hgweb: profile HTTP requests

Currently, running `hg serve --profile` doesn't yield anything useful:
when the process is terminated the profiling output displays results
from the main thread, which typically spends most of its time in
select.select(). Furthermore, it has no meaningful results from
mercurial.* modules because the threads serving HTTP requests don't
actually get profiled.

This patch teaches the hgweb wsgi applications to profile individual
requests. If profiling is enabled, the profiler kicks in after
HTTP/WSGI environment processing but before Mercurial's main request
processing.

The profile results are printed to the configured profiling output.
If running `hg serve` from a shell, they will be printed to stderr,
just before the HTTP request line is logged. If profiling to a file,
we only write a single profile to the file because the file is not
opened in append mode. We could add support for appending to files
in a future patch if someone wants it.

Per request profiling doesn't work with the statprof profiler because
internally that profiler collects samples from the thread that
*initially* requested profiling be enabled. I have plans to address
this by vendoring Facebook's customized statprof and then improving
it.

mercurial/hgweb/hgweb_mod.py

@@ -1,468 +1,470
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import contextlib
 import os
 
 from .common import (
     ErrorResponse,
     HTTP_BAD_REQUEST,
     HTTP_NOT_FOUND,
     HTTP_NOT_MODIFIED,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     caching,
     permhooks,
 )
 from .request import wsgirequest
 
 from .. import (
     encoding,
     error,
     hg,
     hook,
+    profiling,
     repoview,
     templatefilters,
     templater,
     ui as uimod,
     util,
 )
 
 from . import (
     protocol,
     webcommands,
     webutil,
     wsgicgi,
 )
 
 perms = {
     'changegroup': 'pull',
     'changegroupsubset': 'pull',
     'getbundle': 'pull',
     'stream_out': 'pull',
     'listkeys': 'pull',
     'unbundle': 'push',
     'pushkey': 'push',
 }
 
 def makebreadcrumb(url, prefix=''):
     '''Return a 'URL breadcrumb' list
 
     A 'URL breadcrumb' is a list of URL-name pairs,
     corresponding to each of the path items on a URL.
     This can be used to create path navigation entries.
     '''
     if url.endswith('/'):
         url = url[:-1]
     if prefix:
         url = '/' + prefix + url
     relpath = url
     if relpath.startswith('/'):
         relpath = relpath[1:]
 
     breadcrumb = []
     urlel = url
     pathitems = [''] + relpath.split('/')
     for pathel in reversed(pathitems):
         if not pathel or not urlel:
             break
         breadcrumb.append({'url': urlel, 'name': pathel})
         urlel = os.path.dirname(urlel)
     return reversed(breadcrumb)
 
 class requestcontext(object):
     """Holds state/context for an individual request.
 
     Servers can be multi-threaded. Holding state on the WSGI application
     is prone to race conditions. Instances of this class exist to hold
     mutable and race-free state for requests.
     """
     def __init__(self, app, repo):
         self.repo = repo
         self.reponame = app.reponame
 
         self.archives = ('zip', 'gz', 'bz2')
 
         self.maxchanges = self.configint('web', 'maxchanges', 10)
         self.stripecount = self.configint('web', 'stripes', 1)
         self.maxshortchanges = self.configint('web', 'maxshortchanges', 60)
         self.maxfiles = self.configint('web', 'maxfiles', 10)
         self.allowpull = self.configbool('web', 'allowpull', True)
 
         # we use untrusted=False to prevent a repo owner from using
         # web.templates in .hg/hgrc to get access to any file readable
         # by the user running the CGI script
         self.templatepath = self.config('web', 'templates', untrusted=False)
 
         # This object is more expensive to build than simple config values.
         # It is shared across requests. The app will replace the object
         # if it is updated. Since this is a reference and nothing should
         # modify the underlying object, it should be constant for the lifetime
         # of the request.
         self.websubtable = app.websubtable
 
     # 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 configint(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configint(section, name, default,
                                       untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     archivespecs = {
         'bz2': ('application/x-bzip2', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-gzip', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
     }
 
     def archivelist(self, nodeid):
         allowed = self.configlist('web', 'allow_archive')
         for typ, spec in self.archivespecs.iteritems():
             if typ in allowed or self.configbool('web', 'allow%s' % typ):
                 yield {'type': typ, 'extension': spec[2], 'node': nodeid}
 
     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', 'https://mercurial-scm.org/')
         logoimg = self.config('web', 'logoimg', 'hglogo.png')
         staticurl = self.config('web', 'staticurl') or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         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)
 
         def websubfilter(text):
             return templatefilters.websub(text, self.websubtable)
 
         # create the templater
 
         defaults = {
             'url': req.url,
             'logourl': logourl,
             'logoimg': logoimg,
             'staticurl': staticurl,
             'urlbase': urlbase,
             'repo': self.reponame,
             'encoding': encoding.encoding,
             'motd': motd,
             'sessionvars': sessionvars,
             'pathdef': makebreadcrumb(req.url),
             'style': style,
         }
         tmpl = templater.templater.frommapfile(mapfile,
                                                filters={'websub': websubfilter},
                                                defaults=defaults)
         return tmpl
 
 
 class hgweb(object):
     """HTTP server for individual repositories.
 
     Instances of this class serve HTTP responses for a particular
     repository.
 
     Instances are typically used as WSGI applications.
 
     Some servers are multi-threaded. On these servers, there may
     be multiple active threads inside __call__.
     """
     def __init__(self, repo, name=None, baseui=None):
         if isinstance(repo, str):
             if baseui:
                 u = baseui.copy()
             else:
                 u = uimod.ui()
             r = hg.repository(u, repo)
         else:
             # we trust caller to give us a private copy
             r = repo
 
         r.ui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.baseui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.ui.setconfig('ui', 'nontty', 'true', 'hgweb')
         r.baseui.setconfig('ui', 'nontty', 'true', 'hgweb')
         # resolve file patterns relative to repo root
         r.ui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         r.baseui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         # displaying bundling progress bar while serving feel wrong and may
         # break some wsgi implementation.
         r.ui.setconfig('progress', 'disable', 'true', 'hgweb')
         r.baseui.setconfig('progress', 'disable', 'true', 'hgweb')
         self._repos = [hg.cachedlocalrepo(self._webifyrepo(r))]
         self._lastrepo = self._repos[0]
         hook.redirect(True)
         self.reponame = name
 
     def _webifyrepo(self, repo):
         repo = getwebview(repo)
         self.websubtable = webutil.getwebsubs(repo)
         return repo
 
     @contextlib.contextmanager
     def _obtainrepo(self):
         """Obtain a repo unique to the caller.
 
         Internally we maintain a stack of cachedlocalrepo instances
         to be handed out. If one is available, we pop it and return it,
         ensuring it is up to date in the process. If one is not available,
         we clone the most recently used repo instance and return it.
 
         It is currently possible for the stack to grow without bounds
         if the server allows infinite threads. However, servers should
         have a thread limit, thus establishing our limit.
         """
         if self._repos:
             cached = self._repos.pop()
             r, created = cached.fetch()
         else:
             cached = self._lastrepo.copy()
             r, created = cached.fetch()
         if created:
             r = self._webifyrepo(r)
 
         self._lastrepo = cached
         self.mtime = cached.mtime
         try:
             yield r
         finally:
             self._repos.append(cached)
 
     def run(self):
         """Start a server from CGI environment.
 
         Modern servers should be using WSGI and should avoid this
         method, if possible.
         """
         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.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         """Run the WSGI application.
 
         This may be called by multiple threads.
         """
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
         """Internal method to run the WSGI application.
 
         This is typically only called by Mercurial. External consumers
         should be using instances of this class as the WSGI application.
         """
         with self._obtainrepo() as repo:
+            with profiling.maybeprofile(repo.ui):
             for r in self._runwsgi(req, repo):
                 yield r
 
     def _runwsgi(self, req, repo):
         rctx = requestcontext(self, repo)
 
         # This state is global across all threads.
         encoding.encoding = rctx.config('web', 'encoding', encoding.encoding)
         rctx.repo.ui.environ = req.env
 
         # 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'].partition('&')[0]
             query = query.partition(';')[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(rctx, req, perms[cmd])
                 return protocol.call(rctx.repo, req, cmd)
             except ErrorResponse as 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') or
                     req.env.get('X-HgHttp2', '')):
                     req.drain()
                 else:
                     req.headers.append(('Connection', 'Close'))
                 req.respond(inst, protocol.HGTYPE,
                             body='0\n%s\n' % inst)
                 return ''
 
         # 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 util.safehasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0).replace('%2F', '/')
                     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 rctx.archivespecs.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 = rctx.templater(req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(rctx, req, None)
 
             if cmd == '':
                 req.form['cmd'] = [tmpl.cache['default']]
                 cmd = req.form['cmd'][0]
 
             if rctx.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', []):
                 rctx.ctype = ctype
                 content = webcommands.rawfile(rctx, req, tmpl)
             else:
                 content = getattr(webcommands, cmd)(rctx, req, tmpl)
                 req.respond(HTTP_OK, ctype)
 
             return content
 
         except (error.LookupError, error.RepoLookupError) as err:
             req.respond(HTTP_NOT_FOUND, ctype)
             msg = str(err)
             if (util.safehasattr(err, 'name') and
                 not isinstance(err,  error.ManifestLookupError)):
                 msg = 'revision not found: %s' % err.name
             return tmpl('error', error=msg)
         except (error.RepoError, error.RevlogError) as inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=str(inst))
         except ErrorResponse as 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=str(inst))
 
     def check_perm(self, rctx, req, op):
         for permhook in permhooks:
             permhook(rctx, req, op)
 
 def getwebview(repo):
     """The 'web.view' config controls changeset filter to hgweb. Possible
     values are ``served``, ``visible`` and ``all``. Default is ``served``.
     The ``served`` filter only shows changesets that can be pulled from the
     hgweb instance.  The``visible`` filter includes secret changesets but
     still excludes "hidden" one.
 
     See the repoview module for details.
 
     The option has been around undocumented since Mercurial 2.5, but no
     user ever asked about it. So we better keep it undocumented for now."""
     viewconfig = repo.ui.config('web', 'view', 'served',
                                 untrusted=True)
     if viewconfig == 'all':
         return repo.unfiltered()
     elif viewconfig in repoview.filtertable:
         return repo.filtered(viewconfig)
     else:
         return repo.filtered('served')
 

mercurial/hgweb/hgwebdir_mod.py

@@ -1,518 +1,521
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import re
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_NOT_FOUND,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
 )
 from .request import wsgirequest
 
 from .. import (
     encoding,
     error,
     hg,
+    profiling,
     scmutil,
     templater,
     ui as uimod,
     util,
 )
 
 from . import (
     hgweb_mod,
     webutil,
     wsgicgi,
 )
 
 def cleannames(items):
     return [(util.pconvert(name).strip('/'), path) for name, path in items]
 
 def findrepos(paths):
     repos = []
     for prefix, root in cleannames(paths):
         roothead, roottail = os.path.split(root)
         # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
         # /bar/ be served as as foo/N .
         # '*' will not search inside dirs with .hg (except .hg/patches),
         # '**' will search inside dirs with .hg (and thus also find subrepos).
         try:
             recurse = {'*': False, '**': True}[roottail]
         except KeyError:
             repos.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
     >>> conv(urlrepos('hg', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos('', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (prefix + '/' +
                util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path
 
 def geturlcgivars(baseurl, port):
     """
     Extract CGI variables from baseurl
 
     >>> geturlcgivars("http://host.org/base", "80")
     ('host.org', '80', '/base')
     >>> geturlcgivars("http://host.org:8000/base", "80")
     ('host.org', '8000', '/base')
     >>> geturlcgivars('/base', 8000)
     ('', '8000', '/base')
     >>> geturlcgivars("base", '8000')
     ('', '8000', '/base')
     >>> geturlcgivars("http://host", '8000')
     ('host', '8000', '/')
     >>> geturlcgivars("http://host/", '8000')
     ('host', '8000', '/')
     """
     u = util.url(baseurl)
     name = u.host or ''
     if u.port:
         port = u.port
     path = u.path or ""
     if not path.startswith('/'):
         path = '/' + path
 
     return name, str(port), path
 
 class hgwebdir(object):
     """HTTP server for multiple repositories.
 
     Given a configuration, different repositories will be served depending
     on the request path.
 
     Instances are typically used as WSGI applications.
     """
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.ui = None
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
 
     def refresh(self):
         refreshinterval = 20
         if self.ui:
             refreshinterval = self.ui.configint('web', 'refreshinterval',
                                                 refreshinterval)
 
         # refreshinterval <= 0 means to always refresh.
         if (refreshinterval > 0 and
             self.lastrefresh + refreshinterval > time.time()):
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = uimod.ui()
             u.setconfig('ui', 'report_untrusted', 'off', 'hgwebdir')
             u.setconfig('ui', 'nontty', 'true', 'hgwebdir')
             # displaying bundling progress bar while serving feels wrong and may
             # break some wsgi implementations.
             u.setconfig('progress', 'disable', 'true', 'hgweb')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise error.Abort(_('config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = []
             for name, ignored in u.configitems('hgweb-paths'):
                 for path in u.configlist('hgweb-paths', name):
                     paths.append((name, path))
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
         repos = findrepos(paths)
         for prefix, root in u.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in scmutil.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 repos.append((name.lstrip('/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config('web', 'encoding',
                                            encoding.encoding)
         self.style = self.ui.config('web', 'style', 'paper')
         self.templatepath = self.ui.config('web', 'templates', None)
         self.stripecount = self.ui.config('web', 'stripes', 1)
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         self._baseurl = self.ui.config('web', 'baseurl')
         prefix = self.ui.config('web', 'prefix', '')
         if prefix.startswith('/'):
             prefix = prefix[1:]
         if prefix.endswith('/'):
             prefix = prefix[:-1]
         self.prefix = prefix
         self.lastrefresh = time.time()
 
     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.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def read_allowed(self, ui, req):
         """Check allow_read and deny_read config options of a repo's ui object
         to determine user permissions.  By default, with neither option set (or
         both empty), allow all users to read the repo.  There are two ways a
         user can be denied read access:  (1) deny_read is not empty, and the
         user is unauthenticated or deny_read contains user (or *), and (2)
         allow_read is not empty and the user is not in allow_read.  Return True
         if user is allowed to read the repo, else return False."""
 
         user = req.env.get('REMOTE_USER')
 
         deny_read = ui.configlist('web', 'deny_read', untrusted=True)
         if deny_read and (not user or ismember(ui, user, deny_read)):
             return False
 
         allow_read = ui.configlist('web', 'allow_read', untrusted=True)
         # by default, allow reading if no allow_read option has been set
         if (not allow_read) or ismember(ui, user, allow_read):
             return True
 
         return False
 
     def run_wsgi(self, req):
-        return self._runwsgi(req)
+        with profiling.maybeprofile(self.ui):
+            for r in self._runwsgi(req):
+                yield r
 
     def _runwsgi(self, req):
         try:
             self.refresh()
 
             virtual = req.env.get("PATH_INFO", "").strip('/')
             tmpl = self.templater(req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # a static file
             if virtual.startswith('static/') or 'static' in req.form:
                 if virtual.startswith('static/'):
                     fname = virtual[7:]
                 else:
                     fname = req.form['static'][0]
                 static = self.ui.config("web", "static", None,
                                         untrusted=False)
                 if not static:
                     tp = self.templatepath or templater.templatepaths()
                     if isinstance(tp, str):
                         tp = [tp]
                     static = [os.path.join(p, 'static') for p in tp]
                 staticfile(static, fname, req)
                 return []
 
             # top-level index
             elif not virtual:
                 req.respond(HTTP_OK, ctype)
                 return self.makeindex(req, tmpl)
 
             # nested indexes and hgwebs
 
             repos = dict(self.repos)
             virtualrepo = virtual
             while virtualrepo:
                 real = repos.get(virtualrepo)
                 if real:
                     req.env['REPO_NAME'] = virtualrepo
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(req)
                     except IOError as inst:
                         msg = inst.strerror
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, str(inst))
 
                 up = virtualrepo.rfind('/')
                 if up < 0:
                     break
                 virtualrepo = virtualrepo[:up]
 
             # browse subdirectories
             subdir = virtual + '/'
             if [r for r in repos if r.startswith(subdir)]:
                 req.respond(HTTP_OK, ctype)
                 return self.makeindex(req, tmpl, subdir)
 
             # prefixes not found
             req.respond(HTTP_NOT_FOUND, ctype)
             return tmpl("notfound", repo=virtual)
 
         except ErrorResponse as err:
             req.respond(err, ctype)
             return tmpl('error', error=err.message or '')
         finally:
             tmpl = None
 
     def makeindex(self, req, tmpl, subdir=""):
 
         def archivelist(ui, nodeid, url):
             allowed = ui.configlist("web", "allow_archive", untrusted=True)
             archives = []
             for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 if i[0] in allowed or ui.configbool("web", "allow" + i[0],
                                                     untrusted=True):
                     archives.append({"type" : i[0], "extension": i[1],
                                      "node": nodeid, "url": url})
             return archives
 
         def rawentries(subdir="", **map):
 
             descend = self.ui.configbool('web', 'descend', True)
             collapse = self.ui.configbool('web', 'collapse', False)
             seenrepos = set()
             seendirs = set()
             for name, path in self.repos:
 
                 if not name.startswith(subdir):
                     continue
                 name = name[len(subdir):]
                 directory = False
 
                 if '/' in name:
                     if not descend:
                         continue
 
                     nameparts = name.split('/')
                     rootname = nameparts[0]
 
                     if not collapse:
                         pass
                     elif rootname in seendirs:
                         continue
                     elif rootname in seenrepos:
                         pass
                     else:
                         directory = True
                         name = rootname
 
                         # redefine the path to refer to the directory
                         discarded = '/'.join(nameparts[1:])
 
                         # remove name parts plus accompanying slash
                         path = path[:-len(discarded) - 1]
 
                         try:
                             r = hg.repository(self.ui, path)
                             directory = False
                         except (IOError, error.RepoError):
                             pass
 
                 parts = [name]
                 if 'PATH_INFO' in req.env:
                     parts.insert(0, req.env['PATH_INFO'].rstrip('/'))
                 if req.env['SCRIPT_NAME']:
                     parts.insert(0, req.env['SCRIPT_NAME'])
                 url = re.sub(r'/+', '/', '/'.join(parts) + '/')
 
                 # show either a directory entry or a repository
                 if directory:
                     # get the directory's time information
                     try:
                         d = (get_mtime(path), util.makedate()[1])
                     except OSError:
                         continue
 
                     # add '/' to the name to make it obvious that
                     # the entry is a directory, not a regular repository
                     row = {'contact': "",
                            'contact_sort': "",
                            'name': name + '/',
                            'name_sort': name,
                            'url': url,
                            'description': "",
                            'description_sort': "",
                            'lastchange': d,
                            'lastchange_sort': d[1]-d[0],
                            'archives': [],
                            'isdirectory': True,
                            'labels': [],
                            }
 
                     seendirs.add(name)
                     yield row
                     continue
 
                 u = self.ui.copy()
                 try:
                     u.readconfig(os.path.join(path, '.hg', 'hgrc'))
                 except Exception as e:
                     u.warn(_('error reading %s/.hg/hgrc: %s\n') % (path, e))
                     continue
                 def get(section, name, default=None):
                     return u.config(section, name, default, untrusted=True)
 
                 if u.configbool("web", "hidden", untrusted=True):
                     continue
 
                 if not self.read_allowed(u, req):
                     continue
 
                 # update time with local timezone
                 try:
                     r = hg.repository(self.ui, path)
                 except IOError:
                     u.warn(_('error accessing repository at %s\n') % path)
                     continue
                 except error.RepoError:
                     u.warn(_('error accessing repository at %s\n') % path)
                     continue
                 try:
                     d = (get_mtime(r.spath), util.makedate()[1])
                 except OSError:
                     continue
 
                 contact = get_contact(get)
                 description = get("web", "description", "")
                 seenrepos.add(name)
                 name = get("web", "name", name)
                 row = {'contact': contact or "unknown",
                        'contact_sort': contact.upper() or "unknown",
                        'name': name,
                        'name_sort': name,
                        'url': url,
                        'description': description or "unknown",
                        'description_sort': description.upper() or "unknown",
                        'lastchange': d,
                        'lastchange_sort': d[1]-d[0],
                        'archives': archivelist(u, "tip", url),
                        'isdirectory': None,
                        'labels': u.configlist('web', 'labels', untrusted=True),
                        }
 
                 yield row
 
         sortdefault = None, False
         def entries(sortcolumn="", descending=False, subdir="", **map):
             rows = rawentries(subdir=subdir, **map)
 
             if sortcolumn and sortdefault != (sortcolumn, descending):
                 sortkey = '%s_sort' % sortcolumn
                 rows = sorted(rows, key=lambda x: x[sortkey],
                               reverse=descending)
             for row, parity in zip(rows, paritygen(self.stripecount)):
                 row['parity'] = parity
                 yield row
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = sortdefault
         if 'sort' in req.form:
             sortcolumn = req.form['sort'][0]
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
 
         self.refresh()
         self.updatereqenv(req.env)
 
         return tmpl("index", entries=entries, subdir=subdir,
                     pathdef=hgweb_mod.makebreadcrumb('/' + subdir, self.prefix),
                     sortcolumn=sortcolumn, descending=descending,
                     **dict(sort))
 
     def templater(self, req):
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd', '')
 
         def config(section, name, default=None, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
         self.updatereqenv(req.env)
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         styles = (
             req.form.get('style', [None])[0],
             config('web', 'style'),
             'paper'
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
         logourl = config('web', 'logourl', 'https://mercurial-scm.org/')
         logoimg = config('web', 'logoimg', 'hglogo.png')
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         defaults = {
             "encoding": encoding.encoding,
             "motd": motd,
             "url": url,
             "logourl": logourl,
             "logoimg": logoimg,
             "staticurl": staticurl,
             "sessionvars": sessionvars,
             "style": style,
         }
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl
 
     def updatereqenv(self, env):
         if self._baseurl is not None:
             name, port, path = geturlcgivars(self._baseurl, env['SERVER_PORT'])
             env['SERVER_NAME'] = name
             env['SERVER_PORT'] = port
             env['SCRIPT_NAME'] = path

tests/test-profile.t

@@ -1,34 +1,48
 test --time
 
   $ hg --time help -q help 2>&1 | grep time > /dev/null
   $ hg init a
   $ cd a
 
 #if lsprof
 
 test --profile
 
   $ hg --profile st 2>../out
   $ grep CallCount ../out > /dev/null || cat ../out
 
   $ hg --profile --config profiling.output=../out st
   $ grep CallCount ../out > /dev/null || cat ../out
 
   $ hg --profile --config profiling.output=blackbox --config extensions.blackbox= st
   $ grep CallCount .hg/blackbox.log > /dev/null || cat .hg/blackbox.log
 
   $ hg --profile --config profiling.format=text st 2>../out
   $ grep CallCount ../out > /dev/null || cat ../out
 
   $ echo "[profiling]" >> $HGRCPATH
   $ echo "format=kcachegrind" >> $HGRCPATH
 
   $ hg --profile st 2>../out
   $ grep 'events: Ticks' ../out > /dev/null || cat ../out
 
   $ hg --profile --config profiling.output=../out st
   $ grep 'events: Ticks' ../out > /dev/null || cat ../out
 
 #endif
 
+#if lsprof serve
+
+Profiling of HTTP requests works
+
+  $ hg --profile --config profiling.format=text --config profiling.output=../profile.log serve -d -p $HGPORT --pid-file ../hg.pid -A ../access.log
+  $ cat ../hg.pid >> $DAEMON_PIDS
+  $ hg -q clone -U http://localhost:$HGPORT ../clone
+
+A single profile is logged because file logging doesn't append
+  $ grep CallCount ../profile.log | wc -l
+  \s*1 (re)
+
+#endif
+
   $ cd ..