bisect: avoid copying ancestor list for non-merge commits
During a bisection, hg needs to compute a list of all ancestors for every
candidate commit. This is accomplished via a bottom-up traversal of the set of
candidates, during which each revision's ancestor list is populated using the
ancestor list of its parent(s). Previously, this involved copying the entire
list, which could be very long in if the bisection range was large.
To help improve this, we can observe that each candidate commit is visited
exactly once, at which point its ancestor list is copied into its children's
lists and then dropped. In the case of non-merge commits, a commit's ancestor
list consists exactly of its parent's list plus itself. This means that we can
trivially reuse the parent's existing list for one of its non-merge children,
which avoids copying entirely if that commit is the parent's only child. This
makes bisections over linear ranges of commits much faster.
During some informal testing in the large publicly-available `mozilla-central`
repository, this noticeably sped up bisections over large ranges of history:
Setup:
$ cd mozilla-central
$ hg bisect --reset
$ hg bisect --good 0
$ hg log -r tip -T '{rev}\n'
628417
Test:
$ time hg bisect --bad tip --noupdate
Before:
real 3m35.927s
user 3m35.553s
sys 0m0.319s
After:
real 1m41.142s
user 1m40.810s
sys 0m0.285s
"""
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 . 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:
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))