Mercurial > public > mercurial-scm > hg-stable
view mercurial/hook.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 | d15b279ddade |
children | 56b2bcea2529 |
line wrap: on
line source
# hook.py - hook support for mercurial # # Copyright 2007 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 os import sys import time from .i18n import _ from . import ( demandimport, error, extensions, util, ) def _pythonhook(ui, repo, name, hname, funcname, args, throw): '''call python hook. hook is callable object, looked up as name in python module. if callable returns "true", hook fails, else passes. if hook raises exception, treated as hook failure. exception propagates if throw is "true". reason for "true" meaning "hook failed" is so that unmodified commands (e.g. mercurial.commands.update) can be run as hooks without wrappers to convert return values.''' if callable(funcname): obj = funcname funcname = obj.__module__ + "." + obj.__name__ else: d = funcname.rfind('.') if d == -1: raise util.Abort(_('%s hook is invalid ("%s" not in ' 'a module)') % (hname, funcname)) modname = funcname[:d] oldpaths = sys.path if util.mainfrozen(): # binary installs require sys.path manipulation modpath, modfile = os.path.split(modname) if modpath and modfile: sys.path = sys.path[:] + [modpath] modname = modfile with demandimport.deactivated(): try: obj = __import__(modname) except ImportError: e1 = sys.exc_type, sys.exc_value, sys.exc_traceback try: # extensions are loaded with hgext_ prefix obj = __import__("hgext_%s" % modname) except ImportError: e2 = sys.exc_type, sys.exc_value, sys.exc_traceback if ui.tracebackflag: ui.warn(_('exception from first failed import ' 'attempt:\n')) ui.traceback(e1) if ui.tracebackflag: ui.warn(_('exception from second failed import ' 'attempt:\n')) ui.traceback(e2) raise util.Abort(_('%s hook is invalid ' '(import of "%s" failed)') % (hname, modname)) sys.path = oldpaths try: for p in funcname.split('.')[1:]: obj = getattr(obj, p) except AttributeError: raise util.Abort(_('%s hook is invalid ' '("%s" is not defined)') % (hname, funcname)) if not callable(obj): raise util.Abort(_('%s hook is invalid ' '("%s" is not callable)') % (hname, funcname)) ui.note(_("calling hook %s: %s\n") % (hname, funcname)) starttime = time.time() try: # redirect IO descriptors to the ui descriptors so hooks # that write directly to these don't mess up the command # protocol when running through the command server old = sys.stdout, sys.stderr, sys.stdin sys.stdout, sys.stderr, sys.stdin = ui.fout, ui.ferr, ui.fin r = obj(ui=ui, repo=repo, hooktype=name, **args) except Exception as exc: if isinstance(exc, util.Abort): ui.warn(_('error: %s hook failed: %s\n') % (hname, exc.args[0])) else: ui.warn(_('error: %s hook raised an exception: ' '%s\n') % (hname, exc)) if throw: raise ui.traceback() return True finally: sys.stdout, sys.stderr, sys.stdin = old duration = time.time() - starttime ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n', name, funcname, duration) if r: if throw: raise error.HookAbort(_('%s hook failed') % hname) ui.warn(_('warning: %s hook failed\n') % hname) return r def _exthook(ui, repo, name, cmd, args, throw): ui.note(_("running hook %s: %s\n") % (name, cmd)) starttime = time.time() env = {} for k, v in args.iteritems(): if callable(v): v = v() if isinstance(v, dict): # make the dictionary element order stable across Python # implementations v = ('{' + ', '.join('%r: %r' % i for i in sorted(v.iteritems())) + '}') env['HG_' + k.upper()] = v if repo: cwd = repo.root else: cwd = os.getcwd() r = ui.system(cmd, environ=env, cwd=cwd) duration = time.time() - starttime ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n', name, cmd, duration) if r: desc, r = util.explainexit(r) if throw: raise error.HookAbort(_('%s hook %s') % (name, desc)) ui.warn(_('warning: %s hook %s\n') % (name, desc)) return r def _allhooks(ui): hooks = [] for name, cmd in ui.configitems('hooks'): if not name.startswith('priority'): priority = ui.configint('hooks', 'priority.%s' % name, 0) hooks.append((-priority, len(hooks), name, cmd)) return [(k, v) for p, o, k, v in sorted(hooks)] _redirect = False def redirect(state): global _redirect _redirect = state def hook(ui, repo, name, throw=False, **args): if not ui.callhooks: return False r = False oldstdout = -1 try: for hname, cmd in _allhooks(ui): if hname.split('.')[0] != name or not cmd: continue if oldstdout == -1 and _redirect: try: stdoutno = sys.__stdout__.fileno() stderrno = sys.__stderr__.fileno() # temporarily redirect stdout to stderr, if possible if stdoutno >= 0 and stderrno >= 0: sys.__stdout__.flush() oldstdout = os.dup(stdoutno) os.dup2(stderrno, stdoutno) except (OSError, AttributeError): # files seem to be bogus, give up on redirecting (WSGI, etc) pass if callable(cmd): r = _pythonhook(ui, repo, name, hname, cmd, args, throw) or r elif cmd.startswith('python:'): if cmd.count(':') >= 2: path, cmd = cmd[7:].rsplit(':', 1) path = util.expandpath(path) if repo: path = os.path.join(repo.root, path) try: mod = extensions.loadpath(path, 'hghook.%s' % hname) except Exception: ui.write(_("loading %s hook failed:\n") % hname) raise hookfn = getattr(mod, cmd) else: hookfn = cmd[7:].strip() r = _pythonhook(ui, repo, name, hname, hookfn, args, throw) or r else: r = _exthook(ui, repo, hname, cmd, args, throw) or r # The stderr is fully buffered on Windows when connected to a pipe. # A forcible flush is required to make small stderr data in the # remote side available to the client immediately. sys.stderr.flush() finally: if _redirect and oldstdout >= 0: os.dup2(oldstdout, stdoutno) os.close(oldstdout) return r