view contrib/dirstatenonnormalcheck.py @ 31013:693a5bb47854

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

# dirstatenonnormalcheck.py - extension to check the consistency of the
# dirstate's non-normal map
#
# For most operations on dirstate, this extensions checks that the nonnormalset
# contains the right entries.
# It compares the nonnormal file to a nonnormalset built from the map of all
# the files in the dirstate to check that they contain the same files.

from __future__ import absolute_import

from mercurial import (
    dirstate,
    extensions,
)

def nonnormalentries(dmap):
    """Compute nonnormal entries from dirstate's dmap"""
    res = set()
    for f, e in dmap.iteritems():
        if e[0] != 'n' or e[3] == -1:
            res.add(f)
    return res

def checkconsistency(ui, orig, dmap, _nonnormalset, label):
    """Compute nonnormalset from dmap, check that it matches _nonnormalset"""
    nonnormalcomputedmap = nonnormalentries(dmap)
    if _nonnormalset != nonnormalcomputedmap:
        ui.develwarn("%s call to %s\n" % (label, orig), config='dirstate')
        ui.develwarn("inconsistency in nonnormalset\n", config='dirstate')
        ui.develwarn("[nonnormalset] %s\n" % _nonnormalset, config='dirstate')
        ui.develwarn("[map] %s\n" % nonnormalcomputedmap, config='dirstate')

def _checkdirstate(orig, self, arg):
    """Check nonnormal set consistency before and after the call to orig"""
    checkconsistency(self._ui, orig, self._map, self._nonnormalset, "before")
    r = orig(self, arg)
    checkconsistency(self._ui, orig, self._map, self._nonnormalset, "after")
    return r

def extsetup(ui):
    """Wrap functions modifying dirstate to check nonnormalset consistency"""
    dirstatecl = dirstate.dirstate
    devel = ui.configbool('devel', 'all-warnings')
    paranoid = ui.configbool('experimental', 'nonnormalparanoidcheck')
    if devel:
        extensions.wrapfunction(dirstatecl, '_writedirstate', _checkdirstate)
        if paranoid:
            # We don't do all these checks when paranoid is disable as it would
            # make the extension run very slowly on large repos
            extensions.wrapfunction(dirstatecl, 'normallookup', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'otherparent', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'normal', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'write', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'add', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'remove', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'merge', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'drop', _checkdirstate)