Report rp_a0498857d73064d9 fail
Run off target. The tester ran this test by hand on a PC that doesn't match linux+intel, so it doesn't count toward that target's result.
Machine
- Commit
- 78d325922c048ed85fa8ac8660022ca070f494ae
- Baseline
- d5794c82dfa44fd35c041f2dabc919d0ce85a591
- App
- nightly-180-9c109b28, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 5 9600X 6-Core Processor
- gpu
- NVIDIA GeForce RTX 5070
- tags
- linuxnvidianvidia-proprietarydgpu
- driver
- 620.70.6
- ram_gb
- 32
- vram_mb
- 12,227
- gpu_vendor
- nvidia
- os_version
- CachyOS (kernel 7.3.5)
Builds
main (baseline)
530.3 s warm
from d5794c82dfa4
- lift
- 70 s
- read
- 1.2 s
- finish
- 10.1 s
- compile
- 354.6 s
- shaders
- 89.8 s
PR
21.5 s warm
Program cache: warm
Scenarios
recorder-scenes
ok| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| run_hitch_count | 14 | 14.5 | +3.6% |
| log_forbidden_hits | 0 | 0 | ±0% |
| field-still.fps_mean | 106.07 | 103.61 | −2.3% |
| log_expected_missing | 1 | 1 | ±0% |
| run_frametime_max_ms | 4,940.94 | 10,437.94 | +111.3% |
| kokiri-still.fps_mean | 97.75 | 97.55 | −0.2% |
| market-still.fps_mean | 84.95 | 81.61 | −3.9% |
| field-still.draws_mean | 1,198.6 | 1,191.15 | −0.6% |
| field-still.hitch_count | 0 | 0 | ±0% |
| kokiri-still.draws_mean | 700.8 | 694.9 | −0.8% |
| market-still.draws_mean | 2,451.35 | 2,501.1 | +2% |
| kokiri-still.hitch_count | 0 | 0 | ±0% |
| market-still.hitch_count | 0 | 0 | ±0% |
| field-after-turn.fps_mean | 109.47 | 109.65 | +0.2% |
| field-still.stutter_count | 0 | 0 | ±0% |
| kokiri-after-turn.fps_mean | 106.62 | 105.38 | −1.2% |
| kokiri-still.stutter_count | 1 | 0 | −100% |
| market-after-turn.fps_mean | 89.97 | 89.33 | −0.7% |
| market-still.stutter_count | 0 | 0 | ±0% |
| field-after-turn.draws_mean | 1,015.05 | 928.75 | −8.5% |
| field-after-turn.hitch_count | 0 | 0 | ±0% |
| field-still.frametime_max_ms | 13.47 | 14.68 | +9% |
| field-still.frametime_p50_ms | 9.19 | 9.37 | +2% |
| field-still.frametime_p99_ms | 11.61 | 13.05 | +12.4% |
| kokiri-after-turn.draws_mean | 678.2 | 668.35 | −1.5% |
| market-after-turn.draws_mean | 1,839.25 | 2,020.6 | +9.9% |
| kokiri-after-turn.hitch_count | 0 | 0 | ±0% |
| kokiri-still.frametime_max_ms | 19.06 | 17.38 | −8.8% |
| kokiri-still.frametime_p50_ms | 9.95 | 9.98 | +0.4% |
| kokiri-still.frametime_p99_ms | 14.34 | 14.39 | +0.4% |
| market-after-turn.hitch_count | 0 | 0 | ±0% |
| market-still.frametime_max_ms | 20.76 | 19.65 | −5.4% |
| market-still.frametime_p50_ms | 11.59 | 11.91 | +2.7% |
| market-still.frametime_p99_ms | 16.34 | 16.73 | +2.4% |
| field-after-turn.stutter_count | 0 | 0 | ±0% |
| kokiri-after-turn.stutter_count | 0 | 0 | ±0% |
| market-after-turn.stutter_count | 0 | 0 | ±0% |
| field-after-turn.frametime_max_ms | 15.44 | 15.25 | −1.2% |
| field-after-turn.frametime_p50_ms | 9.01 | 9.02 | +0% |
| field-after-turn.frametime_p99_ms | 11.51 | 13.17 | +14.4% |
| field-still.frametime_1pct_low_ms | 12.22 | 13.6 | +11.3% |
| kokiri-after-turn.frametime_max_ms | 14.05 | 14.56 | +3.6% |
| kokiri-after-turn.frametime_p50_ms | 9.32 | 9.44 | +1.3% |
| kokiri-after-turn.frametime_p99_ms | 12.06 | 12.37 | +2.6% |
| kokiri-still.frametime_1pct_low_ms | 15.45 | 15.1 | −2.3% |
| market-after-turn.frametime_max_ms | 19.03 | 18.2 | −4.4% |
| market-after-turn.frametime_p50_ms | 10.93 | 11.11 | +1.6% |
| market-after-turn.frametime_p99_ms | 14.89 | 14.6 | −2% |
| market-still.frametime_1pct_low_ms | 18.05 | 17.8 | −1.4% |
| field-after-turn.frametime_1pct_low_ms | 12.35 | 13.76 | +11.4% |
| kokiri-after-turn.frametime_1pct_low_ms | 12.51 | 13.2 | +5.5% |
| market-after-turn.frametime_1pct_low_ms | 16.34 | 15.47 | −5.4% |
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 | 21 | 22 | 7 | 7 |
| log_forbidden_hits | 0 | 0 | 0 | 0 |
| field-still.fps_mean | 104.19 | 100.44 | 106.79 | 107.95 |
| log_expected_missing | 1 | 1 | 1 | 1 |
| run_frametime_max_ms | 9,769.8 | 20,767.33 | 108.55 | 112.09 |
| kokiri-still.fps_mean | 87.89 | 89.32 | 105.77 | 107.62 |
| market-still.fps_mean | 83.84 | 78.99 | 84.24 | 86.07 |
| field-still.draws_mean | 1,203.8 | 1,189.4 | 1,192.9 | 1,193.4 |
| field-still.hitch_count | 0 | 0 | 0 | 0 |
| kokiri-still.draws_mean | 654.1 | 646.5 | 743.3 | 747.5 |
| market-still.draws_mean | 2,447.2 | 2,566.9 | 2,435.3 | 2,455.5 |
| kokiri-still.hitch_count | 0 | 0 | 0 | 0 |
| market-still.hitch_count | 0 | 0 | 0 | 0 |
| field-after-turn.fps_mean | 102.19 | 99.55 | 119.75 | 116.75 |
| field-still.stutter_count | 0 | 0 | 0 | 0 |
| kokiri-after-turn.fps_mean | 96.55 | 96.02 | 114.74 | 116.69 |
| kokiri-still.stutter_count | 2 | 0 | 0 | 0 |
| market-after-turn.fps_mean | 94.77 | 94.99 | 83.66 | 85.18 |
| market-still.stutter_count | 0 | 0 | 0 | 0 |
| field-after-turn.draws_mean | 1,269.7 | 1,110 | 747.5 | 760.4 |
| field-after-turn.hitch_count | 0 | 0 | 0 | 0 |
| field-still.frametime_max_ms | 13.71 | 16.64 | 12.71 | 13.23 |
| field-still.frametime_p50_ms | 9.32 | 9.6 | 9.15 | 9.06 |
| field-still.frametime_p99_ms | 11.72 | 14.32 | 11.77 | 11.5 |
| kokiri-after-turn.draws_mean | 793.2 | 766 | 570.7 | 563.2 |
| market-after-turn.draws_mean | 1,340.4 | 1,600 | 2,441.2 | 2,338.1 |
| kokiri-after-turn.hitch_count | 0 | 0 | 0 | 0 |
| kokiri-still.frametime_max_ms | 24.56 | 20.76 | 14 | 13.57 |
| kokiri-still.frametime_p50_ms | 10.65 | 10.55 | 9.41 | 9.24 |
| kokiri-still.frametime_p99_ms | 17.3 | 17.24 | 11.55 | 11.38 |
| market-after-turn.hitch_count | 0 | 0 | 0 | 0 |
| market-still.frametime_max_ms | 19.57 | 21.43 | 17.87 | 21.96 |
| market-still.frametime_p50_ms | 11.76 | 12.14 | 11.67 | 11.42 |
| market-still.frametime_p99_ms | 17.17 | 18.08 | 15.38 | 15.5 |
| field-after-turn.stutter_count | 0 | 0 | 0 | 0 |
| kokiri-after-turn.stutter_count | 0 | 0 | 0 | 0 |
| market-after-turn.stutter_count | 0 | 0 | 0 | 0 |
| field-after-turn.frametime_max_ms | 16.05 | 17.98 | 12.53 | 14.82 |
| field-after-turn.frametime_p50_ms | 9.63 | 9.74 | 8.29 | 8.4 |
| field-after-turn.frametime_p99_ms | 12.36 | 15.91 | 10.43 | 10.66 |
| field-still.frametime_1pct_low_ms | 12.45 | 14.99 | 12.2 | 11.99 |
| kokiri-after-turn.frametime_max_ms | 15.88 | 15.8 | 13.32 | 12.21 |
| kokiri-after-turn.frametime_p50_ms | 10.18 | 10.26 | 8.62 | 8.45 |
| kokiri-after-turn.frametime_p99_ms | 12.96 | 13.01 | 11.73 | 11.16 |
| kokiri-still.frametime_1pct_low_ms | 18.87 | 18.18 | 12.02 | 12.04 |
| market-after-turn.frametime_max_ms | 17.47 | 16.75 | 19.64 | 20.58 |
| market-after-turn.frametime_p50_ms | 10.24 | 10.28 | 11.93 | 11.62 |
| market-after-turn.frametime_p99_ms | 13.83 | 13.04 | 16.16 | 15.95 |
| market-still.frametime_1pct_low_ms | 18.31 | 19.28 | 16.32 | 17.8 |
| field-after-turn.frametime_1pct_low_ms | 13.23 | 16.62 | 10.91 | 11.48 |
| kokiri-after-turn.frametime_1pct_low_ms | 13.59 | 14.17 | 12.24 | 11.42 |
| market-after-turn.frametime_1pct_low_ms | 15.04 | 13.76 | 17.17 | 17.64 |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| recorder-scenes | crash | False | 0 | 0 | — | pass | |
| recorder-scenes | kokiri-still.fps_mean.min_delta_pct | 0 | 97.75 | 97.55 | −0.2% | fail | |
| recorder-scenes | kokiri-after-turn.fps_mean.min_delta_pct | 0 | 106.62 | 105.38 | −1.2% | fail | |
| recorder-scenes | field-still.fps_mean.min_delta_pct | 0 | 106.07 | 103.61 | −2.3% | fail | |
| recorder-scenes | field-after-turn.fps_mean.min_delta_pct | 0 | 109.47 | 109.65 | +0.2% | pass | |
| recorder-scenes | market-still.fps_mean.min_delta_pct | 0 | 84.95 | 81.61 | −3.9% | fail | |
| recorder-scenes | market-after-turn.fps_mean.min_delta_pct | 0 | 89.97 | 89.33 | −0.7% | fail | |
| recorder-scenes | kokiri-still.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | kokiri-after-turn.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | field-still.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | field-after-turn.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | market-still.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | market-after-turn.hitch_count.max_delta_pct | 0 | 0 | 0 | ±0% | pass | |
| recorder-scenes | log_forbidden_hits.max | 0 | 0 | 0 | — | pass | |
| recorder-scenes | log_expected_missing.max | 0 | 1 | 1 | — | fail |
Log (PR side, end)
[hos host] vk: host time in GPU resource waits: 1.39 ms a frame (fences 0.01, timelines 1.38, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 399.1 full barriers recorded, 196.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.7; 0x12: 76.5; 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 3.0 ms); 0.5 textures made a frame [hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 7220000 (3889230 pages from the captures) [hos host] vk: sparse mirrors: 103, 1152 MB with memory of 1880 MB (727 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 16944; 613 binds (46.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 141 kept as spares, 0 destroyed; 12 spares now, 788 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 676 dirty pages from their submits' captures, 37708 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): 743 dispatches, 29011 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4140 runs, 562.9 MB compared; 55 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9917 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: mirror of pool 0x105b800000 (4 MB) given back: idle, 6061 submissions since its sync [hos host] vk: mirror of pool 0x7fbb800000 (8 MB) given back: idle, 6001 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 7240000 (3903000 pages from the captures) [hos host] vk: program picks: 10767293 kept (3935875 by the last picks' textures, a uniform buffer bound since), 2485 new, 4230221 with other textures (of 15000000) [hos sead::MainThread] nvn: CommandBufferWaitEvent #340000: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444) [hos host] vk: replay reads of guest memory as submitted: 7260000 (3916997 pages from the captures) [hos host] vk: mirror of pool 0x105c000000 (4 MB) given back: idle, 6029 submissions since its sync [hos host] vk: mirror of pool 0x105cc00000 (4 MB) given back: idle, 6001 submissions since its sync [hos host] vk: 145 mirrors given back (1468 MB in all); 1144 MB of mirrors now, 112 MB of them idle and kept for what the GPU wrote there alone [hos host] vk: mirror of pool 0x105c400000 (4 MB) given back: idle, 6024 submissions since its sync [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 730 dirty pages from their submits' captures, 37514 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): 739 dispatches, 28900 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4144 runs, 562.3 MB compared; 57 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9603 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: mirror of pool 0x7fbd000000 (4 MB) given back: idle, 6053 submissions since its sync [hos host] vk: mirror of pool 0x7f88000000 (4 MB) given back: idle, 6029 submissions since its sync [hos host] vk: mirror of pool 0x7f5dc00000 (36 MB) given back: idle, 6035 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 7280000 (3930923 pages from the captures) [hos host] vk: mirror of pool 0x7f72800000 (20 MB) given back: idle, 6041 submissions since its sync [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 905 ranges, 3360 MB), 219 pages written, 219 copied (0.9 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 0.006, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 4612 texture pages copied (18 MB) [hos host] vk: render targets drawn over from another start, let go: 5121 so far (19890 MB), 4457 of them (17423 MB) between the passes [hos host] vk: replay reads of guest memory as submitted: 7300000 (3944876 pages from the captures) [hos sead::MainThread] vk: readbacks of GPU results: 1299 of 3000 waited for their write-back, 0.09 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: 8852 kept their virtual core (nothing there to wait for), 2924 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: sparse mirrors: 94, 1132 MB with memory of 1792 MB (659 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17316; 620 binds (47.4 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 150 kept as spares, 0 destroyed; 21 spares now, 876 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 698 dirty pages from their submits' captures, 37705 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): 746 dispatches, 29001 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4140 runs, 561.7 MB compared; 54 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9957 in captures, 2 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7320000 (3958789 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos host] vk: 1 textures retired (2395 left, 3713 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: readback pages refreshed from guest memory: 3770341 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 7340000 (3972668 pages from the captures) [hos host] vk: 1 textures retired (2394 left, 3707 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 598 dirty pages from their submits' captures, 37881 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): 749 dispatches, 29079 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4116 runs, 559.6 MB compared; 57 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 10261 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #240000: event 0x100d6c8000 mode 0 value 239999 (lr 0x80291440) [hos host] vk: replay reads of guest memory as submitted: 7360000 (3986603 pages from the captures) [hos host] vk: program picks: 10919046 kept (3991095 by the last picks' textures, a uniform buffer bound since), 2485 new, 4278468 with other textures (of 15200000) [hos host] vk: mirror of pool 0x7f67000000 (12 MB) given back: idle, 6061 submissions since its sync [hos NavMeshCAStepDepWorker1] vcores: 156332 takes, 33462 waits (mean 66 us, longest 11.6 ms, 0 over HOS_VCORE_LOG_MS), 15050 kicks, 14908 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 7380000 (4000579 pages from the captures) [hos host] vk: a frame: 393 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 8.64, present 0.15, draw 5.68, descriptors 1.61, texture lookups 0.12, uploads 0.02, pipelines 0.21, programs 0.78, commands 2.69, dispatch 0.70, memory sync 0.21, queue submit 0.24, slot wait 0.02 [hos host] vk: a frame: mirrors 244 (1132 MB): 4.84 MB synced in 936.1 copies, 18.13 MB written back [hos host] vk: 21840 presents, 83.9 fps; a frame: 2413 draws (0 skipped), 113 dispatches, 148 passes, 143 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (3728717 ms), 0 programs (0 failed), 2395 textures (3714 MB) [hos host] vk: host time in GPU resource waits: 1.31 ms a frame (fences 0.01, timelines 1.30, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 397.8 full barriers recorded, 196.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.6; 0x12: 76.5; 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 3.3 ms); 0.3 textures made a frame [hos host] vk: a frame: 0.01 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: 1 textures retired (2394 left, 3708 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 362 KB; 0 made on demand (0 MB kept now); c1 stages: at most 101 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 93, 1132 MB with memory of 1780 MB (647 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17688; 621 binds (47.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 151 kept as spares, 0 destroyed; 22 spares now, 888 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 470 dirty pages from their submits' captures, 37973 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): 745 dispatches, 29060 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4144 runs, 563.6 MB compared; 56 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9924 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7400000 (4014483 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 17519 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: mirror of pool 0x7f85000000 (16 MB) given back: idle, 6062 submissions since its sync [hos host] vk: mirror of pool 0x1057c00000 (4 MB) given back: idle, 6060 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 7420000 (4028384 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 905 ranges, 3382 MB), 229 pages written, 229 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.010, bytes copied 0.000; 25 kept (92 MB), 12 spare buffers, 8218 texture pages copied (32 MB) [hos host] vk: mirror of pool 0x7f7f400000 (4 MB) given back: idle, 6038 submissions since its sync [hos host] vk: mirror of pool 0x7f87c00000 (4 MB) given back: idle, 6005 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 7440000 (4042372 pages from the captures) [hos host] vk: 1 textures retired (2404 left, 3724 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 678 dirty pages from their submits' captures, 37898 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): 751 dispatches, 29161 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4145 runs, 562.3 MB compared; 55 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9966 in captures, 0 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: mirror of pool 0x7f81c00000 (12 MB) given back: idle, 6021 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 7460000 (4056273 pages from the captures) [hos host] vk: mirror of pool 0x7f86c00000 (4 MB) given back: idle, 6062 submissions since its sync [hos host] vk: mirror of pool 0x7f83000000 (8 MB) given back: idle, 6047 submissions since its sync [hos host] vk: mirror of pool 0x7fb1400000 (16 MB) given back: idle, 6042 submissions since its sync [hos host] vk: mirror of pool 0x1042800000 (4 MB) given back: idle, 6020 submissions since its sync [hos host] vk: mirror of pool 0x7fb2400000 (4 MB) given back: idle, 6020 submissions since its sync [hos host] vk: mirror of pool 0x7fb2800000 (32 MB) given back: idle, 6005 submissions since its sync [hos host] vk: mirror of pool 0x7f95800000 (20 MB) given back: idle, 6003 submissions since its sync [hos host] vk: 163 mirrors given back (1568 MB in all); 1043 MB of mirrors now, 112 MB of them idle and kept for what the GPU wrote there alone [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos host] vk: mirror of pool 0x7fb5400000 (32 MB) given back: idle, 6049 submissions since its sync [hos host] vk: mirror of pool 0x7f88400000 (8 MB) given back: idle, 6046 submissions since its sync [hos host] vk: mirror of pool 0x7fe2c00000 (4 MB) given back: idle, 6008 submissions since its sync [hos host] vk: mirror of pool 0x7f78c00000 (4 MB) given back: idle, 6007 submissions since its sync [hos host] vk: mirror of pool 0x7f94800000 (16 MB) given back: idle, 6005 submissions since its sync [hos host] vk: mirror of pool 0x7f98000000 (4 MB) given back: idle, 6005 submissions since its sync [hos host] vk: mirror of pool 0x7f9cc00000 (8 MB) given back: idle, 6005 submissions since its sync [hos host] vk: program picks: 11070353 kept (4046357 by the last picks' textures, a uniform buffer bound since), 2485 new, 4327161 with other textures (of 15400000) [hos host] vk: replay reads of guest memory as submitted: 7480000 (4070223 pages from the captures) [hos host] vk: 1 textures retired (2407 left, 3718 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: sparse mirrors: 74, 993 MB with memory of 1576 MB (582 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18060; 627 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 41 spares now, 1092 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 699 dirty pages from their submits' captures, 37528 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): 738 dispatches, 28896 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4143 runs, 563.0 MB compared; 56 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9942 in captures, 0 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: 1 textures retired (2406 left, 3712 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7500000 (4084080 pages from the captures) [hos ModuleSystemWorker5] nvn: 1800000 recordings made, 67120 live copies (22.9 MB), 3433 texture copies; 4 command buffers' segments (4.2 MB) [hos host] vk: replay reads of guest memory as submitted: 7520000 (4098068 pages from the captures) [hos sead::MainThread] vk: readbacks of GPU results: 1287 of 3000 waited for their write-back, 0.10 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: 8795 kept their virtual core (nothing there to wait for), 2981 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 560 dirty pages from their submits' captures, 38013 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): 755 dispatches, 29123 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4151 runs, 562.4 MB compared; 56 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9951 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] nvn: CommandBufferWaitEvent #345000: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444) [hos host] vk: replay reads of guest memory as submitted: 7540000 (4112019 pages from the captures) [hos Presentation Thread] vi: 21956 frames presented (82.6 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 409, 15.5-17.8 3, 17.8-22 2, 22-30 0, 30-40 0, over 40 0 [hos host] vk: readback pages refreshed from guest memory: 3843424 pages so far (0 held: may be written ahead in their submission) [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 906 ranges, 3388 MB), 217 pages written, 217 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.013; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 24 kept (78 MB), 12 spare buffers, 6542 texture pages copied (25 MB) [hos host] vk: a frame: 393 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 9.03, present 0.17, draw 5.92, descriptors 1.70, texture lookups 0.20, uploads 0.05, pipelines 0.27, programs 0.86, commands 2.70, dispatch 0.73, memory sync 0.25, queue submit 0.33, slot wait 0.02 [hos host] vk: a frame: mirrors 244 (993 MB): 4.84 MB synced in 936.3 copies, 18.15 MB written back [hos host] vk: 21960 presents, 80.7 fps; a frame: 2414 draws (0 skipped), 113 dispatches, 148 passes, 143 barriers, 6 submits, 0.6 uploads (0.2 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (3728717 ms), 0 programs (0 failed), 2419 textures (3715 MB) [hos host] vk: host time in GPU resource waits: 1.51 ms a frame (fences 0.01, timelines 1.50, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 397.9 full barriers recorded, 196.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.9; 0x12: 76.5; 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 3.2 ms); 0.6 textures made a frame [hos host] vk: a frame: 0.21 MB unswizzled on the CPU in 0.01 ms [hos host] vk: replay reads of guest memory as submitted: 7560000 (4125995 pages from the captures) [hos ModuleSystemWorker1] tex: the game's texture heap: 140 compaction rounds asked for in 21600 frames without one running [hos host] vk: sparse mirrors: 74, 993 MB with memory of 1576 MB (582 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18432; 627 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 41 spares now, 1092 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 709 dirty pages from their submits' captures, 37658 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): 744 dispatches, 29019 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4145 runs, 562.4 MB compared; 58 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9926 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7580000 (4139886 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 6 pages in 6 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: program picks: 11221794 kept (4101509 by the last picks' textures, a uniform buffer bound since), 2485 new, 4375720 with other textures (of 15600000) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4852 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 1 textures retired (2418 left, 3709 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7600000 (4153757 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 host] vk: the recording streams: 48 of 2 MB, the most one held 362 KB; 0 made on demand (0 MB kept now); c1 stages: at most 101 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 742 dirty pages from their submits' captures, 37643 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): 746 dispatches, 28980 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4154 runs, 562.4 MB compared; 57 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9924 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 7620000 (4167698 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 7640000 (4181680 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 7660000 (4195565 pages from the captures) [hos host] vk: sparse mirrors: 74, 993 MB with memory of 1576 MB (582 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18810; 627 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 41 spares now, 1092 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 504 dirty pages from their submits' captures, 38533 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): 750 dispatches, 29622 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4275 runs, 579.2 MB compared; 57 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9940 in captures, 1 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7680000 (4209478 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.03 over 906 ranges, 3388 MB), 218 pages written, 218 copied (0.9 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 0.004, bytes copied 0.000; 24 kept (96 MB), 12 spare buffers, 6640 texture pages copied (25 MB) [hos host] vk: 1 textures retired (2422 left, 3722 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7700000 (4223479 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 249 sync waits (228 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: program picks: 11373324 kept (4156576 by the last picks' textures, a uniform buffer bound since), 2485 new, 4424190 with other textures (of 15800000) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 706 dirty pages from their submits' captures, 36644 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): 726 dispatches, 28173 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4009 runs, 544.0 MB compared; 53 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9613 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 7720000 (4237419 pages from the captures) [hos host] vk: a frame: 393 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 8.65, present 0.14, draw 5.67, descriptors 1.58, texture lookups 0.09, uploads 0.00, pipelines 0.22, programs 0.85, commands 2.63, dispatch 0.72, memory sync 0.20, queue submit 0.20, slot wait 0.02 [hos host] vk: a frame: mirrors 244 (993 MB): 4.85 MB synced in 936.7 copies, 18.14 MB written back [hos host] vk: 22080 presents, 84.1 fps; a frame: 2420 draws (0 skipped), 113 dispatches, 148 passes, 143 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (3728717 ms), 0 programs (0 failed), 2423 textures (3722 MB) [hos host] vk: host time in GPU resource waits: 1.08 ms a frame (fences 0.01, timelines 1.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 397.9 full barriers recorded, 196.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.6; 0x12: 76.5; 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 3.3 ms); 0.1 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #245000: event 0x100d6c8010 mode 0 value 245000 (lr 0x80660adc) [hos host] vk: replay reads of guest memory as submitted: 7740000 (4251321 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1315 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 8984 kept their virtual core (nothing there to wait for), 3048 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: sparse mirrors: 74, 993 MB with memory of 1576 MB (582 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19176; 627 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 41 spares now, 1092 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 726 dirty pages from their submits' captures, 37994 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): 744 dispatches, 29133 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4129 runs, 560.6 MB compared; 49 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9923 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos host] vk: replay reads of guest memory as submitted: 7760000 (4265231 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 3916727 pages so far (0 held: may be written ahead in their submission) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 7780000 (4279123 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7633 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 850 dirty pages from their submits' captures, 36919 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): 743 dispatches, 28434 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 3999 runs, 544.7 MB compared; 56 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9917 in captures, 1 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 7800000 (4293020 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 907 ranges, 3398 MB), 211 pages written, 211 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; 25 kept (104 MB), 9 spare buffers, 6648 texture pages copied (25 MB) [hos host] vk: program picks: 11524815 kept (4211674 by the last picks' textures, a uniform buffer bound since), 2485 new, 4472699 with other textures (of 16000000) [hos host] vk: replay reads of guest memory as submitted: 7820000 (4306979 pages from the captures) [hos sead::MainThread] nvn: CommandBufferWaitEvent #350000: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444) [hos host] vk: 2 textures retired (2443 left, 3814 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: texture slots registered again at another size: 800000 (of 998312 registrations; slot 2654 1920x1080 -> 480x270) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 362 KB; 0 made on demand (0 MB kept now); c1 stages: at most 101 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 74, 993 MB with memory of 1576 MB (582 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19548; 627 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 129 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 41 spares now, 1092 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 623 dirty pages from their submits' captures, 38420 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): 751 dispatches, 29600 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4261 runs, 578.0 MB compared; 54 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9934 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7840000 (4320714 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 7860000 (4334358 pages from the captures) [hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 560000 so far (x1 0x117da08010 x2 0 x3 0x117da08000 x4 0x9b040) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 681 dirty pages from their submits' captures, 36578 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): 722 dispatches, 28106 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 3988 runs, 542.1 MB compared; 52 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9633 in captures, 1 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 7880000 (4348013 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 host] vk: memory: working set 20858 MB (peak 20866), private 11515 MB, staging 48 MB in 3 arenas, 45 made so far (11 ms) [hos host] vk: memory heaps: heap 0 (device): 212 blocks 6370 MB, 18589 allocations 5441 MB; used 7140 of 9969 MB; heap 1 (system): 13 blocks 928 MB, 39 allocations 851 MB; used 3356 of 23390 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB [hos host] vk: image blocks (render targets): 33 blocks 1056 MB, 163 images 458 MB; 90 free ranges, the largest 32 MB [hos host] vk: image blocks (textures, compacted): 92 blocks 2944 MB, 2283 images 2788 MB; 1261 free ranges, the largest 21 MB [hos host] vk: render target images: 2807 reused from the pool, 3606 made new, 3439 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 7140 MB used of 9969 MB allowed (928 MB of it free in the blocks); textures 3845 MB (budget 7132 MB), 2453 textures [hos host] vk: budget: VRAM 6370 of 9969 MB (7140 MB by the driver, 770 MB unaccounted): textures 3845, mirrors 993, blocks free 928, shadows 372, other buffers 154, staging 48, other images 28; RAM 3293 MB (the process's private memory 11515 MB): imports 2408, capture spares 752, captures 86, capture table 34, other buffers 13, others 0 [hos host] vk: textures: decoded ASTC 1920 MB, rendered 1053 MB (49 drawn in one frame, kept: 34009 KB), other 630 MB; used in the last 8 presents 2129 MB [hos host] vk: decoded ASTC used again: 369 textures (838 MB) copied from ones the game finalized, not decoded; 369 of those retired, 50 listed; 1210 MB of blocks hashed in 67 ms [hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x10002d97a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 707 presents ago [hos host] vk: 37 MB: 0x110a997e00 1800x1380x1 x8 levels 1 NVN 0x6, last used 5255 presents ago [hos host] vk: 32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 31 MB: 0x111cc23000 1775x1175x1 x8 levels 1 NVN 0x6, 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): 324 waited for it, 0.96 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 19.7 ms; VRAM 7.0 of 9.7 GB [hos host] vk: a frame: 396 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 8.81, present 0.18, draw 5.79, descriptors 1.73, texture lookups 0.17, uploads 0.02, pipelines 0.21, programs 0.80, commands 2.65, dispatch 0.73, memory sync 0.23, queue submit 0.19, slot wait 0.02 [hos host] vk: a frame: mirrors 245 (993 MB): 4.86 MB synced in 937.0 copies, 18.07 MB written back [hos host] vk: 22200 presents, 82.9 fps; a frame: 2422 draws (0 skipped), 114 dispatches, 148 passes, 143 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (3728717 ms), 0 programs (0 failed), 2455 textures (3845 MB) [hos host] vk: host time in GPU resource waits: 1.22 ms a frame (fences 0.01, timelines 1.21, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 398.9 full barriers recorded, 196.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 7.1 ms a frame (the longest submission 3.6 ms); 0.5 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's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making [hos host] vk: the render thread (600 presents, 12.06 ms a frame): its jobs 9.26 ms a frame (submits 3.96, presents 0.19, others 5.12), idle 2.80; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 151.18 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); 368 captures at a CPU signal; the submits' waits read in 0.040 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 9.29 ms after its hand-over (16.18 at most) [hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 1.88 + 0.38 (the window's copy is in the idle), after it 2.22 + 0.59; after a frame's last recording that reads or writes the game's memory come 1.01 recordings (0.02 ms of GPU time), after its last that reads it 1.01 (0.02 ms) [hos host] vk: frame ahead (600 presents): 12.68 parts a frame recorded in the signal's job, 85.0% of them took nothing that came with the signal; of the others, 1.90 a frame took pages of the signal's capture into a mirror (34.0 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 13 of 368 frames, its first three in 13 [hos host] vk: frame ahead, what came with the signal: 368 signals with a capture, each of 111.1 pages in 12.0 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: 0.29+0.07, 0.19+0.05, 0.11+0.03, 0.25+0.03, 0.85+0.14, 0.22+0.06, 0.18+0.05, 0.02+0.03, 0.02+0.02, 0.02+0.02, 0.03+0.03, 0.04+0.06 [hos host] vk: replay reads of guest memory as submitted: 7900000 (4361727 pages from the captures) [hos host] vk: 2 textures retired (2453 left, 3833 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: 1 textures retired (2452 left, 3827 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: sparse mirrors: 75, 993 MB with memory of 1580 MB (586 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19914; 628 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 130 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 40 spares now, 1088 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 593 dirty pages from their submits' captures, 37926 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): 744 dispatches, 29104 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4136 runs, 558.1 MB compared; 54 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9984 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: replay reads of guest memory as submitted: 7920000 (4375334 pages from the captures) [hos host] vk: program picks: 11676588 kept (4267083 by the last picks' textures, a uniform buffer bound since), 2488 new, 4520923 with other textures (of 16200000) [hos rmbl::VibrationThread] hid: 28672 vibration values, strongest 0.00 since the last count [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 907 ranges, 3406 MB), 226 pages written, 226 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.014; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 8246 texture pages copied (32 MB) [hos host] vk: replay reads of guest memory as submitted: 7940000 (4389022 pages from the captures) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 1331 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 3 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: 9221 kept their virtual core (nothing there to wait for), 3067 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos ModuleSystemWorker1] vcores: 145352 takes, 29866 waits (mean 73 us, longest 16.1 ms, 0 over HOS_VCORE_LOG_MS), 13226 kicks, 13309 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: 1 textures retired (2453 left, 3833 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 768 dirty pages from their submits' captures, 37767 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): 742 dispatches, 29087 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4114 runs, 556.4 MB compared; 50 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9981 in captures, 0 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 7960000 (4402671 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: 3 textures retired (2450 left, 3815 MB): budget 0, drawn over 3, dead targets 0 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 10283 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: readback pages refreshed from guest memory: 3989394 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 7980000 (4416326 pages from the captures) [hos host] vk: 1 textures retired (2449 left, 3808 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8000000 (4429950 pages from the captures) [hos host] vk: sparse mirrors: 75, 993 MB with memory of 1580 MB (586 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20280; 628 binds (48.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 130 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 40 spares now, 1088 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 517 dirty pages from their submits' captures, 36890 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): 723 dispatches, 28240 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4015 runs, 540.6 MB compared; 45 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9682 in captures, 1 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: queues ordered by their events: 126000 submissions stopped at a wait, 125998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 353322, not met 0; captures at a CPU event's wait 8829, 0 of them at a wait met on arrival [hos host] vk: 2 textures retired (2448 left, 3796 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8020000 (4443587 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 host] vk: 4 textures retired (2444 left, 3772 MB): budget 0, drawn over 4, dead targets 0 [hos host] vk: program picks: 11828555 kept (4322589 by the last picks' textures, a uniform buffer bound since), 2488 new, 4568956 with other textures (of 16400000) [hos host] vk: 5 textures retired (2439 left, 3742 MB): budget 0, drawn over 5, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8040000 (4457253 pages from the captures) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 362 KB; 0 made on demand (0 MB kept now); c1 stages: at most 101 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 630 dirty pages from their submits' captures, 37378 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): 738 dispatches, 28529 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4015 runs, 539.8 MB compared; 53 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 10018 in captures, 2 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker4] nvn: 1850000 recordings made, 67416 live copies (23.1 MB), 3445 texture copies; 4 command buffers' segments (4.2 MB) [hos host] vk: 1 textures retired (2441 left, 3754 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a frame: 406 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 8.79, present 0.17, draw 5.65, descriptors 1.61, texture lookups 0.11, uploads 0.00, pipelines 0.21, programs 0.79, commands 2.63, dispatch 0.74, memory sync 0.26, queue submit 0.20, slot wait 0.02 [hos host] vk: a frame: mirrors 246 (1000 MB): 4.92 MB synced in 938.7 copies, 17.99 MB written back [hos host] vk: 22320 presents, 82.6 fps; a frame: 2449 draws (0 skipped), 115 dispatches, 149 passes, 143 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (3728717 ms), 0 programs (0 failed), 2441 textures (3754 MB) [hos host] vk: host time in GPU resource waits: 1.19 ms a frame (fences 0.01, timelines 1.17, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 400.4 full barriers recorded, 196.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.7; 0x12: 76.5; 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 3.0 ms); 0.1 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 0.10 ms (lock 0.00, scan 0.03 over 908 ranges, 3408 MB), 224 pages written, 224 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.020; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.014, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 3768 texture pages copied (14 MB) [hos host] vk: replay reads of guest memory as submitted: 8060000 (4470846 pages from the captures) [hos ModuleSystemWorker3] barrier: 383152 looks: 104624 found the masks moved already, 226108 waited until they moved, 52420 for the whole 1 ms (a wait 344 us on average); 164238 wakes [hos host] vk: 1 textures retired (2440 left, 3748 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8080000 (4484512 pages from the captures) [hos host] vk: sparse mirrors: 76, 1000 MB with memory of 1592 MB (591 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20640; 629 binds (48.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 39 spares now, 1076 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 625 dirty pages from their submits' captures, 36232 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): 706 dispatches, 27804 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 3989 runs, 539.4 MB compared; 49 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9352 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #250000: event 0x100d6c8008 mode 0 value 249995 (lr 0x80660f34) [hos sead::MainThread] nvn: CommandBufferWaitEvent #355000: event 0x1006e38000 mode 0 value 1 (now 0) (lr 0x802eb444) [hos host] vk: replay reads of guest memory as submitted: 8100000 (4498160 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 8120000 (4511900 pages from the captures) [hos Presentation Thread] vi: 22372 frames presented (83.2 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 410, 15.5-17.8 6, 17.8-22 0, 22-30 0, 30-40 0, over 40 0 [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 770 dirty pages from their submits' captures, 36577 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): 720 dispatches, 28122 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4012 runs, 539.8 MB compared; 52 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9697 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: render targets drawn over from another start, let go: 5121 so far (19890 MB), 4457 of them (17423 MB) between the passes [hos host] vk: program picks: 11981230 kept (4378175 by the last picks' textures, a uniform buffer bound since), 2488 new, 4616281 with other textures (of 16600000) [hos host] vk: replay reads of guest memory as submitted: 8140000 (4525703 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 1 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos ModuleSystemWorker4] vk: readbacks of GPU results: 1328 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8913 kept their virtual core (nothing there to wait for), 2863 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02 [hos host] vk: replay reads of guest memory as submitted: 8160000 (4539605 pages from the captures) [hos host] vk: sparse mirrors: 76, 1000 MB with memory of 1592 MB (591 MB spared); blocks given memory later 4387, given back 10473; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 21000; 629 binds (48.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 131 taken from the spares, 115 made new; 170 kept as spares, 0 destroyed; 39 spares now, 1076 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 630, 3090.2 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 700 dirty pages from their submits' captures, 37210 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): 735 dispatches, 28496 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4056 runs, 543.2 MB compared; 55 pages read into the shadows; 372 MB of shadows; pages the shadows knew that the CPU wrote: 9994 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 149 live (2408 MB), 0 retired still imported (0 MB), 26 retired given back (900 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 11846 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 1 textures retired (2450 left, 3805 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 8180000 (4553543 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.03 over 909 ranges, 3410 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; 25 kept (98 MB), 8 spare buffers, 4229 texture pages copied (16 MB) [hos host] vk: readback pages refreshed from guest memory: 4062471 pages so far (0 held: may be written ahead in their submission) [hos host] control: quit asked by a client [hos host] vk: indexed descriptor arrays (close): 2610 in 2610 of 52174 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 2610 texture (17-64: 2610); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4264 pools in the table now) [hos host] vk: pipeline cache: play file 17 saved (3016 KB): 10 pipelines, 10 from the driver's cache, 0 compiled; 5 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)