Mercurial > hg
view mercurial/repocache.py @ 50336:cf4d2f31660d stable
chg: populate CHGHG if not set
Normally, chg determines which `hg` executable to use by first consulting the
`$CHGHG` and `$HG` environment variables, and if neither are present defaults
to the `hg` found in the user's `$PATH`. If built with the `HGPATHREL` compiler
flag, chg will instead assume that there exists an `hg` executable in the same
directory as the `chg` binary and attempt to use that.
This can cause problems in situations where there are multiple actively-used
Mercurial installations on the same system. When a `chg` client connects to a
running command server, the server process performs some basic validation to
determine whether a new command server needs to be spawned. These checks include
things like checking certain "sensitive" environment variables and config
sections, as well as checking whether the mtime of the extensions, hg's
`__version__.py` module, and the Python interpreter have changed.
Crucially, the command server doesn't explicitly check whether the executable it
is running from matches the executable that the `chg` client would have
otherwise invoked had there been no existing command server process. Without
`HGPATHREL`, this still gets implicitly checked during the validation step,
because the only way to specify an alternate hg executable (apart from `$PATH`)
is via the `$CHGHG` and `$HG` environment variables, both of which are checked.
With `HGPATHREL`, however, the command server has no way of knowing which hg
executable the client would have run. This means that a client located at
`/version_B/bin/chg` will happily connect to a command server running
`/version_A/bin/hg` instead of `/version_B/bin/hg` as expected. A simple
solution is to have the client set `$CHGHG` itself, which then allows the
command server's environment validation to work as intended.
I have tested this manually using two locally built hg installations and it
seems to work with no ill effects. That said, I'm not sure how to write an
automated test for this since the `chg` available to the tests isn't even built
with the `HGPATHREL` compiler flag to begin with.
author | Arun Kulshreshtha <akulshreshtha@janestreet.com> |
---|---|
date | Mon, 27 Mar 2023 17:30:14 -0400 |
parents | 642e31cb55f0 |
children | d83d788590a8 |
line wrap: on
line source
# repocache.py - in-memory repository cache for long-running services # # Copyright 2018 Yuya Nishihara <yuya@tcha.org> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. import collections import gc import threading from . import ( error, hg, obsolete, scmutil, util, ) class repoloader: """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