
forest-marketmarket.fps_mean.min_delta_pct1066.3773.5+10.7%pass
forest-marketscreenshot.max_diff0.10.390.59—fail
forest-marketforest.frametime_p99_ms.max_delta_pct2015.6714.06−10.3%pass
forest-marketmarket.frametime_p99_ms.max_delta_pct2019.9217.48−12.2%pass
forest-marketlog_forbidden_hits.max000—pass

Pictures of the failure

This report had 2 pictures of its failure (the last frame of a stuck step, or main's and the PR's picture where they differed too much). The farm keeps those for a day: they were deleted.

Log (PR side, end)

[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2700000 (1530798 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2720000 (1542770 pages from the captures)
[hos Presentation Thread] vi: 15562 frames presented (73.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 341, 15.5-17.8 24, 17.8-22 1, 22-30 1, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1100 ranges, 3455 MB), 213 pages written, 213 copied (0.8 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; 25 kept (116 MB), 10 spare buffers, 6038 texture pages copied (23 MB)
[hos host] vk: readback pages refreshed from guest memory: 1135041 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 72, 859 MB with memory of 1276 MB (416 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 333 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 85 kept as spares, 0 destroyed; 32 spares now, 524 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 482 dirty pages from their submits' captures, 45018 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 888 dispatches, 34610 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4752 runs, 633.9 MB compared; 94 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14558 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 2740000 (1554667 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 72 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #80000: event 0x100c5e8024 mode 0 value 80000 (lr 0x80665068)
[hos host] vk: program picks: 3275634 kept (1113696 by the last picks' textures, a uniform buffer bound since), 55310 new, 1669055 with other textures (of 5000000)
[hos host] vk: replay reads of guest memory as submitted: 2760000 (1566679 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: memory: working set 16000 MB (peak 16016), private 25582 MB, staging 224 MB in 14 arenas, 37 made so far (87 ms)
[hos host] vk: memory heaps: heap 0 (system): 16 blocks 832 MB, 39 allocations 748 MB; used 2860 of 15565 MB; heap 1 (device): 244 blocks 8096 MB, 17014 allocations 7430 MB; used 9299 of 15419 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 25 MB; 1 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 16 blocks 512 MB, 107 images 196 MB; 61 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 132 blocks 4224 MB, 2859 images 4167 MB; 356 free ranges, the largest 19 MB
[hos host] vk: render target images: 267 reused from the pool, 563 made new, 452 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 9299 MB used of 15419 MB allowed (666 MB of it free in the blocks); textures 5861 MB (budget 11000 MB), 2981 textures
[hos host] vk: budget: VRAM 8096 of 15419 MB (9299 MB by the driver, 1203 MB unaccounted): textures 5861, mirrors 859, blocks free 666, shadows 288, staging 224, other buffers 156, other images 41; RAM 2791 MB (the process's private memory 25582 MB): imports 1636, capture spares 628, retired imports 376, captures 112, capture table 31, other buffers 8, others 0
[hos host] vk: textures: decoded ASTC 3667 MB, rendered 850 MB (51 drawn in one frame, kept: 23436 KB), other 685 MB; used in the last 8 presents 2298 MB
[hos host] vk: decoded ASTC used again: 126 textures (190 MB) copied from ones the game finalized, not decoded; 126 of those retired, 163 listed; 786 MB of blocks hashed in 78 ms
[hos host] vk:   288 MB: 0x1146afa000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a4a42c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 3055 presents ago
[hos host] vk:   214 MB: 0x10a11ca600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 3055 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 5135 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113ba8d000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001eb6200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001be1800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5099 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 51 (12319 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); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 18 (3167 KB); 262x104x1 NVN 0x1: 3 (79 KB); 306x104x1 NVN 0x1: 3 (93 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 222 waited for it, 0.42 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 27.6 ms; VRAM 9.1 of 15.1 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 6 program records loaded (4.4 ms), 2 new graphics pipelines, pipelines from the driver's cache 2, from the start's cache 0, compiled 0; 8 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5286 queued, 5286 loaded (median 0.58 ms, 99th percentile 8.78 ms, worst 18.62 ms, 5436 ms and 1283.5 MB read in all); 7622 programs (1465 of them compute variants without their code, 0 graphics programs no note names), 9540 graphics pipelines (0 not in a cache), 407 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1445 pipelines made at create taken by draws; 2962 create calls with nothing kept for their stages, 0 before the index; units 8248 (5286 ready, 0 loading), 14342 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 657 known, 0 learned in this run; 407 compute pipelines made by them at a create call, 250 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 300 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.70, present 0.37, draw 5.16, descriptors 2.00, texture lookups 0.07, uploads 0.00, pipelines 0.25, programs 0.96, commands 1.56, dispatch 0.64, memory sync 0.43, queue submit 0.45, slot wait 0.24
[hos host] vk: a frame: mirrors 157 (859 MB): 4.79 MB synced in 933.7 copies, 17.59 MB written back
[hos host] vk: 15600 presents, 74.0 fps; a frame: 1961 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2981 textures (5861 MB)
[hos host] vk: host time in GPU resource waits: 0.94 ms a frame (fences 0.03, timelines 0.91, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 384.2 full barriers recorded, 197.5 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: 38.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.6 ms a frame (the longest submission 2.6 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, 13.55 ms a frame): its jobs 9.51 ms a frame (submits 5.93, presents 0.29, others 3.29), idle 4.04; the game waited for room at 2 presents, 11.69 ms each (0.04 a frame; 2.47 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); 250 captures at a CPU signal; the submits' waits read in 0.047 ms a frame; readbacks: 1702 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 8.41 ms after its hand-over (25.05 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 1.94 + 0.25 (the window's copy is in the idle), after it 1.34 + 0.36; 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): 9.48 parts a frame recorded in the signal's job, 82.3% of them took nothing that came with the signal; of the others, 1.68 a frame took pages of the signal's capture into a mirror (31.8 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 48 of 250 frames, its first three in 5
[hos host] vk: frame ahead, what came with the signal: 250 signals with a capture, each of 69.3 pages in 5.3 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: 0.20+0.05, 0.07+0.02, 0.47+0.10, 0.24+0.05, 0.15+0.04, 0.15+0.04, 0.01+0.02, 0.01+0.02, 0.01+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 815 dirty pages from their submits' captures, 44463 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): 888 dispatches, 34504 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4880 runs, 650.7 MB compared; 84 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14541 in captures, 0 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2780000 (1578621 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2800000 (1590535 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7434 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 286 KB; 0 made on demand (0 MB kept now); c1 stages: at most 98 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 72, 859 MB with memory of 1276 MB (416 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 333 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 85 kept as spares, 0 destroyed; 32 spares now, 524 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 518 dirty pages from their submits' captures, 44730 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): 891 dispatches, 34565 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5003 runs, 667.7 MB compared; 106 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14385 in captures, 3 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 2820000 (1602556 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1439 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker4] vk: invalidates since the last readbacks line: 9764 kept their virtual core (nothing there to wait for), 3036 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1100 ranges, 3459 MB), 220 pages written, 220 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 0.007, bytes copied 0.000; 25 kept (112 MB), 11 spare buffers, 6672 texture pages copied (26 MB)
[hos host] vk: replay reads of guest memory as submitted: 2840000 (1614488 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 756, 3708.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 457 dirty pages from their submits' captures, 44111 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): 886 dispatches, 33926 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4749 runs, 633.8 MB compared; 105 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14539 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2860000 (1626405 pages from the captures)
[hos host] vk: program picks: 3418118 kept (1165631 by the last picks' textures, a uniform buffer bound since), 55310 new, 1726571 with other textures (of 5200000)
[hos ModuleSystemWorker2] nvn: CommandBufferWaitEvent #140000: event 0x100c5e8004 mode 0 value 81930 (now 81911) (lr 0x82c0326c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 2880000 (1638423 pages from the captures)
[hos host] vk: a frame: 301 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.74, present 0.23, draw 5.21, descriptors 2.05, texture lookups 0.08, uploads 0.00, pipelines 0.25, programs 0.98, commands 1.55, dispatch 0.64, memory sync 0.46, queue submit 0.44, slot wait 0.24
[hos host] vk: a frame: mirrors 157 (859 MB): 4.78 MB synced in 932.9 copies, 17.59 MB written back
[hos host] vk: 15720 presents, 74.3 fps; a frame: 1962 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2984 textures (5862 MB)
[hos host] vk: host time in GPU resource waits: 0.84 ms a frame (fences 0.03, timelines 0.81, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 384.0 full barriers recorded, 197.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.6 ms a frame (the longest submission 2.6 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 72, 859 MB with memory of 1276 MB (416 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 333 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 85 kept as spares, 0 destroyed; 32 spares now, 524 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 807 dirty pages from their submits' captures, 44457 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): 891 dispatches, 34491 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4876 runs, 650.7 MB compared; 97 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14458 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 2900000 (1650337 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2920000 (1662282 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1205146 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 720 dirty pages from their submits' captures, 44010 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): 875 dispatches, 34172 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4874 runs, 650.7 MB compared; 99 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14145 in captures, 2 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1100 ranges, 3459 MB), 226 pages written, 226 copied (0.9 MB)
[hos ModuleSystemWorker4] nvn: 900000 recordings made, 78674 live copies (20.7 MB), 663 texture copies; 4 command buffers' segments (4.2 MB)
[hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.014, bytes copied 0.000; 25 kept (128 MB), 7 spare buffers, 9689 texture pages copied (37 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 136 sync waits (54 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 2940000 (1674295 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 12984 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos tera::FileResourceMgr] vcores: 179986 takes, 34206 waits (mean 65 us, longest 16.8 ms, 0 over HOS_VCORE_LOG_MS), 17602 kicks, 17391 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2960000 (1686212 pages from the captures)
[hos host] vk: program picks: 3560569 kept (1217710 by the last picks' textures, a uniform buffer bound since), 55310 new, 1784120 with other textures (of 5400000)
[hos host] vk: sparse mirrors: 72, 859 MB with memory of 1276 MB (416 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 333 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 85 kept as spares, 0 destroyed; 32 spares now, 524 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 316 dirty pages from their submits' captures, 44893 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 890 dispatches, 34472 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4874 runs, 650.7 MB compared; 90 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14389 in captures, 2 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 2980000 (1698158 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05
[hos host] vk: slow present: 16.8 ms:
[hos host] vk: present 15804 written to <data>\jobs\jb_0a8dd1d22c9c6446\runs\forest-market-g0-02-pr\shots/forest-market-c0-pr-02-market_19s.png (the control bridge)
[hos host] vk: replay reads of guest memory as submitted: 3000000 (1710163 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 85 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1437 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 9867 kept their virtual core (nothing there to wait for), 2933 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 286 KB; 0 made on demand (0 MB kept now); c1 stages: at most 98 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 766 dirty pages from their submits' captures, 44587 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 887 dispatches, 34527 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4869 runs, 650.1 MB compared; 121 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14371 in captures, 0 only in the collection, 36 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3020000 (1722082 pages from the captures)
[hos host] vk: a frame: 299 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.72, present 0.36, draw 5.14, descriptors 2.00, texture lookups 0.07, uploads 0.00, pipelines 0.25, programs 0.97, commands 1.54, dispatch 0.64, memory sync 0.47, queue submit 0.45, slot wait 0.23
[hos host] vk: a frame: mirrors 157 (859 MB): 4.78 MB synced in 932.3 copies, 17.59 MB written back
[hos host] vk: 15840 presents, 73.8 fps; a frame: 1961 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2986 textures (5863 MB)
[hos host] vk: host time in GPU resource waits: 0.95 ms a frame (fences 0.03, timelines 0.92, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 383.8 full barriers recorded, 197.5 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: 38.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.6 ms a frame (the longest submission 2.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #85000: event 0x100c5e802c mode 0 value 84999 (lr 0x80667688)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1100 ranges, 3459 MB), 216 pages written, 216 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (114 MB), 10 spare buffers, 4022 texture pages copied (15 MB)
[hos host] vk: replay reads of guest memory as submitted: 3040000 (1734032 pages from the captures)
[hos host] vk: mirror of pool 0x1041800000 (4 MB) given back: idle, 6005 submissions since its sync
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 434 dirty pages from their submits' captures, 44905 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 895 dispatches, 34587 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4878 runs, 651.4 MB compared; 97 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14496 in captures, 0 only in the collection, 38 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 3060000 (1746039 pages from the captures)
[hos sead::MainThread] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x117a347040 x2 0x6001d40 x3 0x117a347000 x4 0xf33080)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2236 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: late pages' fix (600 recordings with one): of 679 captures with late pages 679 fixed (67.8 pages, 67.9 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; 14 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 96 blocks (6144 KB); of the reads on the CPU, 0 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 13, of an earlier recording 1, not recorded yet 0, of this part 0; pages fixed from stamps 44869, from snapshots 1194; the shadows: 280138 pages synced from captures, 271335 made known by it, 8803 left unknown because the replay or the collection wrote them since
[hos host] vk: program picks: 3702654 kept (1269585 by the last picks' textures, a uniform buffer bound since), 55310 new, 1842035 with other textures (of 5600000)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #145000: event 0x100c5e8004 mode 0 value 85730 (now 85711) (lr 0x82c0326c)
[hos host] vk: replay reads of guest memory as submitted: 3080000 (1757952 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: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 672 dirty pages from their submits' captures, 44601 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): 893 dispatches, 34491 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4871 runs, 650.7 MB compared; 117 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14495 in captures, 2 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3100000 (1769902 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 629 so far (1728 MB), 527 of them (1459 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 3120000 (1781908 pages from the captures)
[hos Presentation Thread] vi: 15934 frames presented (74.3 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 368, 15.5-17.8 3, 17.8-22 0, 22-30 1, 30-40 0, over 40 0
[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: readback pages refreshed from guest memory: 1275644 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 839 dirty pages from their submits' captures, 44595 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 892 dispatches, 34609 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4873 runs, 650.8 MB compared; 94 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14577 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 3140000 (1793822 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1062 ranges, 2837 MB), 214 pages written, 214 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.013; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (108 MB), 12 spare buffers, 4019 texture pages copied (15 MB)
[hos host] vk: a frame: 299 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.56, present 0.22, draw 5.11, descriptors 2.00, texture lookups 0.07, uploads 0.00, pipelines 0.25, programs 0.95, commands 1.53, dispatch 0.64, memory sync 0.42, queue submit 0.45, slot wait 0.22
[hos host] vk: a frame: mirrors 157 (858 MB): 4.79 MB synced in 933.5 copies, 17.59 MB written back
[hos host] vk: 15960 presents, 74.8 fps; a frame: 1960 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2992 textures (5864 MB)
[hos host] vk: host time in GPU resource waits: 0.81 ms a frame (fences 0.03, timelines 0.79, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 383.6 full barriers recorded, 197.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.6; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.6 ms a frame (the longest submission 2.6 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 3160000 (1805774 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 686 dirty pages from their submits' captures, 44562 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 888 dispatches, 34494 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4874 runs, 650.1 MB compared; 107 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14518 in captures, 1 only in the collection, 36 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 3844837 kept (1321473 by the last picks' textures, a uniform buffer bound since), 55310 new, 1899852 with other textures (of 5800000)
[hos host] vk: replay reads of guest memory as submitted: 3180000 (1817779 pages from the captures)
[hos host] vk: queues ordered by their events: 72000 submissions stopped at a wait, 71984 went on once it was reached, 14 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.00 ms at most); waits met 147434, not met 0; captures at a CPU event's wait 8122, 0 of them at a wait met on arrival
[hos sead::MainThread] vk: readbacks of GPU results: 1449 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: invalidates since the last readbacks line: 9879 kept their virtual core (nothing there to wait for), 2921 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4876 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 (1829695 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 286 KB; 0 made on demand (0 MB kept now); c1 stages: at most 98 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 632 dirty pages from their submits' captures, 44676 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 896 dispatches, 34518 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4898 runs, 650.8 MB compared; 85 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14599 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 3220000 (1841644 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1048 ranges, 2501 MB), 213 pages written, 213 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.014; 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 (112 MB), 10 spare buffers, 1971 texture pages copied (7 MB)
[hos host] vk: replay reads of guest memory as submitted: 3240000 (1853650 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 756, 3708.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 459 dirty pages from their submits' captures, 44268 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): 884 dispatches, 33996 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4755 runs, 633.8 MB compared; 118 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14499 in captures, 0 only in the collection, 37 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: replay reads of guest memory as submitted: 3260000 (1865568 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 3280000 (1877516 pages from the captures)
[hos host] vk: program picks: 3987394 kept (1373450 by the last picks' textures, a uniform buffer bound since), 55310 new, 1957295 with other textures (of 6000000)
[hos host] vk: a frame: 301 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.60, present 0.22, draw 5.17, descriptors 2.02, texture lookups 0.08, uploads 0.00, pipelines 0.25, programs 0.98, commands 1.54, dispatch 0.63, memory sync 0.46, queue submit 0.44, slot wait 0.21
[hos host] vk: a frame: mirrors 157 (858 MB): 4.78 MB synced in 933.3 copies, 17.59 MB written back
[hos host] vk: 16080 presents, 74.2 fps; a frame: 1964 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2992 textures (5864 MB)
[hos host] vk: host time in GPU resource waits: 0.78 ms a frame (fences 0.03, timelines 0.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 383.9 full barriers recorded, 197.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.6 ms a frame (the longest submission 3.0 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #150000: event 0x100c5e8004 mode 0 value 89530 (now 89511) (lr 0x82c0326c)
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 673 dirty pages from their submits' captures, 45199 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): 892 dispatches, 35087 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4875 runs, 650.8 MB compared; 105 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14504 in captures, 1 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 3300000 (1889525 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 ModuleSystemWorker3] nvn: CommandBufferSignalEvent #90000: event 0x100c5e8038 mode 0 value 89999 (lr 0x8066189c)
[hos host] vk: replay reads of guest memory as submitted: 3320000 (1901441 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6753 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1345751 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 756, 3708.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 689 dirty pages from their submits' captures, 43871 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): 881 dispatches, 33877 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4879 runs, 650.7 MB compared; 90 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14162 in captures, 0 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3340000 (1913393 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1036 ranges, 2419 MB), 232 pages written, 232 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.013, bytes copied 0.000; 25 kept (104 MB), 11 spare buffers, 3376 texture pages copied (13 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 135 sync waits (48 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos BaseProcExecutor4] vcores: 179133 takes, 33593 waits (mean 63 us, longest 13.7 ms, 0 over HOS_VCORE_LOG_MS), 17188 kicks, 17010 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker5] nvn: 950000 recordings made, 78684 live copies (21.3 MB), 663 texture copies; 3 command buffers' segments (4.1 MB)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1456 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 ModuleSystemWorker1] vk: invalidates since the last readbacks line: 9795 kept their virtual core (nothing there to wait for), 3005 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: 3360000 (1925401 pages from the captures)
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 468 dirty pages from their submits' captures, 44425 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): 875 dispatches, 34291 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4871 runs, 650.7 MB compared; 103 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14471 in captures, 0 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 14 retired still imported (376 MB), 7 retired given back (92 MB)
[hos host] vk: recorder: 8467056 packets run in 10.0 s (busy 1.40 s, spun idle 5.20 s, slept 4141 times, 1914 of them under 200 us), 0 calls made directly (no room); the replay waited for it 33195 times, 94.22 ms in all, the longest 0.20 ms; vkResetDescriptorPool 11989/52.63 ms (max 0.15), vkEndCommandBuffer 12045/25.33 ms (max 0.08), replay_mu unlock 9150/16.26 ms (max 0.20), vmaInvalidateAllocation 11/0.00 ms (max 0.00)
[hos host] vk: replay reads of guest memory as submitted: 3380000 (1937318 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: program picks: 4129647 kept (1425256 by the last picks' textures, a uniform buffer bound since), 55310 new, 2015042 with other textures (of 6200000)
[hos host] vk: replay reads of guest memory as submitted: 3400000 (1949264 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: memory: working set 15981 MB (peak 16016), private 25562 MB, staging 112 MB in 7 arenas, 37 made so far (87 ms)
[hos host] vk: memory heaps: heap 0 (system): 16 blocks 832 MB, 39 allocations 748 MB; used 2500 of 15565 MB; heap 1 (device): 243 blocks 8032 MB, 16999 allocations 7320 MB; used 9235 of 15419 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 25 MB; 1 free ranges, the largest 6 MB
[hos host] vk: image blocks (render targets): 16 blocks 512 MB, 107 images 196 MB; 61 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 132 blocks 4224 MB, 2870 images 4170 MB; 356 free ranges, the largest 19 MB
[hos host] vk: render target images: 267 reused from the pool, 563 made new, 452 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 9235 MB used of 15419 MB allowed (712 MB of it free in the blocks); textures 5864 MB (budget 11000 MB), 2992 textures
[hos host] vk: budget: VRAM 8032 of 15419 MB (9235 MB by the driver, 1203 MB unaccounted): textures 5864, mirrors 858, blocks free 712, shadows 288, other buffers 156, staging 112, other images 41; RAM 2431 MB (the process's private memory 25562 MB): imports 1636, capture spares 624, captures 122, capture table 31, retired imports 16, other buffers 2, others 0
[hos host] vk: textures: decoded ASTC 3667 MB, rendered 850 MB (51 drawn in one frame, kept: 23436 KB), other 687 MB; used in the last 8 presents 2300 MB
[hos host] vk: decoded ASTC used again: 134 textures (194 MB) copied from ones the game finalized, not decoded; 134 of those retired, 185 listed; 788 MB of blocks hashed in 78 ms
[hos host] vk:   288 MB: 0x1146afa000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a4a42c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 3655 presents ago
[hos host] vk:   214 MB: 0x10a11ca600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 3655 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 5735 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113ba8d000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001eb6200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001d49a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2099 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 51 (12319 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); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 18 (3167 KB); 262x104x1 NVN 0x1: 3 (79 KB); 306x104x1 NVN 0x1: 3 (93 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 216 waited for it, 0.35 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 25.3 ms; VRAM 9.0 of 15.1 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 6 program records loaded (4.4 ms), 2 new graphics pipelines, pipelines from the driver's cache 2, from the start's cache 0, compiled 0; 8 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5286 queued, 5286 loaded (median 0.58 ms, 99th percentile 8.78 ms, worst 18.62 ms, 5436 ms and 1283.5 MB read in all); 7622 programs (1465 of them compute variants without their code, 0 graphics programs no note names), 9540 graphics pipelines (0 not in a cache), 407 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1445 pipelines made at create taken by draws; 2962 create calls with nothing kept for their stages, 0 before the index; units 8248 (5286 ready, 0 loading), 14342 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 657 known, 0 learned in this run; 407 compute pipelines made by them at a create call, 250 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 300 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 82 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.76, present 0.22, draw 5.24, descriptors 2.04, texture lookups 0.06, uploads 0.00, pipelines 0.25, programs 0.99, commands 1.58, dispatch 0.65, memory sync 0.44, queue submit 0.45, slot wait 0.22
[hos host] vk: a frame: mirrors 157 (858 MB): 4.78 MB synced in 933.3 copies, 17.59 MB written back
[hos host] vk: 16200 presents, 73.6 fps; a frame: 1961 draws (0 skipped), 111 dispatches, 144 passes, 147 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44139 pipelines (22591 ms), 0 programs (10 failed), 2992 textures (5864 MB)
[hos host] vk: host time in GPU resource waits: 0.79 ms a frame (fences 0.03, timelines 0.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 383.7 full barriers recorded, 197.5 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: 38.8; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.0 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, 13.49 ms a frame): its jobs 9.42 ms a frame (submits 6.13, presents 0.26, others 3.03), idle 4.07; the game waited for room at 1 presents, 11.77 ms each (0.02 a frame; 2.32 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 230 captures at a CPU signal; the submits' waits read in 0.045 ms a frame; readbacks: 1660 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 8.31 ms after its hand-over (26.47 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 1.93 + 0.26 (the window's copy is in the idle), after it 1.33 + 0.35; 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): 9.45 parts a frame recorded in the signal's job, 82.1% of them took nothing that came with the signal; of the others, 1.69 a frame took pages of the signal's capture into a mirror (30.1 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 41 of 230 frames, its first three in 2
[hos host] vk: frame ahead, what came with the signal: 230 signals with a capture, each of 72.4 pages in 5.5 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: 0.20+0.05, 0.06+0.02, 0.47+0.10, 0.25+0.05, 0.14+0.04, 0.15+0.03, 0.01+0.02, 0.02+0.02, 0.01+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 286 KB; 0 made on demand (0 MB kept now); c1 stages: at most 98 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 613 dirty pages from their submits' captures, 44648 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 888 dispatches, 34519 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4890 runs, 650.8 MB compared; 106 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14522 in captures, 3 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3420000 (1961276 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 3440000 (1973191 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1027 ranges, 2387 MB), 216 pages written, 216 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.014; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (116 MB), 12 spare buffers, 2352 texture pages copied (9 MB)
[hos host] vk: sparse mirrors: 71, 858 MB with memory of 1272 MB (413 MB spared); blocks given memory later 2646, given back 6365; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 334 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 53 taken from the spares, 104 made new; 86 kept as spares, 0 destroyed; 33 spares now, 528 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 597 dirty pages from their submits' captures, 44811 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 888 dispatches, 34637 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 4871 runs, 650.7 MB compared; 99 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 14618 in captures, 0 only in the collection, 37 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 105 live (1636 MB), 0 retired still imported (0 MB), 21 retired given back (468 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9134 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3460000 (1985136 pages from the captures)
[hos host] vk: slow present: 17.0 ms:
[hos host] vk: present 16249 written to <data>\jobs\jb_0a8dd1d22c9c6446\runs\forest-market-g0-02-pr\shots/forest-market-c0-pr-02-market.png (the control bridge)
[hos host] control: quit asked by a client
[hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 6 program records loaded (4.4 ms), 2 new graphics pipelines, pipelines from the driver's cache 2, from the start's cache 0, compiled 0; 8 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (close): 5286 queued, 5286 loaded (median 0.58 ms, 99th percentile 8.78 ms, worst 18.62 ms, 5436 ms and 1283.5 MB read in all); 7622 programs (1465 of them compute variants without their code, 0 graphics programs no note names), 9540 graphics pipelines (0 not in a cache), 407 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1445 pipelines made at create taken by draws; 2962 create calls with nothing kept for their stages, 0 before the index; units 8248 (5286 ready, 0 loading), 14342 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (close): 657 known, 0 learned in this run; 407 compute pipelines made by them at a create call, 250 asked that way were in no cache (their code read, as before)
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4311 pools in the table now)
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)