fix issue #17552: add socket.sendfile() method allowing to send a file over a socket by using high-performance os.sendfile() on UNIX. Patch by Giampaolo Rodola'·

giampaolo · giampaolo · commit 915d14190ee0 · 2014-06-11T03:54:30.000+02:00
diff --git a/Doc/library/os.rst b/Doc/library/os.rst
@@ -1092,6 +1092,10 @@ or `the MSDN <http://msdn.microsoft.com/en-us/library/z0kc8e3z.aspx>`_ on Window
 
    Availability: Unix.
 
+   .. note::
+
+      For a higher-level version of this see :mod:`socket.socket.sendfile`.
+
    .. versionadded:: 3.3
 
 
diff --git a/Doc/library/socket.rst b/Doc/library/socket.rst
@@ -1148,6 +1148,21 @@ to sockets.
 
    .. versionadded:: 3.3
 
+.. method:: socket.sendfile(file, offset=0, count=None)
+
+   Send a file until EOF is reached by using high-performance
+   :mod:`os.sendfile` and return the total number of bytes which were sent.
+   *file* must be a regular file object opened in binary mode. If
+   :mod:`os.sendfile` is not available (e.g. Windows) or *file* is not a
+   regular file :meth:`send` will be used instead. *offset* tells from where to
+   start reading the file. If specified, *count* is the total number of bytes
+   to transmit as opposed to sending the file until EOF is reached. File
+   position is updated on return or also in case of error in which case
+   :meth:`file.tell() <io.IOBase.tell>` can be used to figure out the number of
+   bytes which were sent. The socket must be of :const:`SOCK_STREAM` type. Non-
+   blocking sockets are not supported.
+
+   .. versionadded:: 3.5
 
 .. method:: socket.set_inheritable(inheritable)
 
diff --git a/Doc/library/ssl.rst b/Doc/library/ssl.rst
@@ -789,6 +789,9 @@ SSL sockets provide the following methods of :ref:`socket-objects`:
   (but passing a non-zero ``flags`` argument is not allowed)
 - :meth:`~socket.socket.send()`, :meth:`~socket.socket.sendall()` (with
   the same limitation)
+- :meth:`~socket.socket.sendfile()` (but :mod:`os.sendfile` will be used
+  for plain-text sockets only, else :meth:`~socket.socket.send()` will be used)
+   .. versionadded:: 3.5
 - :meth:`~socket.socket.shutdown()`
 
 However, since the SSL (and TLS) protocol has its own framing atop
diff --git a/Doc/whatsnew/3.5.rst b/Doc/whatsnew/3.5.rst
@@ -181,9 +181,18 @@ signal
 
 * Different constants of :mod:`signal` module are now enumeration values using
   the :mod:`enum` module. This allows meaningful names to be printed during
-  debugging, instead of integer “magic numbers”. (contribute by Giampaolo
+  debugging, instead of integer “magic numbers”. (contributed by Giampaolo
   Rodola' in :issue:`21076`)
 
+socket
+------
+
+* New :meth:`socket.socket.sendfile` method allows to send a file over a socket
+  by using high-performance :func:`os.sendfile` function on UNIX resulting in
+  uploads being from 2x to 3x faster than when using plain
+  :meth:`socket.socket.send`.
+  (contributed by Giampaolo Rodola' in :issue:`17552`)
+
 xmlrpc
 ------
 
diff --git a/Lib/socket.py b/Lib/socket.py
@@ -47,7 +47,7 @@
 import _socket
 from _socket import *
 
-import os, sys, io
+import os, sys, io, selectors
 from enum import IntEnum
 
 try:
@@ -109,6 +109,9 @@ def _intenum_converter(value, enum_klass):
     __all__.append("errorTab")
 
 
+class _GiveupOnSendfile(Exception): pass
+
+
 class socket(_socket.socket):
 
     """A subclass of _socket.socket adding the makefile() method."""
@@ -233,6 +236,149 @@ def makefile(self, mode="r", buffering=None, *,
         text.mode = mode
         return text
 
+    if hasattr(os, 'sendfile'):
+
+        def _sendfile_use_sendfile(self, file, offset=0, count=None):
+            self._check_sendfile_params(file, offset, count)
+            sockno = self.fileno()
+            try:
+                fileno = file.fileno()
+            except (AttributeError, io.UnsupportedOperation) as err:
+                raise _GiveupOnSendfile(err)  # not a regular file
+            try:
+                fsize = os.fstat(fileno).st_size
+            except OSError:
+                raise _GiveupOnSendfile(err)  # not a regular file
+            if not fsize:
+                return 0  # empty file
+            blocksize = fsize if not count else count
+
+            timeout = self.gettimeout()
+            if timeout == 0:
+                raise ValueError("non-blocking sockets are not supported")
+            # poll/select have the advantage of not requiring any
+            # extra file descriptor, contrarily to epoll/kqueue
+            # (also, they require a single syscall).
+            if hasattr(selectors, 'PollSelector'):
+                selector = selectors.PollSelector()
+            else:
+                selector = selectors.SelectSelector()
+            selector.register(sockno, selectors.EVENT_WRITE)
+
+            total_sent = 0
+            # localize variable access to minimize overhead
+            selector_select = selector.select
+            os_sendfile = os.sendfile
+            try:
+                while True:
+                    if timeout and not selector_select(timeout):
+                        raise _socket.timeout('timed out')
+                    if count:
+                        blocksize = count - total_sent
+                        if blocksize <= 0:
+                            break
+                    try:
+                        sent = os_sendfile(sockno, fileno, offset, blocksize)
+                    except BlockingIOError:
+                        if not timeout:
+                            # Block until the socket is ready to send some
+                            # data; avoids hogging CPU resources.
+                            selector_select()
+                        continue
+                    except OSError as err:
+                        if total_sent == 0:
+                            # We can get here for different reasons, the main
+                            # one being 'file' is not a regular mmap(2)-like
+                            # file, in which case we'll fall back on using
+                            # plain send().
+                            raise _GiveupOnSendfile(err)
+                        raise err from None
+                    else:
+                        if sent == 0:
+                            break  # EOF
+                        offset += sent
+                        total_sent += sent
+                return total_sent
+            finally:
+                if total_sent > 0 and hasattr(file, 'seek'):
+                    file.seek(offset)
+    else:
+        def _sendfile_use_sendfile(self, file, offset=0, count=None):
+            raise _GiveupOnSendfile(
+                "os.sendfile() not available on this platform")
+
+    def _sendfile_use_send(self, file, offset=0, count=None):
+        self._check_sendfile_params(file, offset, count)
+        if self.gettimeout() == 0:
+            raise ValueError("non-blocking sockets are not supported")
+        if offset:
+            file.seek(offset)
+        blocksize = min(count, 8192) if count else 8192
+        total_sent = 0
+        # localize variable access to minimize overhead
+        file_read = file.read
+        sock_send = self.send
+        try:
+            while True:
+                if count:
+                    blocksize = min(count - total_sent, blocksize)
+                    if blocksize <= 0:
+                        break
+                data = memoryview(file_read(blocksize))
+                if not data:
+                    break  # EOF
+                while True:
+                    try:
+                        sent = sock_send(data)
+                    except BlockingIOError:
+                        continue
+                    else:
+                        total_sent += sent
+                        if sent < len(data):
+                            data = data[sent:]
+                        else:
+                            break
+            return total_sent
+        finally:
+            if total_sent > 0 and hasattr(file, 'seek'):
+                file.seek(offset + total_sent)
+
+    def _check_sendfile_params(self, file, offset, count):
+        if 'b' not in getattr(file, 'mode', 'b'):
+            raise ValueError("file should be opened in binary mode")
+        if not self.type & SOCK_STREAM:
+            raise ValueError("only SOCK_STREAM type sockets are supported")
+        if count is not None:
+            if not isinstance(count, int):
+                raise TypeError(
+                    "count must be a positive integer (got {!r})".format(count))
+            if count <= 0:
+                raise ValueError(
+                    "count must be a positive integer (got {!r})".format(count))
+
+    def sendfile(self, file, offset=0, count=None):
+        """sendfile(file[, offset[, count]]) -> sent
+
+        Send a file until EOF is reached by using high-performance
+        os.sendfile() and return the total number of bytes which
+        were sent.
+        *file* must be a regular file object opened in binary mode.
+        If os.sendfile() is not available (e.g. Windows) or file is
+        not a regular file socket.send() will be used instead.
+        *offset* tells from where to start reading the file.
+        If specified, *count* is the total number of bytes to transmit
+        as opposed to sending the file until EOF is reached.
+        File position is updated on return or also in case of error in
+        which case file.tell() can be used to figure out the number of
+        bytes which were sent.
+        The socket must be of SOCK_STREAM type.
+        Non-blocking sockets are not supported.
+        """
+        try:
+            return self._sendfile_use_sendfile(file, offset, count)
+        except _GiveupOnSendfile:
+            return self._sendfile_use_send(file, offset, count)
+
     def _decref_socketios(self):
         if self._io_refs > 0:
             self._io_refs -= 1
diff --git a/Lib/ssl.py b/Lib/ssl.py
@@ -700,6 +700,16 @@ def sendall(self, data, flags=0):
         else:
             return socket.sendall(self, data, flags)
 
+    def sendfile(self, file, offset=0, count=None):
+        """Send a file, possibly by using os.sendfile() if this is a
+        clear-text socket.  Return the total number of bytes sent.
+        """
+        if self._sslobj is None:
+            # os.sendfile() works with plain sockets only
+            return super().sendfile(file, offset, count)
+        else:
+            return self._sendfile_use_send(file, offset, count)
+
     def recv(self, buflen=1024, flags=0):
         self._checkClosed()
         if self._sslobj:
diff --git a/Lib/test/test_socket.py b/Lib/test/test_socket.py
diff --git a/Lib/test/test_ssl.py b/Lib/test/test_ssl.py
diff --git a/Misc/NEWS b/Misc/NEWS
