##// END OF EJS Templates
revlog: linearize created changegroups in generaldelta revlogs...
revlog: linearize created changegroups in generaldelta revlogs This greatly improves the speed of the bundling process, and often reduces the bundle size considerably. (Although if the repository is already ordered, this has little effect on both time and bundle size.) For non-generaldelta clients, the reduced bundle size translates to a reduced repository size, similar to shrinking the revlogs (which uses the exact same algorithm). For generaldelta clients the difference is minor. When the new bundle format comes, reordering will not be necessary since we can then store the deltaparent relationsships directly. The eventual default behavior for clients and servers is presented in the table below, where "new" implies support for GD as well as the new bundle format: old client new client old server old bundle, no reorder old bundle, no reorder new server, non-GD old bundle, no reorder[1] old bundle, no reorder[2] new server, GD old bundle, reorder[3] new bundle, no reorder[4] [1] reordering is expensive on the server in this case, skip it [2] client can choose to do its own redelta here [3] reordering is needed because otherwise the pull does a lot of extra work on the server [4] reordering isn't needed because client can get deltabase in bundle format Currently, the default is to reorder on GD-servers, and not otherwise. A new setting, bundle.reorder, has been added to override the default reordering behavior. It can be set to either 'auto' (the default), or any true or false value as a standard boolean setting, to either force the reordering on or off regardless of generaldelta. Some timing data from a relatively branch test repository follows. All bundling is done with --all --type none options. Non-generaldelta, non-shrunk repo: ----------------------------------- Size: 276M Without reorder (default): Bundle time: 14.4 seconds Bundle size: 939M With reorder: Bundle time: 1 minute, 29.3 seconds Bundle size: 381M Generaldelta, non-shrunk repo: ----------------------------------- Size: 87M Without reorder: Bundle time: 2 minutes, 1.4 seconds Bundle size: 939M With reorder (default): Bundle time: 25.5 seconds Bundle size: 381M

File last commit:

r13966:a1c31c64 default
r14365:a8e3931e default
Show More
hgweb_mod.py
302 lines | 11.2 KiB | text/x-python | PythonLexer
# hgweb/hgweb_mod.py - Web interface for a repository.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import os
from mercurial import ui, hg, hook, error, encoding, templater
from common import get_stat, ErrorResponse, permhooks, caching
from common import HTTP_OK, HTTP_NOT_MODIFIED, HTTP_BAD_REQUEST
from common import HTTP_NOT_FOUND, HTTP_SERVER_ERROR
from request import wsgirequest
import webcommands, protocol, webutil
perms = {
'changegroup': 'pull',
'changegroupsubset': 'pull',
'getbundle': 'pull',
'stream_out': 'pull',
'listkeys': 'pull',
'unbundle': 'push',
'pushkey': 'push',
}
class hgweb(object):
def __init__(self, repo, name=None, baseui=None):
if isinstance(repo, str):
if baseui:
u = baseui.copy()
else:
u = ui.ui()
self.repo = hg.repository(u, repo)
else:
self.repo = repo
self.repo.ui.setconfig('ui', 'report_untrusted', 'off')
self.repo.ui.setconfig('ui', 'interactive', 'off')
hook.redirect(True)
self.mtime = -1
self.size = -1
self.reponame = name
self.archives = 'zip', 'gz', 'bz2'
self.stripecount = 1
# a repo owner may set web.templates in .hg/hgrc to get any file
# readable by the user running the CGI script
self.templatepath = self.config('web', 'templates')
# The CGI scripts are often run by a user different from the repo owner.
# Trust the settings from the .hg/hgrc files by default.
def config(self, section, name, default=None, untrusted=True):
return self.repo.ui.config(section, name, default,
untrusted=untrusted)
def configbool(self, section, name, default=False, untrusted=True):
return self.repo.ui.configbool(section, name, default,
untrusted=untrusted)
def configlist(self, section, name, default=None, untrusted=True):
return self.repo.ui.configlist(section, name, default,
untrusted=untrusted)
def refresh(self, request=None):
if request:
self.repo.ui.environ = request.env
st = get_stat(self.repo.spath)
# compare changelog size in addition to mtime to catch
# rollbacks made less than a second ago
if st.st_mtime != self.mtime or st.st_size != self.size:
self.mtime = st.st_mtime
self.size = st.st_size
self.repo = hg.repository(self.repo.ui, self.repo.root)
self.maxchanges = int(self.config("web", "maxchanges", 10))
self.stripecount = int(self.config("web", "stripes", 1))
self.maxshortchanges = int(self.config("web", "maxshortchanges", 60))
self.maxfiles = int(self.config("web", "maxfiles", 10))
self.allowpull = self.configbool("web", "allowpull", True)
encoding.encoding = self.config("web", "encoding",
encoding.encoding)
def run(self):
if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
raise RuntimeError("This function is only intended to be "
"called while running as a CGI script.")
import mercurial.hgweb.wsgicgi as wsgicgi
wsgicgi.launch(self)
def __call__(self, env, respond):
req = wsgirequest(env, respond)
return self.run_wsgi(req)
def run_wsgi(self, req):
self.refresh(req)
# work with CGI variables to create coherent structure
# use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
req.url = req.env['SCRIPT_NAME']
if not req.url.endswith('/'):
req.url += '/'
if 'REPO_NAME' in req.env:
req.url += req.env['REPO_NAME'] + '/'
if 'PATH_INFO' in req.env:
parts = req.env['PATH_INFO'].strip('/').split('/')
repo_parts = req.env.get('REPO_NAME', '').split('/')
if parts[:len(repo_parts)] == repo_parts:
parts = parts[len(repo_parts):]
query = '/'.join(parts)
else:
query = req.env['QUERY_STRING'].split('&', 1)[0]
query = query.split(';', 1)[0]
# process this if it's a protocol request
# protocol bits don't need to create any URLs
# and the clients always use the old URL structure
cmd = req.form.get('cmd', [''])[0]
if protocol.iscmd(cmd):
try:
if query:
raise ErrorResponse(HTTP_NOT_FOUND)
if cmd in perms:
self.check_perm(req, perms[cmd])
return protocol.call(self.repo, req, cmd)
except ErrorResponse, inst:
# A client that sends unbundle without 100-continue will
# break if we respond early.
if (cmd == 'unbundle' and
req.env.get('HTTP_EXPECT',
'').lower() != '100-continue'):
req.drain()
req.respond(inst, protocol.HGTYPE)
return '0\n%s\n' % inst.message
# translate user-visible url structure to internal structure
args = query.split('/', 2)
if 'cmd' not in req.form and args and args[0]:
cmd = args.pop(0)
style = cmd.rfind('-')
if style != -1:
req.form['style'] = [cmd[:style]]
cmd = cmd[style + 1:]
# avoid accepting e.g. style parameter as command
if hasattr(webcommands, cmd):
req.form['cmd'] = [cmd]
else:
cmd = ''
if cmd == 'static':
req.form['file'] = ['/'.join(args)]
else:
if args and args[0]:
node = args.pop(0)
req.form['node'] = [node]
if args:
req.form['file'] = args
ua = req.env.get('HTTP_USER_AGENT', '')
if cmd == 'rev' and 'mercurial' in ua:
req.form['style'] = ['raw']
if cmd == 'archive':
fn = req.form['node'][0]
for type_, spec in self.archive_specs.iteritems():
ext = spec[2]
if fn.endswith(ext):
req.form['node'] = [fn[:-len(ext)]]
req.form['type'] = [type_]
# process the web interface request
try:
tmpl = self.templater(req)
ctype = tmpl('mimetype', encoding=encoding.encoding)
ctype = templater.stringify(ctype)
# check read permissions non-static content
if cmd != 'static':
self.check_perm(req, None)
if cmd == '':
req.form['cmd'] = [tmpl.cache['default']]
cmd = req.form['cmd'][0]
if self.configbool('web', 'cache', True):
caching(self, req) # sets ETag header or raises NOT_MODIFIED
if cmd not in webcommands.__all__:
msg = 'no such method: %s' % cmd
raise ErrorResponse(HTTP_BAD_REQUEST, msg)
elif cmd == 'file' and 'raw' in req.form.get('style', []):
self.ctype = ctype
content = webcommands.rawfile(self, req, tmpl)
else:
content = getattr(webcommands, cmd)(self, req, tmpl)
req.respond(HTTP_OK, ctype)
return content
except error.LookupError, err:
req.respond(HTTP_NOT_FOUND, ctype)
msg = str(err)
if 'manifest' not in msg:
msg = 'revision not found: %s' % err.name
return tmpl('error', error=msg)
except (error.RepoError, error.RevlogError), inst:
req.respond(HTTP_SERVER_ERROR, ctype)
return tmpl('error', error=str(inst))
except ErrorResponse, inst:
req.respond(inst, ctype)
if inst.code == HTTP_NOT_MODIFIED:
# Not allowed to return a body on a 304
return ['']
return tmpl('error', error=inst.message)
def templater(self, req):
# determine scheme, port and server name
# this is needed to create absolute urls
proto = req.env.get('wsgi.url_scheme')
if proto == 'https':
proto = 'https'
default_port = "443"
else:
proto = 'http'
default_port = "80"
port = req.env["SERVER_PORT"]
port = port != default_port and (":" + port) or ""
urlbase = '%s://%s%s' % (proto, req.env['SERVER_NAME'], port)
logourl = self.config("web", "logourl", "http://mercurial.selenic.com/")
staticurl = self.config("web", "staticurl") or req.url + 'static/'
if not staticurl.endswith('/'):
staticurl += '/'
# some functions for the templater
def header(**map):
yield tmpl('header', encoding=encoding.encoding, **map)
def footer(**map):
yield tmpl("footer", **map)
def motd(**map):
yield self.config("web", "motd", "")
# figure out which style to use
vars = {}
styles = (
req.form.get('style', [None])[0],
self.config('web', 'style'),
'paper',
)
style, mapfile = templater.stylemap(styles, self.templatepath)
if style == styles[0]:
vars['style'] = style
start = req.url[-1] == '?' and '&' or '?'
sessionvars = webutil.sessionvars(vars, start)
if not self.reponame:
self.reponame = (self.config("web", "name")
or req.env.get('REPO_NAME')
or req.url.strip('/') or self.repo.root)
# create the templater
tmpl = templater.templater(mapfile,
defaults={"url": req.url,
"logourl": logourl,
"staticurl": staticurl,
"urlbase": urlbase,
"repo": self.reponame,
"header": header,
"footer": footer,
"motd": motd,
"sessionvars": sessionvars
})
return tmpl
def archivelist(self, nodeid):
allowed = self.configlist("web", "allow_archive")
for i, spec in self.archive_specs.iteritems():
if i in allowed or self.configbool("web", "allow" + i):
yield {"type" : i, "extension" : spec[2], "node" : nodeid}
archive_specs = {
'bz2': ('application/x-bzip2', 'tbz2', '.tar.bz2', None),
'gz': ('application/x-gzip', 'tgz', '.tar.gz', None),
'zip': ('application/zip', 'zip', '.zip', None),
}
def check_perm(self, req, op):
for hook in permhooks:
hook(self, req, op)