bpo-33671: efficient zero-copy for shutil.copy* functions (Linux, OSX and Win) (#7160)

* have shutil.copyfileobj use sendfile() if possible

* refactoring: use ctx manager

* add test with non-regular file obj

* emulate case where file size can't be determined

* reference _copyfileobj_sendfile directly

* add test for offset() at certain position

* add test for empty file

* add test for non regular file dst

* small refactoring

* leave copyfileobj() alone in order to not introduce any incompatibility

* minor refactoring

* remove old test

* update docstring

* update docstring; rename exception class

* detect platforms which only support file to socket zero copy

* don't run test on platforms where file-to-file zero copy is not supported

* use tempfiles

* reset verbosity

* add test for smaller chunks

* add big file size test

* add comment

* update doc

* update whatsnew doc

* update doc

* catch Exception

* remove unused import

* add test case for error on second sendfile() call

* turn docstring into comment

* add one more test

* update comment

* add Misc/NEWS entry

* get rid of COPY_BUFSIZE; it belongs to another PR

* update doc

* expose posix._fcopyfile() for OSX

* merge from linux branch

* merge from linux branch

* expose fcopyfile

* arg clinic for the win implementation

* convert path type to path_t

* expose CopyFileW

* fix windows tests

* release GIL

* minor refactoring

* update doc

* update comment

* update docstrings

* rename functions

* rename test classes

* update doc

* update doc

* update docstrings and comments

* avoid do import nt|posix modules if unnecessary

* set nt|posix modules to None if not available

* micro speedup

* update description

* add doc note

* use better wording in doc

* rename function using 'fastcopy' prefix instead of 'zerocopy'

* use :ref: in rst doc

* change wording in doc

* add test to make sure sendfile() doesn't get called aymore in case it doesn't support file to file copies

* move CopyFileW in _winapi and actually expose CopyFileExW instead

* fix line endings

* add tests for mode bits

* add docstring

* remove test file mode class; let's keep it for later when Istart addressing OSX fcopyfile() specific copies

* update doc to reflect new changes

* update doc

* adjust tests on win

* fix argument clinic error

* update doc

* OSX: expose copyfile(3) instead of fcopyfile(3); also expose flags arg to python

* osx / copyfile: use path_t instead of char

* do not set dst name in the OSError exception in order to remain consistent with platforms which cannot do that (e.g. linux)

* add same file test

* add test for same file

* have osx copyfile() pre-emptively check if src and dst are the same, otherwise it will return immedialtey and src file content gets deleted

* turn PermissionError into appropriate SameFileError

* expose ERROR_SHARING_VIOLATION in order to raise more appropriate SameFileError

* honour follow_symlinks arg when using CopyFileEx

* update Misc/NEWS

* expose CreateDirectoryEx mock

* change C type

* CreateDirectoryExW actual implementation

* provide specific makedirs() implementation for win

* fix typo

* skeleton for SetNamedSecurityInfo

* get security info for src path

* finally set security attrs

* add unit tests

* mimick os.makedirs() behavior and raise if dst dir exists

* set 2 paths for OSError object

* set 2 paths for OSError object

* expand windows test

* in case of exception on os.sendfile() set filename and filename2 exception attributes

* set 2 filenames (src, dst) for OSError in case copyfile() fails on OSX

* update doc

* do not use CreateDirectoryEx() in copytree() if source dir is a symlink (breaks test_copytree_symlink_dir); instead just create a plain dir and remain consistent with POSIX implementation

* use bytearray() and readinto()

* use memoryview() with bytearray()

* refactoring + introduce a new _fastcopy_binfileobj() fun

* remove CopyFileEx and other C wrappers

* remove code related to CopyFileEx

* Recognize binary files in copyfileobj()
...and use fastest _fastcopy_binfileobj() when possible

* set 1MB copy bufsize on win; also add a global _COPY_BUFSIZE variable

* use ctx manager for memoryview()

* update doc

* remove outdated doc

* remove last CopyFileEx remnants

* OSX - use fcopyfile(3) instead of copyfile(3)

...as an extra safety measure: in case src/dst are "exotic" files (non
regular or living on a network fs etc.) we better fail on open() instead
of copyfile(3) as we're not quite sure what's gonna happen in that
case.

* update doc

1 files changed, 292 insertions, 2 deletions

diff --git a/Lib/test/test_shutil.py b/Lib/test/test_shutil.py
index 2cb2f14..8d51994 100644
--- a/Lib/test/test_shutil.py
+++ b/Lib/test/test_shutil.py
@@ -12,20 +12,28 @@ import errno
 import functools
 import pathlib
 import subprocess
+import random
+import string
+import contextlib
+import io
 from shutil import (make_archive,
                     register_archive_format, unregister_archive_format,
                     get_archive_formats, Error, unpack_archive,
                     register_unpack_format, RegistryError,
                     unregister_unpack_format, get_unpack_formats,
-                    SameFileError)
+                    SameFileError, _GiveupOnFastCopy)
 import tarfile
 import zipfile
+try:
+    import posix
+except ImportError:
+    posix = None
 
 from test import support
 from test.support import TESTFN, FakePath
 
 TESTFN2 = TESTFN + "2"
-
+OSX = sys.platform.startswith("darwin")
 try:
     import grp
     import pwd
@@ -60,6 +68,24 @@ def write_file(path, content, binary=False):
     with open(path, 'wb' if binary else 'w') as fp:
         fp.write(content)
 
+def write_test_file(path, size):
+    """Create a test file with an arbitrary size and random text content."""
+    def chunks(total, step):
+        assert total >= step
+        while total > step:
+            yield step
+            total -= step
+        if total:
+            yield total
+
+    bufsize = min(size, 8192)
+    chunk = b"".join([random.choice(string.ascii_letters).encode()
+                      for i in range(bufsize)])
+    with open(path, 'wb') as f:
+        for csize in chunks(size, bufsize):
+            f.write(chunk)
+    assert os.path.getsize(path) == size
+
 def read_file(path, binary=False):
     """Return contents from a file located at *path*.
 
@@ -84,6 +110,37 @@ def rlistdir(path):
             res.append(name)
     return res
 
+def supports_file2file_sendfile():
+    # ...apparently Linux and Solaris are the only ones
+    if not hasattr(os, "sendfile"):
+        return False
+    srcname = None
+    dstname = None
+    try:
+        with tempfile.NamedTemporaryFile("wb", delete=False) as f:
+            srcname = f.name
+            f.write(b"0123456789")
+
+        with open(srcname, "rb") as src:
+            with tempfile.NamedTemporaryFile("wb", delete=False) as dst:
+                dstname = f.name
+                infd = src.fileno()
+                outfd = dst.fileno()
+                try:
+                    os.sendfile(outfd, infd, 0, 2)
+                except OSError:
+                    return False
+                else:
+                    return True
+    finally:
+        if srcname is not None:
+            support.unlink(srcname)
+        if dstname is not None:
+            support.unlink(dstname)
+
+
+SUPPORTS_SENDFILE = supports_file2file_sendfile()
+
 
 class TestShutil(unittest.TestCase):
 
@@ -1401,6 +1458,8 @@ class TestShutil(unittest.TestCase):
         self.assertRaises(SameFileError, shutil.copyfile, src_file, src_file)
         # But Error should work too, to stay backward compatible.
         self.assertRaises(Error, shutil.copyfile, src_file, src_file)
+        # Make sure file is not corrupted.
+        self.assertEqual(read_file(src_file), 'foo')
 
     def test_copytree_return_value(self):
         # copytree returns its destination path.
@@ -1749,6 +1808,7 @@ class TestCopyFile(unittest.TestCase):
 
         self.assertRaises(OSError, shutil.copyfile, 'srcfile', 'destfile')
 
+    @unittest.skipIf(OSX, "skipped on OSX")
     def test_w_dest_open_fails(self):
 
         srcfile = self.Faux()
@@ -1768,6 +1828,7 @@ class TestCopyFile(unittest.TestCase):
         self.assertEqual(srcfile._exited_with[1].args,
                          ('Cannot open "destfile"',))
 
+    @unittest.skipIf(OSX, "skipped on OSX")
     def test_w_dest_close_fails(self):
 
         srcfile = self.Faux()
@@ -1790,6 +1851,7 @@ class TestCopyFile(unittest.TestCase):
         self.assertEqual(srcfile._exited_with[1].args,
                          ('Cannot close',))
 
+    @unittest.skipIf(OSX, "skipped on OSX")
     def test_w_source_close_fails(self):
 
         srcfile = self.Faux(True)
@@ -1829,6 +1891,234 @@ class TestCopyFile(unittest.TestCase):
         finally:
             os.rmdir(dst_dir)
 
+
+class _ZeroCopyFileTest(object):
+    """Tests common to all zero-copy APIs."""
+    FILESIZE = (10 * 1024 * 1024)  # 10 MiB
+    FILEDATA = b""
+    PATCHPOINT = ""
+
+    @classmethod
+    def setUpClass(cls):
+        write_test_file(TESTFN, cls.FILESIZE)
+        with open(TESTFN, 'rb') as f:
+            cls.FILEDATA = f.read()
+            assert len(cls.FILEDATA) == cls.FILESIZE
+
+    @classmethod
+    def tearDownClass(cls):
+        support.unlink(TESTFN)
+
+    def tearDown(self):
+        support.unlink(TESTFN2)
+
+    @contextlib.contextmanager
+    def get_files(self):
+        with open(TESTFN, "rb") as src:
+            with open(TESTFN2, "wb") as dst:
+                yield (src, dst)
+
+    def zerocopy_fun(self, *args, **kwargs):
+        raise NotImplementedError("must be implemented in subclass")
+
+    def reset(self):
+        self.tearDown()
+        self.tearDownClass()
+        self.setUpClass()
+        self.setUp()
+
+    # ---
+
+    def test_regular_copy(self):
+        with self.get_files() as (src, dst):
+            self.zerocopy_fun(src, dst)
+        self.assertEqual(read_file(TESTFN2, binary=True), self.FILEDATA)
+        # Make sure the fallback function is not called.
+        with self.get_files() as (src, dst):
+            with unittest.mock.patch('shutil.copyfileobj') as m:
+                shutil.copyfile(TESTFN, TESTFN2)
+            assert not m.called
+
+    def test_same_file(self):
+        self.addCleanup(self.reset)
+        with self.get_files() as (src, dst):
+            with self.assertRaises(Exception):
+                self.zerocopy_fun(src, src)
+        # Make sure src file is not corrupted.
+        self.assertEqual(read_file(TESTFN, binary=True), self.FILEDATA)
+
+    def test_non_existent_src(self):
+        name = tempfile.mktemp()
+        with self.assertRaises(FileNotFoundError) as cm:
+            shutil.copyfile(name, "new")
+        self.assertEqual(cm.exception.filename, name)
+
+    def test_empty_file(self):
+        srcname = TESTFN + 'src'
+        dstname = TESTFN + 'dst'
+        self.addCleanup(lambda: support.unlink(srcname))
+        self.addCleanup(lambda: support.unlink(dstname))
+        with open(srcname, "wb"):
+            pass
+
+        with open(srcname, "rb") as src:
+            with open(dstname, "wb") as dst:
+                self.zerocopy_fun(src, dst)
+
+        self.assertEqual(read_file(dstname, binary=True), b"")
+
+    def test_unhandled_exception(self):
+        with unittest.mock.patch(self.PATCHPOINT,
+                                 side_effect=ZeroDivisionError):
+            self.assertRaises(ZeroDivisionError,
+                              shutil.copyfile, TESTFN, TESTFN2)
+
+    def test_exception_on_first_call(self):
+        # Emulate a case where the first call to the zero-copy
+        # function raises an exception in which case the function is
+        # supposed to give up immediately.
+        with unittest.mock.patch(self.PATCHPOINT,
+                                 side_effect=OSError(errno.EINVAL, "yo")):
+            with self.get_files() as (src, dst):
+                with self.assertRaises(_GiveupOnFastCopy):
+                    self.zerocopy_fun(src, dst)
+
+    def test_filesystem_full(self):
+        # Emulate a case where filesystem is full and sendfile() fails
+        # on first call.
+        with unittest.mock.patch(self.PATCHPOINT,
+                                 side_effect=OSError(errno.ENOSPC, "yo")):
+            with self.get_files() as (src, dst):
+                self.assertRaises(OSError, self.zerocopy_fun, src, dst)
+
+
+@unittest.skipIf(not SUPPORTS_SENDFILE, 'os.sendfile() not supported')
+class TestZeroCopySendfile(_ZeroCopyFileTest, unittest.TestCase):
+    PATCHPOINT = "os.sendfile"
+
+    def zerocopy_fun(self, fsrc, fdst):
+        return shutil._fastcopy_sendfile(fsrc, fdst)
+
+    def test_non_regular_file_src(self):
+        with io.BytesIO(self.FILEDATA) as src:
+            with open(TESTFN2, "wb") as dst:
+                with self.assertRaises(_GiveupOnFastCopy):
+                    self.zerocopy_fun(src, dst)
+                shutil.copyfileobj(src, dst)
+
+        self.assertEqual(read_file(TESTFN2, binary=True), self.FILEDATA)
+
+    def test_non_regular_file_dst(self):
+        with open(TESTFN, "rb") as src:
+            with io.BytesIO() as dst:
+                with self.assertRaises(_GiveupOnFastCopy):
+                    self.zerocopy_fun(src, dst)
+                shutil.copyfileobj(src, dst)
+                dst.seek(0)
+                self.assertEqual(dst.read(), self.FILEDATA)
+
+    def test_exception_on_second_call(self):
+        def sendfile(*args, **kwargs):
+            if not flag:
+                flag.append(None)
+                return orig_sendfile(*args, **kwargs)
+            else:
+                raise OSError(errno.EBADF, "yo")
+
+        flag = []
+        orig_sendfile = os.sendfile
+        with unittest.mock.patch('os.sendfile', create=True,
+                                 side_effect=sendfile):
+            with self.get_files() as (src, dst):
+                with self.assertRaises(OSError) as cm:
+                    shutil._fastcopy_sendfile(src, dst)
+        assert flag
+        self.assertEqual(cm.exception.errno, errno.EBADF)
+
+    def test_cant_get_size(self):
+        # Emulate a case where src file size cannot be determined.
+        # Internally bufsize will be set to a small value and
+        # sendfile() will be called repeatedly.
+        with unittest.mock.patch('os.fstat', side_effect=OSError) as m:
+            with self.get_files() as (src, dst):
+                shutil._fastcopy_sendfile(src, dst)
+                assert m.called
+        self.assertEqual(read_file(TESTFN2, binary=True), self.FILEDATA)
+
+    def test_small_chunks(self):
+        # Force internal file size detection to be smaller than the
+        # actual file size. We want to force sendfile() to be called
+        # multiple times, also in order to emulate a src fd which gets
+        # bigger while it is being copied.
+        mock = unittest.mock.Mock()
+        mock.st_size = 65536 + 1
+        with unittest.mock.patch('os.fstat', return_value=mock) as m:
+            with self.get_files() as (src, dst):
+                shutil._fastcopy_sendfile(src, dst)
+                assert m.called
+        self.assertEqual(read_file(TESTFN2, binary=True), self.FILEDATA)
+
+    def test_big_chunk(self):
+        # Force internal file size detection to be +100MB bigger than
+        # the actual file size. Make sure sendfile() does not rely on
+        # file size value except for (maybe) a better throughput /
+        # performance.
+        mock = unittest.mock.Mock()
+        mock.st_size = self.FILESIZE + (100 * 1024 * 1024)
+        with unittest.mock.patch('os.fstat', return_value=mock) as m:
+            with self.get_files() as (src, dst):
+                shutil._fastcopy_sendfile(src, dst)
+                assert m.called
+        self.assertEqual(read_file(TESTFN2, binary=True), self.FILEDATA)
+
+    def test_blocksize_arg(self):
+        with unittest.mock.patch('os.sendfile',
+                                 side_effect=ZeroDivisionError) as m:
+            self.assertRaises(ZeroDivisionError,
+                              shutil.copyfile, TESTFN, TESTFN2)
+            blocksize = m.call_args[0][3]
+            # Make sure file size and the block size arg passed to
+            # sendfile() are the same.
+            self.assertEqual(blocksize, os.path.getsize(TESTFN))
+            # ...unless we're dealing with a small file.
+            support.unlink(TESTFN2)
+            write_file(TESTFN2, b"hello", binary=True)
+            self.addCleanup(support.unlink, TESTFN2 + '3')
+            self.assertRaises(ZeroDivisionError,
+                              shutil.copyfile, TESTFN2, TESTFN2 + '3')
+            blocksize = m.call_args[0][3]
+            self.assertEqual(blocksize, 2 ** 23)
+
+    def test_file2file_not_supported(self):
+        # Emulate a case where sendfile() only support file->socket
+        # fds. In such a case copyfile() is supposed to skip the
+        # fast-copy attempt from then on.
+        assert shutil._HAS_SENDFILE
+        try:
+            with unittest.mock.patch(
+                    self.PATCHPOINT,
+                    side_effect=OSError(errno.ENOTSOCK, "yo")) as m:
+                with self.get_files() as (src, dst):
+                    with self.assertRaises(_GiveupOnFastCopy):
+                        shutil._fastcopy_sendfile(src, dst)
+                assert m.called
+            assert not shutil._HAS_SENDFILE
+
+            with unittest.mock.patch(self.PATCHPOINT) as m:
+                shutil.copyfile(TESTFN, TESTFN2)
+                assert not m.called
+        finally:
+            shutil._HAS_SENDFILE = True
+
+
+@unittest.skipIf(not OSX, 'OSX only')
+class TestZeroCopyOSX(_ZeroCopyFileTest, unittest.TestCase):
+    PATCHPOINT = "posix._fcopyfile"
+
+    def zerocopy_fun(self, src, dst):
+        return shutil._fastcopy_osx(src, dst, posix._COPYFILE_DATA)
+
+
 class TermsizeTests(unittest.TestCase):
     def test_does_not_crash(self):
         """Check if get_terminal_size() returns a meaningful value.