VoxelForge/Standalone/Research/WorldAssemblerM3/Linux128/RunL128Timing.py

#!/usr/bin/env python3
"""Five interleaved L80 readiness runs for L109, 4041d4b and L128."""
from __future__ import annotations

import json
import os
import re
import statistics
import subprocess
import time
from pathlib import Path

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / os.environ.get("L128_TIMING_DIR", "Saved/Linux/l128/timing")
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "L109": ROOT / "Saved/Linux/l109/bin-final/VoxelForgeCoreHeadless-l109-clang",
    "4041d4b": ROOT / "Saved/Linux/l127/bin-clang/VoxelForgeCoreHeadless-l127-clang",
    "L128": ROOT / os.environ.get("L128_CANDIDATE_BINARY",
        "Saved/Linux/l128/bin/VoxelForgeCoreHeadless-clang19"),
}
CAMERAS = {
    0: (8.0, 16.0, -372.2626953125),
    1: (25.8369140625, 3.19921875, -737.0),
    2: (19.166015625, -14.2001953125, -753.3740234375),
    3: (-20.0625, -5.068359375, -900.353515625),
}
PIPELINE = re.compile(r"^\[StreamPipeline\] (.*)$", re.M)
FIELDS = re.compile(r"([a-zA-Z0-9_]+)=([^ ]+)")
NEAR = re.compile(
    r"^\[WorldAssemblerNearLODReady\] lods=0-2 tiles=(\d+)/(\d+) cold_ready_s=([0-9.]+)$",
    re.M)


def run(strate: int, workers: int, version: str, phase: str, replicate: int) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    label = f"s{strate}-w{workers}-{version}-{phase}{replicate}"
    log = OUT / f"{label}.log"
    camera = ",".join(f"{value:.12f}" for value in CAMERAS[strate]) + ",0,0"
    command = [
        "taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "timeout", "1740s", str(BINARIES[version]), str(DATA),
        "--world-assembler-prototype", "--stream-benchmark", "--stream-pipeline",
        f"--workers={workers}", "--clip-radius=3", "--max-clip-level=8",
        "--max-level=8", f"--camera={camera}", "--profile-lod-work",
        "--stream-scheduler-policy=3",
    ]
    started = time.monotonic()
    with log.open("w", encoding="utf-8") as output:
        result = subprocess.run(command, cwd=ROOT, stdout=output,
            stderr=subprocess.STDOUT, check=False, timeout=1740)
    content = log.read_text(encoding="utf-8", errors="replace")
    pipeline_match, near_match = PIPELINE.search(content), NEAR.search(content)
    if result.returncode or pipeline_match is None or near_match is None:
        raise SystemExit(f"readiness run failed or incomplete: {log}; exit={result.returncode}")
    pipeline = dict(FIELDS.findall(pipeline_match.group(1)))
    row = {"strate": strate, "workers": workers, "version": version,
        "phase": phase, "replicate": replicate, "exit_code": result.returncode,
        "wall_s": round(time.monotonic() - started, 3),
        "lod02_ready_s": float(near_match.group(3)),
        "whole_view_ready_s": float(pipeline["whole_view_ready"].removesuffix("s")),
        "whole_tiles": int(pipeline["whole_tiles"].split("/")[0]),
        "log": str(log.relative_to(ROOT))}
    print("[L128TimingRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def cpu_idle_percent(interval_s: float = 2.0) -> float:
    def totals() -> tuple[int, int]:
        fields = Path("/proc/stat").read_text(encoding="utf-8").splitlines()[0].split()
        values = [int(value) for value in fields[1:]]
        return sum(values), values[3] + (values[4] if len(values) > 4 else 0)
    before_total, before_idle = totals()
    time.sleep(interval_s)
    after_total, after_idle = totals()
    return 100.0 * (after_idle-before_idle) / max(1, after_total-before_total)


def main() -> int:
    if not DATA.is_file() or any(not binary.is_file() for binary in BINARIES.values()):
        raise SystemExit("missing L109/4041d4b/L128 timing input")
    OUT.mkdir(parents=True, exist_ok=True)
    load_1m, idle_pct = os.getloadavg()[0], cpu_idle_percent()
    uptime = subprocess.run(["uptime"], cwd=ROOT, text=True,
        capture_output=True, check=True).stdout.strip()
    top = subprocess.run(["ps", "-eo", "pid,pcpu,comm", "--sort=-pcpu"],
        cwd=ROOT, text=True, capture_output=True, check=True).stdout
    (OUT / "machine-load-before.txt").write_text(
        f"uptime: {uptime}\n1-minute load: {load_1m:.2f}\n"
        f"2-second CPU idle: {idle_pct:.1f}%\ntop CPU users:\n{top}", encoding="utf-8")
    print(f"[L128TimingGate] load_1m={load_1m:.2f} cpu_idle_2s={idle_pct:.1f}%",
        flush=True)
    if load_1m >= 0.9 or idle_pct < 97.0:
        raise SystemExit("timing refused: machine is above the quiet-load gate")

    rows = []
    versions = ("L109", "4041d4b", "L128")
    for strate in range(4):
        for workers in (8, 12):
            for version in versions:
                run(strate, workers, version, "warmup", 0)
            for replicate in range(1, 6):
                offset = (replicate - 1) % len(versions)
                order = versions[offset:] + versions[:offset]
                for version in order:
                    rows.append(run(strate, workers, version, "measured", replicate))
                    (OUT / "runs-partial.json").write_text(
                        json.dumps(rows, indent=2) + "\n", encoding="utf-8")

    summary = []
    for strate in range(4):
        for workers in (8, 12):
            item = {"strate": strate, "workers": workers, "replicates": 5}
            medians = {}
            for version in versions:
                group = [row for row in rows if row["strate"] == strate
                    and row["workers"] == workers and row["version"] == version]
                medians[version] = {}
                for key in ("lod02_ready_s", "whole_view_ready_s"):
                    values = [row[key] for row in group]
                    medians[version][key] = statistics.median(values)
                    item[f"{version}_{key}_values"] = values
                    item[f"{version}_{key}_median"] = medians[version][key]
            for comparison in ("L109", "4041d4b"):
                for key in ("lod02_ready_s", "whole_view_ready_s"):
                    item[f"L128_vs_{comparison}_{key}_delta_pct"] = round(
                        100.0 * (medians["L128"][key] / medians[comparison][key]-1.0), 2)
            summary.append(item)
    (OUT / "summary.json").write_text(
        json.dumps({"runs": rows, "summary": summary}, indent=2) + "\n",
        encoding="utf-8")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())