Make framing optional in pickle protocol 4.
This will allow us to control in the future whether to use framing or not.
For example, we may want to turn it off for tiny pickle where it doesn't
help.
The change also improves performance slightly:
### fastpickle ###
Min: 0.608517 -> 0.557358: 1.09x faster
Avg: 0.798892 -> 0.694738: 1.15x faster
Significant (t=3.45)
Stddev: 0.17145 -> 0.12704: 1.3496x smaller
Timeline: http://goo.gl/3xQE1J
### pickle_dict ###
Min: 0.669920 -> 0.615271: 1.09x faster
Avg: 0.733633 -> 0.645058: 1.14x faster
Significant (t=5.05)
Stddev: 0.12041 -> 0.02961: 4.0662x smaller
Timeline: http://goo.gl/LpLSXI
### pickle_list ###
Min: 0.397583 -> 0.368112: 1.08x faster
Avg: 0.412784 -> 0.397223: 1.04x faster
Significant (t=2.78)
Stddev: 0.01518 -> 0.03653: 2.4068x larger
Timeline: http://goo.gl/v39E59
### unpickle_list ###
Min: 0.692935 -> 0.594870: 1.16x faster
Avg: 0.730012 -> 0.628395: 1.16x faster
Significant (t=17.76)
Stddev: 0.02720 -> 0.02995: 1.1012x larger
Timeline: http://goo.gl/2P9AEt
The following not significant results are hidden, use -v to show them:
fastunpickle.
diff --git a/Lib/pickle.py b/Lib/pickle.py
index d1f1538..8449340 100644
--- a/Lib/pickle.py
+++ b/Lib/pickle.py
@@ -188,87 +188,72 @@
self.file_write = file_write
self.current_frame = None
- def _commit_frame(self):
- f = self.current_frame
- with f.getbuffer() as data:
- n = len(data)
- write = self.file_write
- write(FRAME)
- write(pack("<Q", n))
- write(data)
- f.seek(0)
- f.truncate()
-
def start_framing(self):
self.current_frame = io.BytesIO()
def end_framing(self):
- if self.current_frame is not None:
- self._commit_frame()
+ if self.current_frame and self.current_frame.tell() > 0:
+ self.commit_frame(force=True)
self.current_frame = None
+ def commit_frame(self, force=False):
+ if self.current_frame:
+ f = self.current_frame
+ if f.tell() >= self._FRAME_SIZE_TARGET or force:
+ with f.getbuffer() as data:
+ n = len(data)
+ write = self.file_write
+ write(FRAME)
+ write(pack("<Q", n))
+ write(data)
+ f.seek(0)
+ f.truncate()
+
def write(self, data):
- f = self.current_frame
- if f is None:
- return self.file_write(data)
+ if self.current_frame:
+ return self.current_frame.write(data)
else:
- n = len(data)
- if f.tell() >= self._FRAME_SIZE_TARGET:
- self._commit_frame()
- return f.write(data)
+ return self.file_write(data)
+
class _Unframer:
def __init__(self, file_read, file_readline, file_tell=None):
self.file_read = file_read
self.file_readline = file_readline
- self.file_tell = file_tell
- self.framing_enabled = False
self.current_frame = None
- self.frame_start = None
def read(self, n):
- if n == 0:
- return b''
- _file_read = self.file_read
- if not self.framing_enabled:
- return _file_read(n)
- f = self.current_frame
- if f is not None:
- data = f.read(n)
- if data:
- if len(data) < n:
- raise UnpicklingError(
- "pickle exhausted before end of frame")
- return data
- frame_opcode = _file_read(1)
- if frame_opcode != FRAME:
- raise UnpicklingError(
- "expected a FRAME opcode, got {} instead".format(frame_opcode))
- frame_size, = unpack("<Q", _file_read(8))
- if frame_size > sys.maxsize:
- raise ValueError("frame size > sys.maxsize: %d" % frame_size)
- if self.file_tell is not None:
- self.frame_start = self.file_tell()
- f = self.current_frame = io.BytesIO(_file_read(frame_size))
- self.readline = f.readline
- data = f.read(n)
- assert len(data) == n, (len(data), n)
- return data
+ if self.current_frame:
+ data = self.current_frame.read(n)
+ if not data and n != 0:
+ self.current_frame = None
+ return self.file_read(n)
+ if len(data) < n:
+ raise UnpicklingError(
+ "pickle exhausted before end of frame")
+ return data
+ else:
+ return self.file_read(n)
def readline(self):
- if not self.framing_enabled:
+ if self.current_frame:
+ data = self.current_frame.readline()
+ if not data:
+ self.current_frame = None
+ return self.file_readline()
+ if data[-1] != b'\n':
+ raise UnpicklingError(
+ "pickle exhausted before end of frame")
+ return data
+ else:
return self.file_readline()
- else:
- return self.current_frame.readline()
- def tell(self):
- if self.file_tell is None:
- return None
- elif self.current_frame is None:
- return self.file_tell()
- else:
- return self.frame_start + self.current_frame.tell()
+ def load_frame(self, frame_size):
+ if self.current_frame and self.current_frame.read() != b'':
+ raise UnpicklingError(
+ "beginning of a new frame before end of current frame")
+ self.current_frame = io.BytesIO(self.file_read(frame_size))
# Tools used for pickling.
@@ -392,6 +377,8 @@
self._file_write = file.write
except AttributeError:
raise TypeError("file must have a 'write' attribute")
+ self.framer = _Framer(self._file_write)
+ self.write = self.framer.write
self.memo = {}
self.proto = int(protocol)
self.bin = protocol >= 1
@@ -417,18 +404,12 @@
raise PicklingError("Pickler.__init__() was not called by "
"%s.__init__()" % (self.__class__.__name__,))
if self.proto >= 2:
- self._file_write(PROTO + pack("<B", self.proto))
+ self.write(PROTO + pack("<B", self.proto))
if self.proto >= 4:
- framer = _Framer(self._file_write)
- framer.start_framing()
- self.write = framer.write
- else:
- framer = None
- self.write = self._file_write
+ self.framer.start_framing()
self.save(obj)
self.write(STOP)
- if framer is not None:
- framer.end_framing()
+ self.framer.end_framing()
def memoize(self, obj):
"""Store an object in the memo."""
@@ -475,6 +456,8 @@
return GET + repr(i).encode("ascii") + b'\n'
def save(self, obj, save_persistent_id=True):
+ self.framer.commit_frame()
+
# Check for persistent id (defined by a subclass)
pid = self.persistent_id(obj)
if pid is not None and save_persistent_id:
@@ -1078,10 +1061,15 @@
if not 0 <= proto <= HIGHEST_PROTOCOL:
raise ValueError("unsupported pickle protocol: %d" % proto)
self.proto = proto
- if proto >= 4:
- self._unframer.framing_enabled = True
dispatch[PROTO[0]] = load_proto
+ def load_frame(self):
+ frame_size, = unpack('<Q', self.read(8))
+ if frame_size > sys.maxsize:
+ raise ValueError("frame size > sys.maxsize: %d" % frame_size)
+ self._unframer.load_frame(frame_size)
+ dispatch[FRAME[0]] = load_frame
+
def load_persid(self):
pid = self.readline()[:-1].decode("ascii")
self.append(self.persistent_load(pid))