annotate hgext/journal.py @ 40811:e13ab4acf555

rust: peek_mut optim for lazy ancestors

This is one of the two optimizations that are also
present in the Python code: replacing pairs of pop/push
on the BinaryHeap by single updates, hence having it
under the hood maintain its consistency (sift) only once.

On Mozilla central, the measured gain (see details below)
is around 7%.

Creating the PeekMut object by calling peek_mut() right away
instead of peek() first is less efficient (gain is only 4%, stats
not included).
Our interpretation is that its creation has a cost which is vasted
in the cases where it ends by droping the value (Peekmut::pop()
just does self.heap.pop() anyway). On the other hand, the immutable
peek() is very fast: it's just taking a reference in the
underlying vector.

The Python version still has another optimization:
if parent(current) == current-1, then the heap doesn't need
to maintain its consistency, since we already know that
it's bigger than all the others in the heap.
Rust's BinaryHeap doesn't allow us to mutate its biggest
element with no housekeeping, but we tried it anyway, with a
copy of the BinaryHeap implementation with a dedicaded added
method: it's not worth the technical debt in our opinion
(we measured only a further 1.6% improvement).
One possible explanation would be that the sift is really fast
anyway in that case, whereas it's not in the case of Python,
because it's at least partly done in slow Python code.
Still it's possible that replacing BinaryHeap by something more
dedicated to discrete ordered types could be faster.

Measurements on mozilla-central:

Three runs of 'hg perfancestors' on the parent changeset:

Moyenne des médianes: 0.100587
! wall 0.100062 comb 0.100000 user 0.100000 sys 0.000000 (best of 98)
! wall 0.135804 comb 0.130000 user 0.130000 sys 0.000000 (max of 98)
! wall 0.102864 comb 0.102755 user 0.099286 sys 0.003469 (avg of 98)
! wall 0.101486 comb 0.110000 user 0.110000 sys 0.000000 (median of 98)

! wall 0.096804 comb 0.090000 user 0.090000 sys 0.000000 (best of 100)
! wall 0.132235 comb 0.130000 user 0.120000 sys 0.010000 (max of 100)
! wall 0.100258 comb 0.100300 user 0.096000 sys 0.004300 (avg of 100)
! wall 0.098384 comb 0.100000 user 0.100000 sys 0.000000 (median of 100)

! wall 0.099925 comb 0.100000 user 0.100000 sys 0.000000 (best of 98)
! wall 0.133518 comb 0.140000 user 0.130000 sys 0.010000 (max of 98)
! wall 0.102381 comb 0.102449 user 0.098265 sys 0.004184 (avg of 98)
! wall 0.101891 comb 0.090000 user 0.090000 sys 0.000000 (median of 98)

Mean of the medians: 0.100587

On the present changeset:

! wall 0.091344 comb 0.090000 user 0.090000 sys 0.000000 (best of 100)
! wall 0.122728 comb 0.120000 user 0.110000 sys 0.010000 (max of 100)
! wall 0.093268 comb 0.093300 user 0.089300 sys 0.004000 (avg of 100)
! wall 0.092567 comb 0.100000 user 0.090000 sys 0.010000 (median of 100)

! wall 0.093294 comb 0.080000 user 0.080000 sys 0.000000 (best of 100)
! wall 0.144887 comb 0.150000 user 0.140000 sys 0.010000 (max of 100)
! wall 0.097708 comb 0.097700 user 0.093400 sys 0.004300 (avg of 100)
! wall 0.094980 comb 0.100000 user 0.090000 sys 0.010000 (median of 100)

! wall 0.091262 comb 0.090000 user 0.080000 sys 0.010000 (best of 100)
! wall 0.123772 comb 0.130000 user 0.120000 sys 0.010000 (max of 100)
! wall 0.093188 comb 0.093200 user 0.089300 sys 0.003900 (avg of 100)
! wall 0.092364 comb 0.100000 user 0.090000 sys 0.010000 (median of 100)

Mean of the medians is 0.0933

Differential Revision: https://phab.mercurial-scm.org/D5358

# journal.py
#
# Copyright 2014-2016 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""track previous positions of bookmarks (EXPERIMENTAL)

This extension adds a new command: `hg journal`, which shows you where
bookmarks were previously located.

"""

from __future__ import absolute_import

import collections
import errno
import os
import weakref

from mercurial.i18n import _

from mercurial import (
    bookmarks,
    cmdutil,
    dispatch,
    encoding,
    error,
    extensions,
    hg,
    localrepo,
    lock,
    logcmdutil,
    node,
    pycompat,
    registrar,
    util,
)
from mercurial.utils import (
    dateutil,
    procutil,
    stringutil,
)

cmdtable = {}
command = registrar.command(cmdtable)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

# storage format version; increment when the format changes
storageversion = 0

# namespaces
bookmarktype = 'bookmark'
wdirparenttype = 'wdirparent'
# In a shared repository, what shared feature name is used
# to indicate this namespace is shared with the source?
sharednamespaces = {
    bookmarktype: hg.sharedbookmarks,
}

# Journal recording, register hooks and storage object
def extsetup(ui):
    extensions.wrapfunction(dispatch, 'runcommand', runcommand)
    extensions.wrapfunction(bookmarks.bmstore, '_write', recordbookmarks)
    extensions.wrapfilecache(
        localrepo.localrepository, 'dirstate', wrapdirstate)
    extensions.wrapfunction(hg, 'postshare', wrappostshare)
    extensions.wrapfunction(hg, 'copystore', unsharejournal)

def reposetup(ui, repo):
    if repo.local():
        repo.journal = journalstorage(repo)
        repo._wlockfreeprefix.add('namejournal')

        dirstate, cached = localrepo.isfilecached(repo, 'dirstate')
        if cached:
            # already instantiated dirstate isn't yet marked as
            # "journal"-ing, even though repo.dirstate() was already
            # wrapped by own wrapdirstate()
            _setupdirstate(repo, dirstate)

def runcommand(orig, lui, repo, cmd, fullargs, *args):
    """Track the command line options for recording in the journal"""
    journalstorage.recordcommand(*fullargs)
    return orig(lui, repo, cmd, fullargs, *args)

def _setupdirstate(repo, dirstate):
    dirstate.journalstorage = repo.journal
    dirstate.addparentchangecallback('journal', recorddirstateparents)

# hooks to record dirstate changes
def wrapdirstate(orig, repo):
    """Make journal storage available to the dirstate object"""
    dirstate = orig(repo)
    if util.safehasattr(repo, 'journal'):
        _setupdirstate(repo, dirstate)
    return dirstate

def recorddirstateparents(dirstate, old, new):
    """Records all dirstate parent changes in the journal."""
    old = list(old)
    new = list(new)
    if util.safehasattr(dirstate, 'journalstorage'):
        # only record two hashes if there was a merge
        oldhashes = old[:1] if old[1] == node.nullid else old
        newhashes = new[:1] if new[1] == node.nullid else new
        dirstate.journalstorage.record(
            wdirparenttype, '.', oldhashes, newhashes)

# hooks to record bookmark changes (both local and remote)
def recordbookmarks(orig, store, fp):
    """Records all bookmark changes in the journal."""
    repo = store._repo
    if util.safehasattr(repo, 'journal'):
        oldmarks = bookmarks.bmstore(repo)
        for mark, value in store.iteritems():
            oldvalue = oldmarks.get(mark, node.nullid)
            if value != oldvalue:
                repo.journal.record(bookmarktype, mark, oldvalue, value)
    return orig(store, fp)

# shared repository support
def _readsharedfeatures(repo):
    """A set of shared features for this repository"""
    try:
        return set(repo.vfs.read('shared').splitlines())
    except IOError as inst:
        if inst.errno != errno.ENOENT:
            raise
        return set()

def _mergeentriesiter(*iterables, **kwargs):
    """Given a set of sorted iterables, yield the next entry in merged order

    Note that by default entries go from most recent to oldest.
    """
    order = kwargs.pop(r'order', max)
    iterables = [iter(it) for it in iterables]
    # this tracks still active iterables; iterables are deleted as they are
    # exhausted, which is why this is a dictionary and why each entry also
    # stores the key. Entries are mutable so we can store the next value each
    # time.
    iterable_map = {}
    for key, it in enumerate(iterables):
        try:
            iterable_map[key] = [next(it), key, it]
        except StopIteration:
            # empty entry, can be ignored
            pass

    while iterable_map:
        value, key, it = order(iterable_map.itervalues())
        yield value
        try:
            iterable_map[key][0] = next(it)
        except StopIteration:
            # this iterable is empty, remove it from consideration
            del iterable_map[key]

def wrappostshare(orig, sourcerepo, destrepo, **kwargs):
    """Mark this shared working copy as sharing journal information"""
    with destrepo.wlock():
        orig(sourcerepo, destrepo, **kwargs)
        with destrepo.vfs('shared', 'a') as fp:
            fp.write('journal\n')

def unsharejournal(orig, ui, repo, repopath):
    """Copy shared journal entries into this repo when unsharing"""
    if (repo.path == repopath and repo.shared() and
            util.safehasattr(repo, 'journal')):
        sharedrepo = hg.sharedreposource(repo)
        sharedfeatures = _readsharedfeatures(repo)
        if sharedrepo and sharedfeatures > {'journal'}:
            # there is a shared repository and there are shared journal entries
            # to copy. move shared date over from source to destination but
            # move the local file first
            if repo.vfs.exists('namejournal'):
                journalpath = repo.vfs.join('namejournal')
                util.rename(journalpath, journalpath + '.bak')
            storage = repo.journal
            local = storage._open(
                repo.vfs, filename='namejournal.bak', _newestfirst=False)
            shared = (
                e for e in storage._open(sharedrepo.vfs, _newestfirst=False)
                if sharednamespaces.get(e.namespace) in sharedfeatures)
            for entry in _mergeentriesiter(local, shared, order=min):
                storage._write(repo.vfs, entry)

    return orig(ui, repo, repopath)

class journalentry(collections.namedtuple(
        u'journalentry',
        u'timestamp user command namespace name oldhashes newhashes')):
    """Individual journal entry

    * timestamp: a mercurial (time, timezone) tuple
    * user: the username that ran the command
    * namespace: the entry namespace, an opaque string
    * name: the name of the changed item, opaque string with meaning in the
      namespace
    * command: the hg command that triggered this record
    * oldhashes: a tuple of one or more binary hashes for the old location
    * newhashes: a tuple of one or more binary hashes for the new location

    Handles serialisation from and to the storage format. Fields are
    separated by newlines, hashes are written out in hex separated by commas,
    timestamp and timezone are separated by a space.

    """
    @classmethod
    def fromstorage(cls, line):
        (time, user, command, namespace, name,
         oldhashes, newhashes) = line.split('\n')
        timestamp, tz = time.split()
        timestamp, tz = float(timestamp), int(tz)
        oldhashes = tuple(node.bin(hash) for hash in oldhashes.split(','))
        newhashes = tuple(node.bin(hash) for hash in newhashes.split(','))
        return cls(
            (timestamp, tz), user, command, namespace, name,
            oldhashes, newhashes)

    def __bytes__(self):
        """bytes representation for storage"""
        time = ' '.join(map(pycompat.bytestr, self.timestamp))
        oldhashes = ','.join([node.hex(hash) for hash in self.oldhashes])
        newhashes = ','.join([node.hex(hash) for hash in self.newhashes])
        return '\n'.join((
            time, self.user, self.command, self.namespace, self.name,
            oldhashes, newhashes))

    __str__ = encoding.strmethod(__bytes__)

class journalstorage(object):
    """Storage for journal entries

    Entries are divided over two files; one with entries that pertain to the
    local working copy *only*, and one with entries that are shared across
    multiple working copies when shared using the share extension.

    Entries are stored with NUL bytes as separators. See the journalentry
    class for the per-entry structure.

    The file format starts with an integer version, delimited by a NUL.

    This storage uses a dedicated lock; this makes it easier to avoid issues
    with adding entries that added when the regular wlock is unlocked (e.g.
    the dirstate).

    """
    _currentcommand = ()
    _lockref = None

    def __init__(self, repo):
        self.user = procutil.getuser()
        self.ui = repo.ui
        self.vfs = repo.vfs

        # is this working copy using a shared storage?
        self.sharedfeatures = self.sharedvfs = None
        if repo.shared():
            features = _readsharedfeatures(repo)
            sharedrepo = hg.sharedreposource(repo)
            if sharedrepo is not None and 'journal' in features:
                self.sharedvfs = sharedrepo.vfs
                self.sharedfeatures = features

    # track the current command for recording in journal entries
    @property
    def command(self):
        commandstr = ' '.join(
            map(procutil.shellquote, journalstorage._currentcommand))
        if '\n' in commandstr:
            # truncate multi-line commands
            commandstr = commandstr.partition('\n')[0] + ' ...'
        return commandstr

    @classmethod
    def recordcommand(cls, *fullargs):
        """Set the current hg arguments, stored with recorded entries"""
        # Set the current command on the class because we may have started
        # with a non-local repo (cloning for example).
        cls._currentcommand = fullargs

    def _currentlock(self, lockref):
        """Returns the lock if it's held, or None if it's not.

        (This is copied from the localrepo class)
        """
        if lockref is None:
            return None
        l = lockref()
        if l is None or not l.held:
            return None
        return l

    def jlock(self, vfs):
        """Create a lock for the journal file"""
        if self._currentlock(self._lockref) is not None:
            raise error.Abort(_('journal lock does not support nesting'))
        desc = _('journal of %s') % vfs.base
        try:
            l = lock.lock(vfs, 'namejournal.lock', 0, desc=desc)
        except error.LockHeld as inst:
            self.ui.warn(
                _("waiting for lock on %s held by %r\n") % (desc, inst.locker))
            # default to 600 seconds timeout
            l = lock.lock(
                vfs, 'namejournal.lock',
                self.ui.configint("ui", "timeout"), desc=desc)
            self.ui.warn(_("got lock after %s seconds\n") % l.delay)
        self._lockref = weakref.ref(l)
        return l

    def record(self, namespace, name, oldhashes, newhashes):
        """Record a new journal entry

        * namespace: an opaque string; this can be used to filter on the type
          of recorded entries.
        * name: the name defining this entry; for bookmarks, this is the
          bookmark name. Can be filtered on when retrieving entries.
        * oldhashes and newhashes: each a single binary hash, or a list of
          binary hashes. These represent the old and new position of the named
          item.

        """
        if not isinstance(oldhashes, list):
            oldhashes = [oldhashes]
        if not isinstance(newhashes, list):
            newhashes = [newhashes]

        entry = journalentry(
            dateutil.makedate(), self.user, self.command, namespace, name,
            oldhashes, newhashes)

        vfs = self.vfs
        if self.sharedvfs is not None:
            # write to the shared repository if this feature is being
            # shared between working copies.
            if sharednamespaces.get(namespace) in self.sharedfeatures:
                vfs = self.sharedvfs

        self._write(vfs, entry)

    def _write(self, vfs, entry):
        with self.jlock(vfs):
            version = None
            # open file in amend mode to ensure it is created if missing
            with vfs('namejournal', mode='a+b') as f:
                f.seek(0, os.SEEK_SET)
                # Read just enough bytes to get a version number (up to 2
                # digits plus separator)
                version = f.read(3).partition('\0')[0]
                if version and version != "%d" % storageversion:
                    # different version of the storage. Exit early (and not
                    # write anything) if this is not a version we can handle or
                    # the file is corrupt. In future, perhaps rotate the file
                    # instead?
                    self.ui.warn(
                        _("unsupported journal file version '%s'\n") % version)
                    return
                if not version:
                    # empty file, write version first
                    f.write(("%d" % storageversion) + '\0')
                f.seek(0, os.SEEK_END)
                f.write(bytes(entry) + '\0')

    def filtered(self, namespace=None, name=None):
        """Yield all journal entries with the given namespace or name

        Both the namespace and the name are optional; if neither is given all
        entries in the journal are produced.

        Matching supports regular expressions by using the `re:` prefix
        (use `literal:` to match names or namespaces that start with `re:`)

        """
        if namespace is not None:
            namespace = stringutil.stringmatcher(namespace)[-1]
        if name is not None:
            name = stringutil.stringmatcher(name)[-1]
        for entry in self:
            if namespace is not None and not namespace(entry.namespace):
                continue
            if name is not None and not name(entry.name):
                continue
            yield entry

    def __iter__(self):
        """Iterate over the storage

        Yields journalentry instances for each contained journal record.

        """
        local = self._open(self.vfs)

        if self.sharedvfs is None:
            return local

        # iterate over both local and shared entries, but only those
        # shared entries that are among the currently shared features
        shared = (
            e for e in self._open(self.sharedvfs)
            if sharednamespaces.get(e.namespace) in self.sharedfeatures)
        return _mergeentriesiter(local, shared)

    def _open(self, vfs, filename='namejournal', _newestfirst=True):
        if not vfs.exists(filename):
            return

        with vfs(filename) as f:
            raw = f.read()

        lines = raw.split('\0')
        version = lines and lines[0]
        if version != "%d" % storageversion:
            version = version or _('not available')
            raise error.Abort(_("unknown journal file version '%s'") % version)

        # Skip the first line, it's a version number. Normally we iterate over
        # these in reverse order to list newest first; only when copying across
        # a shared storage do we forgo reversing.
        lines = lines[1:]
        if _newestfirst:
            lines = reversed(lines)
        for line in lines:
            if not line:
                continue
            yield journalentry.fromstorage(line)

# journal reading
# log options that don't make sense for journal
_ignoreopts = ('no-merges', 'graph')
@command(
    'journal', [
        ('', 'all', None, 'show history for all names'),
        ('c', 'commits', None, 'show commit metadata'),
    ] + [opt for opt in cmdutil.logopts if opt[1] not in _ignoreopts],
    '[OPTION]... [BOOKMARKNAME]',
    helpcategory=command.CATEGORY_CHANGE_ORGANIZATION)
def journal(ui, repo, *args, **opts):
    """show the previous position of bookmarks and the working copy

    The journal is used to see the previous commits that bookmarks and the
    working copy pointed to. By default the previous locations for the working
    copy.  Passing a bookmark name will show all the previous positions of
    that bookmark. Use the --all switch to show previous locations for all
    bookmarks and the working copy; each line will then include the bookmark
    name, or '.' for the working copy, as well.

    If `name` starts with `re:`, the remainder of the name is treated as
    a regular expression. To match a name that actually starts with `re:`,
    use the prefix `literal:`.

    By default hg journal only shows the commit hash and the command that was
    running at that time. -v/--verbose will show the prior hash, the user, and
    the time at which it happened.

    Use -c/--commits to output log information on each commit hash; at this
    point you can use the usual `--patch`, `--git`, `--stat` and `--template`
    switches to alter the log output for these.

    `hg journal -T json` can be used to produce machine readable output.

    """
    opts = pycompat.byteskwargs(opts)
    name = '.'
    if opts.get('all'):
        if args:
            raise error.Abort(
                _("You can't combine --all and filtering on a name"))
        name = None
    if args:
        name = args[0]

    fm = ui.formatter('journal', opts)
    def formatnodes(nodes):
        return fm.formatlist(map(fm.hexfunc, nodes), name='node', sep=',')

    if opts.get("template") != "json":
        if name is None:
            displayname = _('the working copy and bookmarks')
        else:
            displayname = "'%s'" % name
        ui.status(_("previous locations of %s:\n") % displayname)

    limit = logcmdutil.getlimit(opts)
    entry = None
    ui.pager('journal')
    for count, entry in enumerate(repo.journal.filtered(name=name)):
        if count == limit:
            break

        fm.startitem()
        fm.condwrite(ui.verbose, 'oldnodes', '%s -> ',
                     formatnodes(entry.oldhashes))
        fm.write('newnodes', '%s', formatnodes(entry.newhashes))
        fm.condwrite(ui.verbose, 'user', ' %-8s', entry.user)
        fm.condwrite(
            opts.get('all') or name.startswith('re:'),
            'name', '  %-8s', entry.name)

        fm.condwrite(ui.verbose, 'date', ' %s',
                     fm.formatdate(entry.timestamp, '%Y-%m-%d %H:%M %1%2'))
        fm.write('command', '  %s\n', entry.command)

        if opts.get("commits"):
            if fm.isplain():
                displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
            else:
                displayer = logcmdutil.changesetformatter(
                    ui, repo, fm.nested('changesets'), diffopts=opts)
            for hash in entry.newhashes:
                try:
                    ctx = repo[hash]
                    displayer.show(ctx)
                except error.RepoLookupError as e:
                    fm.plain("%s\n\n" % pycompat.bytestr(e))
            displayer.close()

    fm.end()

    if entry is None:
        ui.status(_("no recorded locations\n"))