procutil: make stream detection in make_line_buffered more correct and strict
In make_line_buffered(), we don’t want to wrap the stream if we know that lines
get flushed to the underlying raw stream already.
Previously, the heuristic was too optimistic. It assumed that any stream which
is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there
are buffered streams that aren’t instances of io.BufferedIOBase, like
Mercurial’s own winstdout.
The new logic is different in two ways:
First, only for the check, if unwraps any combination of WriteAllWrapper and
winstdout.
Second, it skips wrapping the stream only if it is an instance of io.RawIOBase
(or already wrapped). If it is an instance of io.BufferedIOBase, it gets
wrapped. In any other case, the function raises an exception. This ensures
that, if an unknown stream is passed or we add another wrapper in the future,
we don’t wrap the stream if it’s already line buffered or not wrap the stream
if it’s not line buffered. In fact, this was already helpful during development
of this change. Without it, I possibly would have forgot that WriteAllWrapper
needs to be ignored for the check, leading to unnecessary wrapping if stdout is
unbuffered.
The alternative would have been to always wrap unknown streams. However, I
don’t think that anyone would benefit from being less strict. We can expect
streams from the standard library to be subclassing either io.RawIOBase or
io.BufferedIOBase, so running Mercurial in the standard way should not regress
by this change. Py2exe might replace sys.stdout and sys.stderr, but that
currently breaks Mercurial anyway and also these streams don’t claim to be
interactive, so this function is not called for them.
# 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