mercurial/lsprofcalltree.py

copies: avoid instancing more changectx to access parent revisions

We just need to know the revision numbers of the parents, creating full context
is needlessly expensive.

This provide a small, but noticeable performance boost.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 2.885636 comb 2.900000 user 2.870000 sys 0.030000 (median of 10)
after:  ! wall 2.702270 comb 2.710000 user 2.690000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 4.298271 comb 4.290000 user 4.240000 sys 0.050000 (median of 10)
after:  ! wall 3.976610 comb 3.970000 user 3.920000 sys 0.050000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.773397 comb 0.770000 user 0.770000 sys 0.000000 (median of 11)
after:  ! wall 0.701634 comb 0.700000 user 0.700000 sys 0.000000 (median of 13)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013585 comb 0.010000 user 0.010000 sys 0.000000 (median of 217)
after:  ! wall 0.013550 comb 0.010000 user 0.010000 sys 0.000000 (median of 218)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.003202 comb 0.000000 user 0.000000 sys 0.000000 (median of 929)
after:  ! wall 0.002993 comb 0.010000 user 0.010000 sys 0.000000 (median of 992)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12060)
after:  ! wall 0.000072 comb 0.000000 user 0.000000 sys 0.000000 (median of 12804)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.510614 comb 0.500000 user 0.500000 sys 0.000000 (median of 18)
after:  ! wall 0.473681 comb 0.470000 user 0.470000 sys 0.000000 (median of 20)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.126552 comb 0.130000 user 0.130000 sys 0.000000 (median of 77)
after:  ! wall 0.115240 comb 0.110000 user 0.110000 sys 0.000000 (median of 85)

Differential Revision: https://phab.mercurial-scm.org/D7122

"""
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 b'~' + pycompat.sysbytes(code)
    else:
        return b'%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))