Mercurial > public > mercurial-scm > hg-stable
view mercurial/formatter.py @ 26117:4dc5b51f38fe
revlog: change generaldelta delta parent heuristic
The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text,
use it, otherwise use prev". This was problematic when a repo contained multiple
branches that were very different. If commits to branch A were pushed, and the
last full text was branch B, it would generate a fulltext. Then if branch B was
pushed, it would generate another fulltext. The problem is that the last
fulltext (and delta'ing against `prev` in general) has no correlation with the
contents of the incoming revision, and therefore will always have degenerate
cases.
According to the blame, that algorithm was chosen to minimize the chain length.
Since there is already code that protects against that (the delta-vs-fulltext
code), and since it has been improved since the original generaldelta algorithm
went in (2011), I believe the chain length criteria will still be preserved.
The new algorithm always diffs against p1 (or p2 if it's closer), unless the
resulting delta will fail the delta-vs-fulltext check, in which case we delta
against prev.
Some before and after stats on manifest.d size.
internal large repo
old heuristic - 2.0 GB
new heuristic - 1.2 GB
mozilla-central
old heuristic - 242 MB
new heuristic - 261 MB
The regression in mozilla central is due to the new heuristic choosing p2r as
the delta when it's closer to the tip. Switching the algorithm to always prefer
p1r brings the size back down (242 MB). This is result of the way in which
mozilla does merges and pushes, and the result could easily swing the other
direction in other repos (depending on if they merge X into Y or Y into X), but
will never be as degenerate as before.
I future patch will address the regression by introducing an optional, even more
aggressive delta heuristic which will knock the mozilla manifest size down
dramatically.
author | Durham Goode <durham@fb.com> |
---|---|
date | Sun, 30 Aug 2015 13:58:11 -0700 |
parents | 175873e36d03 |
children | 55de800937e0 |
line wrap: on
line source
# formatter.py - generic output formatting for mercurial # # Copyright 2012 Matt Mackall <mpm@selenic.com> # # 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 cPickle import os from .i18n import _ from .node import ( hex, short, ) from . import ( encoding, templater, util, ) class baseformatter(object): def __init__(self, ui, topic, opts): self._ui = ui self._topic = topic self._style = opts.get("style") self._template = opts.get("template") self._item = None # function to convert node to string suitable for this output self.hexfunc = hex def __nonzero__(self): '''return False if we're not doing real templating so we can skip extra work''' return True def _showitem(self): '''show a formatted item once all data is collected''' pass def startitem(self): '''begin an item in the format list''' if self._item is not None: self._showitem() self._item = {} def data(self, **data): '''insert data into item that's not shown in default output''' self._item.update(data) def write(self, fields, deftext, *fielddata, **opts): '''do default text output while assigning data to item''' for k, v in zip(fields.split(), fielddata): self._item[k] = v def condwrite(self, cond, fields, deftext, *fielddata, **opts): '''do conditional write (primarily for plain formatter)''' for k, v in zip(fields.split(), fielddata): self._item[k] = v def plain(self, text, **opts): '''show raw text for non-templated mode''' pass def end(self): '''end output for the formatter''' if self._item is not None: self._showitem() class plainformatter(baseformatter): '''the default text output scheme''' def __init__(self, ui, topic, opts): baseformatter.__init__(self, ui, topic, opts) if ui.debugflag: self.hexfunc = hex else: self.hexfunc = short def __nonzero__(self): return False def startitem(self): pass def data(self, **data): pass def write(self, fields, deftext, *fielddata, **opts): self._ui.write(deftext % fielddata, **opts) def condwrite(self, cond, fields, deftext, *fielddata, **opts): '''do conditional write''' if cond: self._ui.write(deftext % fielddata, **opts) def plain(self, text, **opts): self._ui.write(text, **opts) def end(self): pass class debugformatter(baseformatter): def __init__(self, ui, topic, opts): baseformatter.__init__(self, ui, topic, opts) self._ui.write("%s = [\n" % self._topic) def _showitem(self): self._ui.write(" " + repr(self._item) + ",\n") def end(self): baseformatter.end(self) self._ui.write("]\n") class pickleformatter(baseformatter): def __init__(self, ui, topic, opts): baseformatter.__init__(self, ui, topic, opts) self._data = [] def _showitem(self): self._data.append(self._item) def end(self): baseformatter.end(self) self._ui.write(cPickle.dumps(self._data)) def _jsonifyobj(v): if isinstance(v, tuple): return '[' + ', '.join(_jsonifyobj(e) for e in v) + ']' elif v is None: return 'null' elif v is True: return 'true' elif v is False: return 'false' elif isinstance(v, (int, float)): return str(v) else: return '"%s"' % encoding.jsonescape(v) class jsonformatter(baseformatter): def __init__(self, ui, topic, opts): baseformatter.__init__(self, ui, topic, opts) self._ui.write("[") self._ui._first = True def _showitem(self): if self._ui._first: self._ui._first = False else: self._ui.write(",") self._ui.write("\n {\n") first = True for k, v in sorted(self._item.items()): if first: first = False else: self._ui.write(",\n") self._ui.write(' "%s": %s' % (k, _jsonifyobj(v))) self._ui.write("\n }") def end(self): baseformatter.end(self) self._ui.write("\n]\n") class templateformatter(baseformatter): def __init__(self, ui, topic, opts): baseformatter.__init__(self, ui, topic, opts) self._topic = topic self._t = gettemplater(ui, topic, opts.get('template', '')) def _showitem(self): g = self._t(self._topic, **self._item) self._ui.write(templater.stringify(g)) def lookuptemplate(ui, topic, tmpl): # looks like a literal template? if '{' in tmpl: return tmpl, None # perhaps a stock style? if not os.path.split(tmpl)[0]: mapname = (templater.templatepath('map-cmdline.' + tmpl) or templater.templatepath(tmpl)) if mapname and os.path.isfile(mapname): return None, mapname # perhaps it's a reference to [templates] t = ui.config('templates', tmpl) if t: try: tmpl = templater.unquotestring(t) except SyntaxError: tmpl = t return tmpl, None if tmpl == 'list': ui.write(_("available styles: %s\n") % templater.stylelist()) raise util.Abort(_("specify a template")) # perhaps it's a path to a map or a template if ('/' in tmpl or '\\' in tmpl) and os.path.isfile(tmpl): # is it a mapfile for a style? if os.path.basename(tmpl).startswith("map-"): return None, os.path.realpath(tmpl) tmpl = open(tmpl).read() return tmpl, None # constant string? return tmpl, None def gettemplater(ui, topic, spec): tmpl, mapfile = lookuptemplate(ui, topic, spec) t = templater.templater(mapfile, {}) if tmpl: t.cache[topic] = tmpl return t def formatter(ui, topic, opts): template = opts.get("template", "") if template == "json": return jsonformatter(ui, topic, opts) elif template == "pickle": return pickleformatter(ui, topic, opts) elif template == "debug": return debugformatter(ui, topic, opts) elif template != "": return templateformatter(ui, topic, opts) # developer config: ui.formatdebug elif ui.configbool('ui', 'formatdebug'): return debugformatter(ui, topic, opts) # deprecated config: ui.formatjson elif ui.configbool('ui', 'formatjson'): return jsonformatter(ui, topic, opts) return plainformatter(ui, topic, opts)