revlog: use mmap by default is pre-population is available
Using mmap has a great impact of memory usage on server, and a good impact on
performance in multiple case. Now that we pre-populate memory mapping by
default, there is case where it using mmap is slower. So we use it by default
(if pre-population is available).
Further work to reduce the performance impact of the pre-population will be done
later.
Some benchmark below (using the same setup as
522b4d729e89):
As for
522b4d729e89 the impact on small repository like Mercurial or Pypy is
tiny, ~1% best. However for large repositories we see some performance
improvement without seeing the performance regression that we could have without
pre-populate.
##### For netbeans
### data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
## benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = rust
# benchmark.variants.limit-rev = 1
# benchmark.variants.patch = yes
no-mmap: 0.171579
mmap: 0.166311 (-3.07%, -0.01)
# bin-env-vars.hg.flavor = default
no-mmap: 0.170716
mmap: 0.165218 (-3.22%, -0.01)
# benchmark.variants.patch = no
# benchmark.variants.rev = tip
no-mmap: 0.140862
mmap: 0.137566 (-2.34%, -0.00)
## benchmark.name = hg.command.unbundle
# bin-env-vars.hg.flavor = rust
# benchmark.variants.
issue6528 = disabled
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
# benchmark.variants.source = unbundle
no-mmap: 0.238038
mmap: 0.239912
no-populate: 0.cbd4c9 (+11.71%, +0.03)
#### For Mozilla
### data-env-vars.name = mozilla-try-2019-02-18-ds2-pnm
# benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = rust
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.limit-rev = 1
# benchmark.variants.patch = yes
no-mmap: 0.258440
mmap: 0.237813 (-7.98%, -0.02)
# benchmark.variants.limit-rev = 10
no-mmap: 1.235323
mmap: 1.213578 (-1.76%, -0.02)
## benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = rust
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = none
# benchmark.variants.
issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
no-mmap: 4.790135
mmap: 4.668971 (-2.53%, -0.12)
no-populate: 4.841141 (+1.06%, +0.05)
### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
## benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = default
# benchmark.variants.limit-rev = 1000
# benchmark.variants.rev = tip
no-mmap: 0.206187
mmap: 0.197348 (-4.29%, -0.01)
## benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# benchmark.variants.explicit-rev = none
# benchmark.variants.
issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
no-mmap: 4.768259
mmap: 4.798632
no-populate: 4.953295 (+3.88%, +0.19)
# benchmark.variants.revs = any-100-extra-rev
no-mmap: 4.785946
mmap: 4.903618
no-populate: 5.014963 (+4.79%, +0.23)
## benchmark.name = hg.command.unbundle
# bin-env-vars.hg.flavor = default
# benchmark.variants.
issue6528 = disabled
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
# benchmark.variants.source = unbundle
no-mmap: 1.400121
mmap: 1.423411
no-populate: 1.585365 (+13.23%, +0.19)
#!/usr/bin/env python3
#
# hggettext - carefully extract docstrings for Mercurial
#
# Copyright 2009 Olivia Mackall <olivia@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
# The normalize function is taken from pygettext which is distributed
# with Python under the Python License, which is GPL compatible.
"""Extract docstrings from Mercurial commands.
Compared to pygettext, this script knows about the cmdtable and table
dictionaries used by Mercurial, and will only extract docstrings from
functions mentioned therein.
Use xgettext like normal to extract strings marked as translatable and
join the message cataloges to get the final catalog.
"""
import inspect
import os
import re
import sys
def escape(s):
# The order is important, the backslash must be escaped first
# since the other replacements introduce new backslashes
# themselves.
s = s.replace('\\', '\\\\')
s = s.replace('\n', '\\n')
s = s.replace('\r', '\\r')
s = s.replace('\t', '\\t')
s = s.replace('"', '\\"')
return s
def normalize(s):
# This converts the various Python string types into a format that
# is appropriate for .po files, namely much closer to C style.
lines = s.split('\n')
if len(lines) == 1:
s = '"' + escape(s) + '"'
else:
if not lines[-1]:
del lines[-1]
lines[-1] = lines[-1] + '\n'
lines = map(escape, lines)
lineterm = '\\n"\n"'
s = '""\n"' + lineterm.join(lines) + '"'
return s
def poentry(path, lineno, s):
return (
'#: %s:%d\n' % (path, lineno)
+ 'msgid %s\n' % normalize(s)
+ 'msgstr ""\n'
)
doctestre = re.compile(r'^ +>>> ', re.MULTILINE)
def offset(src, doc, name, lineno, default):
"""Compute offset or issue a warning on stdout."""
# remove doctest part, in order to avoid backslash mismatching
m = doctestre.search(doc)
if m:
doc = doc[: m.start()]
# Backslashes in doc appear doubled in src.
end = src.find(doc.replace('\\', '\\\\'))
if end == -1:
# This can happen if the docstring contains unnecessary escape
# sequences such as \" in a triple-quoted string. The problem
# is that \" is turned into " and so doc wont appear in src.
sys.stderr.write(
"%s:%d:warning:"
" unknown docstr offset, assuming %d lines\n"
% (name, lineno, default)
)
return default
else:
return src.count('\n', 0, end)
def importpath(path):
"""Import a path like foo/bar/baz.py and return the baz module."""
if path.endswith('.py'):
path = path[:-3]
if path.endswith('/__init__'):
path = path[:-9]
path = path.replace('/', '.')
mod = __import__(path)
for comp in path.split('.')[1:]:
mod = getattr(mod, comp)
return mod
def docstrings(path):
"""Extract docstrings from path.
This respects the Mercurial cmdtable/table convention and will
only extract docstrings from functions mentioned in these tables.
"""
mod = importpath(path)
if not path.startswith('mercurial/') and mod.__doc__:
with open(path) as fobj:
src = fobj.read()
lineno = 1 + offset(src, mod.__doc__, path, 1, 7)
print(poentry(path, lineno, mod.__doc__))
functions = list(getattr(mod, 'i18nfunctions', []))
functions = [(f, True) for f in functions]
cmdtable = getattr(mod, 'cmdtable', {})
if not cmdtable:
# Maybe we are processing mercurial.commands?
cmdtable = getattr(mod, 'table', {})
functions.extend((c[0], False) for c in cmdtable.values())
for func, rstrip in functions:
if func.__doc__:
docobj = func # this might be a proxy to provide formatted doc
func = getattr(func, '_origfunc', func)
funcmod = inspect.getmodule(func)
extra = ''
if funcmod.__package__ == funcmod.__name__:
extra = '/__init__'
actualpath = '%s%s.py' % (funcmod.__name__.replace('.', '/'), extra)
src = inspect.getsource(func)
lineno = inspect.getsourcelines(func)[1]
doc = docobj.__doc__
origdoc = getattr(docobj, '_origdoc', '')
if rstrip:
doc = doc.rstrip()
origdoc = origdoc.rstrip()
if origdoc:
lineno += offset(src, origdoc, actualpath, lineno, 1)
else:
lineno += offset(src, doc, actualpath, lineno, 1)
print(poentry(actualpath, lineno, doc))
def rawtext(path):
with open(path) as f:
src = f.read()
print(poentry(path, 1, src))
if __name__ == "__main__":
# It is very important that we import the Mercurial modules from
# the source tree where hggettext is executed. Otherwise we might
# accidentally import and extract strings from a Mercurial
# installation mentioned in PYTHONPATH.
sys.path.insert(0, os.getcwd())
from mercurial import demandimport
demandimport.enable()
for path in sys.argv[1:]:
if path.endswith('.txt'):
rawtext(path)
else:
docstrings(path)