Linux 文件很大却不占空间？用 Python 检查稀疏文件与磁盘分配量

python3 --version
du --version
mkdir sparse-usage-demo
cd sparse-usage-demo

python3 - <<'PYCODE'
import os

size = 8 * 1024 * 1024
with open("sparse.bin", "xb") as stream:
    stream.write(b"HEAD")
    stream.seek(size - 4)
    stream.write(b"TAIL")
    stream.flush()
    os.fsync(stream.fileno())
with open("empty.bin", "xb"):
    pass
print("created sparse.bin and empty.bin")
PYCODE

"""Read Linux regular-file size metadata. Python 3.10+."""
import argparse
import json
import os
import stat
import sys


def inspect_file(path):
    info = os.lstat(path)
    if not stat.S_ISREG(info.st_mode):
        raise ValueError(f"{path!r}: not a regular file; no final symlink following")
    blocks = getattr(info, "st_blocks", None)
    if blocks is None:
        raise ValueError("st_blocks is unavailable on this platform")
    allocated = blocks * 512
    return {
        "path": path,
        "logical_bytes": info.st_size,
        "allocated_bytes": allocated,
        "allocated_less_than_logical": allocated < info.st_size,
        "hard_links": info.st_nlink,
        "device": info.st_dev,
        "inode": info.st_ino,
    }


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("paths", nargs="+", help="regular-file paths; no recursion")
    args = parser.parse_args()
    try:
        rows = [inspect_file(path) for path in args.paths]
    except (OSError, ValueError) as exc:
        print(f"ERROR: {exc}", file=sys.stderr)
        return 2
    print(json.dumps(rows, indent=2, ensure_ascii=True))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())

python3 file_usage.py --help
python3 file_usage.py sparse.bin empty.bin
ls -l -- sparse.bin
du -B1 -- sparse.bin
du --apparent-size -B1 -- sparse.bin
du -b -- sparse.bin

"""Run next to file_usage.py; all fixtures live in a temporary directory."""
import json
import os
from pathlib import Path
import subprocess
import sys
import tempfile

script = Path("file_usage.py").resolve()


def run(paths, expected):
    result = subprocess.run(
        [sys.executable, str(script), *map(str, paths)],
        text=True, capture_output=True, check=False,
    )
    assert result.returncode == expected, result.stderr
    if expected == 0:
        assert result.stderr == "", result.stderr
        return json.loads(result.stdout)
    assert result.stdout == "", result.stdout
    assert result.stderr.startswith("ERROR:"), result.stderr


with tempfile.TemporaryDirectory(prefix="usage-check-", dir=".") as tmp:
    directory = Path(tmp)
    sparse = directory / "sparse.bin"
    size = 8 * 1024 * 1024
    with sparse.open("xb") as stream:
        stream.write(b"HEAD")
        stream.seek(size - 4)
        stream.write(b"TAIL")
        stream.flush()
        os.fsync(stream.fileno())
    empty = directory / "empty.bin"
    empty.touch(exist_ok=False)
    tiny = directory / "tiny.bin"
    tiny.write_bytes(b"x")
    before = sparse.stat()
    rows = run([sparse, empty, tiny], 0)
    assert [row["logical_bytes"] for row in rows] == [size, 0, 1]
    for path, row in zip([sparse, empty, tiny], rows):
        info = path.lstat()
        assert row["allocated_bytes"] == info.st_blocks * 512
        assert row["allocated_less_than_logical"] == (
            row["allocated_bytes"] < row["logical_bytes"]
        )
    assert sparse.stat().st_mtime_ns == before.st_mtime_ns
    with sparse.open("rb") as stream:
        assert stream.read(4) == b"HEAD"
        stream.seek(size // 2)
        assert stream.read(4) == b"\0" * 4
        stream.seek(size - 4)
        assert stream.read() == b"TAIL"
    alias = directory / "alias.bin"
    os.link(sparse, alias)
    linked = run([sparse, alias], 0)
    assert linked[0]["hard_links"] == linked[1]["hard_links"] == 2
    assert (linked[0]["device"], linked[0]["inode"]) == (
        linked[1]["device"], linked[1]["inode"]
    )
    symlink = directory / "link.bin"
    symlink.symlink_to("sparse.bin")
    run([symlink], 2)
    run([directory], 2)
    run([directory / "missing.bin"], 2)
    run([sparse, directory / "missing.bin"], 2)
print("PASS: sizes, blocks, content, hard links, and failure exits")

python3 check_usage.py

PASS: sizes, blocks, content, hard links, and failure exits