hgext/largefiles/remotestore.py

largefiles: optimize update speed by only updating changed largefiles

Historically, during 'hg update', every largefile in the working copy was
hashed (which is a very expensive operation on big files) and any
largefiles that did not have a hash that matched their standin were
updated.

This patch optimizes 'hg update' by keeping track of what standins have
changed between the old and new revisions, and only updating the largefiles
that have changed.  This saves a lot of time by avoiding the unecessary
calculation of a list of sha1 hashes for big files.

With this patch, the time 'hg update' takes to complete is a function of
how many largefiles need to be updated and what their size is.

Performance tests on a repository with about 80 largefiles ranging from
a few MB to about 97 MB are shown below.  The tests show how long it takes
to run 'hg update' with no changes actually being updated.

Mercurial 2.1 release:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved
getting changed largefiles
0 largefiles updated, 0 removed

real    0m10.045s
user    0m9.367s
sys    0m0.674s

With this patch:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved

real    0m0.965s
user    0m0.845s
sys    0m0.115s

The same repsoitory, without the largefiles extension enabled:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved

real    0m0.799s
user    0m0.684s
sys    0m0.111s

So before the patch, 'hg update' with no changes was approximately 9.25s
slower with largefiles enabled.  With this patch, it is approximately 0.165s
slower.

# 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.

'''remote largefile store; the base class for servestore'''

import urllib2

from mercurial import util
from mercurial.i18n import _

import lfutil
import basestore

class remotestore(basestore.basestore):
    '''a largefile store accessed over a network'''
    def __init__(self, ui, repo, url):
        super(remotestore, self).__init__(ui, repo, url)

    def put(self, source, hash):
        if self._verify(hash):
            return
        if self.sendfile(source, hash):
            raise util.Abort(
                _('remotestore: could not put %s to remote store %s')
                % (source, self.url))
        self.ui.debug(
            _('remotestore: put %s to remote store %s') % (source, self.url))

    def exists(self, hash):
        return self._verify(hash)

    def sendfile(self, filename, hash):
        self.ui.debug('remotestore: sendfile(%s, %s)\n' % (filename, hash))
        fd = None
        try:
            try:
                fd = lfutil.httpsendfile(self.ui, filename)
            except IOError, e:
                raise util.Abort(
                    _('remotestore: could not open file %s: %s')
                    % (filename, str(e)))
            return self._put(hash, fd)
        finally:
            if fd:
                fd.close()

    def _getfile(self, tmpfile, filename, hash):
        # quit if the largefile isn't there
        stat = self._stat(hash)
        if stat == 1:
            raise util.Abort(_('remotestore: largefile %s is invalid') % hash)
        elif stat == 2:
            raise util.Abort(_('remotestore: largefile %s is missing') % hash)

        try:
            length, infile = self._get(hash)
        except urllib2.HTTPError, e:
            # 401s get converted to util.Aborts; everything else is fine being
            # turned into a StoreError
            raise basestore.StoreError(filename, hash, self.url, str(e))
        except urllib2.URLError, e:
            # This usually indicates a connection problem, so don't
            # keep trying with the other files... they will probably
            # all fail too.
            raise util.Abort('%s: %s' % (self.url, e.reason))
        except IOError, e:
            raise basestore.StoreError(filename, hash, self.url, str(e))

        # Mercurial does not close its SSH connections after writing a stream
        if length is not None:
            infile = lfutil.limitreader(infile, length)
        return lfutil.copyandhash(lfutil.blockstream(infile), tmpfile)

    def _verify(self, hash):
        return not self._stat(hash)

    def _verifyfile(self, cctx, cset, contents, standin, verified):
        filename = lfutil.splitstandin(standin)
        if not filename:
            return False
        fctx = cctx[standin]
        key = (filename, fctx.filenode())
        if key in verified:
            return False

        verified.add(key)

        stat = self._stat(hash)
        if not stat:
            return False
        elif stat == 1:
            self.ui.warn(
                _('changeset %s: %s: contents differ\n')
                % (cset, filename))
            return True # failed
        elif stat == 2:
            self.ui.warn(
                _('changeset %s: %s missing\n')
                % (cset, filename))
            return True # failed
        else:
            raise RuntimeError('verify failed: unexpected response from '
                               'statlfile (%r)' % stat)