view contrib/dirstatenonnormalcheck.py @ 47120:7109a38830c9

dirstate-tree: Fold "tracked descendants" counter update in main walk

For the purpose of implementing `has_tracked_dir` (which means "has tracked
descendants) without an expensive sub-tree traversal, we maintaing a counter
of tracked descendants on each "directory" node of the tree-shaped dirstate.

Before this changeset, mutating or inserting a node at a given path would
involve:

* Walking the tree from root through ancestors to find the node or the spot
  where to insert it
* Looking at the previous node if any to decide what counter update is needed
* Performing any node mutation
* Walking the tree *again* to update counters in ancestor nodes

When profiling `hg status` on a large repo, this second walk takes times
while loading a the dirstate from disk.

It turns out we have enough information to decide before he first tree walk
what counter update is needed. This changeset merges the two walks, gaining
~10% of the total time for `hg update` (in the same hyperfine benchmark as
the previous changeset).

---

Profiling was done by compiling with this `.cargo/config`:

    [profile.release]
    debug = true

then running with:

    py-spy record -r 500 -n -o /tmp/hg.json --format speedscope -- \
    ./hg status -R $REPO --config experimental.dirstate-tree.in-memory=1

then visualizing the recorded JSON file in https://www.speedscope.app/

Differential Revision: https://phab.mercurial-scm.org/D10554

# 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] != b'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(b"%s call to %s\n" % (label, orig), config=b'dirstate')
        ui.develwarn(b"inconsistency in nonnormalset\n", config=b'dirstate')
        ui.develwarn(b"[nonnormalset] %s\n" % _nonnormalset, config=b'dirstate')
        ui.develwarn(b"[map] %s\n" % nonnormalcomputedmap, config=b'dirstate')


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


def extsetup(ui):
    """Wrap functions modifying dirstate to check nonnormalset consistency"""
    dirstatecl = dirstate.dirstate
    devel = ui.configbool(b'devel', b'all-warnings')
    paranoid = ui.configbool(b'experimental', b'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)