##// END OF EJS Templates
changegroup: port to emitrevisions() (issue5976)...
changegroup: port to emitrevisions() (issue5976) We now have a unified API for emitting revision data from a storage backend. It handles sorting nodes and the complicated delta versus revision decisions for us. This commit ports changegroup to that API. There should be no behavior changes for changegroups not using ellipsis. And lack of test changes seems to confirm that. There are some changes for ellipsis mode, however. Before, when sending an ellipsis revision, we would always send a fulltext revision (as opposed to a delta). There was a TODO tracking this open item. One of the things the emitrevisions() API does for us is figure out whether we can safely emit a delta. So, it is now possible for ellipsis revisions to be sent as deltas! (It does this by not assuming parent/ancestor revisions are available and tracking which revisions have been sent out.) Because we eliminated the list of revision delta request objects, performance has improved substantially: $ hg perfchangegroupchangelog before: ! wall 24.348077 comb 24.330000 user 24.140000 sys 0.190000 (best of 3) after: ! wall 18.245911 comb 18.240000 user 18.100000 sys 0.140000 (best of 3) That's a lot of overhead for creating a few hundred thousand Python objects! This is still a little slower than 4.7. Probably due to 23d582ca introducing a type for the revision/delta results. There is potentially room to optimize. But at some point we need to abstract storage in order to support alternate storage backends. Unfortunately that means using a Python data structure to represent results. And unfortunately there is overhead with every new Python object created. Differential Revision: https://phab.mercurial-scm.org/D4725

File last commit:

r39851:c31ce080 default
r39901:31b7e8e7 default
Show More
store.py
166 lines | 5.6 KiB | text/x-python | PythonLexer
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
# based on bundleheads extension by Gregory Szorc <gps@mozilla.com>
from __future__ import absolute_import
import abc
import hashlib
import os
import subprocess
import tempfile
from mercurial import (
pycompat,
)
from mercurial.utils import (
procutil,
)
NamedTemporaryFile = tempfile.NamedTemporaryFile
class BundleWriteException(Exception):
pass
class BundleReadException(Exception):
pass
class abstractbundlestore(object):
"""Defines the interface for bundle stores.
A bundle store is an entity that stores raw bundle data. It is a simple
key-value store. However, the keys are chosen by the store. The keys can
be any Python object understood by the corresponding bundle index (see
``abstractbundleindex`` below).
"""
__metaclass__ = abc.ABCMeta
@abc.abstractmethod
def write(self, data):
"""Write bundle data to the store.
This function receives the raw data to be written as a str.
Throws BundleWriteException
The key of the written data MUST be returned.
"""
@abc.abstractmethod
def read(self, key):
"""Obtain bundle data for a key.
Returns None if the bundle isn't known.
Throws BundleReadException
The returned object should be a file object supporting read()
and close().
"""
class filebundlestore(object):
"""bundle store in filesystem
meant for storing bundles somewhere on disk and on network filesystems
"""
def __init__(self, ui, repo):
self.ui = ui
self.repo = repo
self.storepath = ui.configpath('scratchbranch', 'storepath')
if not self.storepath:
self.storepath = self.repo.vfs.join("scratchbranches",
"filebundlestore")
if not os.path.exists(self.storepath):
os.makedirs(self.storepath)
def _dirpath(self, hashvalue):
"""First two bytes of the hash are the name of the upper
level directory, next two bytes are the name of the
next level directory"""
return os.path.join(self.storepath, hashvalue[0:2], hashvalue[2:4])
def _filepath(self, filename):
return os.path.join(self._dirpath(filename), filename)
def write(self, data):
filename = hashlib.sha1(data).hexdigest()
dirpath = self._dirpath(filename)
if not os.path.exists(dirpath):
os.makedirs(dirpath)
with open(self._filepath(filename), 'wb') as f:
f.write(data)
return filename
def read(self, key):
try:
with open(self._filepath(key), 'rb') as f:
return f.read()
except IOError:
return None
class externalbundlestore(abstractbundlestore):
def __init__(self, put_binary, put_args, get_binary, get_args):
"""
`put_binary` - path to binary file which uploads bundle to external
storage and prints key to stdout
`put_args` - format string with additional args to `put_binary`
{filename} replacement field can be used.
`get_binary` - path to binary file which accepts filename and key
(in that order), downloads bundle from store and saves it to file
`get_args` - format string with additional args to `get_binary`.
{filename} and {handle} replacement field can be used.
"""
self.put_args = put_args
self.get_args = get_args
self.put_binary = put_binary
self.get_binary = get_binary
def _call_binary(self, args):
p = subprocess.Popen(
pycompat.rapply(procutil.tonativestr, args),
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
close_fds=True)
stdout, stderr = p.communicate()
returncode = p.returncode
return returncode, stdout, stderr
def write(self, data):
# Won't work on windows because you can't open file second time without
# closing it
# TODO: rewrite without str.format() and replace NamedTemporaryFile()
# with pycompat.namedtempfile()
with NamedTemporaryFile() as temp:
temp.write(data)
temp.flush()
temp.seek(0)
formatted_args = [arg.format(filename=temp.name)
for arg in self.put_args]
returncode, stdout, stderr = self._call_binary(
[self.put_binary] + formatted_args)
if returncode != 0:
raise BundleWriteException(
'Failed to upload to external store: %s' % stderr)
stdout_lines = stdout.splitlines()
if len(stdout_lines) == 1:
return stdout_lines[0]
else:
raise BundleWriteException(
'Bad output from %s: %s' % (self.put_binary, stdout))
def read(self, handle):
# Won't work on windows because you can't open file second time without
# closing it
# TODO: rewrite without str.format() and replace NamedTemporaryFile()
# with pycompat.namedtempfile()
with NamedTemporaryFile() as temp:
formatted_args = [arg.format(filename=temp.name, handle=handle)
for arg in self.get_args]
returncode, stdout, stderr = self._call_binary(
[self.get_binary] + formatted_args)
if returncode != 0:
raise BundleReadException(
'Failed to download from external store: %s' % stderr)
return temp.read()