watch_fma_download.py 2.06 KB
#!/usr/bin/env python3
"""Ensure the FMA archive download keeps running; restart if stalled or dead."""

from __future__ import annotations

import argparse
import json
import subprocess
import time
from pathlib import Path

PYTHON = "/usr/local/miniconda3/bin/python"
INSPECT = [PYTHON, "scripts/prepare_fma_archive.py", "inspect"]
BG = [PYTHON, "scripts/prepare_fma_archive.py", "bg-download"]
DEFAULT_LOG = Path("/tmp/fma_modelscope_watch.log")


def inspect() -> dict:
    out = subprocess.check_output(INSPECT, text=True)
    return json.loads(out)


def bg_download() -> dict:
    out = subprocess.check_output(BG, text=True)
    return json.loads(out)


def has_live_curl() -> bool:
    proc = subprocess.run(
        ["bash", "-lc", "ps -ef | grep 'fma_small.zip' | grep -v grep >/dev/null"],
        capture_output=True,
        text=True,
    )
    return proc.returncode == 0


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--interval", type=float, default=5.0)
    parser.add_argument("--cycles", type=int, default=3)
    parser.add_argument("--log-path", default=str(DEFAULT_LOG))
    args = parser.parse_args()

    log_path = Path(args.log_path)
    log_path.parent.mkdir(parents=True, exist_ok=True)
    events = []

    previous_size = None
    for _ in range(args.cycles):
        snapshot = inspect()
        size = int(snapshot["archive_size"])
        live = has_live_curl()
        restarted = None
        if (previous_size is not None and size <= previous_size) or not live:
            restarted = bg_download()
            time.sleep(2)
            snapshot = inspect()
            size = int(snapshot["archive_size"])
            live = has_live_curl()
        event = {
            "snapshot": snapshot,
            "live_curl": live,
            "restarted": restarted,
        }
        events.append(event)
        previous_size = size
        time.sleep(args.interval)

    text = json.dumps({"status": "ok", "events": events}, indent=2, ensure_ascii=False)
    log_path.write_text(text)
    print(text)


if __name__ == "__main__":
    main()