hgext/largefiles/uisetup.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 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.

'''setup for largefiles extension: uisetup'''

from mercurial import archival, cmdutil, commands, extensions, filemerge, hg, \
    httprepo, localrepo, merge, sshrepo, sshserver, wireproto
from mercurial.i18n import _
from mercurial.hgweb import hgweb_mod, protocol

import overrides
import proto

def uisetup(ui):
    # Disable auto-status for some commands which assume that all
    # files in the result are under Mercurial's control

    entry = extensions.wrapcommand(commands.table, 'add',
                                   overrides.override_add)
    addopt = [('', 'large', None, _('add as largefile')),
              ('', 'normal', None, _('add as normal file')),
              ('', 'lfsize', '', _('add all files above this size '
                                   '(in megabytes) as largefiles '
                                   '(default: 10)'))]
    entry[1].extend(addopt)

    entry = extensions.wrapcommand(commands.table, 'addremove',
            overrides.override_addremove)
    entry = extensions.wrapcommand(commands.table, 'remove',
                                   overrides.override_remove)
    entry = extensions.wrapcommand(commands.table, 'forget',
                                   overrides.override_forget)
    entry = extensions.wrapcommand(commands.table, 'status',
                                   overrides.override_status)
    entry = extensions.wrapcommand(commands.table, 'log',
                                   overrides.override_log)
    entry = extensions.wrapcommand(commands.table, 'rollback',
                                   overrides.override_rollback)
    entry = extensions.wrapcommand(commands.table, 'verify',
                                   overrides.override_verify)

    verifyopt = [('', 'large', None, _('verify largefiles')),
                 ('', 'lfa', None,
                     _('verify all revisions of largefiles not just current')),
                 ('', 'lfc', None,
                     _('verify largefile contents not just existence'))]
    entry[1].extend(verifyopt)

    entry = extensions.wrapcommand(commands.table, 'outgoing',
        overrides.override_outgoing)
    outgoingopt = [('', 'large', None, _('display outgoing largefiles'))]
    entry[1].extend(outgoingopt)
    entry = extensions.wrapcommand(commands.table, 'summary',
                                   overrides.override_summary)
    summaryopt = [('', 'large', None, _('display outgoing largefiles'))]
    entry[1].extend(summaryopt)

    entry = extensions.wrapcommand(commands.table, 'update',
                                   overrides.override_update)
    entry = extensions.wrapcommand(commands.table, 'pull',
                                   overrides.override_pull)
    entry = extensions.wrapfunction(merge, '_checkunknownfile',
                                    overrides.override_checkunknownfile)
    entry = extensions.wrapfunction(merge, 'manifestmerge',
                                    overrides.override_manifestmerge)
    entry = extensions.wrapfunction(filemerge, 'filemerge',
                                    overrides.override_filemerge)
    entry = extensions.wrapfunction(cmdutil, 'copy',
                                    overrides.override_copy)

    # Backout calls revert so we need to override both the command and the
    # function
    entry = extensions.wrapcommand(commands.table, 'revert',
                                   overrides.override_revert)
    entry = extensions.wrapfunction(commands, 'revert',
                                    overrides.override_revert)

    # clone uses hg._update instead of hg.update even though they are the
    # same function... so wrap both of them)
    extensions.wrapfunction(hg, 'update', overrides.hg_update)
    extensions.wrapfunction(hg, '_update', overrides.hg_update)
    extensions.wrapfunction(hg, 'clean', overrides.hg_clean)
    extensions.wrapfunction(hg, 'merge', overrides.hg_merge)

    extensions.wrapfunction(archival, 'archive', overrides.override_archive)
    extensions.wrapfunction(cmdutil, 'bailifchanged',
                            overrides.override_bailifchanged)

    # create the new wireproto commands ...
    wireproto.commands['putlfile'] = (proto.putlfile, 'sha')
    wireproto.commands['getlfile'] = (proto.getlfile, 'sha')
    wireproto.commands['statlfile'] = (proto.statlfile, 'sha')

    # ... and wrap some existing ones
    wireproto.commands['capabilities'] = (proto.capabilities, '')
    wireproto.commands['heads'] = (proto.heads, '')
    wireproto.commands['lheads'] = (wireproto.heads, '')

    # make putlfile behave the same as push and {get,stat}lfile behave
    # the same as pull w.r.t. permissions checks
    hgweb_mod.perms['putlfile'] = 'push'
    hgweb_mod.perms['getlfile'] = 'pull'
    hgweb_mod.perms['statlfile'] = 'pull'

    # the hello wireproto command uses wireproto.capabilities, so it won't see
    # our largefiles capability unless we replace the actual function as well.
    proto.capabilities_orig = wireproto.capabilities
    wireproto.capabilities = proto.capabilities

    # these let us reject non-largefiles clients and make them display
    # our error messages
    protocol.webproto.refuseclient = proto.webproto_refuseclient
    sshserver.sshserver.refuseclient = proto.sshproto_refuseclient

    # can't do this in reposetup because it needs to have happened before
    # wirerepo.__init__ is called
    proto.ssh_oldcallstream = sshrepo.sshrepository._callstream
    proto.http_oldcallstream = httprepo.httprepository._callstream
    sshrepo.sshrepository._callstream = proto.sshrepo_callstream
    httprepo.httprepository._callstream = proto.httprepo_callstream

    # don't die on seeing a repo with the largefiles requirement
    localrepo.localrepository.supported |= set(['largefiles'])

    # override some extensions' stuff as well
    for name, module in extensions.extensions():
        if name == 'fetch':
            extensions.wrapcommand(getattr(module, 'cmdtable'), 'fetch',
                overrides.override_fetch)
        if name == 'purge':
            extensions.wrapcommand(getattr(module, 'cmdtable'), 'purge',
                overrides.override_purge)
        if name == 'rebase':
            extensions.wrapcommand(getattr(module, 'cmdtable'), 'rebase',
                overrides.override_rebase)
        if name == 'transplant':
            extensions.wrapcommand(getattr(module, 'cmdtable'), 'transplant',
                overrides.override_transplant)