Files
marqdo-cli/tools/perf/bench.py
T
cflmy 4c8e7fd8ab perf(p6): add a reproducible baseline profile harness
- tools/perf/bench.py builds the release CLI and measures 7 .mq.md workloads
  three times with wall time and peak RSS, validating --json success.
- Check in the schema-tagged JSON report and interpretation; no bytecode/JIT/
  native backend was added, so P6 remains baseline-only, not complete.
- Update STATUS/changelog/tests README.

Gate: fmt, clippy -D warnings, 430 tests passed.
2026-11-20 23:16:02 +08:00

101 lines
3.1 KiB
Python
Executable File

#!/usr/bin/env python3
"""Reproducible P6 baseline profile for selected .mq.md workloads.
Builds the release CLI, runs each workload three times through /usr/bin/time,
and writes a JSON report with wall seconds and peak RSS. This is a baseline
profile, not a claim that P6 optimization is complete.
"""
import json
import os
import statistics
import subprocess
import sys
import tempfile
import time
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
target_dir = Path(os.environ.get("CARGO_TARGET_DIR", ROOT / "target"))
if not target_dir.is_absolute():
target_dir = ROOT / target_dir
BIN = target_dir / "release" / "marqdo"
WORKLOADS = [
("allocator-free-list", "tests/conformance/semantics/55-first-fit-free-list-allocator.mq.md"),
("json-parser", "tests/conformance/semantics/62-json-array-parser.mq.md"),
("table-sort", "tests/conformance/semantics/65-table-sort-stdlib.mq.md"),
("bytecode-vm", "tests/conformance/semantics/63-memory-bytecode-vm.mq.md"),
("matrix-multiply", "tests/conformance/semantics/70-matrix-multiply.mq.md"),
("http-parser", "tests/conformance/semantics/71-http-parser.mq.md"),
("stdlib-print-demo", "stdlib/demo.mq.md"),
]
def run_once(relative: str) -> dict:
with tempfile.NamedTemporaryFile("r", delete=False) as handle:
time_path = handle.name
command = [
"/usr/bin/time",
"-f",
"%e %M",
"-o",
time_path,
str(BIN),
"run",
relative,
"--json",
]
env = dict(os.environ)
env["MARQDO_STDLIB_DIR"] = str(ROOT / "stdlib")
started = time.perf_counter()
output = subprocess.run(
command, cwd=ROOT, env=env, capture_output=True, text=True, timeout=120
)
elapsed = time.perf_counter() - started
timing = Path(time_path).read_text().split()
Path(time_path).unlink(missing_ok=True)
if output.returncode != 0:
raise RuntimeError(f"{relative} failed: {output.stderr}")
report = json.loads(output.stdout)
if not report.get("success"):
raise RuntimeError(f"{relative} reported failure")
return {
"seconds": elapsed,
"max_rss_kb": int(timing[1]),
}
def main() -> int:
subprocess.run(
["cargo", "build", "--release", "-p", "marqdo-cli"],
cwd=ROOT,
check=True,
)
report = {
"schema": "marqdo.perf-baseline",
"schema_version": 1,
"binary": str(BIN.relative_to(ROOT)),
"iterations": 3,
"workloads": [],
}
for name, relative in WORKLOADS:
runs = [run_once(relative) for _ in range(3)]
report["workloads"].append(
{
"name": name,
"source": relative,
"seconds_median": round(statistics.median(r["seconds"] for r in runs), 4),
"seconds_min": min(r["seconds"] for r in runs),
"max_rss_kb_median": int(
statistics.median(r["max_rss_kb"] for r in runs)
),
}
)
json.dump(report, sys.stdout, ensure_ascii=False, indent=2)
sys.stdout.write("\n")
return 0
if __name__ == "__main__":
raise SystemExit(main())