view mercurial/lsprofcalltree.py @ 39872:733db72f0f54

revlog: move revision verification out of verify

File revision verification is performing low-level checks of file
storage, namely that flags are appropriate and revision data can
be resolved.

Since these checks are somewhat revlog-specific and may not
be appropriate for alternate storage backends, this commit moves
those checks from verify.py to revlog.py.

Because we're now emitting warnings/errors that apply to specific
revisions, we taught the iverifyproblem interface to expose the
problematic node and to report this node in verify output. This
was necessary to prevent unwanted test changes.

After this change, revlog.verifyintegrity() and file verify code
in verify.py both iterate over revisions and resolve their fulltext.
But they do so in separate loops. (verify.py needs to resolve
fulltexts as part of calling renamed() - at least when using revlogs.)
This should add overhead.

But on the mozilla-unified repo:

$ hg verify
before: time: real 700.640 secs (user 585.520+0.000 sys 23.480+0.000)
after:  time: real 682.380 secs (user 570.370+0.000 sys 22.240+0.000)

I'm not sure what's going on. Maybe avoiding the filelog attribute
proxies shaved off enough time to offset the losses? Maybe fulltext
resolution has less overhead than I thought?

I've left a comment indicating the potential for optimization. But
because it doesn't produce a performance regression on a large
repository, I'm not going to worry about it.

Differential Revision: https://phab.mercurial-scm.org/D4745

"""
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, print_function

def label(code):
    if isinstance(code, str):
        return '~' + code    # built-in functions ('~' sorts at the end)
    else:
        return '%s %s:%d' % (code.co_name,
                             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
        print('events: Ticks', file=out_file)
        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)
        print('summary: %d' % max_cost, file=self.out_file)

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

        code = entry.code
        if isinstance(code, str):
            print('fi=~', file=out_file)
        else:
            print('fi=%s' % code.co_filename, file=out_file)
        print('fn=%s' % label(code), file=out_file)

        inlinetime = int(entry.inlinetime * 1000)
        if isinstance(code, str):
            print('0 ', inlinetime, file=out_file)
        else:
            print('%d %d' % (code.co_firstlineno, inlinetime), file=out_file)

        # 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)
        print(file=out_file)

    def _subentry(self, lineno, subentry):
        out_file = self.out_file
        code = subentry.code
        print('cfn=%s' % label(code), file=out_file)
        if isinstance(code, str):
            print('cfi=~', file=out_file)
            print('calls=%d 0' % subentry.callcount, file=out_file)
        else:
            print('cfi=%s' % code.co_filename, file=out_file)
            print('calls=%d %d' % (
                subentry.callcount, code.co_firstlineno), file=out_file)

        totaltime = int(subentry.totaltime * 1000)
        print('%d %d' % (lineno, totaltime), file=out_file)