revset: stop serializing node when using "%ln"
Turning hundred of thousand of node from node to hex and back can be slow… what
about we stop doing it?
In many case were we are using node id we should be using revision id. However
this is not a good reason to have a stupidly slow implementation of "%ln".
This caught my attention again because the phase discovery during push make an
extensive use of "%ln" or huge set. In absolute, that phase discovery probably
should use "%ld" and need to improves its algorithmic complexity, but improving
"%ln" seems simple and long overdue. This greatly speeds up `hg push` on
repository with many drafts.
Here are some relevant poulpe benchmarks:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = default
## benchmark.variants.revs = any-1-extra-rev
before: 44.235070
after: 20.416329 (-53.85%, -23.82)
## benchmark.variants.revs = any-100-extra-rev
before: 49.234697
after: 26.519829 (-46.14%, -22.71)
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 10.138396
after: 7.750458 (-23.55%, -2.39)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 1.263859
after: 0.700229 (-44.60%, -0.56)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 399.484481
after: 346.5089 (-13.26%, -52.98)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 4.540080
after: 3.401700 (-25.07%, -1.14)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 2.975765
after: 1.870798 (-37.13%, -1.10)
"""
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))