view hgext/fsmonitor/state.py @ 33649:377e8ddaebef stable

pathauditor: disable cache of audited paths by default (issue5628)

The initial attempt was to discard cache when appropriate, but it appears
to be error prone. We had to carefully inspect all places where audit() is
called e.g. without actually updating filesystem, before removing files and
directories, etc.

So, this patch disables the cache of audited paths by default, and enables
it only for the following cases:

 - short-lived auditor objects
 - repo.vfs, repo.svfs, and repo.cachevfs, which are managed directories
   and considered sort of append-only (a file/directory would never be
   replaced with a symlink)

There would be more cacheable vfs objects (e.g. mq.queue.opener), but I
decided not to inspect all of them in this patch. We can make them cached
later.

Benchmark result:

- using old clone of http://selenic.com/repo/linux-2.6/ (38319 files)
- on tmpfs
- run HGRCPATH=/dev/null hg up -q --time tip && hg up -q null
- try 4 times and take the last three results

original:
real 7.480 secs (user 1.140+22.760 sys 0.150+1.690)
real 8.010 secs (user 1.070+22.280 sys 0.170+2.120)
real 7.470 secs (user 1.120+22.390 sys 0.120+1.910)

clearcache (the other series):
real 7.680 secs (user 1.120+23.420 sys 0.140+1.970)
real 7.670 secs (user 1.110+23.620 sys 0.130+1.810)
real 7.740 secs (user 1.090+23.510 sys 0.160+1.940)

enable cache only for vfs and svfs (this series):
real 8.730 secs (user 1.500+25.190 sys 0.260+2.260)
real 8.750 secs (user 1.490+25.170 sys 0.250+2.340)
real 9.010 secs (user 1.680+25.340 sys 0.280+2.540)

remove cache function at all (for reference):
real 9.620 secs (user 1.440+27.120 sys 0.250+2.980)
real 9.420 secs (user 1.400+26.940 sys 0.320+3.130)
real 9.760 secs (user 1.530+27.270 sys 0.250+2.970)

# 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', default='on')
        self.walk_on_invalidate = self._ui.configbool(
            'fsmonitor', 'walk_on_invalidate', False)
        self.timeout = float(self._ui.config(
            'fsmonitor', 'timeout', default='2'))

    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