view mercurial/httppeer.py @ 21424:d13b4ecdb680

test: split test-largefile.t in multiple file The `test-largefiles.t` unified test is significantly longer (about 30%) than any other tests in the mercurial test suite. As a result, its is alway the last test my test runner is waiting for at the end of a run. In practice, this means that `test-largefile.t` is wasting half a minute of my life every times I'm running the mercurial test suites. This probably mean more a few cumulated day by now. I've finally decided to split it up in multiple smaller tests to bring it back in reasonable length. This changeset extracts independent test cases in two files. One dedicated to wire protocole testing, and another one dedicated to all other tests that could be independently extracted. No test case were haltered in the making of this changeset. Various timing available below. All timing have been done on a with 90 jobs on a 64 cores machine. Similar result are shown on firefly (20 jobs on 12 core). General timing of the whole run -------------------------------- We see a 25% real time improvement for no significant cpu time impact. Before split: real 2m1.149s user 58m4.662s sys 11m28.563s After split: real 1m31.977s user 57m45.993s sys 11m33.634s Last test to finish (using run-test.py --time) ---------------------------------------------- test-largefile.t is now finishing at the same time than other slow tests. Before split: Time Test 119.280 test-largefiles.t 93.995 test-mq.t 89.897 test-subrepo.t 86.920 test-glog.t 85.508 test-rename-merge2.t 83.594 test-revset.t 79.824 test-keyword.t 78.077 test-mq-header-date.t After split: Time Test 90.414 test-mq.t 88.594 test-largefiles.t 85.363 test-subrepo.t 81.059 test-glog.t 78.927 test-rename-merge2.t 78.021 test-revset.t 77.777 test-command-template.t Timing of largefile test themself ----------------------------------- Running only tests prefixed with "test-largefiles". No significant change in cumulated time. Before: Time Test 58.673 test-largefiles.t 2.931 test-largefiles-cache.t 0.583 test-largefiles-small-disk.t After: Time Test 31.754 test-largefiles.t 17.460 test-largefiles-misc.t 8.888 test-largefiles-wireproto.t 2.864 test-largefiles-cache.t 0.580 test-largefiles-small-disk.t
author Pierre-Yves David <pierre-yves.david@fb.com>
date Fri, 16 May 2014 13:18:57 -0700
parents d36440d84328
children cde6904f1992
line wrap: on
line source

# httppeer.py - HTTP repository proxy classes for mercurial
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from node import nullid
from i18n import _
import tempfile
import changegroup, statichttprepo, error, httpconnection, url, util, wireproto
import os, urllib, urllib2, zlib, httplib
import errno, socket

def zgenerator(f):
    zd = zlib.decompressobj()
    try:
        for chunk in util.filechunkiter(f):
            while chunk:
                yield zd.decompress(chunk, 2**18)
                chunk = zd.unconsumed_tail
    except httplib.HTTPException:
        raise IOError(None, _('connection ended unexpectedly'))
    yield zd.flush()

class httppeer(wireproto.wirepeer):
    def __init__(self, ui, path):
        self.path = path
        self.caps = None
        self.handler = None
        self.urlopener = None
        u = util.url(path)
        if u.query or u.fragment:
            raise util.Abort(_('unsupported URL component: "%s"') %
                             (u.query or u.fragment))

        # urllib cannot handle URLs with embedded user or passwd
        self._url, authinfo = u.authinfo()

        self.ui = ui
        self.ui.debug('using %s\n' % self._url)

        self.urlopener = url.opener(ui, authinfo)

    def __del__(self):
        if self.urlopener:
            for h in self.urlopener.handlers:
                h.close()
                getattr(h, "close_all", lambda : None)()

    def url(self):
        return self.path

    # look up capabilities only when needed

    def _fetchcaps(self):
        self.caps = set(self._call('capabilities').split())

    def _capabilities(self):
        if self.caps is None:
            try:
                self._fetchcaps()
            except error.RepoError:
                self.caps = set()
            self.ui.debug('capabilities: %s\n' %
                          (' '.join(self.caps or ['none'])))
        return self.caps

    def lock(self):
        raise util.Abort(_('operation not supported over http'))

    def _callstream(self, cmd, **args):
        if cmd == 'pushkey':
            args['data'] = ''
        data = args.pop('data', None)
        size = 0
        if util.safehasattr(data, 'length'):
            size = data.length
        elif data is not None:
            size = len(data)
        headers = args.pop('headers', {})
        if data is not None and 'Content-Type' not in headers:
            headers['Content-Type'] = 'application/mercurial-0.1'


        if size and self.ui.configbool('ui', 'usehttp2', False):
            headers['Expect'] = '100-Continue'
            headers['X-HgHttp2'] = '1'

        self.ui.debug("sending %s command\n" % cmd)
        q = [('cmd', cmd)]
        headersize = 0
        if len(args) > 0:
            httpheader = self.capable('httpheader')
            if httpheader:
                headersize = int(httpheader.split(',')[0])
        if headersize > 0:
            # The headers can typically carry more data than the URL.
            encargs = urllib.urlencode(sorted(args.items()))
            headerfmt = 'X-HgArg-%s'
            contentlen = headersize - len(headerfmt % '000' + ': \r\n')
            headernum = 0
            for i in xrange(0, len(encargs), contentlen):
                headernum += 1
                header = headerfmt % str(headernum)
                headers[header] = encargs[i:i + contentlen]
            varyheaders = [headerfmt % str(h) for h in range(1, headernum + 1)]
            headers['Vary'] = ','.join(varyheaders)
        else:
            q += sorted(args.items())
        qs = '?%s' % urllib.urlencode(q)
        cu = "%s%s" % (self._url, qs)
        req = urllib2.Request(cu, data, headers)
        if data is not None:
            self.ui.debug("sending %s bytes\n" % size)
            req.add_unredirected_header('Content-Length', '%d' % size)
        try:
            resp = self.urlopener.open(req)
        except urllib2.HTTPError, inst:
            if inst.code == 401:
                raise util.Abort(_('authorization failed'))
            raise
        except httplib.HTTPException, inst:
            self.ui.debug('http error while sending %s command\n' % cmd)
            self.ui.traceback()
            raise IOError(None, inst)
        except IndexError:
            # this only happens with Python 2.3, later versions raise URLError
            raise util.Abort(_('http error, possibly caused by proxy setting'))
        # record the url we got redirected to
        resp_url = resp.geturl()
        if resp_url.endswith(qs):
            resp_url = resp_url[:-len(qs)]
        if self._url.rstrip('/') != resp_url.rstrip('/'):
            if not self.ui.quiet:
                self.ui.warn(_('real URL is %s\n') % resp_url)
        self._url = resp_url
        try:
            proto = resp.getheader('content-type')
        except AttributeError:
            proto = resp.headers.get('content-type', '')

        safeurl = util.hidepassword(self._url)
        if proto.startswith('application/hg-error'):
            raise error.OutOfBandError(resp.read())
        # accept old "text/plain" and "application/hg-changegroup" for now
        if not (proto.startswith('application/mercurial-') or
                (proto.startswith('text/plain')
                 and not resp.headers.get('content-length')) or
                proto.startswith('application/hg-changegroup')):
            self.ui.debug("requested URL: '%s'\n" % util.hidepassword(cu))
            raise error.RepoError(
                _("'%s' does not appear to be an hg repository:\n"
                  "---%%<--- (%s)\n%s\n---%%<---\n")
                % (safeurl, proto or 'no content-type', resp.read(1024)))

        if proto.startswith('application/mercurial-'):
            try:
                version = proto.split('-', 1)[1]
                version_info = tuple([int(n) for n in version.split('.')])
            except ValueError:
                raise error.RepoError(_("'%s' sent a broken Content-Type "
                                        "header (%s)") % (safeurl, proto))
            if version_info > (0, 1):
                raise error.RepoError(_("'%s' uses newer protocol %s") %
                                      (safeurl, version))

        return resp

    def _call(self, cmd, **args):
        fp = self._callstream(cmd, **args)
        try:
            return fp.read()
        finally:
            # if using keepalive, allow connection to be reused
            fp.close()

    def _callpush(self, cmd, cg, **args):
        # have to stream bundle to a temp file because we do not have
        # http 1.1 chunked transfer.

        types = self.capable('unbundle')
        try:
            types = types.split(',')
        except AttributeError:
            # servers older than d1b16a746db6 will send 'unbundle' as a
            # boolean capability. They only support headerless/uncompressed
            # bundles.
            types = [""]
        for x in types:
            if x in changegroup.bundletypes:
                type = x
                break

        tempname = changegroup.writebundle(cg, None, type)
        fp = httpconnection.httpsendfile(self.ui, tempname, "rb")
        headers = {'Content-Type': 'application/mercurial-0.1'}

        try:
            try:
                r = self._call(cmd, data=fp, headers=headers, **args)
                vals = r.split('\n', 1)
                if len(vals) < 2:
                    raise error.ResponseError(_("unexpected response:"), r)
                return vals
            except socket.error, err:
                if err.args[0] in (errno.ECONNRESET, errno.EPIPE):
                    raise util.Abort(_('push failed: %s') % err.args[1])
                raise util.Abort(err.args[1])
        finally:
            fp.close()
            os.unlink(tempname)

    def _calltwowaystream(self, cmd, fp, **args):
        fh = None
        filename = None
        try:
            # dump bundle to disk
            fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
            fh = os.fdopen(fd, "wb")
            d = fp.read(4096)
            while d:
                fh.write(d)
                d = fp.read(4096)
            fh.close()
            # start http push
            fp = httpconnection.httpsendfile(self.ui, filename, "rb")
            headers = {'Content-Type': 'application/mercurial-0.1'}
            return self._callstream(cmd, data=fp, headers=headers, **args)
        finally:
            if fh is not None:
                fh.close()
                os.unlink(filename)

    def _callcompressable(self, cmd, **args):
        stream =  self._callstream(cmd, **args)
        return util.chunkbuffer(zgenerator(stream))

    def _abort(self, exception):
        raise exception

class httpspeer(httppeer):
    def __init__(self, ui, path):
        if not url.has_https:
            raise util.Abort(_('Python support for SSL and HTTPS '
                               'is not installed'))
        httppeer.__init__(self, ui, path)

def instance(ui, path, create):
    if create:
        raise util.Abort(_('cannot create new http repository'))
    try:
        if path.startswith('https:'):
            inst = httpspeer(ui, path)
        else:
            inst = httppeer(ui, path)
        try:
            # Try to do useful work when checking compatibility.
            # Usually saves a roundtrip since we want the caps anyway.
            inst._fetchcaps()
        except error.RepoError:
            # No luck, try older compatibility check.
            inst.between([(nullid, nullid)])
        return inst
    except error.RepoError, httpexception:
        try:
            r = statichttprepo.instance(ui, "static-" + path, create)
            ui.note('(falling back to static-http)\n')
            return r
        except error.RepoError:
            raise httpexception # use the original http RepoError instead