##// END OF EJS Templates
commit: improve the files field of changelog for merges...
commit: improve the files field of changelog for merges Currently, the files list of merge commits repeats all the deletions (either actual deletions, or files that got renamed) that happened between base and p2 of the merge. If p2 is the main branch, the list can easily be much bigger than the change being merged. This results in various problems worth improving: - changelog is bigger than necessary - `hg log directory` lists many unrelated merge commits, and `hg log -v -r commit` frequently fills multiple screens worth of files - it possibly slows down adjustlinkrev, by forcing it to read more manifests, and that function can certainly be a bottleneck - the server side of pulls can waste a lot of time simply opening the filelogs for pointless files (the constant factors for opening even a tiny filelog is apparently pretty bad) So stop listing such files as described in the code. Impacted merge commits and their descendants get a different hash than they would have without this. This doesn't seem problematic, except for convert. The previous commit helped with that in the hg->hg case (but if you do svn->hg twice from scratch, hashes can still change). The rest of the description is numbers. I don't have much to report, because recreating the files list of existing repositories is not easy: - debugupgradeformat and bundle/unbundle don't recreate the list - export/import tends to choke quickly applying patches or on description that contain diffs, - merge commits from the convert extension don't have the right files list for reasons orthogonal to the current commit - replaying the merge with hg update/hg merge/hg revert --all/hg commit can end up failing in hg revert - I wasn't sure that using debugsetparents + debugrebuilddirstate would really build the right thing I measured commit time before and after this change, in a case with no files filtered out, several files filtered out (no difference) and 5k files filtered out (+1% time). Recreating the 100 more recent merges in a private repo, the concatenated uncompressed files lists goes from 1.12MB to 0.52MB. Excluding 3 merges that are not representative, then the size goes from 570k to 15k. I converted part of mozilla-central, and observed file list shrinking quite a bit too, starting at the very first merge, 733641d9feaf, going from 550 files to 10 files (although they have relatively few merges, so they probably wouldn't care). Differential Revision: https://phab.mercurial-scm.org/D6613

File last commit:

r37644:0a9c0d34 default
r42827:b928b229 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__