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
# server.py - utility and factory of server
#
# Copyright 2005-2007 Olivia Mackall <olivia@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import os
from .i18n import _
from .pycompat import open
from . import (
chgserver,
cmdutil,
commandserver,
error,
hgweb,
pycompat,
util,
)
from .utils import (
procutil,
urlutil,
)
def runservice(
opts,
parentfn=None,
initfn=None,
runfn=None,
logfile=None,
runargs=None,
appendpid=False,
):
'''Run a command as a service.'''
postexecargs = {}
if opts[b'daemon_postexec']:
for inst in opts[b'daemon_postexec']:
if inst.startswith(b'unlink:'):
postexecargs[b'unlink'] = inst[7:]
elif inst.startswith(b'chdir:'):
postexecargs[b'chdir'] = inst[6:]
elif inst != b'none':
raise error.Abort(
_(b'invalid value for --daemon-postexec: %s') % inst
)
# When daemonized on Windows, redirect stdout/stderr to the lockfile (which
# gets cleaned up after the child is up and running), so that the parent can
# read and print the error if this child dies early. See 594dd384803c. On
# other platforms, the child can write to the parent's stdio directly, until
# it is redirected prior to runfn().
if pycompat.iswindows and opts[b'daemon_postexec']:
if b'unlink' in postexecargs and os.path.exists(
postexecargs[b'unlink']
):
procutil.stdout.flush()
procutil.stderr.flush()
fd = os.open(
postexecargs[b'unlink'], os.O_WRONLY | os.O_APPEND | os.O_BINARY
)
try:
os.dup2(fd, procutil.stdout.fileno())
os.dup2(fd, procutil.stderr.fileno())
finally:
os.close(fd)
def writepid(pid):
if opts[b'pid_file']:
if appendpid:
mode = b'ab'
else:
mode = b'wb'
fp = open(opts[b'pid_file'], mode)
fp.write(b'%d\n' % pid)
fp.close()
if opts[b'daemon'] and not opts[b'daemon_postexec']:
# Signal child process startup with file removal
lockfd, lockpath = pycompat.mkstemp(prefix=b'hg-service-')
os.close(lockfd)
try:
if not runargs:
runargs = procutil.hgcmd() + pycompat.sysargv[1:]
runargs.append(b'--daemon-postexec=unlink:%s' % lockpath)
# Don't pass --cwd to the child process, because we've already
# changed directory.
for i in range(1, len(runargs)):
if runargs[i].startswith(b'--cwd='):
del runargs[i]
break
elif runargs[i].startswith(b'--cwd'):
del runargs[i : i + 2]
break
def condfn():
return not os.path.exists(lockpath)
pid = procutil.rundetached(runargs, condfn)
if pid < 0:
# If the daemonized process managed to write out an error msg,
# report it.
if pycompat.iswindows and os.path.exists(lockpath):
with open(lockpath, b'rb') as log:
for line in log:
procutil.stderr.write(line)
raise error.Abort(_(b'child process failed to start'))
writepid(pid)
finally:
util.tryunlink(lockpath)
if parentfn:
return parentfn(pid)
else:
return
if initfn:
initfn()
if not opts[b'daemon']:
writepid(procutil.getpid())
if opts[b'daemon_postexec']:
try:
os.setsid()
except AttributeError:
pass
if b'chdir' in postexecargs:
os.chdir(postexecargs[b'chdir'])
procutil.hidewindow()
procutil.stdout.flush()
procutil.stderr.flush()
nullfd = os.open(os.devnull, os.O_RDWR)
logfilefd = nullfd
if logfile:
logfilefd = os.open(
logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND, 0o666
)
os.dup2(nullfd, procutil.stdin.fileno())
os.dup2(logfilefd, procutil.stdout.fileno())
os.dup2(logfilefd, procutil.stderr.fileno())
stdio = (
procutil.stdin.fileno(),
procutil.stdout.fileno(),
procutil.stderr.fileno(),
)
if nullfd not in stdio:
os.close(nullfd)
if logfile and logfilefd not in stdio:
os.close(logfilefd)
# Only unlink after redirecting stdout/stderr, so Windows doesn't
# complain about a sharing violation.
if b'unlink' in postexecargs:
os.unlink(postexecargs[b'unlink'])
if runfn:
return runfn()
_cmdservicemap = {
b'chgunix': chgserver.chgunixservice,
b'pipe': commandserver.pipeservice,
b'unix': commandserver.unixforkingservice,
}
def _createcmdservice(ui, repo, opts):
mode = opts[b'cmdserver']
try:
servicefn = _cmdservicemap[mode]
except KeyError:
raise error.Abort(_(b'unknown mode %s') % mode)
commandserver.setuplogging(ui, repo)
return servicefn(ui, repo, opts)
def _createhgwebservice(ui, repo, opts):
# this way we can check if something was given in the command-line
if opts.get(b'port'):
opts[b'port'] = urlutil.getport(opts.get(b'port'))
alluis = {ui}
if repo:
baseui = repo.baseui
alluis.update([repo.baseui, repo.ui])
else:
baseui = ui
webconf = opts.get(b'web_conf') or opts.get(b'webdir_conf')
if webconf:
if opts.get(b'subrepos'):
raise error.Abort(_(b'--web-conf cannot be used with --subrepos'))
# load server settings (e.g. web.port) to "copied" ui, which allows
# hgwebdir to reload webconf cleanly
servui = ui.copy()
servui.readconfig(webconf, sections=[b'web'])
alluis.add(servui)
elif opts.get(b'subrepos'):
servui = ui
# If repo is None, hgweb.createapp() already raises a proper abort
# message as long as webconf is None.
if repo:
webconf = dict()
cmdutil.addwebdirpath(repo, b"", webconf)
else:
servui = ui
optlist = (
b"name templates style address port prefix ipv6"
b" accesslog errorlog certificate encoding"
)
for o in optlist.split():
val = opts.get(o, b'')
if val in (None, b''): # should check against default options instead
continue
for u in alluis:
u.setconfig(b"web", o, val, b'serve')
app = hgweb.createapp(baseui, repo, webconf)
return hgweb.httpservice(servui, app, opts)
def createservice(ui, repo, opts):
if opts[b"cmdserver"]:
return _createcmdservice(ui, repo, opts)
else:
return _createhgwebservice(ui, repo, opts)