##// END OF EJS Templates
manifest: proxy to revlog instance instead of inheriting...
manifest: proxy to revlog instance instead of inheriting Previously, manifestrevlog inherited revlog.revlog and therefore exposed all its APIs. This inevitably resulted in consumers calling low-level revlog APIs. As part of abstracting storage, we want to formalize the interface for manifest storage. The revlog API is much too large to define as the interface. Like we did for filelog, this commit divorces the manifest class from revlog so that we can standardize on a smaller API surface. The way I went about this commit was I broke the inheritance, ran tests, and added proxies until all tests passed. Like filelog, there are a handful of attributes that don't belong on the interface. And like filelog, we'll tease these out in the future. As part of this, we formalize an interface for manifest storage and add checks that manifestrevlog conforms to the interface. Adding proxies will introduce some overhead due to extra attribute lookups and function calls. On the mozilla-unified repository: $ hg verify before: real 627.220 secs (user 525.870+0.000 sys 18.800+0.000) after: real 628.930 secs (user 532.050+0.000 sys 18.320+0.000) $ hg serve (for a clone) before: user 223.580+0.000 sys 14.270+0.000 after: user 227.720+0.000 sys 13.920+0.000 $ hg clone before: user 506.390+0.000 sys 29.720+0.000 after: user 513.080+0.000 sys 28.280+0.000 There appears to be some overhead here. But it appears to be 1-2%. I think that is an appropriate price to pay for storage abstraction, which will eventually let us have much nicer things. If the overhead is noticed in other operations (whose CPU time isn't likely dwarfed by fulltext resolution) or if we want to cut down on the overhead, we could dynamically build up a type whose methods are effectively aliased to a revlog instance's. I'm inclined to punt on that problem for now. We may have to do it for the changelog. At which point it could be implemented in a generic way and ported to filelog and manifestrevlog easily enough I would think. .. api:: manifest.manifestrevlog no longer inherits from revlog The manifestrevlog class now wraps a revlog instance instead of inheriting from revlog. Various attributes and methods on instances are no longer available. Differential Revision: https://phab.mercurial-scm.org/D4386

File last commit:

r37644:0a9c0d34 default
r39350:7f5e6d3e default
Show More
thread.py
162 lines | 5.5 KiB | text/x-python | PythonLexer
# Copyright 2009 Brian Quinlan. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""Implements ThreadPoolExecutor."""
from __future__ import absolute_import
import atexit
from . import _base
import itertools
import Queue as queue
import threading
import weakref
import sys
try:
from multiprocessing import cpu_count
except ImportError:
# some platforms don't have multiprocessing
def cpu_count():
return None
__author__ = 'Brian Quinlan (brian@sweetapp.com)'
# Workers are created as daemon threads. This is done to allow the interpreter
# to exit when there are still idle threads in a ThreadPoolExecutor's thread
# pool (i.e. shutdown() was not called). However, allowing workers to die with
# the interpreter has two undesirable properties:
# - The workers would still be running during interpretor shutdown,
# meaning that they would fail in unpredictable ways.
# - The workers could be killed while evaluating a work item, which could
# be bad if the callable being evaluated has external side-effects e.g.
# writing to a file.
#
# To work around this problem, an exit handler is installed which tells the
# workers to exit when their work queues are empty and then waits until the
# threads finish.
_threads_queues = weakref.WeakKeyDictionary()
_shutdown = False
def _python_exit():
global _shutdown
_shutdown = True
items = list(_threads_queues.items()) if _threads_queues else ()
for t, q in items:
q.put(None)
for t, q in items:
t.join(sys.maxint)
atexit.register(_python_exit)
class _WorkItem(object):
def __init__(self, future, fn, args, kwargs):
self.future = future
self.fn = fn
self.args = args
self.kwargs = kwargs
def run(self):
if not self.future.set_running_or_notify_cancel():
return
try:
result = self.fn(*self.args, **self.kwargs)
except:
e, tb = sys.exc_info()[1:]
self.future.set_exception_info(e, tb)
else:
self.future.set_result(result)
def _worker(executor_reference, work_queue):
try:
while True:
work_item = work_queue.get(block=True)
if work_item is not None:
work_item.run()
# Delete references to object. See issue16284
del work_item
continue
executor = executor_reference()
# Exit if:
# - The interpreter is shutting down OR
# - The executor that owns the worker has been collected OR
# - The executor that owns the worker has been shutdown.
if _shutdown or executor is None or executor._shutdown:
# Notice other workers
work_queue.put(None)
return
del executor
except:
_base.LOGGER.critical('Exception in worker', exc_info=True)
class ThreadPoolExecutor(_base.Executor):
# Used to assign unique thread names when thread_name_prefix is not supplied.
_counter = itertools.count().next
def __init__(self, max_workers=None, thread_name_prefix=''):
"""Initializes a new ThreadPoolExecutor instance.
Args:
max_workers: The maximum number of threads that can be used to
execute the given calls.
thread_name_prefix: An optional name prefix to give our threads.
"""
if max_workers is None:
# Use this number because ThreadPoolExecutor is often
# used to overlap I/O instead of CPU work.
max_workers = (cpu_count() or 1) * 5
if max_workers <= 0:
raise ValueError("max_workers must be greater than 0")
self._max_workers = max_workers
self._work_queue = queue.Queue()
self._threads = set()
self._shutdown = False
self._shutdown_lock = threading.Lock()
self._thread_name_prefix = (thread_name_prefix or
("ThreadPoolExecutor-%d" % self._counter()))
def submit(self, fn, *args, **kwargs):
with self._shutdown_lock:
if self._shutdown:
raise RuntimeError('cannot schedule new futures after shutdown')
f = _base.Future()
w = _WorkItem(f, fn, args, kwargs)
self._work_queue.put(w)
self._adjust_thread_count()
return f
submit.__doc__ = _base.Executor.submit.__doc__
def _adjust_thread_count(self):
# When the executor gets lost, the weakref callback will wake up
# the worker threads.
def weakref_cb(_, q=self._work_queue):
q.put(None)
# TODO(bquinlan): Should avoid creating new threads if there are more
# idle threads than items in the work queue.
num_threads = len(self._threads)
if num_threads < self._max_workers:
thread_name = '%s_%d' % (self._thread_name_prefix or self,
num_threads)
t = threading.Thread(name=thread_name, target=_worker,
args=(weakref.ref(self, weakref_cb),
self._work_queue))
t.daemon = True
t.start()
self._threads.add(t)
_threads_queues[t] = self._work_queue
def shutdown(self, wait=True):
with self._shutdown_lock:
self._shutdown = True
self._work_queue.put(None)
if wait:
for t in self._threads:
t.join(sys.maxint)
shutdown.__doc__ = _base.Executor.shutdown.__doc__