bpo-43785: Improve BZ2File performance by removing RLock (GH-25299)

Remove `RLock` from `BZ2File`. It makes `BZ2File` to thread unsafe, but
gzip and lzma don't use it too.

Co-authored-by: Gregory P. Smith <greg@krypto.org>

Lib/bz2.py

@@ -13,7 +13,6 @@
 import io
 import os
 import _compression
-from threading import RLock
 
 from _bz2 import BZ2Compressor, BZ2Decompressor
 
@@ -53,9 +52,6 @@
         If mode is 'r', the input file may be the concatenation of
         multiple compressed streams.
         """
-        # This lock must be recursive, so that BufferedIOBase's
-        # writelines() does not deadlock.
-        self._lock = RLock()
         self._fp = None
         self._closefp = False
         self._mode = _MODE_CLOSED
@@ -104,7 +100,6 @@
         May be called more than once without error. Once the file is
         closed, any other operation on it will raise a ValueError.
         """
-        with self._lock:
         if self._mode == _MODE_CLOSED:
             return
         try:
@@ -153,7 +148,6 @@
         Always returns at least one byte of data, unless at EOF.
         The exact number of bytes returned is unspecified.
         """
-        with self._lock:
         self._check_can_read()
         # Relies on the undocumented fact that BufferedReader.peek()
         # always returns at least one byte (except at EOF), independent
@@ -166,7 +160,6 @@
         If size is negative or omitted, read until EOF is reached.
         Returns b'' if the file is already at EOF.
         """
-        with self._lock:
         self._check_can_read()
         return self._buffer.read(size)
 
@@ -177,7 +170,6 @@
 
         Returns b'' if the file is at EOF.
         """
-        with self._lock:
         self._check_can_read()
         if size < 0:
             size = io.DEFAULT_BUFFER_SIZE
@@ -188,7 +180,6 @@
 
         Returns the number of bytes read (0 for EOF).
         """
-        with self._lock:
         self._check_can_read()
         return self._buffer.readinto(b)
 
@@ -203,7 +194,6 @@
             if not hasattr(size, "__index__"):
                 raise TypeError("Integer argument expected")
             size = size.__index__()
-        with self._lock:
         self._check_can_read()
         return self._buffer.readline(size)
 
@@ -218,7 +208,6 @@
             if not hasattr(size, "__index__"):
                 raise TypeError("Integer argument expected")
             size = size.__index__()
-        with self._lock:
         self._check_can_read()
         return self._buffer.readlines(size)
 
@@ -229,7 +218,6 @@
         always len(data). Note that due to buffering, the file on disk
         may not reflect the data written until close() is called.
         """
-        with self._lock:
         self._check_can_write()
         compressed = self._compressor.compress(data)
         self._fp.write(compressed)
@@ -244,7 +232,6 @@
 
         Line separators are not added between the written byte strings.
         """
-        with self._lock:
         return _compression.BaseStream.writelines(self, seq)
 
     def seek(self, offset, whence=io.SEEK_SET):
@@ -262,9 +249,8 @@
         Note that seeking is emulated, so depending on the parameters,
         this operation may be extremely slow.
         """
-        with self._lock:
         self._check_can_seek()
         return self._buffer.seek(offset, whence)
 
     def tell(self):
         """Return the current file position."""
@@ -266,9 +252,8 @@
         self._check_can_seek()
         return self._buffer.seek(offset, whence)
 
     def tell(self):
         """Return the current file position."""
-        with self._lock:
         self._check_not_closed()
         if self._mode == _MODE_READ:
             return self._buffer.tell()

Misc/NEWS.d/next/Library/2021-04-09-14-51-58.bpo-43785.1mM5xE.rst

+Improve ``bz2.BZ2File`` performance by removing the RLock from BZ2File.
+This makes BZ2File thread unsafe in the face of multiple simultaneous
+readers or writers, just like its equivalent classes in :mod:`gzip` and
+:mod:`lzma` have always been.  Patch by Inada Naoki.