Files
mtusi2026lab3/research/analyze.py
T

118 lines
3.8 KiB
Python

import argparse
import csv
import json
import statistics
from pathlib import Path
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt # noqa: E402
def main():
parser = argparse.ArgumentParser()
parser.add_argument("directory")
args = parser.parse_args()
directory = Path(args.directory)
meta = json.loads((directory / "run.json").read_text())
assert meta["complete"]
rows = [
json.loads((directory / name).read_text()) for name in meta["cells"]
]
keys = [
"series",
"replicas",
"concurrency",
"repeat",
"pool_size",
"successful_rps",
"errors",
"error_ratio",
"p50_ms",
"p95_ms",
"p99_ms",
]
with (directory / "summary.csv").open("w", newline="") as stream:
writer = csv.DictWriter(stream, fieldnames=keys)
writer.writeheader()
writer.writerows({k: r[k] for k in keys} for r in rows)
fig, axes = plt.subplots(1, 2, figsize=(11, 4), constrained_layout=True)
for ax, series in zip(axes, ["fixed", "growing"], strict=True):
for concurrency in [1, 8, 32]:
values = [
statistics.median(
r["successful_rps"]
for r in rows
if r["series"] == series
and r["replicas"] == n
and r["concurrency"] == concurrency
)
for n in [1, 2, 4]
]
ax.plot([1, 2, 4], values, marker="o", label=f"C={concurrency}")
ax.set(
title=series,
xlabel="API replicas",
ylabel="Successful HTTP requests/s",
xticks=[1, 2, 4],
)
ax.legend()
ax.grid(alpha=0.3)
fig.savefig(directory / "scaling.png", dpi=160)
plt.close(fig)
pool = {
n: statistics.median(
r["successful_rps"]
for r in rows
if r["series"] == "pool" and r["pool_size"] == n
)
for n in [1, 10]
}
lines = [
"# Измерения масштабирования",
"",
f"Source commit: `{meta['source_commit']}`.",
"",
"Медианы повторов; latency percentile внутри каждого прогона относится только к успешным ответам.",
"",
"| Серия | API | C | RPS | p95, ms | Ошибки |",
"|---|---:|---:|---:|---:|---:|",
]
for series in ["fixed", "growing"]:
for n in [1, 2, 4]:
for c in [1, 8, 32]:
group = [
r
for r in rows
if r["series"] == series
and r["replicas"] == n
and r["concurrency"] == c
]
lines.append(
f"| {series} | {n} | {c} | {statistics.median(r['successful_rps'] for r in group):.1f} | {statistics.median(r['p95_ms'] for r in group):.2f} | {sum(r['errors'] for r in group)} |"
)
lines.extend(
[
"",
f"Пул1 → пул10: {pool[1]:.1f} → {pool[10]:.1f} успешных RPS (N2/C32, три повтора).",
"",
"Настройка считается подтверждённым улучшением только при наблюдаемом выигрыше; это ограниченная локальная серия.",
]
)
(directory / "analysis.md").write_text("\n".join(lines) + "\n")
print(
json.dumps(
{
"cells": len(rows),
"success": sum(r["success"] for r in rows),
"errors": sum(r["errors"] for r in rows),
"pool_rps": pool,
}
)
)
if __name__ == "__main__":
main()