view mercurial/hook.py @ 43198:c16fe77e340a

pathcopies: give up any optimization based on `introrev` Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the introduction revision during path copies. However, further checking show that finding the introduction revision is still expensive and that we are better off without it. So we simply drop it and only rely on the linkrev optimisation. I ran `perfpathcopies` on 6989 pair of revision in the pypy repository (`hg perfhelper-pathcopies`. The result is massively in favor of dropping this condition. The result of the copy tracing are unchanged. Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it can return wrong result. The following changesets broke test-mv-cp-st-diff.t - if not f.isintroducedafter(limit): + if limit >= 0 and f.linkrev() < limit: return None Here are various numbers (before this changeset/after this changesets) source destination before after saved-time ratio worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675 c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743 22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420 682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074 5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817 worse 1% dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320 worse 5% c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488 worse 10% 3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156 worse 25% 321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259 median 2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947 best 25% 915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673 best 10% ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278 best 5% d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126 best 1% 81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813 best cases c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483 c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508 058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442 9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463 442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487 As one can see, the average case is not really impacted. However, the worth case we get after this changeset are much better than the one we had before it. We have 30 pairs where improvements are above 10 minutes. This reflect in the combined time for all pairs before: 26256s after: 1300s (-95%) If we remove these pathological 30 cases, we still see a significant improvements: before: 1631s after: 1245s (-24%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Thu, 10 Oct 2019 03:49:33 +0200
parents 8ff1ecfadcd1
children 313e3a279828
line wrap: on
line source

# hook.py - hook support for mercurial
#
# Copyright 2007 Matt Mackall <mpm@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.

from __future__ import absolute_import

import os
import sys

from .i18n import _
from .pycompat import getattr
from . import (
    demandimport,
    encoding,
    error,
    extensions,
    pycompat,
    util,
)
from .utils import (
    procutil,
    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 = pycompat.sysbytes(obj.__module__ + r"." + obj.__name__)
    else:
        d = funcname.rfind(b'.')
        if d == -1:
            raise error.HookLoadError(
                _(b'%s hook is invalid: "%s" not in a module')
                % (hname, funcname)
            )
        modname = funcname[:d]
        oldpaths = sys.path
        if procutil.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__(r"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
                    raise error.HookLoadError(
                        _(b'%s hook is invalid: import of "%s" failed')
                        % (hname, modname),
                        hint=tracebackhint,
                    )
        sys.path = oldpaths
        try:
            for p in funcname.split(b'.')[1:]:
                obj = getattr(obj, p)
        except AttributeError:
            raise error.HookLoadError(
                _(b'%s hook is invalid: "%s" is not defined')
                % (hname, funcname)
            )
        if not callable(obj):
            raise error.HookLoadError(
                _(b'%s hook is invalid: "%s" is not callable')
                % (hname, funcname)
            )

    ui.note(_(b"calling hook %s: %s\n") % (hname, 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,
            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

    for k, v in pycompat.iteritems(args):
        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,))

    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, (None, None, 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.'):
            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


def runhooks(ui, repo, htype, hooks, throw=False, **args):
    args = pycompat.byteskwargs(args)
    res = {}
    oldstdout = -1

    try:
        for hname, cmd in hooks:
            if oldstdout == -1 and _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

            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 = extensions.loadpath(path, b'hghook.%s' % hname)
                    except Exception:
                        ui.write(_(b"loading %s hook failed:\n") % hname)
                        raise
                    hookfn = getattr(mod, 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
    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.
        procutil.stderr.flush()

        if _redirect and oldstdout >= 0:
            procutil.stdout.flush()  # write hook output to stderr fd
            os.dup2(oldstdout, stdoutno)
            os.close(oldstdout)

    return res