view mercurial/repocache.py @ 44763:94f4f2ec7dee stable

packaging: support building Inno installer with PyOxidizer

We want to start distributing Mercurial on Python 3 on
Windows. PyOxidizer will be our vehicle for achieving that.

This commit implements basic support for producing Inno
installers using PyOxidizer.

While it is an eventual goal of PyOxidizer to produce
installers, those features aren't yet implemented. So our
strategy for producing Mercurial installers is similar to
what we've been doing with py2exe: invoke a build system to
produce files then stage those files into a directory so they
can be turned into an installer.

We had to make significant alterations to the pyoxidizer.bzl
config file to get it to produce the files that we desire for
a Windows install. This meant differentiating the build targets
so we can target Windows specifically.

We've added a new module to hgpackaging to deal with interacting
with PyOxidizer. It is similar to pyexe: we invoke a build process
then copy files to a staging directory. Ideally these extra
files would be defined in pyoxidizer.bzl. But I don't think it
is worth doing at this time, as PyOxidizer's config files are
lacking some features to make this turnkey.

The rest of the change is introducing a variant of the
Inno installer code that invokes PyOxidizer instead of
py2exe.

Comparing the Python 2.7 based Inno installers with this
one, the following changes were observed:

* No lib/*.{pyd, dll} files
* No Microsoft.VC90.CRT.manifest
* No msvc{m,p,r}90.dll files
* python27.dll replaced with python37.dll
* Add vcruntime140.dll file

The disappearance of the .pyd and .dll files is acceptable, as
PyOxidizer has embedded these in hg.exe and loads them from
memory.

The disappearance of the *90* files is acceptable because those
provide the Visual C++ 9 runtime, as required by Python 2.7.
Similarly, the appearance of vcruntime140.dll is a requirement
of Python 3.7.

Differential Revision: https://phab.mercurial-scm.org/D8473

# repocache.py - in-memory repository cache for long-running services
#
# Copyright 2018 Yuya Nishihara <[e-mail]>
#
# 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

import collections
import gc
import threading

from . import (
    error,
    hg,
    obsolete,
    scmutil,
    util,
)


class repoloader(object):
    """Load repositories in background thread

    This is designed for a forking server. A cached repo cannot be obtained
    until the server fork()s a worker and the loader thread stops.
    """

    def __init__(self, ui, maxlen):
        self._ui = ui.copy()
        self._cache = util.lrucachedict(max=maxlen)
        # use deque and Event instead of Queue since deque can discard
        # old items to keep at most maxlen items.
        self._inqueue = collections.deque(maxlen=maxlen)
        self._accepting = False
        self._newentry = threading.Event()
        self._thread = None

    def start(self):
        assert not self._thread
        if self._inqueue.maxlen == 0:
            # no need to spawn loader thread as the cache is disabled
            return
        self._accepting = True
        self._thread = threading.Thread(target=self._mainloop)
        self._thread.start()

    def stop(self):
        if not self._thread:
            return
        self._accepting = False
        self._newentry.set()
        self._thread.join()
        self._thread = None
        self._cache.clear()
        self._inqueue.clear()

    def load(self, path):
        """Request to load the specified repository in background"""
        self._inqueue.append(path)
        self._newentry.set()

    def get(self, path):
        """Return a cached repo if available

        This function must be called after fork(), where the loader thread
        is stopped. Otherwise, the returned repo might be updated by the
        loader thread.
        """
        if self._thread and self._thread.is_alive():
            raise error.ProgrammingError(
                b'cannot obtain cached repo while loader is active'
            )
        return self._cache.peek(path, None)

    def _mainloop(self):
        while self._accepting:
            # Avoid heavy GC after fork(), which would cancel the benefit of
            # COW. We assume that GIL is acquired while GC is underway in the
            # loader thread. If that isn't true, we might have to move
            # gc.collect() to the main thread so that fork() would never stop
            # the thread where GC is in progress.
            gc.collect()

            self._newentry.wait()
            while self._accepting:
                self._newentry.clear()
                try:
                    path = self._inqueue.popleft()
                except IndexError:
                    break
                scmutil.callcatch(self._ui, lambda: self._load(path))

    def _load(self, path):
        start = util.timer()
        # TODO: repo should be recreated if storage configuration changed
        try:
            # pop before loading so inconsistent state wouldn't be exposed
            repo = self._cache.pop(path)
        except KeyError:
            repo = hg.repository(self._ui, path).unfiltered()
        _warmupcache(repo)
        repo.ui.log(
            b'repocache',
            b'loaded repo into cache: %s (in %.3fs)\n',
            path,
            util.timer() - start,
        )
        self._cache.insert(path, repo)


# TODO: think about proper API of preloading cache
def _warmupcache(repo):
    repo.invalidateall()
    repo.changelog
    repo.obsstore._all
    repo.obsstore.successors
    repo.obsstore.predecessors
    repo.obsstore.children
    for name in obsolete.cachefuncs:
        obsolete.getrevs(repo, name)
    repo._phasecache.loadphaserevs(repo)


# TODO: think about proper API of attaching preloaded attributes
def copycache(srcrepo, destrepo):
    """Copy cached attributes from srcrepo to destrepo"""
    destfilecache = destrepo._filecache
    srcfilecache = srcrepo._filecache
    if b'changelog' in srcfilecache:
        destfilecache[b'changelog'] = ce = srcfilecache[b'changelog']
        ce.obj.opener = ce.obj._realopener = destrepo.svfs
    if b'obsstore' in srcfilecache:
        destfilecache[b'obsstore'] = ce = srcfilecache[b'obsstore']
        ce.obj.svfs = destrepo.svfs
    if b'_phasecache' in srcfilecache:
        destfilecache[b'_phasecache'] = ce = srcfilecache[b'_phasecache']
        ce.obj.opener = destrepo.svfs