mirror of
https://github.com/valentderah/totk-pc-recomp.git
synced 2026-11-21 12:55:57 +00:00
Each submission part writes a timestamp pair under TOTK_TRACE=perf; the completion thread reads it and sums the busy time without double-counting overlap. A second 60-frame perf line carries GPU ms per frame, fence waits of the render thread and of other threads, VRAM usage and budget (VK_EXT_memory_budget, else the allocator's own blocks against the heap size), working set and private bytes, and bound: gpu, cpu or pace. Devices without timestamp bits or a timestamp period log one line and show gpu n/a. vk_mem_resolve now reports the pool class of a span. The replay counts bytes bound or copied per class and use, and vk_mem_census logs the live pools by kind and flags with that traffic at frame 1800 (every 1800 frames with perf). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
68 lines
3.3 KiB
Python
68 lines
3.3 KiB
Python
"""Condense the TOTK_TRACE=perf and TOTK_TRACE=sched lines of a game log over a frame window.
|
|
|
|
python tools/perf_summary.py build/v121/logs/fight.log 1560 2600
|
|
"""
|
|
import re
|
|
import statistics
|
|
import sys
|
|
|
|
PERF = re.compile(r'perf: frame (\d+): interval avg ([\d.]+) ms max ([\d.]+) ms \(([\d.]+) fps\); render thread blocked: '
|
|
r'pacing (\d+)%.*?pipeline build (\d+)%.*?texture (\d+)%')
|
|
GPU = re.compile(r'perf: frame (\d+): gpu avg (?:([\d.]+) ms|n/a).*?fence wait per frame: render thread ([\d.]+) ms, '
|
|
r'other threads ([\d.]+) ms; vram (?:([\d.]+) of ([\d.]+) MiB|n/a).*?ram working set ([\d.]+) MiB, '
|
|
r'private ([\d.]+) MiB; bound: (\w+)')
|
|
SCHED = re.compile(r'sched: frame (\d+): (.*)')
|
|
THREAD = re.compile(r'sched: (render )?(0x[0-9a-f]+) (p\d+ m\d+) run (\d+)% core (\d+)% host (\d+)% sleep (\d+)% '
|
|
r'sync (\d+)% cv (\d+)% lock (\d+)% addr (\d+)% cpu (\d+)% blocks (\d+) preempted (\d+)')
|
|
RWAIT = re.compile(r'sched: render wait (\d): (.*)')
|
|
|
|
|
|
def main():
|
|
if len(sys.argv) < 2:
|
|
sys.exit(__doc__)
|
|
lo = int(sys.argv[2]) if len(sys.argv) > 2 else 1560
|
|
hi = int(sys.argv[3]) if len(sys.argv) > 3 else 10**9
|
|
fr, fps, mx, gpu, vram, ram, bound = None, [], [], [], [], [], {}
|
|
for line in open(sys.argv[1], encoding='utf-8', errors='replace'):
|
|
if line.startswith('run_game:'):
|
|
print(line.rstrip())
|
|
elif m := PERF.search(line):
|
|
f = int(m[1])
|
|
if lo < f <= hi:
|
|
fps.append(float(m[4]))
|
|
mx.append(float(m[3]))
|
|
print(f'perf {f}: {m[4]} fps max {m[3]} pacing {m[5]}% pipe {m[6]}% tex {m[7]}%')
|
|
elif m := GPU.search(line):
|
|
f = int(m[1])
|
|
if lo < f <= hi:
|
|
if m[2]:
|
|
gpu.append(float(m[2]))
|
|
if m[5]:
|
|
vram.append((float(m[5]), float(m[6])))
|
|
ram.append((float(m[7]), float(m[8])))
|
|
bound[m[9]] = bound.get(m[9], 0) + 1
|
|
print(f' gpu {f}: {m[2] or "n/a"} ms, fence wait render {m[3]} other {m[4]} ms, '
|
|
f'vram {m[5] or "n/a"} MiB, ram ws {m[7]} private {m[8]} MiB, bound {m[9]}')
|
|
elif m := SCHED.search(line):
|
|
fr = int(m[1])
|
|
if lo < fr <= hi:
|
|
print(f' sched {fr}: {m[2]}')
|
|
elif (m := THREAD.search(line)) and fr and lo < fr <= hi:
|
|
print(f' {m[1] or ""}{m[2]} {m[3]} run {m[4]} core {m[5]} host {m[6]} sleep {m[7]} sync {m[8]} cv {m[9]} '
|
|
f'lock {m[10]} addr {m[11]} cpu {m[12]} blk {m[13]} pre {m[14]}')
|
|
elif (m := RWAIT.search(line)) and fr and lo < fr <= hi:
|
|
print(f' rw{m[1]}: {m[2]}')
|
|
if fps:
|
|
print(f'SUMMARY frames {lo}-{hi}: mean fps {statistics.mean(fps):.1f}, min window fps {min(fps):.1f}, '
|
|
f'max frame {max(mx):.1f} ms')
|
|
if ram:
|
|
g = f'gpu mean {statistics.mean(gpu):.2f} ms' if gpu else 'gpu n/a'
|
|
v = f'vram max {max(u for u, _ in vram):.0f} of {vram[-1][1]:.0f} MiB' if vram else 'vram n/a'
|
|
b = ', '.join(f'{k} {n}' for k, n in sorted(bound.items()))
|
|
print(f'SUMMARY gpu: {g}, {v}, ram ws max {max(w for w, _ in ram):.0f} MiB, '
|
|
f'private max {max(p for _, p in ram):.0f} MiB; bound windows: {b}')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|