fncache: avoid loading the filename cache when not actually modifying it
With time, fncache can become very large. The mozilla-central repo for example,
has a 31M and growing fncache file. Loading this file takes time (280ms for the
mozilla-central repository).
In many scenarios, we don't need to load fncache at all. For example, when
committing changes to existing files, or pushing such commits to another clone.
This patch detects when a name is added via store.vfs(), and only loads the
cache if a) the data metadata file doesn't already exist, or b) when opening
for appending, the data or metadata file exists but has size (a transaction
rollback leaves behind such files).
Benchmarks (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz
and flash drive), each test without and with patch run 5 times:
* committing to an existing file, against the mozilla-central repository.
Baseline real time average 2.3736, with patch 1.9884.
* unbundling a large changeset consisting *only* of existing-file modifications
(159 revisions, 1050 modifications, mozilla-central
4a250a0e4f29:beea9ac7d823), into a clone limited to the ancestor revision of
that revset). Baseline real time average 1.5048, with patch 1.3108.
#!/usr/bin/env python
#
# check-py3-compat - check Python 3 compatibility of Mercurial files
#
# Copyright 2015 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function
import ast
import importlib
import os
import sys
import traceback
def check_compat_py2(f):
"""Check Python 3 compatibility for a file with Python 2"""
with open(f, 'rb') as fh:
content = fh.read()
root = ast.parse(content)
# Ignore empty files.
if not root.body:
return
futures = set()
haveprint = False
for node in ast.walk(root):
if isinstance(node, ast.ImportFrom):
if node.module == '__future__':
futures |= set(n.name for n in node.names)
elif isinstance(node, ast.Print):
haveprint = True
if 'absolute_import' not in futures:
print('%s not using absolute_import' % f)
if haveprint and 'print_function' not in futures:
print('%s requires print_function' % f)
def check_compat_py3(f):
"""Check Python 3 compatibility of a file with Python 3."""
with open(f, 'rb') as fh:
content = fh.read()
try:
ast.parse(content)
except SyntaxError as e:
print('%s: invalid syntax: %s' % (f, e))
return
# Try to import the module.
# For now we only support modules in packages because figuring out module
# paths for things not in a package can be confusing.
if (f.startswith(('hgdemandimport/', 'hgext/', 'mercurial/'))
and not f.endswith('__init__.py')):
assert f.endswith('.py')
name = f.replace('/', '.')[:-3]
try:
importlib.import_module(name)
except Exception as e:
exc_type, exc_value, tb = sys.exc_info()
# We walk the stack and ignore frames from our custom importer,
# import mechanisms, and stdlib modules. This kinda/sorta
# emulates CPython behavior in import.c while also attempting
# to pin blame on a Mercurial file.
for frame in reversed(traceback.extract_tb(tb)):
if frame.name == '_call_with_frames_removed':
continue
if 'importlib' in frame.filename:
continue
if 'mercurial/__init__.py' in frame.filename:
continue
if frame.filename.startswith(sys.prefix):
continue
break
if frame.filename:
filename = os.path.basename(frame.filename)
print('%s: error importing: <%s> %s (error at %s:%d)' % (
f, type(e).__name__, e, filename, frame.lineno))
else:
print('%s: error importing module: <%s> %s (line %d)' % (
f, type(e).__name__, e, frame.lineno))
if __name__ == '__main__':
if sys.version_info[0] == 2:
fn = check_compat_py2
else:
fn = check_compat_py3
for f in sys.argv[1:]:
fn(f)
sys.exit(0)