GH-120754: Disable buffering in Path.read_bytes (#122111)

`Path.read_bytes()` is used to read a whole file. buffering /
BufferedIO is focused around making small, possibly interleaved,
read/write efficient which doesn't add value in this case.

On my Mac, running the benchmark:

```python
import pyperf
from pathlib import Path

def read_all(all_paths):
    for p in all_paths:
        p.read_bytes()

def read_file(path_obj):
    path_obj.read_bytes()

all_rst = list(Path("Doc").glob("**/*.rst"))
all_py = list(Path(".").glob("**/*.py"))
assert all_rst, "Should have found rst files"
assert all_py, "Should have found python source files"

runner = pyperf.Runner()
runner.bench_func("read_file_small", read_file, Path("Doc/howto/clinic.rst"))
runner.bench_func("read_file_large", read_file, Path("Doc/c-api/typeobj.rst"))
```

before:
```python
.....................
read_file_small: Mean +- std dev: 6.80 us +- 0.07 us
.....................
read_file_large: Mean +- std dev: 10.8 us +- 0.2 us
````

after:
```python
.....................
read_file_small: Mean +- std dev: 5.67 us +- 0.05 us
.....................
read_file_large: Mean +- std dev: 9.77 us +- 0.52 us
```
This commit is contained in:
Cody Maloney 2024-08-16 13:52:41 -07:00 committed by GitHub
parent 8ef358dae1
commit 35d8ac7cd7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 2 deletions

View File

@ -585,7 +585,7 @@ def read_bytes(self):
""" """
Open the file in bytes mode, read it, and close the file. Open the file in bytes mode, read it, and close the file.
""" """
with self.open(mode='rb') as f: with self.open(mode='rb', buffering=0) as f:
return f.read() return f.read()
def read_text(self, encoding=None, errors=None, newline=None): def read_text(self, encoding=None, errors=None, newline=None):

View File

@ -1464,7 +1464,7 @@ def stat(self, *, follow_symlinks=True):
def open(self, mode='r', buffering=-1, encoding=None, def open(self, mode='r', buffering=-1, encoding=None,
errors=None, newline=None): errors=None, newline=None):
if buffering != -1: if buffering != -1 and not (buffering == 0 and 'b' in mode):
raise NotImplementedError raise NotImplementedError
path_obj = self.resolve() path_obj = self.resolve()
path = str(path_obj) path = str(path_obj)

View File

@ -0,0 +1 @@
``Pathlib.read_bytes`` no longer opens the file in Python's buffered I/O mode. This reduces overheads as the code reads a file in whole leading to a modest speedup.