view mercurial/lsprofcalltree.py @ 41247:a89b20a49c13

rust-cpython: using MissingAncestors from Python code

As precedently done with LazyAncestors on cpython.rs, we test for the
presence of the 'rustext' module.

incrementalmissingrevs() has two callers within the Mercurial core:
`setdiscovery.partialdiscovery` and the `only()` revset.

This move shows a significant discovery performance improvement
in cases where the baseline is slow: using perfdiscovery on the PyPy
repos, prepared with `contrib/discovery-helper <repo> 50 100`, we
get averaged medians of 403ms with the Rust version vs 742ms without
(about 45% better).

But there are still indications that performance can be worse in cases
the baseline is fast, possibly due to the conversion from Python to
Rust and back becoming the bottleneck. We could measure this on
mozilla-central in cases were the delta is just a few changesets.
This requires confirmation, but if that's the reason, then an
upcoming `partialdiscovery` fully in Rust should solve the problem.

Differential Revision: https://phab.mercurial-scm.org/D5551

"""
lsprofcalltree.py - lsprof output which is readable by kcachegrind

Authors:
    * David Allouche <david <at> allouche.net>
    * Jp Calderone & Itamar Shtull-Trauring
    * Johan Dahlin

This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""

from __future__ import absolute_import

from . import (
    pycompat,
)

def label(code):
    if isinstance(code, str):
        # built-in functions ('~' sorts at the end)
        return '~' + pycompat.sysbytes(code)
    else:
        return '%s %s:%d' % (pycompat.sysbytes(code.co_name),
                             pycompat.sysbytes(code.co_filename),
                             code.co_firstlineno)

class KCacheGrind(object):
    def __init__(self, profiler):
        self.data = profiler.getstats()
        self.out_file = None

    def output(self, out_file):
        self.out_file = out_file
        out_file.write(b'events: Ticks\n')
        self._print_summary()
        for entry in self.data:
            self._entry(entry)

    def _print_summary(self):
        max_cost = 0
        for entry in self.data:
            totaltime = int(entry.totaltime * 1000)
            max_cost = max(max_cost, totaltime)
        self.out_file.write(b'summary: %d\n' % max_cost)

    def _entry(self, entry):
        out_file = self.out_file

        code = entry.code
        if isinstance(code, str):
            out_file.write(b'fi=~\n')
        else:
            out_file.write(b'fi=%s\n' % pycompat.sysbytes(code.co_filename))

        out_file.write(b'fn=%s\n' % label(code))

        inlinetime = int(entry.inlinetime * 1000)
        if isinstance(code, str):
            out_file.write(b'0 %d\n' % inlinetime)
        else:
            out_file.write(b'%d %d\n' % (code.co_firstlineno, inlinetime))

        # recursive calls are counted in entry.calls
        if entry.calls:
            calls = entry.calls
        else:
            calls = []

        if isinstance(code, str):
            lineno = 0
        else:
            lineno = code.co_firstlineno

        for subentry in calls:
            self._subentry(lineno, subentry)

        out_file.write(b'\n')

    def _subentry(self, lineno, subentry):
        out_file = self.out_file
        code = subentry.code
        out_file.write(b'cfn=%s\n' % label(code))
        if isinstance(code, str):
            out_file.write(b'cfi=~\n')
            out_file.write(b'calls=%d 0\n' % subentry.callcount)
        else:
            out_file.write(b'cfi=%s\n' % pycompat.sysbytes(code.co_filename))
            out_file.write(b'calls=%d %d\n' % (
                subentry.callcount, code.co_firstlineno))

        totaltime = int(subentry.totaltime * 1000)
        out_file.write(b'%d %d\n' % (lineno, totaltime))