##// END OF EJS Templates
procutil: avoid using os.fork() to implement runbgcommand...
procutil: avoid using os.fork() to implement runbgcommand We ran into the following deadlock: - some command creates an ssh peer, then raises without explicitly closing the peer (hg id + extension in our case) - dispatch catches the exception, calls ui.log('commandfinish', ..) (the sshpeer is still not closed), which calls logtoprocess, which calls procutil.runbgcommand. - in the child of runbgcommand's fork(), between the fork and the exec, the opening of file descriptors triggers a gc which runs the destructor for sshpeer, which waits on ssh's stderr being closed, which never happens since ssh's stderr is held open by the parent of the fork where said destructor hasn't run Remotefilelog appears to have a hack around this deadlock as well. I don't know if there's more subtlety to it, because even though the problem is determistic, it is very fragile, so I didn't manage to reduce it. I can imagine three ways of tackling this problem: 1. don't run any python between fork and exec in runbgcommand 2. make the finalizer harmless after the fork 3. close the peer without relying on gc behavior This commit goes with 1, as forking without exec'ing is tricky in general in a language with gc finalizers. And maybe it's better in the presence of rust threads. A future commit will try 2 or 3. Performance wise: at low memory usage, it's an improvement. At higher memory usage, it's about 2x faster than before when ensurestart=True, but 2x slower when ensurestart=False. Not sure if that matters. The reason for that last bit is that the subprocess.Popen always waits for the execve to finish, and at high memory usage, execve is slow because it deallocates the large page table. Numbers and script: before after mem=1.0GB, ensurestart=True 52.1ms 26.0ms mem=1.0GB, ensurestart=False 14.7ms 26.0ms mem=0.5GB, ensurestart=True 23.2ms 11.2ms mem=0.5GB, ensurestart=False 6.2ms 11.3ms mem=0.2GB, ensurestart=True 15.7ms 7.4ms mem=0.2GB, ensurestart=False 4.3ms 8.1ms mem=0.0GB, ensurestart=True 2.3ms 0.7ms mem=0.0GB, ensurestart=False 0.8ms 0.8ms import time for memsize in [1_000_000_000, 500_000_000, 250_000_000, 0]: mem = 'a' * memsize for ensurestart in [True, False]: now = time.time() n = 100 for i in range(n): procutil.runbgcommand([b'true'], {}, ensurestart=ensurestart) after = time.time() ms = (after - now) / float(n) * 1000 print(f'mem={memsize / 1e9:.1f}GB, ensurestart={ensurestart} -> {ms:.1f}ms') Differential Revision: https://phab.mercurial-scm.org/D9019

File last commit:

r47543:521ac0d7 stable
r47651:8759e22f default
Show More
urllibcompat.py
238 lines | 5.9 KiB | text/x-python | PythonLexer
# urllibcompat.py - adapters to ease using urllib2 on Py2 and urllib on Py3
#
# Copyright 2017 Google, Inc.
#
# 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
from .pycompat import getattr
from . import pycompat
_sysstr = pycompat.sysstr
class _pycompatstub(object):
def __init__(self):
self._aliases = {}
def _registeraliases(self, origin, items):
"""Add items that will be populated at the first access"""
items = map(_sysstr, items)
self._aliases.update(
(item.replace('_', '').lower(), (origin, item)) for item in items
)
def _registeralias(self, origin, attr, name):
"""Alias ``origin``.``attr`` as ``name``"""
self._aliases[_sysstr(name)] = (origin, _sysstr(attr))
def __getattr__(self, name):
try:
origin, item = self._aliases[name]
except KeyError:
raise AttributeError(name)
self.__dict__[name] = obj = getattr(origin, item)
return obj
httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()
if pycompat.ispy3:
import urllib.parse
urlreq._registeraliases(
urllib.parse,
(
b"splitattr",
b"splitpasswd",
b"splitport",
b"splituser",
b"urlparse",
b"urlunparse",
),
)
urlreq._registeralias(urllib.parse, b"parse_qs", b"parseqs")
urlreq._registeralias(urllib.parse, b"parse_qsl", b"parseqsl")
urlreq._registeralias(urllib.parse, b"unquote_to_bytes", b"unquote")
import urllib.request
urlreq._registeraliases(
urllib.request,
(
b"AbstractHTTPHandler",
b"BaseHandler",
b"build_opener",
b"FileHandler",
b"FTPHandler",
b"ftpwrapper",
b"HTTPHandler",
b"HTTPSHandler",
b"install_opener",
b"pathname2url",
b"HTTPBasicAuthHandler",
b"HTTPDigestAuthHandler",
b"HTTPPasswordMgrWithDefaultRealm",
b"ProxyHandler",
b"Request",
b"url2pathname",
b"urlopen",
),
)
import urllib.response
urlreq._registeraliases(
urllib.response,
(
b"addclosehook",
b"addinfourl",
),
)
import urllib.error
urlerr._registeraliases(
urllib.error,
(
b"HTTPError",
b"URLError",
),
)
import http.server
httpserver._registeraliases(
http.server,
(
b"HTTPServer",
b"BaseHTTPRequestHandler",
b"SimpleHTTPRequestHandler",
b"CGIHTTPRequestHandler",
),
)
# urllib.parse.quote() accepts both str and bytes, decodes bytes
# (if necessary), and returns str. This is wonky. We provide a custom
# implementation that only accepts bytes and emits bytes.
def quote(s, safe='/'):
# bytestr has an __iter__ that emits characters. quote_from_bytes()
# does an iteration and expects ints. We coerce to bytes to appease it.
if isinstance(s, pycompat.bytestr):
s = bytes(s)
s = urllib.parse.quote_from_bytes(s, safe=safe)
return s.encode('ascii', 'strict')
# urllib.parse.urlencode() returns str. We use this function to make
# sure we return bytes.
def urlencode(query, doseq=False):
s = urllib.parse.urlencode(query, doseq=doseq)
return s.encode('ascii')
urlreq.quote = quote
urlreq.urlencode = urlencode
def getfullurl(req):
return req.full_url
def gethost(req):
return req.host
def getselector(req):
return req.selector
def getdata(req):
return req.data
def hasdata(req):
return req.data is not None
else:
# pytype: disable=import-error
import BaseHTTPServer
import CGIHTTPServer
import SimpleHTTPServer
import urllib2
import urllib
import urlparse
# pytype: enable=import-error
urlreq._registeraliases(
urllib,
(
b"addclosehook",
b"addinfourl",
b"ftpwrapper",
b"pathname2url",
b"quote",
b"splitattr",
b"splitpasswd",
b"splitport",
b"splituser",
b"unquote",
b"url2pathname",
b"urlencode",
),
)
urlreq._registeraliases(
urllib2,
(
b"AbstractHTTPHandler",
b"BaseHandler",
b"build_opener",
b"FileHandler",
b"FTPHandler",
b"HTTPBasicAuthHandler",
b"HTTPDigestAuthHandler",
b"HTTPHandler",
b"HTTPPasswordMgrWithDefaultRealm",
b"HTTPSHandler",
b"install_opener",
b"ProxyHandler",
b"Request",
b"urlopen",
),
)
urlreq._registeraliases(
urlparse,
(
b"urlparse",
b"urlunparse",
),
)
urlreq._registeralias(urlparse, b"parse_qs", b"parseqs")
urlreq._registeralias(urlparse, b"parse_qsl", b"parseqsl")
urlerr._registeraliases(
urllib2,
(
b"HTTPError",
b"URLError",
),
)
httpserver._registeraliases(
BaseHTTPServer,
(
b"HTTPServer",
b"BaseHTTPRequestHandler",
),
)
httpserver._registeraliases(
SimpleHTTPServer, (b"SimpleHTTPRequestHandler",)
)
httpserver._registeraliases(CGIHTTPServer, (b"CGIHTTPRequestHandler",))
def gethost(req):
return req.get_host()
def getselector(req):
return req.get_selector()
def getfullurl(req):
return req.get_full_url()
def getdata(req):
return req.get_data()
def hasdata(req):
return req.has_data()