perf: clear vfs audit_cache before each run
When generating a stream clone, we spend a large amount of time auditing path.
Before this changes, the first run was warming the vfs cache for the other
runs, leading to a large runtime difference and a "faulty" reported timing for
the operation.
We now clear this important cache between run to get a more realistic timing.
Below are some example of median time change when clearing these cases. The
maximum time for a run did not changed significantly.
### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
# benchmark.name = hg.perf.exchange.stream.generate
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.version = latest
no-clearing: 17.289905
cache-clearing: 21.587965 (+24.86%, +4.30)
## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog
no-clearing: 32.670748
cache-clearing: 40.467095 (+23.86%, +7.80)
## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
no-clearing: 37.838858
cache-clearing: 46.072749 (+21.76%, +8.23)
## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog
no-clearing: 32.969395
cache-clearing: 39.646209 (+20.25%, +6.68)
In addition, this significantly reduce the timing difference between the
performance command, from the perf extensions and a `real `hg bundle` call
producing a stream bundle. Some significant differences remain especially on
the "mozilla-try" repositories, but they are now smaller.
Note that some of that difference will actually not be
attributable to the stream generation (like maybe phases or branch map
computation).
Below are some benchmarks done on a currently draft changeset fixing some
unrelated slowness in `hg bundle` (34a78972af409d1ff37c29e60f6ca811ad1a457d)
### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
hg.perf.exchange.stream.generate: 21.587965
hg.command.bundle: 24.301799 (+12.57%, +2.71)
## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 40.467095
hg.command.bundle: 44.831317 (+10.78%, +4.36)
## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 39.646209
hg.command.bundle: 45.395258 (+14.50%, +5.75)
## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 46.072749
hg.command.bundle: 55.882608 (+21.29%, +9.81)
## data-env-vars.name = mozilla-try-2023-03-22-zlib-general-delta
hg.perf.exchange.stream.generate: 334.716708
hg.command.bundle: 377.856767 (+12.89%, +43.14)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 302.972301
hg.command.bundle: 326.098755 (+7.63%, +23.13)
# Copyright 2020 Joerg Sonnenberger <joerg@bec.de>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""changeset_published is a hook to send a mail when an
existing draft changeset is moved to the public phase.
Correct message threading requires the same messageidseed to be used for both
the original notification and the new mail.
Usage:
[notify]
messageidseed = myseed
[hooks]
txnclose-phase.changeset_published = \
python:hgext.hooklib.changeset_published.hook
"""
import email.errors as emailerrors
import email.utils as emailutils
from mercurial.i18n import _
from mercurial import (
encoding,
error,
formatter,
logcmdutil,
mail,
pycompat,
registrar,
)
from mercurial.utils import (
dateutil,
stringutil,
)
from .. import notify
configtable = {}
configitem = registrar.configitem(configtable)
configitem(
b'notify_published',
b'domain',
default=None,
)
configitem(
b'notify_published',
b'messageidseed',
default=None,
)
configitem(
b'notify_published',
b'template',
default=b'''Subject: changeset published
This changeset has been published.
''',
)
def _report_commit(ui, repo, ctx):
domain = ui.config(b'notify_published', b'domain') or ui.config(
b'notify', b'domain'
)
messageidseed = ui.config(
b'notify_published', b'messageidseed'
) or ui.config(b'notify', b'messageidseed')
template = ui.config(b'notify_published', b'template')
spec = formatter.literal_templatespec(template)
templater = logcmdutil.changesettemplater(ui, repo, spec)
ui.pushbuffer()
n = notify.notifier(ui, repo, b'incoming')
subs = set()
for sub, spec in n.subs:
if spec is None:
subs.add(sub)
continue
revs = repo.revs(b'%r and %d:', spec, ctx.rev())
if len(revs):
subs.add(sub)
continue
if len(subs) == 0:
ui.debug(
b'notify_published: no subscribers to selected repo and revset\n'
)
return
templater.show(
ctx,
changes=ctx.changeset(),
baseurl=ui.config(b'web', b'baseurl'),
root=repo.root,
webroot=n.root,
)
data = ui.popbuffer()
try:
msg = mail.parsebytes(data)
except emailerrors.MessageParseError as inst:
raise error.Abort(stringutil.forcebytestr(inst))
msg['In-reply-to'] = notify.messageid(ctx, domain, messageidseed)
msg['Message-Id'] = notify.messageid(
ctx, domain, messageidseed + b'-published'
)
msg['Date'] = encoding.strfromlocal(
dateutil.datestr(format=b"%a, %d %b %Y %H:%M:%S %1%2")
)
if not msg['From']:
sender = ui.config(b'email', b'from') or ui.username()
if b'@' not in sender or b'@localhost' in sender:
sender = n.fixmail(sender)
msg['From'] = mail.addressencode(ui, sender, n.charsets, n.test)
msg['To'] = ', '.join(sorted(subs))
msgtext = msg.as_bytes()
if ui.configbool(b'notify', b'test'):
ui.write(msgtext)
if not msgtext.endswith(b'\n'):
ui.write(b'\n')
else:
ui.status(_(b'notify_published: sending mail for %d\n') % ctx.rev())
mail.sendmail(
ui, emailutils.parseaddr(msg['From'])[1], subs, msgtext, mbox=n.mbox
)
def hook(ui, repo, hooktype, node=None, **kwargs):
if hooktype != b"txnclose-phase":
raise error.Abort(
_(b'Unsupported hook type %r') % pycompat.bytestr(hooktype)
)
ctx = repo.unfiltered()[node]
if kwargs['oldphase'] == b'draft' and kwargs['phase'] == b'public':
_report_commit(ui, repo, ctx)