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)
import _lsprof
import sys
Profiler = _lsprof.Profiler
# PyPy doesn't expose profiler_entry from the module.
profiler_entry = getattr(_lsprof, 'profiler_entry', None)
__all__ = [b'profile', b'Stats']
def profile(f, *args, **kwds):
"""XXX docstring"""
p = Profiler()
p.enable(subcalls=True, builtins=True)
try:
f(*args, **kwds)
finally:
p.disable()
return Stats(p.getstats())
class Stats:
"""XXX docstring"""
def __init__(self, data):
self.data = data
def sort(self, crit="inlinetime"):
"""XXX docstring"""
# profiler_entries isn't defined when running under PyPy.
if profiler_entry:
if crit not in profiler_entry.__dict__:
raise ValueError(b"Can't sort by %s" % crit)
elif self.data and not getattr(self.data[0], crit, None):
raise ValueError(b"Can't sort by %s" % crit)
self.data.sort(key=lambda x: getattr(x, crit), reverse=True)
for e in self.data:
if e.calls:
e.calls.sort(key=lambda x: getattr(x, crit), reverse=True)
def pprint(self, top=None, file=None, limit=None, climit=None):
"""XXX docstring"""
if file is None:
file = sys.stdout
d = self.data
if top is not None:
d = d[:top]
cols = b"% 12d %12d %11.4f %11.4f %s\n"
hcols = b"% 12s %12s %12s %12s %s\n"
file.write(
hcols
% (
b"CallCount",
b"Recursive",
b"Total(s)",
b"Inline(s)",
b"module:lineno(function)",
)
)
count = 0
for e in d:
file.write(
cols
% (
e.callcount,
e.reccallcount,
e.totaltime,
e.inlinetime,
label(e.code),
)
)
count += 1
if limit is not None and count == limit:
return
ccount = 0
if climit and e.calls:
for se in e.calls:
file.write(
cols
% (
se.callcount,
se.reccallcount,
se.totaltime,
se.inlinetime,
b" %s" % label(se.code),
)
)
count += 1
ccount += 1
if limit is not None and count == limit:
return
if climit is not None and ccount == climit:
break
def freeze(self):
"""Replace all references to code objects with string
descriptions; this makes it possible to pickle the instance."""
# this code is probably rather ickier than it needs to be!
for i in range(len(self.data)):
e = self.data[i]
if not isinstance(e.code, str):
self.data[i] = type(e)((label(e.code),) + e[1:])
if e.calls:
for j in range(len(e.calls)):
se = e.calls[j]
if not isinstance(se.code, str):
e.calls[j] = type(se)((label(se.code),) + se[1:])
_fn2mod = {}
def label(code):
if isinstance(code, str):
return code.encode('latin-1')
try:
mname = _fn2mod[code.co_filename]
except KeyError:
for k, v in list(sys.modules.items()):
if v is None:
continue
if not isinstance(getattr(v, '__file__', None), str):
continue
if v.__file__.startswith(code.co_filename):
mname = _fn2mod[code.co_filename] = k
break
else:
mname = _fn2mod[code.co_filename] = '<%s>' % code.co_filename
res = '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)
return res.encode('latin-1')