Report rp_9a4f0a6f8dd38bb0 error
This report disagrees with its peers.
field-turn-and-stand run_frametime_max_ms: -85.5% against peers' -20.9% field-turn-and-stand run_hitch_count: -11.1% against peers' -50.0% field-turn-and-stand#1 run_frametime_max_ms: +721.7% against peers' -28.8% field-turn-and-stand#1 run_hitch_count: -71.4% against peers' +28.6% field-turn-and-stand#2 run_frametime_max_ms: -29.4% against peers' +81.3% field-turn-and-stand#2 run_hitch_count: -46.2% against peers' +0.0%
no scenario could be judged: a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)
Machine
- Commit
- 742b053ae6b0a34dca75a574db424c559f22850f
- Baseline
- 068fb8ebe232d455ef48e817702b03ccc62d8520
- App
- nightly-215-8c201c87, attempt 7
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 5 5600X 6-Core Processor
- gpu
- AMD Radeon RX 6600 (RADV NAVI23)
- tags
- linuxamdradvdgpu
- driver
- 26.2.6
- ram_gb
- 64
- vram_mb
- 8,176
- gpu_vendor
- amd
- os_version
- EndeavourOS (kernel 7.3.4)
Builds
main (baseline)
1,321.2 s warm
from 068fb8ebe232
- lift
- 148.4 s
- read
- 4.2 s
- finish
- 38.1 s
- compile
- 896.8 s
- shaders
- 212.5 s
PR
29.8 s warm
Program cache: warm
Scenarios
field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=0 (PR only)
timeout
a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| value_pool_mb | 0 | 0 | ±0% |
| run_hitch_count | 9 | 8 | −11.1% |
| log_forbidden_hits | 0 | 0 | ±0% |
| log_expected_missing | 0 | 0 | ±0% |
| run_frametime_max_ms | 905.79 | 131.62 | −85.5% |
| value_reused_by_size | — | 0 | — |
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | — | — |
| value_pool_mb | 0 | 0 |
| run_hitch_count | 9 | 8 |
| log_forbidden_hits | 0 | 0 |
| log_expected_missing | 0 | 0 |
| run_frametime_max_ms | 905.79 | 131.62 |
| value_reused_by_size | — | 0 |
field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=1 (PR only)
timeout
a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | — | — |
| value_pool_mb | 197 | 0 | −100% |
| run_hitch_count | 35 | 10 | −71.4% |
| standing.fps_mean | 59.2 | — | — |
| log_forbidden_hits | 0 | 0 | ±0% |
| standing.draws_mean | 1,072.7 | — | — |
| log_expected_missing | 0 | 0 | ±0% |
| run_frametime_max_ms | 408.06 | 3,353.17 | +721.7% |
| standing.hitch_count | 1 | — | — |
| standing.vram_mean_mb | 5,117 | — | — |
| standing.vram_peak_mb | 5,117 | — | — |
| standing.stutter_count | 2 | — | — |
| standing.frametime_max_ms | 52.34 | — | — |
| standing.frametime_p50_ms | 16.57 | — | — |
| standing.frametime_p99_ms | 23.52 | — | — |
| standing.frametime_1pct_low_ms | 27.36 | — | — |
| value_reused_by_size | — | 33 | — |
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | — |
| value_pool_mb | 197 | 0 |
| run_hitch_count | 35 | 10 |
| standing.fps_mean | 59.2 | — |
| log_forbidden_hits | 0 | 0 |
| standing.draws_mean | 1,072.7 | — |
| log_expected_missing | 0 | 0 |
| run_frametime_max_ms | 408.06 | 3,353.17 |
| standing.hitch_count | 1 | — |
| value_reused_by_size | — | 33 |
| standing.vram_mean_mb | 5,117 | — |
| standing.vram_peak_mb | 5,117 | — |
| standing.stutter_count | 2 | — |
| standing.frametime_max_ms | 52.34 | — |
| standing.frametime_p50_ms | 16.57 | — |
| standing.frametime_p99_ms | 23.52 | — |
| standing.frametime_1pct_low_ms | 27.36 | — |
field-turn-and-stand RX_VK_TARGET_REUSE_MEMORY=2 (PR only)
timeout
a step ran out of time at step 2 (wait map HyruleField_Child): timeout: not met in time (then the game was in play on KokiriForest_Child)
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| value_pool_mb | 0 | 0 | ±0% |
| run_hitch_count | 13 | 7 | −46.2% |
| log_forbidden_hits | 0 | 0 | ±0% |
| log_expected_missing | 0 | 0 | ±0% |
| run_frametime_max_ms | 162.38 | 114.65 | −29.4% |
| value_reused_by_size | — | 15 | — |
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | — | — |
| value_pool_mb | 0 | 0 |
| run_hitch_count | 13 | 7 |
| log_forbidden_hits | 0 | 0 |
| log_expected_missing | 0 | 0 |
| run_frametime_max_ms | 162.38 | 114.65 |
| value_reused_by_size | — | 15 |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=0 (PR only) | crash | False | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=0 (PR only) | screenshot.max_diff | 0.15 | — | — | — | skippedthe plan has no screenshot probe |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=0 (PR only) | log_forbidden_hits.max | 0 | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=1 (PR only) | crash | False | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=1 (PR only) | screenshot.max_diff | 0.15 | — | — | — | skippedthe plan has no screenshot probe |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=1 (PR only) | log_forbidden_hits.max | 0 | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=2 (PR only) | crash | False | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=2 (PR only) | screenshot.max_diff | 0.15 | — | — | — | skippedthe plan has no screenshot probe |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=2 (PR only) | log_forbidden_hits.max | 0 | 0 | 0 | — | pass |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=1 (PR only) | standing.frametime_p99_ms: RX_VK_TARGET_REUSE_MEMORY=1 vs RX_VK_TARGET_REUSE_MEMORY=0 (PR) | 20 | — | — | — | skippedthe metric was not measured in both cells |
| field-turn-and-stand | RX_VK_TARGET_REUSE_MEMORY=2 (PR only) | standing.frametime_p99_ms: RX_VK_TARGET_REUSE_MEMORY=2 vs RX_VK_TARGET_REUSE_MEMORY=0 (PR) | 20 | — | — | — | skippedthe metric was not measured in both cells |
Pictures of the failure
The last frame of a step that got stuck, or main's and the PR's picture where they differed more than the plan allows; shrunk, and kept a day: until .
Log (PR side, end)
[hos host] vk: host time in GPU resource waits: 5.93 ms a frame (fences 0.00, timelines 5.93, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 457.6 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 10.8 ms a frame (the longest submission 6.4 ms); 0.0 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 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 187 pages written, 187 copied (0.7 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 0.002, bytes copied 0.000; 24 kept (80 MB), 4 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: write-backs left out (600 submits): 1298, 5440.7 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 897 dirty pages from their submits' captures, 68117 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): 1305 dispatches, 53407 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6645 runs, 997.4 MB compared; 119 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26777 in captures, 2 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 1140000 (581508 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos Presentation Thread] vi: 4105 frames presented (52.7 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 28, 15.5-17.8 74, 17.8-22 141, 22-30 17, 30-40 2, over 40 2 [hos host] vk: replay reads of guest memory as submitted: 1160000 (591856 pages from the captures) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 976 of 3000 waited for their write-back, 1.06 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 4114 kept their virtual core (nothing there to wait for), 2798 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1114 dirty pages from their submits' captures, 66911 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): 1284 dispatches, 52624 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6544 runs, 982.5 MB compared; 132 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26380 in captures, 0 only in the collection, 59 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #45000: event 0x100d6c8010 mode 0 value 45002 (lr 0x80660bcc) [hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 185 pages written, 185 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (76 MB), 4 spare buffers, 0 texture pages copied (0 MB) [hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.00 since the last count [hos host] vk: replay reads of guest memory as submitted: 1180000 (602429 pages from the captures) [hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 100000 so far (x1 0x11789a4000 x2 0x1 x3 0x11789a4000 x4 0x4040) [hos ModuleSystemWorker3] barrier: 137326 looks: 22638 found the masks moved already, 38977 waited until they moved, 75711 for the whole 1 ms (a wait 761 us on average); 30504 wakes [hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #65000: event 0x100d6c8038 mode 0 value 45563 (now 45544) (lr 0x80661fac) [hos host] vk: memory: working set 11004 MB (peak 11301), private 5906 MB, staging 32 MB in 2 arenas, 25 made so far (1 ms) [hos host] vk: memory heaps: heap 0 (system): 8 blocks 164 MB, 32 allocations 111 MB; used 1280 of 31523 MB; heap 1 (device): 160 blocks 4153 MB, 14394 allocations 3717 MB; used 4853 of 6331 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 5 images 27 MB; 2 free ranges, the largest 4 MB [hos host] vk: image blocks (render targets): 24 blocks 384 MB, 94 images 239 MB; 28 free ranges, the largest 16 MB [hos host] vk: image blocks (textures, compacted): 33 blocks 1056 MB, 1037 images 918 MB; 131 free ranges, the largest 17 MB [hos host] vk: render target images: 58 reused from the pool, 227 made new, 131 destroyed from it, 15 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=2), 4 missed after their image was taken by size; it holds 0 (0 MB) [hos host] vk: render targets not reused by size: 184 with the pool empty (0 of them with targets still in the dead queue), 19 with none in it a present yet, 0 with none of a kind they can use, 8 with all smaller (the largest 23% short on average), 5 with all bigger (over 1.5 times), 11 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 131 idle [hos host] vk: VRAM: 4853 MB used of 6331 MB allowed (435 MB of it free in the blocks); textures 2335 MB (budget 4715 MB), 1140 textures [hos host] vk: budget: VRAM 4153 of 6331 MB (4853 MB by the driver, 699 MB unaccounted): textures 2335, mirrors 813, blocks free 435, shadows 268, other buffers 225, other images 43, staging 32; RAM 1245 MB (the process's private memory 5906 MB): imports 1108, captures 74, capture table 26, capture spares 22, other buffers 15, others 0 [hos host] vk: textures: decoded ASTC 991 MB, rendered 754 MB (103 drawn in one frame, kept: 47857 KB), other 268 MB; used in the last 8 presents 1749 MB [hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 0 listed; 379 MB of blocks hashed in 38 ms [hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago [hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 47 MB: 0x10c2c99000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 4 presents ago [hos host] vk: 47 MB: 0x10bba9a200 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 3 presents ago [hos host] vk: 47 MB: 0x10afd32400 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB); [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos Presentation Thread] vk: presents after the CPU's signal (600): 254 waited for it, 0.87 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 66.5 ms; VRAM 4.7 of 6.2 GB [hos host] vk: a frame: 53 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.47, present 0.13, draw 4.55, descriptors 1.36, texture lookups 0.08, uploads 0.00, pipelines 0.13, programs 0.64, commands 2.09, dispatch 0.81, memory sync 0.36, queue submit 0.73, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.59 MB synced in 907.6 copies, 16.92 MB written back [hos host] vk: 4200 presents, 50.1 fps; a frame: 674 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1140 textures (2335 MB) [hos host] vk: host time in GPU resource waits: 7.10 ms a frame (fences 0.00, timelines 7.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.1 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 11.9 ms a frame (the longest submission 7.4 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 18.41 ms a frame): its jobs 7.73 ms a frame (submits 3.15, presents 0.14, others 4.44), idle 10.67; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 3.06 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); 394 captures at a CPU signal; the submits' waits read in 0.025 ms a frame; readbacks: 2997 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 6.94 ms after its hand-over (30.97 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 4.69 + 0.40 (the window's copy is in the idle), after it 2.02 + 0.26; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.06 ms of GPU time), after its last that reads it 1.00 (0.06 ms) [hos host] vk: frame ahead (600 presents): 3.63 parts a frame recorded in the signal's job, 72.0% of them took nothing that came with the signal; of the others, 1.02 a frame took pages of the signal's capture into a mirror (24.1 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 130 of 394 frames, its first three in 129 [hos host] vk: frame ahead, what came with the signal: 394 signals with a capture, each of 34.8 pages in 4.3 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any) [hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.97+0.20, 0.37+0.03, 0.63+0.02, 0.06+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, 0.00+0.00 [hos host] vk: program picks: 1021650 kept (322035 by the last picks' textures, a uniform buffer bound since), 20653 new, 757696 with other textures (of 1800000) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1267 dirty pages from their submits' captures, 67029 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): 1282 dispatches, 52717 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6493 runs, 978.5 MB compared; 125 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26596 in captures, 1 only in the collection, 57 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [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: 1200000 (612672 pages from the captures) [hos host] vk: queues ordered by their events: 24000 submissions stopped at a wait, 23967 went on once it was reached, 31 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 3 (stopped 50.08 ms at most); waits met 65798, not met 0; captures at a CPU event's wait 2007, 0 of them at a wait met on arrival [hos host] vk: readback pages refreshed from guest memory: 567177 pages so far (0 held: may be written ahead in their submission) [hos ModuleSystemWorker3] vcores: 99266 takes, 13532 waits (mean 51 us, longest 6.7 ms, 0 over HOS_VCORE_LOG_MS), 5929 kicks, 6104 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 1220000 (622909 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 184 pages written, 184 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (82 MB), 2 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1254, 5256.2 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 900 dirty pages from their submits' captures, 65812 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): 1263 dispatches, 51652 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6473 runs, 967.7 MB compared; 139 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26032 in captures, 3 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos host] vk: replay reads of guest memory as submitted: 1240000 (633140 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos ModuleSystemWorker3] vk: readbacks of GPU results: 997 of 3000 waited for their write-back, 0.98 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 4478 kept their virtual core (nothing there to wait for), 3202 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a frame: 52 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.21, present 0.13, draw 4.43, descriptors 1.34, texture lookups 0.08, uploads 0.00, pipelines 0.13, programs 0.63, commands 2.03, dispatch 0.82, memory sync 0.36, queue submit 0.68, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.57 MB synced in 906.2 copies, 16.92 MB written back [hos host] vk: 4320 presents, 55.4 fps; a frame: 673 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1140 textures (2335 MB) [hos host] vk: host time in GPU resource waits: 5.99 ms a frame (fences 0.00, timelines 5.99, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 457.9 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 11.1 ms a frame (the longest submission 6.9 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [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 316 KB; 0 made on demand (0 MB kept now); c1 stages: at most 104 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 1298, 5440.7 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1088 dirty pages from their submits' captures, 67968 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): 1305 dispatches, 53411 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6654 runs, 998.5 MB compared; 115 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26814 in captures, 2 only in the collection, 59 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: render targets drawn over from another start, let go: 133 so far (422 MB), 130 of them (422 MB) between the passes [hos sead::MainThread] nvn: GPU waits in 5 s: 78 sync waits (99 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 1260000 (643381 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 187 pages written, 187 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (86 MB), 3 spare buffers, 0 texture pages copied (0 MB) [hos Presentation Thread] vi: 4372 frames presented (53.3 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 29, 15.5-17.8 68, 17.8-22 144, 22-30 26, 30-40 0, over 40 0 [hos host] vk: replay reads of guest memory as submitted: 1280000 (653594 pages from the captures) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 975 dirty pages from their submits' captures, 67020 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): 1284 dispatches, 52657 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6535 runs, 981.5 MB compared; 114 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26449 in captures, 1 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #70000: event 0x100d6c8038 mode 0 value 49363 (now 49344) (lr 0x80661fac) [hos ModuleSystemWorker5] nvn: 450000 recordings made, 44217 live copies (12.4 MB), 319 texture copies; 4 command buffers' segments (4.2 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos host] vk: replay reads of guest memory as submitted: 1300000 (663826 pages from the captures) [hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #50000: event 0x100d6c8004 mode 0 value 49996 (lr 0x80291440) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [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: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 185 pages written, 185 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (76 MB), 4 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1053 dirty pages from their submits' captures, 67165 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): 1283 dispatches, 52677 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6540 runs, 981.5 MB compared; 119 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26804 in captures, 0 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a frame: 53 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.21, present 0.14, draw 4.34, descriptors 1.28, texture lookups 0.08, uploads 0.00, pipelines 0.13, programs 0.62, commands 2.01, dispatch 0.82, memory sync 0.35, queue submit 0.67, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.58 MB synced in 907.5 copies, 16.92 MB written back [hos host] vk: 4440 presents, 51.3 fps; a frame: 675 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1141 textures (2340 MB) [hos host] vk: host time in GPU resource waits: 7.45 ms a frame (fences 0.00, timelines 7.45, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 457.6 full barriers recorded, 230.3 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 11.9 ms a frame (the longest submission 7.8 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 1320000 (674065 pages from the captures) [hos host] vk: 1 textures retired (1140 left, 2335 MB): budget 0, drawn over 1, dead targets 0 [hos ModuleSystemWorker3] vk: readbacks of GPU results: 869 of 3000 waited for their write-back, 1.29 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 4288 kept their virtual core (nothing there to wait for), 2880 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: program picks: 1135926 kept (357420 by the last picks' textures, a uniform buffer bound since), 20653 new, 843420 with other textures (of 2000000) [hos host] vk: replay reads of guest memory as submitted: 1340000 (684584 pages from the captures) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1014 dirty pages from their submits' captures, 67654 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): 1285 dispatches, 52734 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6552 runs, 983.3 MB compared; 130 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26728 in captures, 2 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos BaseProcExecutor0] vcores: 100456 takes, 13998 waits (mean 50 us, longest 2.6 ms, 0 over HOS_VCORE_LOG_MS), 6106 kicks, 6222 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: readback pages refreshed from guest memory: 638146 pages so far (0 held: may be written ahead in their submission) [hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 190 pages written, 190 copied (0.7 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 0.003, bytes copied 0.000; 25 kept (76 MB), 4 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: replay reads of guest memory as submitted: 1360000 (694914 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: write-backs left out (600 submits): 1298, 5440.7 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 935 dirty pages from their submits' captures, 68406 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): 1306 dispatches, 53470 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6651 runs, 997.4 MB compared; 134 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 27043 in captures, 2 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 1 textures retired (1139 left, 2329 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a frame: 53 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.39, present 0.13, draw 4.49, descriptors 1.32, texture lookups 0.08, uploads 0.00, pipelines 0.14, programs 0.63, commands 2.10, dispatch 0.83, memory sync 0.38, queue submit 0.66, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.61 MB synced in 907.8 copies, 16.94 MB written back [hos host] vk: 4560 presents, 51.9 fps; a frame: 676 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1139 textures (2329 MB) [hos host] vk: host time in GPU resource waits: 6.95 ms a frame (fences 0.00, timelines 6.95, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.1 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.0 ms a frame (the longest submission 6.9 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 1380000 (705263 pages from the captures) [hos sead::MainThread] nvn: CommandBufferWaitEvent #75000: event 0x100d6c8038 mode 0 value 53163 (now 53144) (lr 0x80661fac) [hos ModuleSystemWorker3] barrier: 157114 looks: 26042 found the masks moved already, 42077 waited until they moved, 88995 for the whole 1 ms (a wait 781 us on average); 33290 wakes [hos sead::MainThread] nvn: GPU waits in 5 s: 67 sync waits (76 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos host] vk: replay reads of guest memory as submitted: 1400000 (715612 pages from the captures) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 316 KB; 0 made on demand (0 MB kept now); c1 stages: at most 104 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 859 dirty pages from their submits' captures, 67395 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): 1283 dispatches, 52600 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6548 runs, 982.6 MB compared; 124 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26620 in captures, 1 only in the collection, 59 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 187 pages written, 187 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (80 MB), 2 spare buffers, 0 texture pages copied (0 MB) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 961 of 3000 waited for their write-back, 1.11 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: 4215 kept their virtual core (nothing there to wait for), 2953 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vi: 4631 frames presented (51.7 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 19, 15.5-17.8 47, 17.8-22 165, 22-30 28, 30-40 0, over 40 0 [hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 120000 so far (x1 0x11789b6000 x2 0 x3 0x11789b6000 x4 0xf0040) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [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: 1420000 (725974 pages from the captures) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1233 dirty pages from their submits' captures, 67150 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): 1283 dispatches, 52693 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6548 runs, 981.5 MB compared; 130 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26763 in captures, 1 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a frame: 52 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.24, present 0.13, draw 4.55, descriptors 1.38, texture lookups 0.08, uploads 0.00, pipelines 0.14, programs 0.64, commands 2.09, dispatch 0.82, memory sync 0.37, queue submit 0.67, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.60 MB synced in 907.4 copies, 16.92 MB written back [hos host] vk: 4680 presents, 51.3 fps; a frame: 675 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1139 textures (2329 MB) [hos host] vk: host time in GPU resource waits: 7.16 ms a frame (fences 0.00, timelines 7.16, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.1 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 11.9 ms a frame (the longest submission 7.0 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #55000: event 0x100d6c8020 mode 0 value 55000 (lr 0x80665068) [hos host] vk: replay reads of guest memory as submitted: 1440000 (736329 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 186 pages written, 186 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (74 MB), 6 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1107 dirty pages from their submits' captures, 67163 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): 1283 dispatches, 52596 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6547 runs, 981.6 MB compared; 134 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26647 in captures, 1 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos host] vk: replay reads of guest memory as submitted: 1460000 (746688 pages from the captures) [hos host] vk: program picks: 1250344 kept (392928 by the last picks' textures, a uniform buffer bound since), 20653 new, 929002 with other textures (of 2200000) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [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 nn.npln.Callback] vcores: 98853 takes, 13440 waits (mean 53 us, longest 3.7 ms, 0 over HOS_VCORE_LOG_MS), 5770 kicks, 5908 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 1480000 (757300 pages from the captures) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 977 of 3000 waited for their write-back, 1.15 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: 4423 kept their virtual core (nothing there to wait for), 3001 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #80000: event 0x100d6c8038 mode 0 value 56963 (now 56944) (lr 0x80661fac) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1307 dirty pages from their submits' captures, 67312 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): 1285 dispatches, 52752 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6543 runs, 981.5 MB compared; 133 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26645 in captures, 0 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker3] nvn: 500000 recordings made, 44237 live copies (12.5 MB), 319 texture copies; 6 command buffers' segments (4.3 MB) [hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1259 ranges, 1863 MB), 186 pages written, 186 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (94 MB), 3 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: memory: working set 11006 MB (peak 11301), private 5906 MB, staging 32 MB in 2 arenas, 25 made so far (1 ms) [hos host] vk: memory heaps: heap 0 (system): 8 blocks 164 MB, 31 allocations 115 MB; used 1280 of 31523 MB; heap 1 (device): 160 blocks 4153 MB, 14394 allocations 3717 MB; used 4853 of 6331 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 5 images 27 MB; 2 free ranges, the largest 4 MB [hos host] vk: image blocks (render targets): 24 blocks 384 MB, 94 images 239 MB; 28 free ranges, the largest 16 MB [hos host] vk: image blocks (textures, compacted): 33 blocks 1056 MB, 1037 images 918 MB; 131 free ranges, the largest 17 MB [hos host] vk: render target images: 58 reused from the pool, 229 made new, 133 destroyed from it, 15 reused by size (on a pooled one's memory, RX_VK_TARGET_REUSE_MEMORY=2), 4 missed after their image was taken by size; it holds 0 (0 MB) [hos host] vk: render targets not reused by size: 186 with the pool empty (0 of them with targets still in the dead queue), 19 with none in it a present yet, 0 with none of a kind they can use, 8 with all smaller (the largest 23% short on average), 5 with all bigger (over 1.5 times), 11 with some of each, 0 over a block, 0 refused by the driver, 0 not bound; the pool let go of 0 over its bound and 133 idle [hos host] vk: VRAM: 4853 MB used of 6331 MB allowed (435 MB of it free in the blocks); textures 2335 MB (budget 4715 MB), 1140 textures [hos host] vk: budget: VRAM 4153 of 6331 MB (4853 MB by the driver, 699 MB unaccounted): textures 2335, mirrors 813, blocks free 435, shadows 268, other buffers 225, other images 43, staging 32; RAM 1249 MB (the process's private memory 5906 MB): imports 1108, captures 94, capture table 26, capture spares 14, other buffers 7, others 0 [hos host] vk: textures: decoded ASTC 991 MB, rendered 754 MB (103 drawn in one frame, kept: 47857 KB), other 268 MB; used in the last 8 presents 1744 MB [hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 0 listed; 379 MB of blocks hashed in 38 ms [hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago [hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 47 MB: 0x10c2c99000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 4 presents ago [hos host] vk: 47 MB: 0x10bba9a200 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 3 presents ago [hos host] vk: 47 MB: 0x10afd32400 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (177 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 1 (175 KB); [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos Presentation Thread] vk: presents after the CPU's signal (600): 264 waited for it, 0.83 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 28.4 ms; VRAM 4.7 of 6.2 GB [hos host] vk: a frame: 52 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.38, present 0.13, draw 4.58, descriptors 1.35, texture lookups 0.08, uploads 0.00, pipelines 0.14, programs 0.65, commands 2.13, dispatch 0.84, memory sync 0.37, queue submit 0.67, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.61 MB synced in 908.5 copies, 16.92 MB written back [hos host] vk: 4800 presents, 51.4 fps; a frame: 676 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1140 textures (2335 MB) [hos host] vk: host time in GPU resource waits: 7.31 ms a frame (fences 0.00, timelines 7.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.7 full barriers recorded, 230.6 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.2 ms a frame (the longest submission 7.1 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 19.16 ms a frame): its jobs 7.97 ms a frame (submits 2.94, presents 0.14, others 4.89), idle 11.19; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 3.30 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); 419 captures at a CPU signal; the submits' waits read in 0.028 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 7.17 ms after its hand-over (11.65 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 4.68 + 0.42 (the window's copy is in the idle), after it 1.93 + 0.26; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.06 ms of GPU time), after its last that reads it 1.00 (0.06 ms) [hos host] vk: frame ahead (600 presents): 3.63 parts a frame recorded in the signal's job, 71.4% of them took nothing that came with the signal; of the others, 1.04 a frame took pages of the signal's capture into a mirror (24.0 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 122 of 419 frames, its first three in 122 [hos host] vk: frame ahead, what came with the signal: 419 signals with a capture, each of 34.4 pages in 4.4 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: 0.93+0.20, 0.35+0.03, 0.61+0.03, 0.05+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, 0.00+0.00 [hos host] vk: readback pages refreshed from guest memory: 709353 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 1500000 (767536 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 71 sync waits (89 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1019 dirty pages from their submits' captures, 67273 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): 1283 dispatches, 52676 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6546 runs, 981.5 MB compared; 136 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26725 in captures, 1 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos host] vk: replay reads of guest memory as submitted: 1520000 (777741 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 Presentation Thread] vi: 4884 frames presented (50.4 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 10, 15.5-17.8 31, 17.8-22 182, 22-30 30, 30-40 0, over 40 0 [hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1258 ranges, 1861 MB), 188 pages written, 188 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (92 MB), 4 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: replay reads of guest memory as submitted: 1540000 (787980 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 316 KB; 0 made on demand (0 MB kept now); c1 stages: at most 104 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 977 dirty pages from their submits' captures, 67321 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): 1283 dispatches, 52694 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6547 runs, 981.6 MB compared; 124 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26813 in captures, 0 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a frame: 53 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.03, present 0.13, draw 4.21, descriptors 1.23, texture lookups 0.08, uploads 0.00, pipelines 0.13, programs 0.61, commands 1.95, dispatch 0.80, memory sync 0.35, queue submit 0.64, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.60 MB synced in 907.8 copies, 16.92 MB written back [hos host] vk: 4920 presents, 49.9 fps; a frame: 677 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1140 textures (2335 MB) [hos host] vk: host time in GPU resource waits: 7.76 ms a frame (fences 0.00, timelines 7.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.4 full barriers recorded, 230.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.5 ms a frame (the longest submission 7.2 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: render targets drawn over from another start, let go: 133 so far (422 MB), 130 of them (422 MB) between the passes [hos host] vk: replay reads of guest memory as submitted: 1560000 (798207 pages from the captures) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 839 of 3000 waited for their write-back, 1.47 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 4174 kept their virtual core (nothing there to wait for), 2994 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #60000: event 0x100d6c8028 mode 0 value 59999 (lr 0x80667410) [hos ModuleSystemWorker5] barrier: 176555 looks: 29099 found the masks moved already, 45049 waited until they moved, 102407 for the whole 1 ms (a wait 797 us on average); 35912 wakes [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 858 dirty pages from their submits' captures, 67359 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): 1283 dispatches, 52543 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6541 runs, 981.5 MB compared; 133 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26737 in captures, 2 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB) [hos host] vk: replay reads of guest memory as submitted: 1580000 (808434 pages from the captures) [hos host] vk: slow present: 16.3 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 Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1258 ranges, 1861 MB), 186 pages written, 186 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 24 kept (92 MB), 7 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: present 4974 written to <data>/jobs/jb_4c4e033c19f4a1ff/runs/field-turn-and-stand-g2-01-pr/shots/field-turn-and-stand-pr-01-last-frame.png (the control bridge) [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #85000: event 0x100d6c8038 mode 0 value 60763 (now 60744) (lr 0x80661fac) [hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29968 went on once it was reached, 31 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 3 (stopped 50.08 ms at most); waits met 85279, not met 0; captures at a CPU event's wait 2553, 0 of them at a wait met on arrival [hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05 [hos host] vk: replay reads of guest memory as submitted: 1600000 (818669 pages from the captures) [hos host] vk: write-backs left out (600 submits): 1276, 5348.5 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1600 dirty pages from their submits' captures, 66811 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): 1284 dispatches, 52582 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6577 runs, 984.5 MB compared; 171 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26461 in captures, 0 only in the collection, 57 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] vcores: 97146 takes, 13682 waits (mean 49 us, longest 2.5 ms, 0 over HOS_VCORE_LOG_MS), 5978 kicks, 6129 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: program picks: 1364793 kept (428600 by the last picks' textures, a uniform buffer bound since), 20653 new, 1014553 with other textures (of 2400000) [hos host] vk: a frame: 53 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 83 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 7.24, present 0.26, draw 4.45, descriptors 1.30, texture lookups 0.08, uploads 0.00, pipelines 0.14, programs 0.64, commands 2.07, dispatch 0.81, memory sync 0.36, queue submit 0.65, slot wait 0.04 [hos host] vk: a frame: mirrors 67 (813 MB): 4.60 MB synced in 906.6 copies, 16.96 MB written back [hos host] vk: 5040 presents, 50.9 fps; a frame: 677 draws (0 skipped), 98 dispatches, 146 passes, 144 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 37368 pipelines (1402 ms), 0 programs (10 failed), 1140 textures (2335 MB) [hos host] vk: host time in GPU resource waits: 7.37 ms a frame (fences 0.00, timelines 7.37, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 458.5 full barriers recorded, 230.6 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: 45.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.3 ms a frame (the longest submission 8.1 ms); 0.0 textures made a frame [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 1620000 (828892 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.05 over 1258 ranges, 1861 MB), 186 pages written, 186 copied (0.7 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 0.002, bytes copied 0.000; 24 kept (90 MB), 6 spare buffers, 0 texture pages copied (0 MB) [hos host] vk: 1 textures retired (1139 left, 2329 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: sparse mirrors: 51, 813 MB with memory of 976 MB (162 MB spared); blocks given memory later 97, given back 1245; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 90 binds (42.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 7 taken from the spares, 60 made new; 16 kept as spares, 0 destroyed; 9 spares now, 288 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1254, 5256.2 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1245 dirty pages from their submits' captures, 66379 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): 1263 dispatches, 51920 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 6441 runs, 965.6 MB compared; 152 pages read into the shadows; 268 MB of shadows; pages the shadows knew that the CPU wrote: 26318 in captures, 1 only in the collection, 58 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 59 live (1108 MB), 0 retired still imported (0 MB), 10 retired given back (260 MB)


