view mercurial/lsprofcalltree.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

"""
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))