phases: rework the logic of _pushdiscoveryphase to bound complexity
This rework the various graph traversal in _pushdiscoveryphase to keep the
complexity in check.
This is done though a couple of things:
- first, limiting the space we have to explore, for example, if we are not in
publishing push, we don't need to consider remote draft roots that are also
draft locally, as there is nothing to be moved there.
- avoid unbounded descendant computation, and use the faster "rev between"
computation.
This provide a massive boost to performance when exchanging with repository with
a massive amount of draft, like mozilla-try:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = default
## benchmark.variants.revs = any-1-extra-rev
before: 20.346590 seconds
after: 11.232059 seconds (-38.15%, -7.48 seconds)
## benchmark.variants.revs = any-100-extra-rev
before: 24.752051 seconds
after: 15.367412 seconds (-37.91%, -9.38 seconds)
After this changes, the push operation is still quite too slow. Some of this
can be attributed to general phases slowness (reading all the roots from disk
for example) and other know slowness (not using persistent-nodemap, branchmap,
tags, etc. We are also working on them, but with this series, phase discovery
during push no longer showing up in profile and this is a pretty nice and bit
low-hanging fruit out of the way.
### (same case as the above)
# benchmark.variants.revs = any-1-extra-rev
pre-%ln-change: 44.235070
this-changeset: 11.232059 seconds (-74.61%, -33.00 seconds)
# benchmark.variants.revs = any-100-extra-rev
pre-%ln-change: 49.234697
this-changeset: 15.367412 seconds (-68.79%, -33.87 seconds)
Note that with this change, the `hg push` performance is now much closer to the
`hg pull` performance, even it still lagging behind a bit. (and the overall
performance are still too slow).
### data-env-vars.name = mozilla-try-2023-03-22-ds2-pnm
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.pulled-delta-reuse-policy = default
# bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 6.517450
hg.command.push: 11.219888
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 10.160991
hg.command.push: 14.251107
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.pulled-delta-reuse-policy = default
## bin-env-vars.hg.flavor = default
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 8.577772
hg.command.push: 11.232059
## bin-env-vars.hg.flavor = default
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 13.152976
hg.command.push: 15.367412
## bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 8.731982
hg.command.push: 11.178751
## bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 13.184236
hg.command.push: 15.620843
# 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)
# ensure the phase cache is fully initialized
repo._phasecache.phase(repo, repo.changelog.tiprev())
# 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._inner.opener = 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