##// END OF EJS Templates
revlog: change generaldelta delta parent heuristic...
revlog: change generaldelta delta parent heuristic The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text, use it, otherwise use prev". This was problematic when a repo contained multiple branches that were very different. If commits to branch A were pushed, and the last full text was branch B, it would generate a fulltext. Then if branch B was pushed, it would generate another fulltext. The problem is that the last fulltext (and delta'ing against `prev` in general) has no correlation with the contents of the incoming revision, and therefore will always have degenerate cases. According to the blame, that algorithm was chosen to minimize the chain length. Since there is already code that protects against that (the delta-vs-fulltext code), and since it has been improved since the original generaldelta algorithm went in (2011), I believe the chain length criteria will still be preserved. The new algorithm always diffs against p1 (or p2 if it's closer), unless the resulting delta will fail the delta-vs-fulltext check, in which case we delta against prev. Some before and after stats on manifest.d size. internal large repo old heuristic - 2.0 GB new heuristic - 1.2 GB mozilla-central old heuristic - 242 MB new heuristic - 261 MB The regression in mozilla central is due to the new heuristic choosing p2r as the delta when it's closer to the tip. Switching the algorithm to always prefer p1r brings the size back down (242 MB). This is result of the way in which mozilla does merges and pushes, and the result could easily swing the other direction in other repos (depending on if they merge X into Y or Y into X), but will never be as degenerate as before. I future patch will address the regression by introducing an optional, even more aggressive delta heuristic which will knock the mozilla manifest size down dramatically.

File last commit:

r18642:a40d608e default
r26117:4dc5b51f default
Show More
lsprof.py
109 lines | 3.6 KiB | text/x-python | PythonLexer
import sys
from _lsprof import Profiler, profiler_entry
__all__ = ['profile', '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(object):
"""XXX docstring"""
def __init__(self, data):
self.data = data
def sort(self, crit="inlinetime"):
"""XXX docstring"""
if crit not in profiler_entry.__dict__:
raise ValueError("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 = "% 12s %12s %11.4f %11.4f %s\n"
hcols = "% 12s %12s %12s %12s %s\n"
file.write(hcols % ("CallCount", "Recursive", "Total(s)",
"Inline(s)", "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,
" %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
try:
mname = _fn2mod[code.co_filename]
except KeyError:
for k, v in list(sys.modules.iteritems()):
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
return '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)
if __name__ == '__main__':
import os
sys.argv = sys.argv[1:]
if not sys.argv:
print >> sys.stderr, "usage: lsprof.py <script> <arguments...>"
sys.exit(2)
sys.path.insert(0, os.path.abspath(os.path.dirname(sys.argv[0])))
stats = profile(execfile, sys.argv[0], globals(), locals())
stats.sort()
stats.pprint()