Beanstalk Longshot test farm
Menu

Report rp_2a5f529c8aec9bba error

#2008 perf(vk): the mesh-draw scan looks each op's kind up in a table

linux+nvidia on Hidden tester,

This report disagrees with its peers.

field-headless run_frametime_max_ms: +32.7% against peers' -3.9%
field-headless run_hitch_count: +25.0% against peers' -40.0%
Insufficient frame-time evidence for 1 required comparison(s). See rule results. a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)

Machine

Commit
9391932ee7c58ee7cb6f20a47b669226b7a9a752
Baseline
f1f2dc5bd2821cef061798ba40a043d281ac1707
App
nightly-217-14cc1aa3, attempt 1
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 5 9600X 6-Core Processor
gpu
NVIDIA GeForce RTX 5070
tags
linuxnvidianvidia-proprietarydgpu
driver
620.70.6
ram_gb
32
vram_mb
12,227
gpu_vendor
nvidia
os_version
CachyOS (kernel 7.3.5)

Builds

main (baseline)

105.6 s warm

from f1f2dc5bd282

lift
73.5 s
read
1.3 s
finish
10 s
compile
13.2 s
shaders
6.5 s

PR

26.1 s warm

Program cache: warm

Scenarios

field-headless

timeout

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

Metric (median)mainPRΔ
run_hitch_count45+25%
run_frametime_max_ms498.28661.44+32.7%
Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code——
run_hitch_count45
run_frametime_max_ms498.28661.44

Rules

ScenarioCellRuleLimitmainPRΔ %Status
field-headlesscrashFalse00—pass
field-headlessfield.fps_mean.min_delta_pct0———skippedthe metric was not measured
field-headlessscreenshot.max_diff0.05———skippedthe plan has no screenshot probe
field-headlessfield.frametime_p99_ms.max_delta_pct0———inconclusiveneed two usable starts per side (baseline: 0, PR: 0)

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-headless-baseline0-last-frame.png
field-headless-baseline0-last-frame.png
field-headless-pr1-last-frame.png
field-headless-pr1-last-frame.png

Log (PR side, end)

[hos Presentation Thread] vk: capture: a submit 0.06 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 198 pages written, 198 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (94 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 183 KB; 0 made on demand (0 MB kept now); c1 stages: at most 85 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 25 sets (ub 323, sb 157, cis 498, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 1166, 4887.4 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 128 dirty pages from their submits' captures, 61277 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): 1175 dispatches, 47714 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6508 runs, 922.0 MB compared; 197 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20291 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #165000: event 0x100d6c8030 mode 0 value 112441 (now 112422) (lr 0x806614d8)
[hos host] vk: replay reads of guest memory as submitted: 2700000 (1400644 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 2720000 (1411280 pages from the captures)
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: memory: working set 9781 MB (peak 10965), private 2412 MB, staging 32 MB in 2 arenas, 16 made so far (5 ms)
[hos host] vk: memory heaps: heap 0 (device): 139 blocks 4402 MB, 14484 allocations 4077 MB; used 4458 of 10266 MB; heap 1 (system): 11 blocks 864 MB, 39 allocations 855 MB; used 1961 of 23390 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB
[hos host] vk: image blocks (render targets): 13 blocks 416 MB, 100 images 221 MB; 32 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 39 blocks 1248 MB, 781 images 1240 MB; 290 free ranges, the largest 7 MB
[hos host] vk: render target images: 71 reused from the pool, 271 made new, 167 destroyed from it, 17 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=1), 5 missed after their image was taken by size; it holds 0 (0 MB)
[hos host] vk: render targets not reused by size: 224 with the pool empty (0 of them with targets still in the dead queue), 22 with none in it a present yet, 0 with none of a kind they can use, 5 with all smaller (the largest 12% short on average), 6 with all bigger (over 1.5 times), 14 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 167 idle
[hos host] vk: VRAM: 4458 MB used of 10266 MB allowed (324 MB of it free in the blocks); textures 2720 MB (budget 7132 MB), 892 textures
[hos host] vk: budget: VRAM 4402 of 10266 MB (4458 MB by the driver, 56 MB unaccounted): textures 2720, mirrors 804, blocks free 324, shadows 320, other buffers 140, other images 60, staging 32; RAM 1961 MB (the process's private memory 2412 MB): imports 1080, capture spares 760, captures 82, capture table 26, other buffers 13, others 0
[hos host] vk: textures: decoded ASTC 1372 MB, rendered 854 MB (104 drawn in one frame, kept: 48870 KB), other 295 MB; used in the last 8 presents 2198 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 3 listed; 294 MB of blocks hashed in 14 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 5628 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10002ac7800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5585 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 171 dirty pages from their submits' captures, 62377 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): 1195 dispatches, 48639 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6535 runs, 922.1 MB compared; 187 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20932 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vk: presents after the CPU's signal (600): 55 waited for it, 0.17 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 15.4 ms; VRAM 4.4 of 10.0 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), 650 new graphics pipelines, pipelines from the driver's cache 225, from the start's cache 0, compiled 529; 133504 draws and dispatches left out, 458 waits (1613.1 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; 7015 create calls with nothing kept for their stages, 0 before the index; units 7015 (0 ready, 0 loading), 12472 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: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.25, present 0.12, draw 2.29, descriptors 0.74, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.36, commands 1.00, dispatch 0.62, memory sync 0.16, queue submit 0.11, slot wait 0.02
[hos host] vk: a frame: mirrors 64 (804 MB): 4.52 MB synced in 900.3 copies, 17.08 MB written back
[hos host] vk: 12000 presents, 110.5 fps; a frame: 644 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 892 textures (2720 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.4 full barriers recorded, 205.4 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 129.0, an op 454.3, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 3.5 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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: the render thread (600 presents, 9.05 ms a frame): its jobs 4.58 ms a frame (submits 3.65, presents 0.12, others 0.81), idle 4.47; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 2.61 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); 109 captures at a CPU signal; the submits' waits read in 0.018 ms a frame; readbacks: 2934 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 4.16 ms after its hand-over (6.45 at most)
[hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 2.76 + 0.42 (the window's copy is in the idle), after it 0.57 + 0.31; 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): 5.00 parts a frame recorded in the signal's job, 86.4% of them took nothing that came with the signal; of the others, 0.68 a frame took pages of the signal's capture into a mirror (12.8 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 59 of 109 frames, its first three in 59
[hos host] vk: frame ahead, what came with the signal: 109 signals with a capture, each of 20.5 pages in 3.0 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.02+0.07, 0.49+0.12, 0.01+0.04, 0.02+0.04, 0.03+0.04, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vi: real-time step on: ratio 0.555, game's frame rate 60
[hos BaseProcExecutor2] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 36 made): 28191655 lookups, 232771 missed (0.83 %)
[hos Presentation Thread] vi: 12031 frames presented (110.5 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 553, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 2740000 (1421969 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.06 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 199 pages written, 199 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (80 MB), 8 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 997 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 4300 kept their virtual core (nothing there to wait for), 2868 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1166, 4887.4 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 393 dirty pages from their submits' captures, 61049 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): 1173 dispatches, 47745 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6416 runs, 905.1 MB compared; 191 pages read into the shadows; 320 MB of shadows (170 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20371 in captures, 0 only in the collection, 53 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2760000 (1432630 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #115000: event 0x100d6c8018 mode 0 value 115000 (lr 0x80660c94)
[hos BaseProcExecutor4] vcores: 187115 takes, 27119 waits (mean 51 us, longest 5.6 ms, 0 over HOS_VCORE_LOG_MS), 11147 kicks, 11050 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[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: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 146 dirty pages from their submits' captures, 62316 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): 1194 dispatches, 48658 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6539 runs, 922.1 MB compared; 188 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20741 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos host] vk: a frame: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.28, present 0.11, draw 2.36, descriptors 0.78, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.37, commands 1.03, dispatch 0.63, memory sync 0.16, queue submit 0.10, slot wait 0.02
[hos host] vk: a frame: mirrors 64 (804 MB): 4.53 MB synced in 901.4 copies, 17.08 MB written back
[hos host] vk: 12120 presents, 110.0 fps; a frame: 643 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 893 textures (2725 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.4 full barriers recorded, 205.4 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 129.1, an op 454.3, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 4.9 ms a frame (the longest submission 4.2 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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: replay reads of guest memory as submitted: 2780000 (1443359 pages from the captures)
[hos host] vk: program picks: 2427303 kept (778591 by the last picks' textures, a uniform buffer bound since), 1179 new, 1771517 with other textures (of 4200000)
[hos Presentation Thread] vk: capture: a submit 0.06 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 199 pages written, 199 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (74 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #170000: event 0x100d6c8030 mode 0 value 116241 (now 116222) (lr 0x806614d8)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 140 dirty pages from their submits' captures, 62435 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): 1193 dispatches, 48687 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6519 runs, 921.1 MB compared; 202 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20794 in captures, 0 only in the collection, 53 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2800000 (1454063 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1555294 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 993 of 3000 waited for their write-back, 0.00 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker5] vk: invalidates since the last readbacks line: 4072 kept their virtual core (nothing there to wait for), 2840 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: 2820000 (1464847 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: the recording streams: 48 of 1 MB, the most one held 183 KB; 0 made on demand (0 MB kept now); c1 stages: at most 85 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 25 sets (ub 323, sb 157, cis 498, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1166, 4887.4 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 242 dirty pages from their submits' captures, 61369 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): 1176 dispatches, 47798 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6429 runs, 906.1 MB compared; 193 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 197 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20448 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 199 pages written, 199 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (76 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a frame: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.25, present 0.10, draw 2.38, descriptors 0.78, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.38, commands 1.03, dispatch 0.62, memory sync 0.16, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 64 (804 MB): 4.53 MB synced in 901.4 copies, 17.08 MB written back
[hos host] vk: 12240 presents, 111.4 fps; a frame: 644 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 893 textures (2725 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.1 full barriers recorded, 205.3 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 128.9, an op 454.2, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 3.5 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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: replay reads of guest memory as submitted: 2840000 (1475471 pages from the captures)
[hos ModuleSystemWorker2] nvn: 950000 recordings made, 44130 live copies (12.0 MB), 322 texture copies; 2 command buffers' segments (4.1 MB)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 256 dirty pages from their submits' captures, 62287 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): 1195 dispatches, 48659 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6533 runs, 922.1 MB compared; 197 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20824 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 1 textures retired (892 left, 2720 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 2860000 (1486129 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[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: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 212 dirty pages from their submits' captures, 62365 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): 1194 dispatches, 48677 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6522 runs, 922.1 MB compared; 188 pages read into the shadows; 320 MB of shadows (170 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20819 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos host] vk: replay reads of guest memory as submitted: 2880000 (1496727 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 201 pages written, 201 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (74 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 17 sync waits (3 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #120000: event 0x100d6c8024 mode 0 value 120000 (lr 0x80665068)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #175000: event 0x100d6c8030 mode 0 value 120041 (now 120022) (lr 0x806614d8)
[hos host] vk: a frame: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.25, present 0.10, draw 2.32, descriptors 0.75, texture lookups 0.07, uploads 0.00, pipelines 0.08, programs 0.36, commands 1.01, dispatch 0.62, memory sync 0.16, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 64 (804 MB): 4.53 MB synced in 901.2 copies, 17.08 MB written back
[hos host] vk: 12360 presents, 111.1 fps; a frame: 644 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 893 textures (2725 MB)
[hos host] vk: host time in GPU resource waits: 0.03 ms a frame (fences 0.01, timelines 0.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.1 full barriers recorded, 205.3 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 129.0, an op 454.2, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 4.0 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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 ModuleSystemWorker4] vk: readbacks of GPU results: 996 of 3000 waited for their write-back, 0.00 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: 4575 kept their virtual core (nothing there to wait for), 3105 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: 2900000 (1507310 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 224 dirty pages from their submits' captures, 62379 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): 1193 dispatches, 48678 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6513 runs, 921.1 MB compared; 183 pages read into the shadows; 320 MB of shadows (170 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20914 in captures, 0 only in the collection, 53 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: DrawMeshTasksIndirect: 260000 so far (x1 0x117df8b070 x2 0 x3 0x117df8b040 x4 0x44b040)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: queues ordered by their events: 66000 submissions stopped at a wait, 65998 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 176414, not met 0; captures at a CPU event's wait 4615, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 2920000 (1517929 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: 2542394 kept (815520 by the last picks' textures, a uniform buffer bound since), 1179 new, 1856426 with other textures (of 4400000)
[hos host] vk: render targets drawn over from another start, let go: 143 so far (446 MB), 131 of them (404 MB) between the passes
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1166, 4887.4 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 280 dirty pages from their submits' captures, 61133 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): 1175 dispatches, 47791 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6429 runs, 906.1 MB compared; 181 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20415 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos Presentation Thread] vk: capture: a submit 0.06 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 199 pages written, 199 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (80 MB), 9 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1626186 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 2940000 (1528588 pages from the captures)
[hos host] vk: a frame: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.26, present 0.10, draw 2.32, descriptors 0.75, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.37, commands 1.01, dispatch 0.62, memory sync 0.16, queue submit 0.10, slot wait 0.02
[hos host] vk: a frame: mirrors 64 (804 MB): 4.53 MB synced in 902.0 copies, 17.08 MB written back
[hos host] vk: 12480 presents, 111.0 fps; a frame: 644 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 894 textures (2730 MB)
[hos host] vk: host time in GPU resource waits: 0.02 ms a frame (fences 0.01, timelines 0.01, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.2 full barriers recorded, 205.3 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 129.0, an op 454.3, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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: the recording streams: 48 of 1 MB, the most one held 183 KB; 0 made on demand (0 MB kept now); c1 stages: at most 85 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 25 sets (ub 323, sb 157, cis 498, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 89 dirty pages from their submits' captures, 62638 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): 1195 dispatches, 48681 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6534 runs, 922.1 MB compared; 188 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20854 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2960000 (1539434 pages from the captures)
[hos host] vk: 1 textures retired (893 left, 2725 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos sead::MainThread] nvn: EventSignal (CPU) #25000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: 1 textures retired (892 left, 2720 MB): budget 0, drawn over 1, dead targets 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 Presentation Thread] vk: capture: a submit 0.07 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 202 pages written, 202 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (76 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1006 of 3000 waited for their write-back, 0.00 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: 4471 kept their virtual core (nothing there to wait for), 2953 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 211 dirty pages from their submits' captures, 62451 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): 1195 dispatches, 48713 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6526 runs, 922.1 MB compared; 201 pages read into the shadows; 320 MB of shadows (170 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20722 in captures, 1 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos host] vk: replay reads of guest memory as submitted: 2980000 (1550075 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #180000: event 0x100d6c8030 mode 0 value 123841 (now 123822) (lr 0x806614d8)
[hos host] vk: 1 textures retired (892 left, 2720 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 3000000 (1560773 pages from the captures)
[hos Presentation Thread] vi: 12585 frames presented (110.7 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 553, 15.5-17.8 1, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: present 12582 written to /<user>/<user>/Beanstalk/jobs/jb_c0a73b60121b6feb/runs/field-headless-g0-01-pr/shots/field-headless-pr-01-last-frame.png (the control bridge)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 273 dirty pages from their submits' captures, 62248 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): 1195 dispatches, 48642 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6528 runs, 922.1 MB compared; 186 pages read into the shadows; 320 MB of shadows (170 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20864 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: memory: working set 9941 MB (peak 10965), private 2413 MB, staging 32 MB in 2 arenas, 16 made so far (5 ms)
[hos host] vk: memory heaps: heap 0 (device): 139 blocks 4402 MB, 14486 allocations 4086 MB; used 4458 of 10266 MB; heap 1 (system): 13 blocks 944 MB, 39 allocations 850 MB; used 2041 of 23390 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): 13 blocks 416 MB, 101 images 226 MB; 32 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 39 blocks 1248 MB, 781 images 1240 MB; 290 free ranges, the largest 7 MB
[hos host] vk: render target images: 71 reused from the pool, 275 made new, 170 destroyed from it, 18 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=1), 5 missed after their image was taken by size; it holds 0 (0 MB)
[hos host] vk: render targets not reused by size: 228 with the pool empty (0 of them with targets still in the dead queue), 22 with none in it a present yet, 0 with none of a kind they can use, 5 with all smaller (the largest 12% short on average), 6 with all bigger (over 1.5 times), 14 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 170 idle
[hos host] vk: VRAM: 4458 MB used of 10266 MB allowed (315 MB of it free in the blocks); textures 2725 MB (budget 7132 MB), 893 textures
[hos host] vk: budget: VRAM 4402 of 10266 MB (4458 MB by the driver, 56 MB unaccounted): textures 2725, mirrors 804, shadows 320, blocks free 315, other buffers 140, other images 63, staging 32; RAM 1956 MB (the process's private memory 2413 MB): imports 1080, capture spares 754, captures 88, capture table 26, other buffers 8, others 0
[hos host] vk: textures: decoded ASTC 1372 MB, rendered 859 MB (104 drawn in one frame, kept: 48870 KB), other 295 MB; used in the last 8 presents 2203 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 3 listed; 294 MB of blocks hashed in 14 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 6228 presents ago
[hos host] vk:   54 MB: 0x10002ac7800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 6185 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB);
[hos host] vk: malloc: 2562 MB in arenas (2176 MB in use, 386 MB free, 0 MB of it at the tops), 16 MB mapped
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos Presentation Thread] vk: presents after the CPU's signal (600): 46 waited for it, 0.19 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: malloc_trim: 386 MB free in the arenas now, the process's private memory 2413 -> 2385 MB (6 ms)
[hos host] vk: status: 600 frames, the slowest 15.4 ms; VRAM 4.4 of 10.0 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), 650 new graphics pipelines, pipelines from the driver's cache 225, from the start's cache 0, compiled 529; 133504 draws and dispatches left out, 458 waits (1613.1 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; 7015 create calls with nothing kept for their stages, 0 before the index; units 7015 (0 ready, 0 loading), 12472 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: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.26, present 0.19, draw 2.38, descriptors 0.78, texture lookups 0.07, uploads 0.00, pipelines 0.08, programs 0.37, commands 1.03, dispatch 0.62, memory sync 0.16, queue submit 0.12, slot wait 0.02
[hos host] vk: a frame: mirrors 64 (804 MB): 4.53 MB synced in 901.0 copies, 17.08 MB written back
[hos host] vk: 12600 presents, 109.4 fps; a frame: 643 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 893 textures (2725 MB)
[hos host] vk: host time in GPU resource waits: 0.05 ms a frame (fences 0.01, timelines 0.04, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.1 full barriers recorded, 205.4 left out (nothing recorded since the one before), 18.2 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: 39.5; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 129.1, an op 454.3, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 3.7 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.1 MB), ASTC or BC 0.0 (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: the render thread (600 presents, 9.04 ms a frame): its jobs 4.60 ms a frame (submits 3.72, presents 0.13, others 0.75), idle 4.44; the game waited for room at 1 presents, 2.14 ms each (0.00 a frame; 2.91 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); 99 captures at a CPU signal; the submits' waits read in 0.018 ms a frame; readbacks: 2936 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 4.18 ms after its hand-over (11.78 at most)
[hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 2.74 + 0.42 (the window's copy is in the idle), after it 0.58 + 0.32; 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): 5.00 parts a frame recorded in the signal's job, 87.7% of them took nothing that came with the signal; of the others, 0.62 a frame took pages of the signal's capture into a mirror (13.7 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 60 of 99 frames, its first three in 60
[hos host] vk: frame ahead, what came with the signal: 99 signals with a capture, each of 21.9 pages in 2.9 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: 0.02+0.07, 0.50+0.13, 0.01+0.04, 0.02+0.04, 0.03+0.04, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #125000: event 0x100d6c802c mode 0 value 124999 (lr 0x80667688)
[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: 3020000 (1571451 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.07 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 201 pages written, 201 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 132 dirty pages from their submits' captures, 62390 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): 1195 dispatches, 48661 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6545 runs, 922.1 MB compared; 177 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20815 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos ModuleSystemWorker1] nvn: 1000000 recordings made, 44034 live copies (12.1 MB), 322 texture copies; 5 command buffers' segments (4.2 MB)
[hos ModuleSystemWorker1] vcores: 184498 takes, 27181 waits (mean 55 us, longest 7.6 ms, 0 over HOS_VCORE_LOG_MS), 11237 kicks, 11100 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 3040000 (1582148 pages from the captures)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1009 of 3000 waited for their write-back, 0.00 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: 4326 kept their virtual core (nothing there to wait for), 3098 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1166, 4887.4 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 118 dirty pages from their submits' captures, 61661 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): 1183 dispatches, 48012 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6415 runs, 905.1 MB compared; 158 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20627 in captures, 0 only in the collection, 53 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: program picks: 2657341 kept (852373 by the last picks' textures, a uniform buffer bound since), 1179 new, 1941479 with other textures (of 4600000)
[hos host] vk: replay reads of guest memory as submitted: 3060000 (1592799 pages from the captures)
[hos host] vk: 1 textures retired (892 left, 2720 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a frame: 49 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 2429 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.19, present 0.10, draw 2.26, descriptors 0.73, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.36, commands 0.98, dispatch 0.62, memory sync 0.16, queue submit 0.11, slot wait 0.01
[hos host] vk: a frame: mirrors 64 (804 MB): 4.52 MB synced in 900.9 copies, 17.08 MB written back
[hos host] vk: 12720 presents, 112.1 fps; a frame: 644 draws (0 skipped), 95 dispatches, 120 passes, 138 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 803 pipelines (103112 ms), 562 programs (0 failed), 892 textures (2720 MB)
[hos host] vk: host time in GPU resource waits: 0.01 ms a frame (fences 0.01, timelines 0.00, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 329.0 full barriers recorded, 205.3 left out (nothing recorded since the one before), 18.2 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: 39.4; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 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, 41.0 from 25.0 batches at the game's barriers (41.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 128.9, an op 454.2, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 5: 22.0; 48: 7.0;
[hos host] vk: GPU time 5.0 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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 sead::MainThread] vk: capture: a submit 0.06 ms (lock 0.00, scan 0.02 over 1332 ranges, 1840 MB), 199 pages written, 199 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (82 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: readback pages refreshed from guest memory: 1697339 pages so far (0 held: may be written ahead in their submission)
[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: reaper: 5 images (25 MB) destroyed in 10 s, 0 of them where they were handed over (its cap or VRAM pressure); the queue at most 1 (5 MB)
[hos host] vk: replay reads of guest memory as submitted: 3080000 (1603478 pages from the captures)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 183 KB; 0 made on demand (0 MB kept now); c1 stages: at most 85 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 25 sets (ub 323, sb 157, cis 498, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 50, 804 MB with memory of 1032 MB (227 MB spared); blocks given memory later 65, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 80 binds (6.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 8 taken from the spares, 56 made new; 14 kept as spares, 0 destroyed; 6 spares now, 272 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 342 dirty pages from their submits' captures, 61826 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): 1184 dispatches, 48365 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6527 runs, 922.1 MB compared; 197 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20729 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 54 live (1080 MB), 0 retired still imported (0 MB), 11 retired given back (320 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #185000: event 0x100d6c8030 mode 0 value 127641 (now 127622) (lr 0x806614d8)
[hos host] vk: replay reads of guest memory as submitted: 3100000 (1614280 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.02
[hos host] vk: write-backs left out (600 submits): 1188, 4979.6 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 105 dirty pages from their submits' captures, 62582 from earlier ones', 71 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): 1194 dispatches, 48690 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6534 runs, 921.1 MB compared; 194 pages read into the shadows; 320 MB of shadows (171 MB of pages known, in 198 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 20773 in captures, 0 only in the collection, 53 only by the replay itself
[hos host] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 71;