稀疏文件把逻辑长度与分配块分开

from pathlib import Path
from tempfile import TemporaryDirectory
import ctypes,hashlib,os

size=16*1024*1024;first=4*1024*1024;second=12*1024*1024
libc=ctypes.CDLL(None,use_errno=True);libc.fallocate.argtypes=[ctypes.c_int,ctypes.c_int,ctypes.c_longlong,ctypes.c_longlong];libc.fallocate.restype=ctypes.c_int
def digest(path):
    with path.open('rb') as handle:return hashlib.file_digest(handle,'sha256').hexdigest()
with TemporaryDirectory(prefix='xbcatm-sparse-') as directory:
    root=Path(directory);path=root/'sparse';fd=os.open(path,os.O_RDWR|os.O_CREAT|os.O_EXCL,0o600)
    try:
        os.lseek(fd,size,os.SEEK_SET);assert os.fstat(fd).st_size==0
        os.ftruncate(fd,size);assert os.fstat(fd).st_size==size and os.fstat(fd).st_blocks==0
        assert os.pread(fd,16,0)==b'\0'*16
        os.pwrite(fd,b'A',first);os.pwrite(fd,b'B',second);os.fsync(fd)
        allocated=os.fstat(fd).st_blocks*512;assert allocated<size
        data_start=os.lseek(fd,0,os.SEEK_DATA);hole_start=os.lseek(fd,data_start,os.SEEK_HOLE)
        assert data_start==first and first<hole_start<=second
        print('seek alone leaves size zero; truncate creates zero-reading holes; sparse size',size,'allocated',allocated)
        print('first SEEK_DATA',data_start,'following SEEK_HOLE',hole_start)
        dense=root/'dense'
        with path.open('rb') as source,dense.open('wb') as target:
            while chunk:=source.read(65536):target.write(chunk)
            target.flush();os.fsync(target.fileno())
        assert digest(path)==digest(dense)
        assert dense.stat().st_blocks*512>=size
        print('explicitly writing all copied bytes preserves content but allocates the zero-filled ranges')
        result=libc.fallocate(fd,0x01|0x02,first,4096)  # KEEP_SIZE | PUNCH_HOLE
        assert result==0,os.strerror(ctypes.get_errno())
        os.fsync(fd)
        assert os.fstat(fd).st_size==size and os.pread(fd,1,first)==b'\0'
        assert os.pread(fd,1,second)==b'B' and os.fstat(fd).st_blocks*512<allocated
        print('punching the aligned data range releases its blocks and makes it read zero without changing file length')
        reserved=root/'reserved'
        with reserved.open('w+b') as handle:
            os.posix_fallocate(handle.fileno(),0,size);os.fsync(handle.fileno())
            info=os.fstat(handle.fileno());assert info.st_size==size and info.st_blocks*512>=size
            assert handle.read(16)==b'\0'*16
        print('preallocation reserves blocks even while the newly allocated range reads as zeros')
    finally:os.close(fd)