##// END OF EJS Templates
exchangev2: fetch manifest revisions...
exchangev2: fetch manifest revisions Now that the server has support for retrieving manifest data, we can implement the client bits to call it. We teach the changeset fetching code to capture the manifest revisions that are encountered on incoming changesets. We then feed this into a new function which filters out known manifests and then batches up manifest data requests to the server. This is different from the previous wire protocol in a few notable ways. First, the client fetches manifest data separately and explicitly. Before, we'd ask the server for data pertaining to some changesets (via a "getbundle" command) and manifests (and files) would be sent automatically. Providing an API for looking up just manifest data separately gives clients much more flexibility for manifest management. For example, a client may choose to only fetch manifest data on demand instead of prefetching it (i.e. partial clone). Second, we send N commands to the server for manifest retrieval instead of 1. This property has a few nice side-effects. One is that the deterministic nature of the requests lends itself to server-side caching. For example, say the remote has 50,000 manifests. If the server is configured to cache responses, each time a new commit arrives, you will have a cache miss and need to regenerate all outgoing data. But if you makes N requests requesting 10,000 manifests each, a new commit will still yield cache hits on the initial, unchanged manifest batches/requests. A derived benefit from these properties is that resumable clone is conceptually simpler to implement. When making a monolithic request for all of the repository data, recovering from an interrupted clone is hard because the server was in the driver's seat and was maintaining state about all the data that needed transferred. With the client driving fetching, the client can persist the set of unfetched entities and retry/resume a fetch if something goes wrong. Or we can fetch all data N changesets at a time and slowly build up a repository. This approach is drastically easier to implement when we have server APIs exposing low-level repository primitives (such as manifests and files). We don't yet support tree manifests. But it should be possible to implement that with the existing wire protocol command. Differential Revision: https://phab.mercurial-scm.org/D4489

File last commit:

r35854:d4e5b265 default
r39674:d292328e default
Show More
lsprof.py
121 lines | 4.0 KiB | text/x-python | PythonLexer
from __future__ import absolute_import, print_function
import _lsprof
import sys
Profiler = _lsprof.Profiler
# PyPy doesn't expose profiler_entry from the module.
profiler_entry = getattr(_lsprof, 'profiler_entry', None)
__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=r"inlinetime"):
"""XXX docstring"""
# profiler_entries isn't defined when running under PyPy.
if profiler_entry:
if crit not in profiler_entry.__dict__:
raise ValueError("Can't sort by %s" % crit)
elif self.data and not getattr(self.data[0], crit, None):
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("usage: lsprof.py <script> <arguments...>", file=sys.stderr)
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()