Beanstalk Longshot test farm
Menu

Report rp_8fe1f5398fa836a9 fail

#1993 WIP: perf(vk): report words looked up through a hash index and merged in place

linux+amd+radv on manasuazo/agent-03253d,

This report disagrees with its peers.

kokiri-forest run_hitch_count: +74.1% against peers' +10.0%

Machine

Commit
ecd1b8a4992f8d2380327c79576f1682acbc3c2d
Baseline
f1f2dc5bd2821cef061798ba40a043d281ac1707
App
nightly-221-a9505cc3, attempt 2
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 5 5500F 6-Core Processor
gpu
AMD Radeon RX 580 Series (RADV POLARIS10)
tags
linuxamdradvdgpu
driver
26.2.7
ram_gb
32
vram_mb
8,192
gpu_vendor
amd
os_version
<host> (kernel 7.3.4)

Builds

main (baseline)

0 s warm

from f1f2dc5bd282

a base kept from before

PR

42.5 s warm

Program cache: warm

Scenarios

kokiri-forest

ok
Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count42.574+74.1%
forest.hitch_count22.553+135.6%
log_forbidden_hits00±0%
forest.stutter_count39.566+67.1%
log_expected_missing00±0%
run_frametime_max_ms549.28555.06+1.1%
forest.frametime_max_ms58.3458.56+0.4%
forest.frametime_p50_ms21.3922.15+3.5%
forest.frametime_p99_ms32.8640.18+22.3%
forest.frametime_1pct_low_ms38.6244.82+16.1%
screenshot_diff—0.54—

Pictures against main: forest-start diff 0.8442 (main against itself 0.0596), forest-end diff 0.486 (main against itself 0.0924)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0000
run_hitch_count172212668
forest.hitch_count0010645
log_forbidden_hits0000
forest.stutter_count0013279
log_expected_missing0000
run_frametime_max_ms524.26574.1536.03574.3
forest.frametime_max_ms38.3538.7778.3578.32
forest.frametime_p50_ms21.422.2322.0621.38
forest.frametime_p99_ms23.42555.3642.33
forest.frametime_1pct_low_ms24.0326.2963.3553.2
screenshot_diff—0.230.84—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
kokiri-forestcrashFalse00—pass
kokiri-forestscreenshot.max_diff00.090.84—fail
kokiri-forestforest.frametime_p99_ms.max_delta_pct532.8640.18+22.3%fail
kokiri-forestlog_forbidden_hits.max000—pass

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 .

kokiri-forest-forest-start-main-failed.png
kokiri-forest-forest-start-main-failed.png
kokiri-forest-forest-start-pr-failed.png
kokiri-forest-forest-start-pr-failed.png
kokiri-forest-forest-end-main-failed.png
kokiri-forest-forest-end-main-failed.png

Log (PR side, end)

[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: 32 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.92, present 0.20, draw 5.67, descriptors 1.36, texture lookups 0.11, uploads 0.00, pipelines 0.12, programs 0.56, commands 3.39, dispatch 0.78, memory sync 0.26, queue submit 1.54, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.69 MB synced in 917.8 copies, 16.60 MB written back
[hos host] vk: 12000 presents, 42.7 fps; a frame: 702 draws (0 skipped), 104 dispatches, 147 passes, 151 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1188 textures (3539 MB)
[hos host] vk: host time in GPU resource waits: 12.33 ms a frame (fences 0.03, timelines 12.30, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 502.3 full barriers recorded, 286.5 left out (nothing recorded since the one before), 18.1 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: 51.7; 0x12: 69.5; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 16.1 ms a frame (the longest submission 6.5 ms); 0.2 textures made a frame: colour targets 0.1 (0.2 MB), depth 0.1 (0.5 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, 22.99 ms a frame): its jobs 8.84 ms a frame (submits 1.10, presents 0.20, others 7.53), idle 14.16; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.02 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); 600 captures at a CPU signal; the submits' waits read in 0.022 ms a frame; readbacks: 3000 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 7.73 ms after its hand-over (55.48 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 1.36 + 2.59 (the window's copy is in the idle), after it 0.79 + 2.44; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.19 ms of GPU time), after its last that reads it 1.00 (0.19 ms)
[hos host] vk: frame ahead (600 presents): 5.99 parts a frame recorded in the signal's job, 65.9% of them took nothing that came with the signal; of the others, 2.04 a frame took pages of the signal's capture into a mirror (76.9 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 0 of 600 frames, its first three in 0
[hos host] vk: frame ahead, what came with the signal: 600 signals with a capture, each of 107.0 pages in 9.0 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: 0.14+0.27, 0.13+1.81, 0.13+0.09, 0.35+0.08, 0.03+0.11, 0.02+0.08, 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: 4 textures retired (1184 left, 3503 MB): budget 0, drawn over 4, dead targets 0
[hos Presentation Thread] vi: real-time step on: ratio 1.368, game's frame rate 44
[hos host] vk: replay reads of guest memory as submitted: 5320000 (2660573 pages from the captures)
[hos host] vk: late pages' fix (600 recordings with one): of 600 captures with late pages 600 fixed (65.5 pages, 66.5 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; 599 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 582 blocks (37248 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 159, of an earlier recording 440, not recorded yet 0, of this part 0; pages fixed from stamps 38122, from snapshots 1194; the shadows: 288997 pages synced from captures, 288397 made known by it, 600 left unknown because the replay or the collection wrote them since
[hos host] vk: 4 textures retired (1180 left, 3466 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: reaper: 105 images (409 MB) destroyed in 10 s, 0 of them where they were handed over (its cap or VRAM pressure); the queue at most 10 (54 MB)
[hos host] vk: 7 textures retired (1173 left, 3402 MB): budget 0, drawn over 7, dead targets 0
[hos host] vk: 2 textures retired (1171 left, 3384 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3672 dirty pages from their submits' captures, 51903 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): 1073 dispatches, 42419 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5879 runs, 763.1 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22150 in captures, 0 only in the collection, 45 only by the replay itself
[hos host] vk:   read live, by pool:
[hos BaseProcExecutor2] vcores: 75149 takes, 9612 waits (mean 57 us, longest 2.1 ms, 0 over HOS_VCORE_LOG_MS), 3971 kicks, 4309 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 5340000 (2670587 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #260000: event 0x100d6c8048 mode 0 value 193601 (now 193582) (lr 0x806661f8)
[hos host] vk: 11 textures retired (1171 left, 3384 MB): budget 0, drawn over 0, dead targets 11
[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: 1 textures retired (1170 left, 3374 MB): budget 0, drawn over 1, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 185 pages written, 185 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (108 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 5360000 (2680880 pages from the captures)
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1034, 4334.1 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): 3518 dirty pages from their submits' captures, 52764 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): 1075 dispatches, 43003 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5901 runs, 763.2 MB compared; 93 pages read into the shadows; 256 MB of shadows (121 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22623 in captures, 0 only in the collection, 45 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.03
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1023 of 3000 waited for their write-back, 0.78 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: 3790 kept their virtual core (nothing there to wait for), 2866 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos ModuleSystemWorker1] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 35 made): 11280391 lookups, 93636 missed (0.83 %)
[hos host] vk: a frame: 31 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.70, present 0.20, draw 3.86, descriptors 1.38, texture lookups 0.10, uploads 0.00, pipelines 0.12, programs 0.57, commands 1.55, dispatch 0.77, memory sync 0.25, queue submit 1.54, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.70 MB synced in 917.5 copies, 16.59 MB written back
[hos host] vk: 12120 presents, 44.0 fps; a frame: 698 draws (0 skipped), 103 dispatches, 147 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1172 textures (3393 MB)
[hos host] vk: host time in GPU resource waits: 11.79 ms a frame (fences 0.03, timelines 11.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 500.8 full barriers recorded, 285.9 left out (nothing recorded since the one before), 17.7 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: 51.4; 0x12: 69.1; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.7 ms a frame (the longest submission 5.8 ms); 0.2 textures made a frame: colour targets 0.1 (0.2 MB), depth 0.1 (0.2 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: 5380000 (2690838 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #195000: event 0x100d6c8028 mode 0 value 194999 (lr 0x80667410)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 179 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 101 sets (ub 1283, sb 789, cis 4434, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3521 dirty pages from their submits' captures, 51666 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): 1065 dispatches, 42105 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5975 runs, 779.0 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22130 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: GPU waits in 5 s: 221 sync waits (1353 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: readback pages refreshed from guest memory: 3105222 pages so far (0 held: may be written ahead in their submission)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 184 pages written, 184 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; 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 (116 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 4533518 kept (1765853 by the last picks' textures, a uniform buffer bound since), 31523 new, 3234958 with other textures (of 7800000)
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 440000 so far (x1 0x117db40020 x2 0 x3 0x117db40000 x4 0x44b040)
[hos host] vk: replay reads of guest memory as submitted: 5400000 (2700790 pages from the captures)
[hos Presentation Thread] vi: 12174 frames presented (44.6 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 116, 22-30 101, 30-40 3, over 40 3
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3547 dirty pages from their submits' captures, 51695 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): 1067 dispatches, 42109 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5876 runs, 763.6 MB compared; 93 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22079 in captures, 0 only in the collection, 47 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos host] vk: 1 textures retired (1171 left, 3384 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos host] vk: replay reads of guest memory as submitted: 5420000 (2710742 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: write-backs left out (600 submits): 1012, 4241.9 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): 3519 dirty pages from their submits' captures, 51610 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): 1063 dispatches, 42085 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5879 runs, 763.1 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22102 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 1367 so far (2032 MB), 1225 of them (1822 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 5440000 (2720706 pages from the captures)
[hos host] vk: a frame: 31 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.06, present 0.18, draw 3.74, descriptors 1.31, texture lookups 0.08, uploads 0.00, pipelines 0.12, programs 0.54, commands 1.54, dispatch 0.77, memory sync 0.25, queue submit 1.47, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.69 MB synced in 915.6 copies, 16.59 MB written back
[hos host] vk: 12240 presents, 45.8 fps; a frame: 700 draws (0 skipped), 103 dispatches, 148 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1171 textures (3384 MB)
[hos host] vk: host time in GPU resource waits: 10.91 ms a frame (fences 0.03, timelines 10.88, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 500.8 full barriers recorded, 285.7 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: 50.7; 0x12: 69.5; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.4 ms a frame (the longest submission 5.8 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 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 182 pages written, 182 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; 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 (116 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: 1 textures retired (1170 left, 3374 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferWaitEvent #265000: event 0x100d6c8048 mode 0 value 197401 (now 197382) (lr 0x806661f8)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1029 of 3000 waited for their write-back, 0.83 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: 3960 kept their virtual core (nothing there to wait for), 2952 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos ModuleSystemWorker1] vcores: 76633 takes, 9925 waits (mean 63 us, longest 2.4 ms, 0 over HOS_VCORE_LOG_MS), 4145 kicks, 4474 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3564 dirty pages from their submits' captures, 51733 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): 1064 dispatches, 42196 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5880 runs, 763.0 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22199 in captures, 0 only in the collection, 45 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos host] vk: replay reads of guest memory as submitted: 5460000 (2730643 pages from the captures)
[hos host] vk: queues ordered by their events: 90000 submissions stopped at a wait, 89938 went on once it was reached, 60 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 5 (stopped 50.06 ms at most); waits met 265992, not met 0; captures at a CPU event's wait 11777, 0 of them at a wait met on arrival
[hos host] vk: 1 textures retired (1170 left, 3374 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos ModuleSystemWorker4] nvn: 1450000 recordings made, 43923 live copies (12.2 MB), 398 texture copies; 5 command buffers' segments (4.2 MB)
[hos host] vk: replay reads of guest memory as submitted: 5480000 (2740638 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3526 dirty pages from their submits' captures, 51609 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): 1064 dispatches, 42140 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5878 runs, 763.0 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22110 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: texture slots registered again at another size: 1000000 (of 1253025 registrations; slot 14354 1280x720 -> 640x360)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 184 pages written, 184 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (114 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 5500000 (2750771 pages from the captures)
[hos host] vk: a frame: 31 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.31, present 0.18, draw 3.70, descriptors 1.31, texture lookups 0.09, uploads 0.00, pipelines 0.12, programs 0.54, commands 1.51, dispatch 0.76, memory sync 0.25, queue submit 1.48, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.69 MB synced in 917.4 copies, 16.59 MB written back
[hos host] vk: 12360 presents, 44.5 fps; a frame: 701 draws (0 skipped), 103 dispatches, 147 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1170 textures (3374 MB)
[hos host] vk: host time in GPU resource waits: 11.47 ms a frame (fences 0.03, timelines 11.43, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 500.8 full barriers recorded, 285.7 left out (nothing recorded since the one before), 17.8 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: 51.2; 0x12: 69.1; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.6 ms a frame (the longest submission 6.1 ms); 0.1 textures made a frame: colour targets 0.1 (0.1 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: 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 179 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 101 sets (ub 1283, sb 789, cis 4434, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3686 dirty pages from their submits' captures, 52429 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): 1080 dispatches, 42644 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5892 runs, 763.2 MB compared; 93 pages read into the shadows; 256 MB of shadows (121 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22606 in captures, 0 only in the collection, 45 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 225 sync waits (1284 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: readback pages refreshed from guest memory: 3175917 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #200000: event 0x100d6c8034 mode 0 value 199999 (lr 0x806616b0)
[hos host] vk: replay reads of guest memory as submitted: 5520000 (2760888 pages from the captures)
[hos Presentation Thread] vi: 12399 frames presented (44.9 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 115, 22-30 105, 30-40 3, over 40 2
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos sead::MainThread] vk: readbacks of GPU results: 1029 of 3000 waited for their write-back, 0.79 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: 3871 kept their virtual core (nothing there to wait for), 3041 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1034, 4334.1 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): 3506 dirty pages from their submits' captures, 52260 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): 1069 dispatches, 42734 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5989 runs, 779.2 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22113 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 184 pages written, 184 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; 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 (116 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 4650403 kept (1811619 by the last picks' textures, a uniform buffer bound since), 31789 new, 3317807 with other textures (of 8000000)
[hos host] vk: replay reads of guest memory as submitted: 5540000 (2770915 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #270000: event 0x100d6c8048 mode 0 value 201201 (now 201182) (lr 0x806661f8)
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3525 dirty pages from their submits' captures, 51690 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): 1066 dispatches, 42147 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5886 runs, 763.1 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22147 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos host] vk: replay reads of guest memory as submitted: 5560000 (2780854 pages from the captures)
[hos host] vk: a frame: 31 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.56, present 0.18, draw 3.70, descriptors 1.29, texture lookups 0.08, uploads 0.00, pipelines 0.12, programs 0.54, commands 1.52, dispatch 0.77, memory sync 0.25, queue submit 1.56, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.69 MB synced in 916.5 copies, 16.59 MB written back
[hos host] vk: 12480 presents, 43.9 fps; a frame: 700 draws (0 skipped), 103 dispatches, 148 passes, 151 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1170 textures (3374 MB)
[hos host] vk: host time in GPU resource waits: 11.83 ms a frame (fences 0.03, timelines 11.80, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 501.2 full barriers recorded, 286.3 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: 51.4; 0x12: 69.5; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.6 ms a frame (the longest submission 5.9 ms); 0.1 textures made a frame: colour targets 0.1 (0.1 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 BaseProcExecutor1] vcores: 77237 takes, 10008 waits (mean 61 us, longest 3.1 ms, 0 over HOS_VCORE_LOG_MS), 4085 kicks, 4482 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos sead::MainThread] nvn: EventSignal (CPU) #25000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 184 pages written, 184 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; 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 (128 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 5580000 (2790866 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3540 dirty pages from their submits' captures, 51756 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): 1064 dispatches, 42171 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5867 runs, 763.5 MB compared; 93 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22161 in captures, 0 only in the collection, 47 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: 5600000 (2800812 pages from the captures)
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3527 dirty pages from their submits' captures, 51609 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): 1064 dispatches, 42127 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5884 runs, 763.1 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22093 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1029 of 3000 waited for their write-back, 0.88 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: 3975 kept their virtual core (nothing there to wait for), 2937 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos ModuleSystemWorker3] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 35 made): 11521935 lookups, 93363 missed (0.81 %)
[hos host] vk: replay reads of guest memory as submitted: 5620000 (2810810 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 182 pages written, 182 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (114 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 179 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 101 sets (ub 1283, sb 789, cis 4434, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3530 dirty pages from their submits' captures, 51683 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): 1064 dispatches, 42156 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5876 runs, 763.0 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22119 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] nvn: GPU waits in 5 s: 222 sync waits (1260 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: memory: working set 6137 MB (peak 6399), private 980 MB, staging 32 MB in 2 arenas, 20 made so far (22 ms)
[hos host] vk: memory heaps: heap 0 (device): 105 blocks 4875 MB, 14552 allocations 4647 MB; used 4908 of 7322 MB; heap 1 (system): 16 blocks 824 MB, 39 allocations 782 MB; used 1938 of 15816 MB; heap 2 (device): 57 blocks 141 MB, 149 allocations 125 MB; used 257 of 256 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 3 free ranges, the largest 0 MB
[hos host] vk: image blocks (render targets): 17 blocks 272 MB, 102 images 194 MB; 76 free ranges, the largest 15 MB
[hos host] vk: image blocks (textures, compacted): 38 blocks 1216 MB, 1060 images 1099 MB; 545 free ranges, the largest 16 MB
[hos host] vk: render target images: 311 reused from the pool, 1663 made new, 1558 destroyed from it, 48 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=1), 4 missed after their image was taken by size; it holds 0 (0 MB)
[hos host] vk: render targets not reused by size: 1315 with the pool empty (0 of them with targets still in the dead queue), 86 with none in it a present yet, 0 with none of a kind they can use, 112 with all smaller (the largest 54% short on average), 146 with all bigger (over 1.5 times), 4 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 1558 idle
[hos host] vk: VRAM: 5166 MB used of 7578 MB allowed (243 MB of it free in the blocks); textures 3393 MB (budget 4629 MB), 1172 textures
[hos host] vk: budget: VRAM 5016 of 7578 MB (5166 MB by the driver, 149 MB unaccounted): textures 3393, mirrors 798, shadows 256, blocks free 243, other buffers 213, other images 79, staging 32; RAM 1872 MB (the process's private memory 980 MB): imports 1064, capture spares 650, captures 114, capture table 26, other buffers 18, others 0
[hos host] vk: textures: decoded ASTC 1012 MB, rendered 678 MB (79 drawn in one frame, kept: 41981 KB), other 275 MB; used in the last 8 presents 1663 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 0 listed; 345 MB of blocks hashed in 31 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: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   47 MB: 0x10c2c99000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 3 presents ago
[hos host] vk:   47 MB: 0x10afd32400 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago
[hos host] vk:   47 MB: 0x10bba9a200 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 31 (12653 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 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); 262x104x1 NVN 0x1: 3 (79 KB); 306x104x1 NVN 0x1: 3 (93 KB); 592x49x1 NVN 0x25: 3 (339 KB); 640x360x1 NVN 0x29: 2 (3600 KB); 656x113x1 NVN 0x1: 3 (217 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos host] vk: malloc: 1147 MB in arenas (870 MB in use, 276 MB free, 7 MB of it at the tops), 18 MB mapped
[hos host] vk: malloc_trim: 269 MB free in the arenas now, the process's private memory 980 -> 968 MB (9 ms)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos Presentation Thread] vk: presents after the CPU's signal (600): 600 waited for it, 5.81 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 62.8 ms; VRAM 5.0 of 7.4 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), 649 new graphics pipelines, pipelines from the driver's cache 821, from the start's cache 0, compiled 0; 2667 draws and dispatches left out, 457 waits (2151.4 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: 31 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.40, present 0.19, draw 3.68, descriptors 1.26, texture lookups 0.08, uploads 0.00, pipelines 0.12, programs 0.54, commands 1.53, dispatch 0.76, memory sync 0.24, queue submit 1.47, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.69 MB synced in 916.4 copies, 16.59 MB written back
[hos host] vk: 12600 presents, 44.8 fps; a frame: 701 draws (0 skipped), 103 dispatches, 148 passes, 151 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1172 textures (3393 MB)
[hos host] vk: host time in GPU resource waits: 11.34 ms a frame (fences 0.03, timelines 11.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 500.9 full barriers recorded, 286.0 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: 51.0; 0x12: 69.5; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.7 ms a frame (the longest submission 5.8 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, 22.43 ms a frame): its jobs 8.48 ms a frame (submits 0.91, presents 0.19, others 7.38), idle 13.95; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.00 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); 600 captures at a CPU signal; the submits' waits read in 0.022 ms a frame; readbacks: 3000 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 7.45 ms after its hand-over (38.04 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 1.16 + 2.59 (the window's copy is in the idle), after it 0.64 + 2.44; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.19 ms of GPU time), after its last that reads it 1.00 (0.19 ms)
[hos host] vk: frame ahead (600 presents): 6.00 parts a frame recorded in the signal's job, 66.0% of them took nothing that came with the signal; of the others, 2.04 a frame took pages of the signal's capture into a mirror (77.0 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 0 of 600 frames, its first three in 0
[hos host] vk: frame ahead, what came with the signal: 600 signals with a capture, each of 107.0 pages in 9.0 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: 0.25+0.28, 0.06+1.81, 0.03+0.09, 0.28+0.08, 0.01+0.11, 0.02+0.08, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: readback pages refreshed from guest memory: 3246484 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: late pages' fix (600 recordings with one): of 600 captures with late pages 600 fixed (65.2 pages, 66.2 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; 595 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 582 blocks (37248 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 147, of an earlier recording 448, not recorded yet 0, of this part 0; pages fixed from stamps 37923, from snapshots 1195; the shadows: 288643 pages synced from captures, 288043 made known by it, 600 left unknown because the replay or the collection wrote them since
[hos Presentation Thread] vi: 12618 frames presented (43.7 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 111, 22-30 101, 30-40 2, over 40 5
[hos host] vk: replay reads of guest memory as submitted: 5640000 (2820753 pages from the captures)
[hos host] vk: reaper: 49 images (197 MB) destroyed in 10 s, 0 of them where they were handed over (its cap or VRAM pressure); the queue at most 10 (64 MB)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 460000 so far (x1 0x117df8b070 x2 0 x3 0x117df8b040 x4 0x44b040)
[hos host] vk: 1 textures retired (1171 left, 3384 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3639 dirty pages from their submits' captures, 52007 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): 1074 dispatches, 42418 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5883 runs, 763.1 MB compared; 153 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 155 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22139 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #205000: event 0x100d6c8040 mode 0 value 204999 (lr 0x806621e8)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #275000: event 0x100d6c8048 mode 0 value 205001 (now 204982) (lr 0x806661f8)
[hos host] vk: replay reads of guest memory as submitted: 5660000 (2831098 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 130 pages in 2 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.02 over 1253 ranges, 1835 MB), 185 pages written, 185 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (114 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: write-backs left out (600 submits): 1034, 4334.1 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): 3541 dirty pages from their submits' captures, 52781 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): 1074 dispatches, 42961 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5905 runs, 763.2 MB compared; 111 pages read into the shadows; 256 MB of shadows (121 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22324 in captures, 0 only in the collection, 46 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 4767450 kept (1857596 by the last picks' textures, a uniform buffer bound since), 32052 new, 3400497 with other textures (of 8200000)
[hos host] vk: replay reads of guest memory as submitted: 5680000 (2841076 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1015 of 3000 waited for their write-back, 0.83 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: 3976 kept their virtual core (nothing there to wait for), 2936 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos ModuleSystemWorker4] nvn: 1500000 recordings made, 43943 live copies (12.2 MB), 398 texture copies; 6 command buffers' segments (4.3 MB)
[hos BaseProcExecutor1] vcores: 75457 takes, 9865 waits (mean 63 us, longest 3.2 ms, 0 over HOS_VCORE_LOG_MS), 4008 kicks, 4425 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a frame: 32 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 3016 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.00, present 0.19, draw 3.68, descriptors 1.28, texture lookups 0.09, uploads 0.00, pipelines 0.12, programs 0.54, commands 1.51, dispatch 0.77, memory sync 0.25, queue submit 1.46, slot wait 0.06
[hos host] vk: a frame: mirrors 68 (798 MB): 4.70 MB synced in 917.3 copies, 16.59 MB written back
[hos host] vk: 12720 presents, 43.2 fps; a frame: 706 draws (0 skipped), 103 dispatches, 147 passes, 151 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 925 pipelines (400 ms), 555 programs (11 failed), 1172 textures (3393 MB)
[hos host] vk: host time in GPU resource waits: 12.17 ms a frame (fences 0.03, timelines 12.14, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 501.0 full barriers recorded, 286.0 left out (nothing recorded since the one before), 17.8 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: 51.5; 0x12: 69.1; 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): 41.0 converted one by one, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 41.0 for the compute fallback (no mesh shaders in use: one by one); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none
[hos host] vk: GPU time 15.8 ms a frame (the longest submission 8.6 ms); 0.2 textures made a frame: colour targets 0.1 (0.2 MB), depth 0.1 (0.2 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: 5700000 (2851041 pages from the captures)
[hos host] vk: sparse mirrors: 48, 798 MB with memory of 948 MB (149 MB spared); blocks given memory later 127, given back 1234; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 88 binds (12.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 6 taken from the spares, 62 made new; 20 kept as spares, 0 destroyed; 14 spares now, 308 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1012, 4241.9 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): 3546 dirty pages from their submits' captures, 51645 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): 1065 dispatches, 42130 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5962 runs, 778.9 MB compared; 92 pages read into the shadows; 256 MB of shadows (122 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 22129 in captures, 0 only in the collection, 45 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 56 live (1064 MB), 0 retired still imported (0 MB), 12 retired given back (256 MB)
[hos host] vk: 1 textures retired (1171 left, 3384 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: present 12740 written to <data>/jobs/jb_9229e0142dcd8ad2/runs/kokiri-forest-g0-02-pr/shots/kokiri-forest-c0-pr-02-forest-end.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: 0 program records loaded (0.0 ms), 649 new graphics pipelines, pipelines from the driver's cache 821, from the start's cache 0, compiled 0; 2667 draws and dispatches left out, 457 waits (2151.4 ms)
[hos host] vk: program loads at create (close): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 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 (close): 0 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them)
[hos host] vk: module identifiers (close): 0 known, 0 learned in this run; 0 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: indexed descriptor arrays (close): 16 in 16 of 1086 program stages, 0 of them near a limit
[hos host] vk: indexed descriptor arrays (close), fragment stages: 16 texture (17-64: 16); the longest 64
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4524 pools in the table now)
[hos host] vk: pipeline cache: play file 5 saved (2 KB): 1 pipelines, 1 from the driver's cache, 0 compiled; 0 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)