view hgext/fsmonitor/state.py @ 42743:8c9a6adec67a

rust-discovery: using the children cache in add_missing

The DAG range computation often needs to get back to very old
revisions, and turns out to be disproportionately long, given
that the end goal is to remove the descendents of the given
missing revisons from the undecided set.

The fast iteration capabilities available in the Rust case make
it possible to avoid the DAG range entirely, at the cost of
precomputing the children cache, and to simply iterate on
children of the given missing revisions.

This is a case where staying on the same side of the interface
between the two languages has clear benefits.

On discoveries with initial undecided sets
small enough to bypass sampling entirely, the total cost of
computing the children cache and the subsequent iteration
becomes better than the Python + C counterpart, which relies on
reachableroots2.

For example, on a repo with more than one million revisions with
an initial undecided set of 11 elements, we get these figures:

Rust version with simple iteration
  addcommons: 57.287us
  first undecided computation: 184.278334ms
  first children cache computation: 131.056us
  addmissings iteration: 42.766us
  first addinfo total: 185.24 ms

Python + C version
  first addcommons: 0.29 ms
  addcommons 0.21 ms
  first undecided computation 191.35 ms
  addmissings 45.75 ms
  first addinfo total: 237.77 ms

On discoveries with large undecided sets, the initial price paid
makes the first addinfo slower than the Python + C version,
but that's more than compensated by the gain in sampling and
subsequent iterations.
Here's an extreme example with an undecided set of a million revisions:

Rust version:
  first undecided computation: 293.842629ms
  first children cache computation: 407.911297ms
  addmissings iteration: 34.312869ms
  first addinfo total: 776.02 ms
  taking initial sample
  query 2: sampling time: 1318.38 ms
  query 2; still undecided: 1005013, sample size is: 200
  addmissings: 143.062us

Python + C version:
  first undecided computation 298.13 ms
  addmissings 80.13 ms
  first addinfo total: 399.62 ms
  taking initial sample
  query 2: sampling time: 3957.23 ms
  query 2; still undecided: 1005013, sample size is: 200
  addmissings 52.88 ms

Differential Revision: https://phab.mercurial-scm.org/D6428

# state.py - fsmonitor persistent state
#
# Copyright 2013-2016 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.

from __future__ import absolute_import

import errno
import os
import socket
import struct

from mercurial.i18n import _
from mercurial import (
    pathutil,
    util,
)

_version = 4
_versionformat = ">I"

class state(object):
    def __init__(self, repo):
        self._vfs = repo.vfs
        self._ui = repo.ui
        self._rootdir = pathutil.normasprefix(repo.root)
        self._lastclock = None
        self._identity = util.filestat(None)

        self.mode = self._ui.config('fsmonitor', 'mode')
        self.walk_on_invalidate = self._ui.configbool(
            'fsmonitor', 'walk_on_invalidate')
        self.timeout = float(self._ui.config('fsmonitor', 'timeout'))

    def get(self):
        try:
            file = self._vfs('fsmonitor.state', 'rb')
        except IOError as inst:
            self._identity = util.filestat(None)
            if inst.errno != errno.ENOENT:
                raise
            return None, None, None

        self._identity = util.filestat.fromfp(file)

        versionbytes = file.read(4)
        if len(versionbytes) < 4:
            self._ui.log(
                'fsmonitor', 'fsmonitor: state file only has %d bytes, '
                'nuking state\n' % len(versionbytes))
            self.invalidate()
            return None, None, None
        try:
            diskversion = struct.unpack(_versionformat, versionbytes)[0]
            if diskversion != _version:
                # different version, nuke state and start over
                self._ui.log(
                    'fsmonitor', 'fsmonitor: version switch from %d to '
                    '%d, nuking state\n' % (diskversion, _version))
                self.invalidate()
                return None, None, None

            state = file.read().split('\0')
            # state = hostname\0clock\0ignorehash\0 + list of files, each
            # followed by a \0
            if len(state) < 3:
                self._ui.log(
                    'fsmonitor', 'fsmonitor: state file truncated (expected '
                    '3 chunks, found %d), nuking state\n', len(state))
                self.invalidate()
                return None, None, None
            diskhostname = state[0]
            hostname = socket.gethostname()
            if diskhostname != hostname:
                # file got moved to a different host
                self._ui.log('fsmonitor', 'fsmonitor: stored hostname "%s" '
                             'different from current "%s", nuking state\n' %
                             (diskhostname, hostname))
                self.invalidate()
                return None, None, None

            clock = state[1]
            ignorehash = state[2]
            # discard the value after the last \0
            notefiles = state[3:-1]

        finally:
            file.close()

        return clock, ignorehash, notefiles

    def set(self, clock, ignorehash, notefiles):
        if clock is None:
            self.invalidate()
            return

        # Read the identity from the file on disk rather than from the open file
        # pointer below, because the latter is actually a brand new file.
        identity = util.filestat.frompath(self._vfs.join('fsmonitor.state'))
        if identity != self._identity:
            self._ui.debug('skip updating fsmonitor.state: identity mismatch\n')
            return

        try:
            file = self._vfs('fsmonitor.state', 'wb', atomictemp=True,
                checkambig=True)
        except (IOError, OSError):
            self._ui.warn(_("warning: unable to write out fsmonitor state\n"))
            return

        with file:
            file.write(struct.pack(_versionformat, _version))
            file.write(socket.gethostname() + '\0')
            file.write(clock + '\0')
            file.write(ignorehash + '\0')
            if notefiles:
                file.write('\0'.join(notefiles))
                file.write('\0')

    def invalidate(self):
        try:
            os.unlink(os.path.join(self._rootdir, '.hg', 'fsmonitor.state'))
        except OSError as inst:
            if inst.errno != errno.ENOENT:
                raise
        self._identity = util.filestat(None)

    def setlastclock(self, clock):
        self._lastclock = clock

    def getlastclock(self):
        return self._lastclock