VoxelForge/Standalone/Research/WorldAssemblerM3/Linux114/RunL114Timing.py

#!/usr/bin/env python3
"""Five interleaved L80 readiness runs for L109, L113, and L114."""
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 / "Saved/Linux/l114/timing"
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "L109": ROOT / "Saved/Linux/l109/bin-final/VoxelForgeCoreHeadless-l109-clang",
    "L113": ROOT / "Saved/Linux/l113/bin/VoxelForgeCoreHeadless-l113-clang",
    "L114": ROOT / "Saved/Linux/l114/bin/VoxelForgeCoreHeadless-l114-clang",
}
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"{v:.12f}" for v 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",
    ]
    start = 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 = PIPELINE.search(content)
    near_match = NEAR.search(content)
    if result.returncode or pipeline_match is None or near_match is None:
        raise SystemExit(f"readiness run failed or trace missing: {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() - start, 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("[L114TimingRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if not DATA.is_file() or any(not binary.is_file() for binary in BINARIES.values()):
        raise SystemExit("missing L109/L113/L114 data or timing binary")
    OUT.mkdir(parents=True, exist_ok=True)
    load_1m = os.getloadavg()[0]
    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}\ntop CPU users:\n{top}",
        encoding="utf-8")
    print(f"[L114TimingGate] load_1m={load_1m:.2f} uptime={uptime}", flush=True)
    if load_1m >= 1.5:
        raise SystemExit(f"timing refused: 1-minute load {load_1m:.2f} is not below 1.5")
    rows = []
    versions = ("L109", "L113", "L114")
    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", "L113"):
                for key in ("lod02_ready_s", "whole_view_ready_s"):
                    item[f"L114_vs_{comparison}_{key}_delta_pct"] = round(
                        100.0 * (medians["L114"][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())