view hgext/largefiles/proto.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

# Copyright 2011 Fog Creek Software
#
# 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 re

from mercurial.i18n import _

from mercurial import (
    error,
    httppeer,
    util,
    wireprototypes,
    wireprotov1peer,
)

from . import (
    lfutil,
)

urlerr = util.urlerr
urlreq = util.urlreq

LARGEFILES_REQUIRED_MSG = ('\nThis repository uses the largefiles extension.'
                           '\n\nPlease enable it in your Mercurial config '
                           'file.\n')

# these will all be replaced by largefiles.uisetup
ssholdcallstream = None
httpoldcallstream = None

def putlfile(repo, proto, sha):
    '''Server command for putting a largefile into a repository's local store
    and into the user cache.'''
    with proto.mayberedirectstdio() as output:
        path = lfutil.storepath(repo, sha)
        util.makedirs(os.path.dirname(path))
        tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)

        try:
            for p in proto.getpayload():
                tmpfp.write(p)
            tmpfp._fp.seek(0)
            if sha != lfutil.hexsha1(tmpfp._fp):
                raise IOError(0, _('largefile contents do not match hash'))
            tmpfp.close()
            lfutil.linktousercache(repo, sha)
        except IOError as e:
            repo.ui.warn(_('largefiles: failed to put %s into store: %s\n') %
                         (sha, e.strerror))
            return wireprototypes.pushres(
                1, output.getvalue() if output else '')
        finally:
            tmpfp.discard()

    return wireprototypes.pushres(0, output.getvalue() if output else '')

def getlfile(repo, proto, sha):
    '''Server command for retrieving a largefile from the repository-local
    cache or user cache.'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        raise error.Abort(_('requested largefile %s not present in cache')
                          % sha)
    f = open(filename, 'rb')
    length = os.fstat(f.fileno())[6]

    # Since we can't set an HTTP content-length header here, and
    # Mercurial core provides no way to give the length of a streamres
    # (and reading the entire file into RAM would be ill-advised), we
    # just send the length on the first line of the response, like the
    # ssh proto does for string responses.
    def generator():
        yield '%d\n' % length
        for chunk in util.filechunkiter(f):
            yield chunk
    return wireprototypes.streamreslegacy(gen=generator())

def statlfile(repo, proto, sha):
    '''Server command for checking if a largefile is present - returns '2\n' if
    the largefile is missing, '0\n' if it seems to be in good condition.

    The value 1 is reserved for mismatched checksum, but that is too expensive
    to be verified on every stat and must be caught be running 'hg verify'
    server side.'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        return wireprototypes.bytesresponse('2\n')
    return wireprototypes.bytesresponse('0\n')

def wirereposetup(ui, repo):
    class lfileswirerepository(repo.__class__):
        def putlfile(self, sha, fd):
            # unfortunately, httprepository._callpush tries to convert its
            # input file-like into a bundle before sending it, so we can't use
            # it ...
            if issubclass(self.__class__, httppeer.httppeer):
                res = self._call('putlfile', data=fd, sha=sha,
                    headers={r'content-type': r'application/mercurial-0.1'})
                try:
                    d, output = res.split('\n', 1)
                    for l in output.splitlines(True):
                        self.ui.warn(_('remote: '), l) # assume l ends with \n
                    return int(d)
                except ValueError:
                    self.ui.warn(_('unexpected putlfile response: %r\n') % res)
                    return 1
            # ... but we can't use sshrepository._call because the data=
            # argument won't get sent, and _callpush does exactly what we want
            # in this case: send the data straight through
            else:
                try:
                    ret, output = self._callpush("putlfile", fd, sha=sha)
                    if ret == "":
                        raise error.ResponseError(_('putlfile failed:'),
                                output)
                    return int(ret)
                except IOError:
                    return 1
                except ValueError:
                    raise error.ResponseError(
                        _('putlfile failed (unexpected response):'), ret)

        def getlfile(self, sha):
            """returns an iterable with the chunks of the file with sha sha"""
            stream = self._callstream("getlfile", sha=sha)
            length = stream.readline()
            try:
                length = int(length)
            except ValueError:
                self._abort(error.ResponseError(_("unexpected response:"),
                                                length))

            # SSH streams will block if reading more than length
            for chunk in util.filechunkiter(stream, limit=length):
                yield chunk
            # HTTP streams must hit the end to process the last empty
            # chunk of Chunked-Encoding so the connection can be reused.
            if issubclass(self.__class__, httppeer.httppeer):
                chunk = stream.read(1)
                if chunk:
                    self._abort(error.ResponseError(_("unexpected response:"),
                                                    chunk))

        @wireprotov1peer.batchable
        def statlfile(self, sha):
            f = wireprotov1peer.future()
            result = {'sha': sha}
            yield result, f
            try:
                yield int(f.value)
            except (ValueError, urlerr.httperror):
                # If the server returns anything but an integer followed by a
                # newline, newline, it's not speaking our language; if we get
                # an HTTP error, we can't be sure the largefile is present;
                # either way, consider it missing.
                yield 2

    repo.__class__ = lfileswirerepository

# advertise the largefiles=serve capability
def _capabilities(orig, repo, proto):
    '''announce largefile server capability'''
    caps = orig(repo, proto)
    caps.append('largefiles=serve')
    return caps

def heads(orig, repo, proto):
    '''Wrap server command - largefile capable clients will know to call
    lheads instead'''
    if lfutil.islfilesrepo(repo):
        return wireprototypes.ooberror(LARGEFILES_REQUIRED_MSG)

    return orig(repo, proto)

def sshrepocallstream(self, cmd, **args):
    if cmd == 'heads' and self.capable('largefiles'):
        cmd = 'lheads'
    if cmd == 'batch' and self.capable('largefiles'):
        args[r'cmds'] = args[r'cmds'].replace('heads ', 'lheads ')
    return ssholdcallstream(self, cmd, **args)

headsre = re.compile(br'(^|;)heads\b')

def httprepocallstream(self, cmd, **args):
    if cmd == 'heads' and self.capable('largefiles'):
        cmd = 'lheads'
    if cmd == 'batch' and self.capable('largefiles'):
        args[r'cmds'] = headsre.sub('lheads', args[r'cmds'])
    return httpoldcallstream(self, cmd, **args)