Report rp_6ed6fe8ef91ac4f5 fail
This report disagrees with its peers.
three-areas field-after-turn.frametime_1pct_low_ms: +25.8% against peers' -15.2% three-areas field-after-turn.frametime_max_ms: +254.9% against peers' -12.0% three-areas field-still.frametime_1pct_low_ms: +43.4% against peers' -8.1% three-areas field-still.frametime_max_ms: +284.5% against peers' -10.5% three-areas forest-after-turn.frametime_max_ms: +322.1% against peers' -6.3% three-areas forest-still.fps_mean: +14.4% against peers' -17.7% three-areas forest-still.frametime_1pct_low_ms: +17.1% against peers' -40.4% three-areas forest-still.frametime_max_ms: +61.7% against peers' -32.9% three-areas forest-still.frametime_p99_ms: -14.5% against peers' -39.9% three-areas forest-still.hitch_count: +400.0% against peers' +2.9% three-areas forest-still.stutter_count: +400.0% against peers' -66.7% three-areas market-after-turn.draws_mean: -0.1% against peers' +93.8% three-areas market-after-turn.frametime_max_ms: +117.8% against peers' +16.0% three-areas market-still.fps_mean: -24.5% against peers' +4.5% three-areas market-still.hitch_count: +133.8% against peers' +5.5% three-areas market-still.stutter_count: +108.3% against peers' +400.0% three-areas run_frametime_max_ms: +47.2% against peers' +7.3% three-areas run_hitch_count: +128.1% against peers' -14.1%
Machine
- Commit
- a2cc7b53eccfdc2de4b4dc118aac04d434c2f5e7
- Baseline
- 9ea65c7bf55719be396977dbe6f69d98cf3cdf44
- App
- nightly-187-84ad90a8, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 7 5800X3D 8-Core Processor
- gpu
- AMD Radeon RX 7900 XTX (RADV NAVI31)
- tags
- linuxamdradvdgpu
- driver
- 26.2.7
- ram_gb
- 64
- vram_mb
- 24,560
- gpu_vendor
- amd
- os_version
- Bazzite (kernel 7.3.4)
Builds
main (baseline)
46.6 s warm
from 9ea65c7bf557
- lift
- 0.8 s
- read
- 4.7 s
- finish
- 15.5 s
- compile
- 11.1 s
- shaders
- 5.1 s
PR
735.4 s warm
- lift
- 100.5 s
- read
- 2.5 s
- finish
- 19.4 s
- compile
- 612.5 s
Program cache: warm
Scenarios
three-areas
ok| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| run_hitch_count | 83.5 | 190.5 | +128.1% |
| field-still.fps_mean | 103.22 | 117.2 | +13.5% |
| run_frametime_max_ms | 357.76 | 526.65 | +47.2% |
| forest-still.fps_mean | 99.25 | 113.58 | +14.4% |
| market-still.fps_mean | 70.71 | 53.38 | −24.5% |
| field-still.draws_mean | 1,190 | 1,192.35 | +0.2% |
| field-still.hitch_count | 0 | 4 | — |
| forest-still.draws_mean | 709.9 | 787 | +10.9% |
| market-still.draws_mean | 2,464.65 | 2,453.75 | −0.4% |
| forest-still.hitch_count | 0.5 | 2.5 | +400% |
| market-still.hitch_count | 37 | 86.5 | +133.8% |
| field-after-turn.fps_mean | 93.49 | 121.19 | +29.6% |
| field-still.stutter_count | 0 | 4 | — |
| forest-after-turn.fps_mean | 102.11 | 119.85 | +17.4% |
| forest-still.stutter_count | 0.5 | 2.5 | +400% |
| market-after-turn.fps_mean | 89.36 | 96.35 | +7.8% |
| market-still.stutter_count | 42 | 87.5 | +108.3% |
| field-after-turn.draws_mean | 1,143.95 | 743.5 | −35% |
| field-after-turn.hitch_count | 0 | 3 | — |
| field-still.frametime_max_ms | 15.71 | 60.42 | +284.5% |
| field-still.frametime_p50_ms | 9.75 | 8.4 | −13.9% |
| field-still.frametime_p99_ms | 12.25 | 10.39 | −15.2% |
| forest-after-turn.draws_mean | 618.75 | 700.5 | +13.2% |
| market-after-turn.draws_mean | 926.05 | 925.4 | −0.1% |
| forest-after-turn.hitch_count | 0 | 1.5 | — |
| forest-still.frametime_max_ms | 39.32 | 63.6 | +61.7% |
| forest-still.frametime_p50_ms | 10.54 | 9.05 | −14.1% |
| forest-still.frametime_p99_ms | 12.93 | 11.06 | −14.5% |
| market-after-turn.hitch_count | 0 | 0.5 | — |
| market-still.frametime_max_ms | 64.38 | 66.23 | +2.9% |
| market-still.frametime_p50_ms | 12.56 | 14.63 | +16.5% |
| market-still.frametime_p99_ms | 61.82 | 63.78 | +3.2% |
| field-after-turn.stutter_count | 0 | 3 | — |
| forest-after-turn.stutter_count | 0 | 1.5 | — |
| market-after-turn.stutter_count | 0 | 1 | — |
| field-after-turn.frametime_max_ms | 16.08 | 57.05 | +254.9% |
| field-after-turn.frametime_p50_ms | 10.71 | 8.23 | −23.1% |
| field-after-turn.frametime_p99_ms | 13.75 | 9.51 | −30.8% |
| field-still.frametime_1pct_low_ms | 13.11 | 18.8 | +43.4% |
| forest-after-turn.frametime_max_ms | 14.36 | 60.61 | +322.1% |
| forest-after-turn.frametime_p50_ms | 10.38 | 8.35 | −19.5% |
| forest-after-turn.frametime_p99_ms | 12.79 | 10.67 | −16.6% |
| forest-still.frametime_1pct_low_ms | 14.48 | 16.96 | +17.1% |
| market-after-turn.frametime_max_ms | 18.96 | 41.28 | +117.8% |
| market-after-turn.frametime_p50_ms | 10.71 | 10.3 | −3.8% |
| market-after-turn.frametime_p99_ms | 15.04 | 13.24 | −12% |
| market-still.frametime_1pct_low_ms | 62.38 | 64.39 | +3.2% |
| field-after-turn.frametime_1pct_low_ms | 14.16 | 17.82 | +25.8% |
| forest-after-turn.frametime_1pct_low_ms | 13.22 | 15.37 | +16.2% |
| market-after-turn.frametime_1pct_low_ms | 16.7 | 16.32 | −2.3% |
| screenshot_diff | — | 0.76 | — |
Pictures against main: forest diff 0.6891 (main against itself 0.7041), forest-turned diff 0.7543 (main against itself 0.6153), field diff 0.0148 (main against itself 0.013), field-turned diff 0.546 (main against itself 0.6545), market diff 0.074 (main against itself 0.0449), market-turned diff 0.7745 (main against itself 0.6442)
Runs (4)
| Metric | main 0 | pr 1 | pr 2 | main 3 |
|---|---|---|---|---|
| hang | no | no | no | no |
| crashed | no | no | no | no |
| exit_code | 0 | 0 | 0 | 0 |
| run_hitch_count | 81 | 204 | 177 | 86 |
| field-still.fps_mean | 104.75 | 117.62 | 116.78 | 101.68 |
| run_frametime_max_ms | 271.81 | 701.05 | 352.25 | 443.72 |
| forest-still.fps_mean | 84.05 | 112.9 | 114.27 | 114.46 |
| market-still.fps_mean | 70.29 | 51.78 | 54.97 | 71.13 |
| field-still.draws_mean | 1,191.7 | 1,184.9 | 1,199.8 | 1,188.3 |
| field-still.hitch_count | 0 | 2 | 6 | 0 |
| forest-still.draws_mean | 670.8 | 786.9 | 787.1 | 749 |
| market-still.draws_mean | 2,455.8 | 2,480.7 | 2,426.8 | 2,473.5 |
| forest-still.hitch_count | 0 | 3 | 2 | 1 |
| market-still.hitch_count | 38 | 94 | 79 | 36 |
| field-after-turn.fps_mean | 99.46 | 116.59 | 125.78 | 87.52 |
| field-still.stutter_count | 0 | 2 | 6 | 0 |
| forest-after-turn.fps_mean | 81.76 | 116.39 | 123.31 | 122.46 |
| forest-still.stutter_count | 0 | 3 | 2 | 1 |
| market-after-turn.fps_mean | 89.31 | 110.11 | 82.59 | 89.42 |
| market-still.stutter_count | 40 | 96 | 79 | 44 |
| field-after-turn.draws_mean | 1,015.8 | 747.4 | 739.6 | 1,272.1 |
| field-after-turn.hitch_count | 0 | 5 | 1 | 0 |
| field-still.frametime_max_ms | 14.3 | 59.1 | 61.74 | 17.12 |
| field-still.frametime_p50_ms | 9.6 | 8.43 | 8.37 | 9.9 |
| field-still.frametime_p99_ms | 11.79 | 10.02 | 10.76 | 12.71 |
| forest-after-turn.draws_mean | 724.2 | 731.4 | 669.6 | 513.3 |
| market-after-turn.draws_mean | 779.8 | 521.2 | 1,329.6 | 1,072.3 |
| forest-after-turn.hitch_count | 0 | 2 | 1 | 0 |
| forest-still.frametime_max_ms | 17.19 | 63.68 | 63.52 | 61.45 |
| forest-still.frametime_p50_ms | 12.44 | 9.07 | 9.03 | 8.64 |
| forest-still.frametime_p99_ms | 14.75 | 11.04 | 11.08 | 11.12 |
| market-after-turn.hitch_count | 0 | 0 | 1 | 0 |
| market-still.frametime_max_ms | 64.12 | 66.12 | 66.34 | 64.63 |
| market-still.frametime_p50_ms | 12.62 | 14.75 | 14.52 | 12.51 |
| market-still.frametime_p99_ms | 61.73 | 63.95 | 63.62 | 61.91 |
| field-after-turn.stutter_count | 0 | 5 | 1 | 0 |
| forest-after-turn.stutter_count | 0 | 2 | 1 | 0 |
| market-after-turn.stutter_count | 0 | 1 | 1 | 0 |
| field-after-turn.frametime_max_ms | 14.97 | 58.21 | 55.9 | 17.18 |
| field-after-turn.frametime_p50_ms | 9.99 | 8.48 | 7.98 | 11.42 |
| field-after-turn.frametime_p99_ms | 12.79 | 9.86 | 9.16 | 14.7 |
| field-still.frametime_1pct_low_ms | 12.36 | 14.53 | 23.07 | 13.86 |
| forest-after-turn.frametime_max_ms | 16.1 | 60.83 | 60.4 | 12.62 |
| forest-after-turn.frametime_p50_ms | 12.58 | 8.55 | 8.15 | 8.18 |
| forest-after-turn.frametime_p99_ms | 15.21 | 11.3 | 10.04 | 10.36 |
| forest-still.frametime_1pct_low_ms | 15.18 | 17.99 | 15.93 | 13.78 |
| market-after-turn.frametime_max_ms | 18.23 | 20.14 | 62.41 | 19.68 |
| market-after-turn.frametime_p50_ms | 10.52 | 8.87 | 11.73 | 10.9 |
| market-after-turn.frametime_p99_ms | 15.59 | 12.06 | 14.41 | 14.49 |
| market-still.frametime_1pct_low_ms | 62.12 | 64.58 | 64.2 | 62.64 |
| field-after-turn.frametime_1pct_low_ms | 13.2 | 23.54 | 12.1 | 15.13 |
| forest-after-turn.frametime_1pct_low_ms | 15.5 | 17.5 | 13.24 | 10.95 |
| market-after-turn.frametime_1pct_low_ms | 16.66 | 13.66 | 18.99 | 16.74 |
| screenshot_diff | — | 0.77 | 0.75 | — |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| three-areas | crash | False | 0 | 0 | — | pass | |
| three-areas | forest-still.fps_mean.min_delta_pct | 0 | 99.25 | 113.58 | +14.4% | pass | |
| three-areas | forest-after-turn.fps_mean.min_delta_pct | 0 | 102.11 | 119.85 | +17.4% | pass | |
| three-areas | field-still.fps_mean.min_delta_pct | 0 | 103.22 | 117.2 | +13.5% | pass | |
| three-areas | field-after-turn.fps_mean.min_delta_pct | 0 | 93.49 | 121.19 | +29.6% | pass | |
| three-areas | market-still.fps_mean.min_delta_pct | 0 | 70.71 | 53.38 | −24.5% | fail | |
| three-areas | market-after-turn.fps_mean.min_delta_pct | 0 | 89.36 | 96.35 | +7.8% | pass | |
| three-areas | screenshot.max_diff | 0.05 | 0.7 | 0.77 | — | fail | |
| three-areas | forest-still.frametime_p99_ms.max_delta_pct | 15 | 12.93 | 11.06 | −14.5% | pass | |
| three-areas | forest-after-turn.frametime_p99_ms.max_delta_pct | 15 | 12.79 | 10.67 | −16.6% | pass | |
| three-areas | field-still.frametime_p99_ms.max_delta_pct | 15 | 12.25 | 10.39 | −15.2% | pass | |
| three-areas | field-after-turn.frametime_p99_ms.max_delta_pct | 15 | 13.75 | 9.51 | −30.8% | pass | |
| three-areas | market-still.frametime_p99_ms.max_delta_pct | 15 | 61.82 | 63.78 | +3.2% | pass | |
| three-areas | market-after-turn.frametime_p99_ms.max_delta_pct | 15 | 15.04 | 13.24 | −12% | pass |
Pictures of the failure
This report had 2 pictures of its failure (the last frame of a stuck step, or main's and the PR's picture where they differed too much). The farm keeps those for a day: they were deleted.
Log (PR side, end)
[hos host] vk: replay reads of guest memory as submitted: 7600000 (3781751 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 11496 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 939 ranges, 3453 MB), 214 pages written, 214 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.012; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 24 kept (96 MB), 12 spare buffers, 5602 texture pages copied (21 MB) [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 16686; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3811 dirty pages from their submits' captures, 60138 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): 1171 dispatches, 45916 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6727 runs, 890.7 MB compared; 108 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19531 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: replay reads of guest memory as submitted: 7620000 (3793796 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: memory: working set 10380 MB (peak 13457), private 3441 MB, staging 48 MB in 3 arenas, 42 made so far (1 ms) [hos host] vk: memory heaps: heap 0 (system): 14 blocks 840 MB, 39 allocations 780 MB; used 3324 of 31886 MB; heap 1 (device): 348 blocks 11572 MB, 20840 allocations 10760 MB; used 12317 of 23061 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 2 free ranges, the largest 0 MB [hos host] vk: image blocks (render targets): 26 blocks 832 MB, 187 images 514 MB; 146 free ranges, the largest 32 MB [hos host] vk: image blocks (textures, compacted): 219 blocks 7008 MB, 4588 images 6856 MB; 1066 free ranges, the largest 21 MB [hos host] vk: render target images: 5102 reused from the pool, 5107 made new, 4914 destroyed from it; it holds 11 (41 MB) [hos host] vk: VRAM: 12317 MB used of 23061 MB allowed (812 MB of it free in the blocks); textures 9078 MB (budget 11000 MB), 4784 textures [hos host] vk: budget: VRAM 11572 of 23061 MB (12317 MB by the driver, 744 MB unaccounted): textures 9078, mirrors 984, blocks free 812, shadows 332, other buffers 228, staging 48, other images 46, target pool 41; RAM 3274 MB (the process's private memory 3441 MB): imports 2460, capture spares 664, captures 104, capture table 34, other buffers 12, others 0 [hos host] vk: textures: decoded ASTC 5721 MB, rendered 1218 MB (49 drawn in one frame, kept: 35858 KB), other 1287 MB; used in the last 8 presents 2134 MB [hos host] vk: decoded ASTC used again: 161 textures (312 MB) copied from ones the game finalized, not decoded; 161 of those retired, 526 listed; 1177 MB of blocks hashed in 111 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 5217 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 5217 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 17673 presents ago [hos host] vk: 54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7271 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: 72 (15549 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 140x42x1 NVN 0x25: 1 (22 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 36 (6334 KB); [hos Presentation Thread] vk: presents after the CPU's signal (600): 553 waited for it, 1.52 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 63.8 ms; VRAM 12.0 of 22.5 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: 26 program records loaded (7.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 6027 queued, 6027 loaded (median 0.16 ms, 99th percentile 2.62 ms, worst 120.85 ms, 2146 ms and 1393.3 MB read in all); 8777 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 10846 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2123 pipelines made at create taken by draws; 2770 create calls with nothing kept for their stages, 0 before the index; units 8797 (6027 ready, 0 loading), 14428 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (play): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before) [hos host] vk: a frame: 201 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.04, present 0.21, draw 4.31, descriptors 1.54, texture lookups 0.11, uploads 0.00, pipelines 0.14, programs 0.48, commands 1.86, dispatch 0.51, memory sync 0.27, queue submit 0.81, slot wait 0.06 [hos host] vk: a frame: mirrors 259 (984 MB): 4.98 MB synced in 916.8 copies, 17.81 MB written back [hos host] vk: 27600 presents, 84.6 fps; a frame: 1306 draws (0 skipped), 96 dispatches, 219 passes, 174 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4784 textures (9078 MB) [hos host] vk: host time in GPU resource waits: 2.86 ms a frame (fences 0.00, timelines 2.86, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 518.3 full barriers recorded, 271.2 left out (nothing recorded since the one before), 46.1 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: 34.5; 0x12: 107.8; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.9 ms a frame (the longest submission 3.1 ms); 2.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 12.43 ms a frame): its jobs 7.90 ms a frame (submits 0.93, presents 0.24, others 6.74), idle 4.53; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.64 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); 582 captures at a CPU signal; the submits' waits read in 0.039 ms a frame; readbacks: 2998 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 7.27 ms after its hand-over (13.92 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 1.84 + 0.22 (the window's copy is in the idle), after it 3.04 + 0.25; 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): 5.41 parts a frame recorded in the signal's job, 63.1% of them took nothing that came with the signal; of the others, 2.00 a frame took pages of the signal's capture into a mirror (77.1 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 21 of 578 frames, its first three in 21 [hos host] vk: frame ahead, what came with the signal: 582 signals with a capture, each of 141.0 pages in 11.0 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: 0.91+0.05, 0.84+0.11, 0.68+0.05, 0.26+0.02, 0.06+0.02, 0.02+0.00, 0.01+0.00, 0.00+0.00, 0.09+0.00, 0.16+0.00, 0.00+0.00, 0.00+0.00 [hos host] vk: replay reads of guest memory as submitted: 7640000 (3805831 pages from the captures) [hos host] vk: 1 textures retired (4783 left, 9068 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3216 dirty pages from their submits' captures, 59555 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): 1152 dispatches, 45163 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6579 runs, 872.9 MB compared; 119 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 18962 in captures, 1 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #410000: event 0x100d6c800c mode 0 value 284359 (now 284340) (lr 0x80660e38) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 886 of 3000 waited for their write-back, 0.28 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: 8008 kept their virtual core (nothing there to wait for), 3000 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: 1 textures retired (4782 left, 9057 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7660000 (3817879 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 4421650 pages so far (0 held: may be written ahead in their submission) [hos Presentation Thread] vi: 27648 frames presented (83.5 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 417, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 1 [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 938 ranges, 3451 MB), 208 pages written, 208 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.008; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (92 MB), 12 spare buffers, 5602 texture pages copied (21 MB) [hos sead::MainThread] nvn: CommandBufferSignalEvent #285000: event 0x100d6c8040 mode 0 value 284999 (lr 0x806621e8) [hos host] vk: 11 textures retired (4782 left, 9057 MB): budget 0, drawn over 0, dead targets 11 [hos host] vk: replay reads of guest memory as submitted: 7680000 (3829897 pages from the captures) [hos host] vk: program picks: 11288030 kept (4107618 by the last picks' textures, a uniform buffer bound since), 70701 new, 4841268 with other textures (of 16200000) [hos host] vk: 2 textures retired (4780 left, 9035 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17280; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3645 dirty pages from their submits' captures, 59737 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): 1159 dispatches, 45581 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6725 runs, 890.7 MB compared; 113 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19513 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [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: 2 textures retired (4778 left, 9013 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7700000 (3841937 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 11 textures retired (4778 left, 9013 MB): budget 0, drawn over 0, dead targets 11 [hos host] vk: replay reads of guest memory as submitted: 7720000 (3853984 pages from the captures) [hos host] vk: 44 textures retired (4775 left, 9044 MB): budget 0, drawn over 2, dead targets 42 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 311 KB; 0 made on demand (0 MB kept now); c1 stages: at most 125 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3634 dirty pages from their submits' captures, 60435 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): 1168 dispatches, 45980 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6615 runs, 873.1 MB compared; 113 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19565 in captures, 0 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a frame: 199 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.00, present 0.22, draw 4.13, descriptors 1.40, texture lookups 0.12, uploads 0.00, pipelines 0.14, programs 0.47, commands 1.83, dispatch 0.51, memory sync 0.24, queue submit 0.83, slot wait 0.08 [hos host] vk: a frame: mirrors 259 (984 MB): 4.99 MB synced in 918.2 copies, 17.81 MB written back [hos host] vk: 27720 presents, 86.1 fps; a frame: 1298 draws (0 skipped), 95 dispatches, 219 passes, 174 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4776 textures (9053 MB) [hos host] vk: host time in GPU resource waits: 2.72 ms a frame (fences 0.00, timelines 2.72, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 518.4 full barriers recorded, 270.8 left out (nothing recorded since the one before), 46.0 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: 34.4; 0x12: 107.8; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.9 ms a frame (the longest submission 3.1 ms); 2.5 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 938 ranges, 3451 MB), 210 pages written, 210 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 24 kept (98 MB), 12 spare buffers, 6434 texture pages copied (25 MB) [hos host] vk: 11 textures retired (4788 left, 9114 MB): budget 0, drawn over 0, dead targets 11 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8651 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 7740000 (3866005 pages from the captures) [hos host] vk: 1 textures retired (4791 left, 9155 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: queues ordered by their events: 162000 submissions stopped at a wait, 159749 went on once it was reached, 2249 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 163 (stopped 54.99 ms at most); waits met 411131, not met 0; captures at a CPU event's wait 20176, 0 of them at a wait met on arrival [hos ModuleSystemWorker5] vk: readbacks of GPU results: 816 of 3000 waited for their write-back, 0.28 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: 8220 kept their virtual core (nothing there to wait for), 3044 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17874; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3576 dirty pages from their submits' captures, 59079 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): 1153 dispatches, 45024 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6702 runs, 890.5 MB compared; 131 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19082 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: replay reads of guest memory as submitted: 7760000 (3878038 pages from the captures) [hos host] vk: 11 textures retired (4798 left, 9283 MB): budget 0, drawn over 0, dead targets 11 [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: replay reads of guest memory as submitted: 7780000 (3889985 pages from the captures) [hos host] vk: program picks: 11429435 kept (4154418 by the last picks' textures, a uniform buffer bound since), 70701 new, 4899863 with other textures (of 16400000) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3435 dirty pages from their submits' captures, 59283 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): 1165 dispatches, 45715 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6677 runs, 889.7 MB compared; 124 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19439 in captures, 0 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 11 textures retired (4801 left, 9310 MB): budget 0, drawn over 0, dead targets 11 [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #415000: event 0x100d6c800c mode 0 value 288159 (now 288140) (lr 0x80660e38) [hos host] vk: texture #15581 0x1000a56ca00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 27823 (drawn at 27762) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 938 ranges, 3449 MB), 204 pages written, 204 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.008; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 24 kept (98 MB), 12 spare buffers, 6431 texture pages copied (25 MB) [hos host] vk: 1 textures retired (4800 left, 9299 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7800000 (3901814 pages from the captures) [hos host] vk: 1 textures retired (4807 left, 9310 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a frame: 191 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.99, present 0.22, draw 4.16, descriptors 1.41, texture lookups 0.14, uploads 0.00, pipelines 0.14, programs 0.49, commands 1.84, dispatch 0.51, memory sync 0.25, queue submit 0.82, slot wait 0.06 [hos host] vk: a frame: mirrors 259 (984 MB): 4.94 MB synced in 916.0 copies, 17.82 MB written back [hos host] vk: 27840 presents, 85.4 fps; a frame: 1278 draws (0 skipped), 96 dispatches, 213 passes, 172 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4807 textures (9310 MB) [hos host] vk: host time in GPU resource waits: 2.78 ms a frame (fences 0.00, timelines 2.78, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 511.7 full barriers recorded, 267.0 left out (nothing recorded since the one before), 42.5 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: 34.4; 0x12: 105.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.9 ms a frame (the longest submission 3.1 ms); 3.9 textures made a frame [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: 12 textures retired (4811 left, 9354 MB): budget 0, drawn over 1, dead targets 11 [hos OptimizeChangeBanc] vcores: 136940 takes, 26097 waits (mean 70 us, longest 10.7 ms, 0 over HOS_VCORE_LOG_MS), 11813 kicks, 12026 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 7820000 (3913878 pages from the captures) [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18468; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3148 dirty pages from their submits' captures, 58946 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): 1149 dispatches, 44910 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6583 runs, 874.4 MB compared; 113 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19026 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: 2 textures retired (4810 left, 9343 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7840000 (3925906 pages from the captures) [hos host] vk: 3 textures retired (4808 left, 9321 MB): budget 0, drawn over 3, dead targets 0 [hos host] vk: readback pages refreshed from guest memory: 4495634 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 0.01, writes collected 0.03 [hos host] vk: 11 textures retired (4816 left, 9408 MB): budget 0, drawn over 0, dead targets 11 [hos sead::MainThread] nvn: 2100000 recordings made, 67953 live copies (20.2 MB), 3871 texture copies; 5 command buffers' segments (4.2 MB) [hos sead::MainThread] vk: readbacks of GPU results: 879 of 3000 waited for their write-back, 0.27 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: 8290 kept their virtual core (nothing there to wait for), 2974 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: 3 textures retired (4816 left, 9413 MB): budget 0, drawn over 3, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 939 ranges, 3453 MB), 206 pages written, 206 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.009; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 6775 texture pages copied (26 MB) [hos sead::MainThread] nvn: DrawMeshTasksIndirect: 660000 so far (x1 0x117cfbb040 x2 0 x3 0x117cfbb040 x4 0x9b040) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5826 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 7860000 (3937921 pages from the captures) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3499 dirty pages from their submits' captures, 60435 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): 1163 dispatches, 45926 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6772 runs, 891.5 MB compared; 111 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19519 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 13 textures retired (4815 left, 9395 MB): budget 0, drawn over 2, dead targets 11 [hos sead::MainThread] nvn: CommandBufferSignalEvent #290000: event 0x100d6c8000 mode 0 value 289999 (lr 0x80291440) [hos host] vk: 5 textures retired (4810 left, 9349 MB): budget 0, drawn over 5, dead targets 0 [hos host] vk: 13 textures retired (4808 left, 9331 MB): budget 0, drawn over 2, dead targets 11 [hos sead::MainThread] nvn: GPU waits in 5 s: 379 sync waits (398 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 7880000 (3949963 pages from the captures) [hos host] vk: render targets drawn over from another start, let go: 9779 so far (37511 MB), 8710 of them (32801 MB) between the passes [hos host] vk: 6 textures retired (4802 left, 9273 MB): budget 0, drawn over 6, dead targets 0 [hos host] vk: 8 textures retired (4801 left, 9263 MB): budget 0, drawn over 8, dead targets 0 [hos host] vk: a frame: 197 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.05, present 0.22, draw 4.34, descriptors 1.57, texture lookups 0.12, uploads 0.00, pipelines 0.14, programs 0.49, commands 1.86, dispatch 0.52, memory sync 0.26, queue submit 0.82, slot wait 0.06 [hos host] vk: a frame: mirrors 259 (984 MB): 5.00 MB synced in 918.9 copies, 17.83 MB written back [hos host] vk: 27960 presents, 84.1 fps; a frame: 1301 draws (0 skipped), 97 dispatches, 219 passes, 175 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4802 textures (9273 MB) [hos host] vk: host time in GPU resource waits: 2.92 ms a frame (fences 0.00, timelines 2.92, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 519.2 full barriers recorded, 271.2 left out (nothing recorded since the one before), 46.2 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: 34.5; 0x12: 108.0; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.1 ms); 2.1 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: program picks: 11570519 kept (4201211 by the last picks' textures, a uniform buffer bound since), 70701 new, 4958779 with other textures (of 16600000) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 311 KB; 0 made on demand (0 MB kept now); c1 stages: at most 125 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19062; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3691 dirty pages from their submits' captures, 59577 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): 1158 dispatches, 45413 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6679 runs, 874.2 MB compared; 114 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19248 in captures, 0 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: 18 textures retired (4791 left, 9215 MB): budget 0, drawn over 7, dead targets 11 [hos host] vk: replay reads of guest memory as submitted: 7900000 (3962001 pages from the captures) [hos host] vk: texture #16000 0x1000a7ad200 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 27975 (drawn at 27914) [hos ModuleSystemWorker5] barrier: 349244 looks: 103484 found the masks moved already, 243317 waited until they moved, 2443 for the whole 1 ms (a wait 228 us on average); 188559 wakes [hos host] vk: 16 textures retired (4797 left, 9216 MB): budget 0, drawn over 5, dead targets 11 [hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 919 ranges, 3281 MB), 211 pages written, 211 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.012; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 24 kept (102 MB), 12 spare buffers, 6061 texture pages copied (23 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 2 textures retired (4802 left, 9270 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7920000 (3974003 pages from the captures) [hos host] vk: 3 textures retired (4800 left, 9248 MB): budget 0, drawn over 3, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3644 dirty pages from their submits' captures, 60077 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): 1162 dispatches, 45738 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6777 runs, 891.6 MB compared; 118 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19679 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 11 textures retired (4800 left, 9248 MB): budget 0, drawn over 0, dead targets 11 [hos sead::MainThread] nvn: CommandBufferWaitEvent #420000: event 0x100d6c800c mode 0 value 291959 (now 291940) (lr 0x80660e38) [hos host] vk: 11 textures retired (4800 left, 9248 MB): budget 0, drawn over 0, dead targets 11 [hos host] vk: replay reads of guest memory as submitted: 7940000 (3986039 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos sead::MainThread] vk: readbacks of GPU results: 843 of 3000 waited for their write-back, 0.28 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: 8354 kept their virtual core (nothing there to wait for), 2910 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: 7960000 (3998074 pages from the captures) [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19662; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3727 dirty pages from their submits' captures, 60198 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): 1164 dispatches, 45975 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6755 runs, 890.4 MB compared; 109 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19617 in captures, 0 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: 9 textures retired (4794 left, 9183 MB): budget 0, drawn over 9, dead targets 0 [hos Presentation Thread] vi: 28073 frames presented (84.9 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 425, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0 [hos host] vk: late pages' fix (600 recordings with one): of 614 captures with late pages 614 fixed (62.1 pages, 63.0 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; 325 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 122 blocks (7808 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 32, of an earlier recording 293, not recorded yet 0, of this part 0; pages fixed from stamps 36902, from snapshots 1199; the shadows: 242794 pages synced from captures, 239940 made known by it, 2854 left unknown because the replay or the collection wrote them since [hos host] vk: 10 textures retired (4784 left, 9074 MB): budget 0, drawn over 10, dead targets 0 [hos host] vk: a frame: 200 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.05, present 0.21, draw 4.43, descriptors 1.63, texture lookups 0.13, uploads 0.00, pipelines 0.14, programs 0.49, commands 1.88, dispatch 0.52, memory sync 0.24, queue submit 0.79, slot wait 0.06 [hos host] vk: a frame: mirrors 259 (984 MB): 5.00 MB synced in 919.7 copies, 17.83 MB written back [hos host] vk: 28080 presents, 84.8 fps; a frame: 1305 draws (0 skipped), 97 dispatches, 219 passes, 174 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4784 textures (9074 MB) [hos host] vk: host time in GPU resource waits: 2.86 ms a frame (fences 0.00, timelines 2.86, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 520.2 full barriers recorded, 270.9 left out (nothing recorded since the one before), 45.6 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: 34.5; 0x12: 107.8; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.9 ms a frame (the longest submission 3.0 ms); 2.7 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 920 ranges, 3277 MB), 214 pages written, 214 copied (0.8 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 0.006, bytes copied 0.000; 25 kept (110 MB), 11 spare buffers, 6575 texture pages copied (25 MB) [hos host] vk: replay reads of guest memory as submitted: 7980000 (4010134 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 17180 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 13 textures retired (4785 left, 9089 MB): budget 0, drawn over 2, dead targets 11 [hos host] vk: 1 textures retired (4785 left, 9089 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: program picks: 11712470 kept (4249197 by the last picks' textures, a uniform buffer bound since), 70701 new, 5016828 with other textures (of 16800000) [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3277 dirty pages from their submits' captures, 59165 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): 1149 dispatches, 44888 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6617 runs, 874.0 MB compared; 108 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19034 in captures, 8 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8000000 (4022193 pages from the captures) [hos host] vk: 16 textures retired (4780 left, 9034 MB): budget 0, drawn over 5, dead targets 11 [hos host] vk: readback pages refreshed from guest memory: 4569350 pages so far (0 held: may be written ahead in their submission) [hos host] vk: 1 textures retired (4779 left, 9023 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8020000 (4034206 pages from the captures) [hos host] vk: 1 textures retired (4778 left, 9012 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: 2 textures retired (4776 left, 8991 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20256; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3684 dirty pages from their submits' captures, 59933 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): 1156 dispatches, 45780 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6714 runs, 890.7 MB compared; 124 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19259 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 913 ranges, 3229 MB), 209 pages written, 209 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.009; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (102 MB), 12 spare buffers, 6928 texture pages copied (27 MB) [hos host] vk: 1 textures retired (4775 left, 8980 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8040000 (4046228 pages from the captures) [hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #295000: event 0x100d6c8010 mode 0 value 295000 (lr 0x80660adc) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 854 of 3000 waited for their write-back, 0.28 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: 8179 kept their virtual core (nothing there to wait for), 3085 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: memory: working set 10394 MB (peak 13457), private 3455 MB, staging 48 MB in 3 arenas, 42 made so far (1 ms) [hos host] vk: memory heaps: heap 0 (system): 14 blocks 840 MB, 39 allocations 772 MB; used 3324 of 31886 MB; heap 1 (device): 346 blocks 11508 MB, 20826 allocations 10685 MB; used 12253 of 23061 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 2 free ranges, the largest 0 MB [hos host] vk: image blocks (render targets): 24 blocks 768 MB, 173 images 440 MB; 135 free ranges, the largest 26 MB [hos host] vk: image blocks (textures, compacted): 219 blocks 7008 MB, 4588 images 6855 MB; 1067 free ranges, the largest 21 MB [hos host] vk: render target images: 6193 reused from the pool, 5536 made new, 5357 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 12253 MB used of 23061 MB allowed (822 MB of it free in the blocks); textures 9045 MB (budget 11000 MB), 4781 textures [hos host] vk: budget: VRAM 11508 of 23061 MB (12253 MB by the driver, 744 MB unaccounted): textures 9045, mirrors 984, blocks free 822, shadows 332, other buffers 228, staging 48, other images 46; RAM 3266 MB (the process's private memory 3455 MB): imports 2460, capture spares 664, captures 98, capture table 34, other buffers 10, others 0 [hos host] vk: textures: decoded ASTC 5721 MB, rendered 1190 MB (49 drawn in one frame, kept: 35858 KB), other 1288 MB; used in the last 8 presents 1976 MB [hos host] vk: decoded ASTC used again: 167 textures (319 MB) copied from ones the game finalized, not decoded; 167 of those retired, 594 listed; 1178 MB of blocks hashed in 111 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 5817 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 5817 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 18273 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: 0x10002ce3a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 5817 presents ago [hos host] vk: 54 MB: 0x100032c0400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 8029 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 72 (15549 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 140x42x1 NVN 0x25: 1 (22 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 36 (6334 KB); [hos Presentation Thread] vk: presents after the CPU's signal (600): 555 waited for it, 1.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 16.0 ms; VRAM 12.0 of 22.5 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: 26 program records loaded (7.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 6027 queued, 6027 loaded (median 0.16 ms, 99th percentile 2.62 ms, worst 120.85 ms, 2146 ms and 1393.3 MB read in all); 8777 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 10846 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2123 pipelines made at create taken by draws; 2770 create calls with nothing kept for their stages, 0 before the index; units 8797 (6027 ready, 0 loading), 14428 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (play): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before) [hos host] vk: a frame: 201 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 53 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.02, present 0.20, draw 4.30, descriptors 1.46, texture lookups 0.11, uploads 0.00, pipelines 0.14, programs 0.50, commands 1.91, dispatch 0.51, memory sync 0.28, queue submit 0.84, slot wait 0.07 [hos host] vk: a frame: mirrors 259 (984 MB): 4.98 MB synced in 916.0 copies, 17.81 MB written back [hos host] vk: 28200 presents, 84.7 fps; a frame: 1310 draws (0 skipped), 95 dispatches, 219 passes, 174 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 53917 pipelines (1051 ms), 0 programs (10 failed), 4781 textures (9045 MB) [hos host] vk: host time in GPU resource waits: 2.82 ms a frame (fences 0.00, timelines 2.82, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 518.1 full barriers recorded, 271.6 left out (nothing recorded since the one before), 46.1 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: 34.5; 0x12: 107.7; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.9 ms a frame (the longest submission 3.0 ms); 1.6 textures made a frame [hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 11.76 ms a frame): its jobs 7.60 ms a frame (submits 0.87, presents 0.22, others 6.51), idle 4.17; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.69 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); 585 captures at a CPU signal; the submits' waits read in 0.038 ms a frame; readbacks: 2995 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 6.91 ms after its hand-over (10.25 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 1.88 + 0.23 (the window's copy is in the idle), after it 2.51 + 0.24; 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): 5.12 parts a frame recorded in the signal's job, 61.2% of them took nothing that came with the signal; of the others, 1.99 a frame took pages of the signal's capture into a mirror (73.3 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 17 of 585 frames, its first three in 17 [hos host] vk: frame ahead, what came with the signal: 585 signals with a capture, each of 136.5 pages in 11.0 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: 0.85+0.04, 0.87+0.11, 0.65+0.04, 0.14+0.02, 0.00+0.01, 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: replay reads of guest memory as submitted: 8060000 (4058258 pages from the captures) [hos host] vk: 1 textures retired (4780 left, 9034 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 host] vk: the recording streams: 48 of 2 MB, the most one held 311 KB; 0 made on demand (0 MB kept now); c1 stages: at most 125 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 1029, 5047.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3964 dirty pages from their submits' captures, 59203 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): 1156 dispatches, 45287 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6589 runs, 872.9 MB compared; 106 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19109 in captures, 2 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 11 textures retired (4780 left, 9034 MB): budget 0, drawn over 0, dead targets 11 [hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #425000: event 0x100d6c800c mode 0 value 295759 (now 295740) (lr 0x80660e38) [hos host] vk: replay reads of guest memory as submitted: 8080000 (4070293 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.01, scan 0.04 over 875 ranges, 3015 MB), 211 pages written, 211 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.009; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (104 MB), 10 spare buffers, 5390 texture pages copied (21 MB) [hos host] vk: replay reads of guest memory as submitted: 8100000 (4082286 pages from the captures) [hos host] vk: program picks: 11854656 kept (4297331 by the last picks' textures, a uniform buffer bound since), 70701 new, 5074642 with other textures (of 17000000) [hos host] vk: (its written part: 1 of 1 KB readable, 936 bytes not zero; levels L0) [hos host] vk: texture 0x111b321c00 3064x2656x1 x1 levels 1 NVN 0x4b (7968 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 1 KB of it [hos host] vk: (its written part: 1 of 1 KB readable, 936 bytes not zero; levels L0) [hos host] vk: texture 0x111b321c00 3064x2656x1 x1 levels 1 NVN 0x4b (7968 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 1 KB of it [hos host] vk: sparse mirrors: 74, 984 MB with memory of 1464 MB (479 MB spared); blocks given memory later 4189, given back 12560; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20850; 643 binds (156.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 128 made new; 185 kept as spares, 0 destroyed; 54 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3674 dirty pages from their submits' captures, 59664 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): 1159 dispatches, 45545 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6711 runs, 890.7 MB compared; 134 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19384 in captures, 0 only in the collection, 50 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 152 live (2460 MB), 0 retired still imported (0 MB), 47 retired given back (1364 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6394 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 1 textures retired (4783 left, 9067 MB): budget 0, drawn over 1, dead targets 0 [hos tera::FileResourceMgr] vcores: 135198 takes, 25652 waits (mean 77 us, longest 12.1 ms, 0 over HOS_VCORE_LOG_MS), 11486 kicks, 11764 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 8120000 (4094334 pages from the captures) [hos ModuleSystemWorker2] nvn: 2150000 recordings made, 67906 live copies (19.8 MB), 3887 texture copies; 5 command buffers' segments (4.2 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 12 textures retired (4783 left, 9067 MB): budget 0, drawn over 1, dead targets 11 [hos host] vk: 2 textures retired (4783 left, 9067 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1050, 5150.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3633 dirty pages from their submits' captures, 60242 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): 1161 dispatches, 45922 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6719 runs, 889.7 MB compared; 118 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 19319 in captures, 0 only in the collection, 49 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8140000 (4106366 pages from the captures) [hos host] vk: present 28316 written to <data>/jobs/jb_19e624f98a68503c/runs/three-areas-g0-02-pr/shots/three-areas-c0-pr-02-market-turned.png (the control bridge) [hos host] vk: 1 textures retired (4782 left, 9056 MB): budget 0, drawn over 1, dead targets 0 [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: 26 program records loaded (7.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 6027 queued, 6027 loaded (median 0.16 ms, 99th percentile 2.62 ms, worst 120.85 ms, 2146 ms and 1393.3 MB read in all); 8777 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 10846 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2123 pipelines made at create taken by draws; 2770 create calls with nothing kept for their stages, 0 before the index; units 8797 (6027 ready, 0 loading), 14428 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (close): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before) [hos host] vk: indexed descriptor arrays (close): 2631 in 2631 of 55777 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 2631 texture (17-64: 2631); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4257 pools in the table now) [hos host] control: exiting [hos host] stop: close work done (a file the game was writing waited for, at most 3 s)