view contrib/dirstatenonnormalcheck.py @ 30212:260af19891f2

changegroup: increase write buffer size to 128k

By default, Python defers to the operating system for choosing the
default buffer size on opened files. On my Linux machine, the default
is 4k, which is really small for 2016.

This patch bumps the write buffer size when writing
changegroups/bundles to 128k. This matches the 128k read buffer
we already use on revlogs.

It's worth noting that this only impacts when writing to an explicit
file (such as during `hg bundle`). Buffers when writing to bundle
files via the repo vfs or to a temporary file are not impacted.

When producing a none-v2 bundle file of the mozilla-unified repository,
this change caused the number of write() system calls to drop from
952,449 to 29,788. After this change, the most frequent system
calls are fstat(), read(), lseek(), and open(). There were
2,523,672 system calls after this patch (so a net decrease of
~950k is statistically significant).

This change shows no performance change on my system. But I have a
high-end system with a fast SSD. It is quite possible this change
will have a significant impact on network file systems, where
extra network round trips due to excessive I/O system calls could
introduce significant latency.

# 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)