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
# hook.py - hook support for mercurial
#
# Copyright 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 contextlib
import errno
import os
import sys
from .i18n import _
from . import (
demandimport,
encoding,
error,
extensions,
pycompat,
util,
)
from .utils import (
procutil,
resourceutil,
stringutil,
)
def pythonhook(ui, repo, htype, hname, funcname, args, throw):
"""call python hook. hook is callable object, looked up as
name in python module. if callable returns "true", hook
fails, else passes. if hook raises exception, treated as
hook failure. exception propagates if throw is "true".
reason for "true" meaning "hook failed" is so that
unmodified commands (e.g. mercurial.commands.update) can
be run as hooks without wrappers to convert return values."""
if callable(funcname):
obj = funcname
funcname = obj.__module__ + "." + obj.__name__
else:
funcname = pycompat.sysstr(funcname)
d = funcname.rfind('.')
if d == -1:
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" not in a module')
% (hname, stringutil.forcebytestr(funcname))
)
modname = funcname[:d]
oldpaths = sys.path
if resourceutil.mainfrozen():
# binary installs require sys.path manipulation
modpath, modfile = os.path.split(modname)
if modpath and modfile:
sys.path = sys.path[:] + [modpath]
modname = modfile
with demandimport.deactivated():
try:
obj = __import__(pycompat.sysstr(modname))
except (ImportError, SyntaxError):
e1 = sys.exc_info()
try:
# extensions are loaded with hgext_ prefix
obj = __import__("hgext_%s" % pycompat.sysstr(modname))
except (ImportError, SyntaxError):
e2 = sys.exc_info()
if ui.tracebackflag:
ui.warn(
_(
b'exception from first failed import '
b'attempt:\n'
)
)
ui.traceback(e1)
if ui.tracebackflag:
ui.warn(
_(
b'exception from second failed import '
b'attempt:\n'
)
)
ui.traceback(e2)
if not ui.tracebackflag:
tracebackhint = _(
b'run with --traceback for stack trace'
)
else:
tracebackhint = None
msg = _(b'%s hook is invalid: import of "%s" failed')
msg %= (
stringutil.forcebytestr(hname),
stringutil.forcebytestr(modname),
)
raise error.HookLoadError(msg, hint=tracebackhint)
sys.path = oldpaths
try:
for p in funcname.split('.')[1:]:
obj = getattr(obj, p)
except AttributeError:
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" is not defined')
% (hname, stringutil.forcebytestr(funcname))
)
if not callable(obj):
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" is not callable')
% (hname, stringutil.forcebytestr(funcname))
)
ui.note(
_(b"calling hook %s: %s\n") % (hname, stringutil.forcebytestr(funcname))
)
starttime = util.timer()
try:
r = obj(ui=ui, repo=repo, hooktype=htype, **pycompat.strkwargs(args))
except Exception as exc:
if isinstance(exc, error.Abort):
ui.warn(_(b'error: %s hook failed: %s\n') % (hname, exc.args[0]))
else:
ui.warn(
_(b'error: %s hook raised an exception: %s\n')
% (hname, stringutil.forcebytestr(exc))
)
if throw:
raise
if not ui.tracebackflag:
ui.warn(_(b'(run with --traceback for stack trace)\n'))
ui.traceback()
return True, True
finally:
duration = util.timer() - starttime
ui.log(
b'pythonhook',
b'pythonhook-%s: %s finished in %0.2f seconds\n',
htype,
stringutil.forcebytestr(funcname),
duration,
)
if r:
if throw:
raise error.HookAbort(_(b'%s hook failed') % hname)
ui.warn(_(b'warning: %s hook failed\n') % hname)
return r, False
def _exthook(ui, repo, htype, name, cmd, args, throw):
starttime = util.timer()
env = {}
# make in-memory changes visible to external process
if repo is not None:
tr = repo.currenttransaction()
repo.dirstate.write(tr)
if tr and tr.writepending():
env[b'HG_PENDING'] = repo.root
env[b'HG_HOOKTYPE'] = htype
env[b'HG_HOOKNAME'] = name
if ui.config(b'hooks', b'%s:run-with-plain' % name) == b'auto':
plain = ui.plain()
else:
plain = ui.configbool(b'hooks', b'%s:run-with-plain' % name)
if plain:
env[b'HGPLAIN'] = b'1'
else:
env[b'HGPLAIN'] = b''
for k, v in args.items():
# transaction changes can accumulate MBs of data, so skip it
# for external hooks
if k == b'changes':
continue
if callable(v):
v = v()
if isinstance(v, (dict, list)):
v = stringutil.pprint(v)
env[b'HG_' + k.upper()] = v
if ui.configbool(b'hooks', b'tonative.%s' % name, False):
oldcmd = cmd
cmd = procutil.shelltonative(cmd, env)
if cmd != oldcmd:
ui.note(_(b'converting hook "%s" to native\n') % name)
ui.note(_(b"running hook %s: %s\n") % (name, cmd))
if repo:
cwd = repo.root
else:
cwd = encoding.getcwd()
r = ui.system(cmd, environ=env, cwd=cwd, blockedtag=b'exthook-%s' % (name,))
if repo is not None and repo.currentwlock() is None:
repo.invalidatedirstate()
if repo is not None and repo.currentlock() is None:
repo.invalidate()
duration = util.timer() - starttime
ui.log(
b'exthook',
b'exthook-%s: %s finished in %0.2f seconds\n',
name,
cmd,
duration,
)
if r:
desc = procutil.explainexit(r)
if throw:
raise error.HookAbort(_(b'%s hook %s') % (name, desc))
ui.warn(_(b'warning: %s hook %s\n') % (name, desc))
return r
# represent an untrusted hook command
_fromuntrusted = object()
def _allhooks(ui):
"""return a list of (hook-id, cmd) pairs sorted by priority"""
hooks = _hookitems(ui)
# Be careful in this section, propagating the real commands from untrusted
# sources would create a security vulnerability, make sure anything altered
# in that section uses "_fromuntrusted" as its command.
untrustedhooks = _hookitems(ui, _untrusted=True)
for name, value in untrustedhooks.items():
trustedvalue = hooks.get(name, ((), (), name, _fromuntrusted))
if value != trustedvalue:
(lp, lo, lk, lv) = trustedvalue
hooks[name] = (lp, lo, lk, _fromuntrusted)
# (end of the security sensitive section)
return [(k, v) for p, o, k, v in sorted(hooks.values())]
def _hookitems(ui, _untrusted=False):
"""return all hooks items ready to be sorted"""
hooks = {}
for name, cmd in ui.configitems(b'hooks', untrusted=_untrusted):
if (
name.startswith(b'priority.')
or name.startswith(b'tonative.')
or b':' in name
):
continue
priority = ui.configint(b'hooks', b'priority.%s' % name, 0)
hooks[name] = ((-priority,), (len(hooks),), name, cmd)
return hooks
_redirect = False
def redirect(state):
global _redirect
_redirect = state
def hashook(ui, htype):
"""return True if a hook is configured for 'htype'"""
if not ui.callhooks:
return False
for hname, cmd in _allhooks(ui):
if hname.split(b'.')[0] == htype and cmd:
return True
return False
def hook(ui, repo, htype, throw=False, **args):
if not ui.callhooks:
return False
hooks = []
for hname, cmd in _allhooks(ui):
if hname.split(b'.')[0] == htype and cmd:
hooks.append((hname, cmd))
res = runhooks(ui, repo, htype, hooks, throw=throw, **args)
r = False
for hname, cmd in hooks:
r = res[hname][0] or r
return r
@contextlib.contextmanager
def redirect_stdio():
"""Redirects stdout to stderr, if possible."""
oldstdout = -1
try:
if _redirect:
try:
stdoutno = procutil.stdout.fileno()
stderrno = procutil.stderr.fileno()
# temporarily redirect stdout to stderr, if possible
if stdoutno >= 0 and stderrno >= 0:
procutil.stdout.flush()
oldstdout = os.dup(stdoutno)
os.dup2(stderrno, stdoutno)
except (OSError, AttributeError):
# files seem to be bogus, give up on redirecting (WSGI, etc)
pass
yield
finally:
# The stderr is fully buffered on Windows when connected to a pipe.
# A forcible flush is required to make small stderr data in the
# remote side available to the client immediately.
try:
procutil.stderr.flush()
except IOError as err:
if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
raise error.StdioError(err)
if _redirect and oldstdout >= 0:
try:
procutil.stdout.flush() # write hook output to stderr fd
except IOError as err:
if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
raise error.StdioError(err)
os.dup2(oldstdout, stdoutno)
os.close(oldstdout)
def runhooks(ui, repo, htype, hooks, throw=False, **args):
args = pycompat.byteskwargs(args)
res = {}
with redirect_stdio():
for hname, cmd in hooks:
if cmd is _fromuntrusted:
if throw:
raise error.HookAbort(
_(b'untrusted hook %s not executed') % hname,
hint=_(b"see 'hg help config.trusted'"),
)
ui.warn(_(b'warning: untrusted hook %s not executed\n') % hname)
r = 1
raised = False
elif callable(cmd):
r, raised = pythonhook(ui, repo, htype, hname, cmd, args, throw)
elif cmd.startswith(b'python:'):
if cmd.count(b':') >= 2:
path, cmd = cmd[7:].rsplit(b':', 1)
path = util.expandpath(path)
if repo:
path = os.path.join(repo.root, path)
try:
mod_name = 'hghook.%s' % pycompat.sysstr(hname)
mod = extensions.loadpath(path, mod_name)
except Exception:
ui.write(_(b"loading %s hook failed:\n") % hname)
raise
hookfn = getattr(mod, pycompat.sysstr(cmd))
else:
hookfn = cmd[7:].strip()
r, raised = pythonhook(
ui, repo, htype, hname, hookfn, args, throw
)
else:
r = _exthook(ui, repo, htype, hname, cmd, args, throw)
raised = False
res[hname] = r, raised
return res