siftlode/backend/app/downloads/runner.py

"""Download/edit child process — runs ONE job's heavy work (yt-dlp download or ffmpeg edit) in its
own process, launched and supervised by the worker (`app.worker._run_supervised`).

Why a separate process: a worker THREAD can't be killed, a C-level spin (a catastrophic regex, a
tight yt-dlp retry loop) can't even be cooperatively cancelled, and one such thread starves the
others via the GIL. Running the work in a child means the supervisor can SIGTERM/SIGKILL it (and its
process group, so ffmpeg grandchildren die too) on a stall / pause / wall-clock breach.

Contract: the asset is already claimed ('downloading') by the parent. This process does the work and
writes the terminal job/asset state itself (done / error, or a cooperative pause via the in-flight
progress hook), then exits 0. An unexpected crash exits non-zero and the parent fails the job.
"""

import os
import shutil
import subprocess
import sys

from app import logs
from app import logsink
from app.config import settings
from app.db import SessionLocal
from app.downloads import edit as editmod
from app.downloads import formats
from app.models import DownloadJob

log = logs.get_logger(__name__)


def _deprioritize() -> None:
    """Lower THIS child's CPU + IO priority so its yt-dlp/ffmpeg work — every descendant inherits the
    handicap — can never starve the co-located API, Postgres, or Plex playback. Run once at startup,
    before any heavy work. Every step is best-effort: a failed renice must never fail a download."""
    nice_inc = settings.download_child_nice
    if nice_inc > 0:
        try:
            os.nice(nice_inc)  # relative increment; the child starts at the worker's nice (0)
        except OSError as exc:
            log.info("could not renice download child: %s", str(exc)[:120])
    cls = settings.download_child_ionice_class
    if cls > 0 and shutil.which("ionice"):  # util-linux; absent on some minimal images
        try:
            subprocess.run(
                ["ionice", "-c", str(cls), "-p", str(os.getpid())],
                capture_output=True,
                timeout=5,
                check=False,
            )
        except (OSError, subprocess.SubprocessError) as exc:
            log.info("could not ionice download child: %s", str(exc)[:120])
    # Cap OpenMP-parallel ffmpeg filters to the same budget as the encoder threads, so a filter
    # graph can't fan out across every core behind ffmpeg's own `-threads` cap.
    os.environ.setdefault("OMP_NUM_THREADS", str(editmod.encode_thread_cap()))


def main() -> None:
    logs.configure_logging("runner")
    _deprioritize()
    if len(sys.argv) != 2:
        # noqa T201: a usage line is for the person who typed the command. Logging is already
        # configured here, and in a deployment it writes JSON records — the one reader of this
        # line wants the bare sentence, not a record with a request id they do not have.
        print(  # noqa: T201
            "usage: python -m app.downloads.runner <job_id>", file=sys.stderr
        )
        raise SystemExit(2)
    job_id = int(sys.argv[1])
    # This whole process exists to run ONE job — tag every line it prints with it, so the child's
    # output joins up with the worker's and the API's view of the same download.
    logs.set_job(job_id)
    logsink.start()  # flushed at exit (atexit) — this process has no shutdown hook of its own

    with SessionLocal() as db:
        job = db.get(DownloadJob, job_id)
        if job is None:
            return
        asset_id = job.asset_id
        job_kind = job.job_kind
        spec = dict(job.profile_snapshot or {})
        source_kind, source_ref = job.source_kind, job.source_ref
        user_id = job.user_id
    if asset_id is None:
        return

    _run(job_id, asset_id, job_kind, source_kind, source_ref, spec, user_id)


def _run(job_id, asset_id, job_kind, source_kind, source_ref, spec, user_id) -> None:
    """Run the job, and be the last stop before Python's own exception hook.

    What gets past the pipeline is a failure it could not even record (the database refused the
    write that fails the job). Python's hook would print it to stderr raw — and its context is the
    download's own failure, whose text is the URL or ffmpeg's stderr naming the file. Here it is
    one line with the whole chain scrubbed; the non-zero exit then has the worker fail the job
    (`cause=child_exit`)."""
    # Imported here (not at module top) so the child pays the yt-dlp import cost only when it has
    # real work, and to keep the import graph obvious: runner is a thin entry over the pipeline.
    from app.downloads.pipeline import _download, _process_edit

    with formats.hiding(source_ref):
        try:
            if job_kind == "edit":
                _process_edit(job_id, asset_id)
            else:
                _download(job_id, asset_id, source_kind, source_ref, spec, user_id)
        except Exception as exc:  # noqa: BLE001 — whatever it is, it is reported here or raw
            # noqa TRY400: the stack goes with it scrubbed (`scrubbed_stack`); `exc_info` is raw.
            log.error(  # noqa: TRY400
                "the download child for job %s failed",
                job_id,
                extra={
                    **logs.event(
                        "download.child.failed", job_id=job_id, error_type=type(exc).__name__
                    ),
                    **logs.scrubbed_stack(exc, formats.log_safe),
                },
            )
            raise SystemExit(1) from None


if __name__ == "__main__":
    main()