view hgext/largefiles/localstore.py @ 40736:0728d87a8631

store: append to fncache if there are only new files to write

Before this patch, if we have to add a new entry to fncache, we write the whole
fncache again which slows things down on large fncache which have millions of
entries. Addition of a new entry is common operation while pulling new files or
commiting a new file.

This patch adds a new fncache.addls set which keeps track of the additions
happening and store them. When we write the fncache, we will just read the addls
set and append those entries at the end of fncache.
We make sure that the entries are new entries by loading the fncache and making
sure entry does not exists there. In future if we can check if an entry is new
without loading the fncache, that will speed up things more.

Performance numbers for commiting a new file:

mercurial repo
before: 0.08784651756286621
after: 0.08474504947662354

mozilla-central
before: 1.83314049243927
after: 1.7054164409637451

netbeans
before: 0.7953150272369385
after: 0.7202838659286499

pypy
before: 0.17805707454681396
after: 0.13431048393249512

In our internal repo, the performance improvement is in seconds.

I have used octobus's ASV perf benchmark thing to get the above numbers. I also
see some minute perf improvements related to creating a new commit without a new
file, but I believe that's just some noise.

Differential Revision: https://phab.mercurial-scm.org/D5301

# Copyright 2009-2010 Gregory P. Ward
# Copyright 2009-2010 Intelerad Medical Systems Incorporated
# Copyright 2010-2011 Fog Creek Software
# Copyright 2010-2011 Unity Technologies
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''store class for local filesystem'''
from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import util

from . import (
    basestore,
    lfutil,
)

class localstore(basestore.basestore):
    '''localstore first attempts to grab files out of the store in the remote
    Mercurial repository.  Failing that, it attempts to grab the files from
    the user cache.'''

    def __init__(self, ui, repo, remote):
        self.remote = remote.local()
        super(localstore, self).__init__(ui, repo, self.remote.url())

    def put(self, source, hash):
        if lfutil.instore(self.remote, hash):
            return
        lfutil.link(source, lfutil.storepath(self.remote, hash))

    def exists(self, hashes):
        retval = {}
        for hash in hashes:
            retval[hash] = lfutil.instore(self.remote, hash)
        return retval

    def _getfile(self, tmpfile, filename, hash):
        path = lfutil.findfile(self.remote, hash)
        if not path:
            raise basestore.StoreError(filename, hash, self.url,
                _("can't get file locally"))
        with open(path, 'rb') as fd:
            return lfutil.copyandhash(
                util.filechunkiter(fd), tmpfile)

    def _verifyfiles(self, contents, filestocheck):
        failed = False
        for cset, filename, expectedhash in filestocheck:
            storepath, exists = lfutil.findstorepath(self.repo, expectedhash)
            if not exists:
                storepath, exists = lfutil.findstorepath(
                    self.remote, expectedhash)
            if not exists:
                self.ui.warn(
                    _('changeset %s: %s references missing %s\n')
                    % (cset, filename, storepath))
                failed = True
            elif contents:
                actualhash = lfutil.hashfile(storepath)
                if actualhash != expectedhash:
                    self.ui.warn(
                        _('changeset %s: %s references corrupted %s\n')
                        % (cset, filename, storepath))
                    failed = True
        return failed