view mercurial/unionrepo.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

# unionrepo.py - repository class for viewing union of repository changesets
#
# Derived from bundlerepo.py
# Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
# Copyright 2013 Unity Technologies, Mads Kiilerich <[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.

"""Repository class for "in-memory pull" of one local repository to another,
allowing operations like diff and log with revsets.
"""

from node import nullid
from i18n import _
import os
import util, mdiff, cmdutil, scmutil
import localrepo, changelog, manifest, filelog, revlog

class unionrevlog(revlog.revlog):
    def __init__(self, opener, indexfile, revlog2, linkmapper):
        # How it works:
        # To retrieve a revision, we just need to know the node id so we can
        # look it up in revlog2.
        #
        # To differentiate a rev in the second revlog from a rev in the revlog,
        # we check revision against repotiprev.
        opener = scmutil.readonlyvfs(opener)
        revlog.revlog.__init__(self, opener, indexfile)
        self.revlog2 = revlog2

        n = len(self)
        self.repotiprev = n - 1
        self.bundlerevs = set() # used by 'bundle()' revset expression
        for rev2 in self.revlog2:
            rev = self.revlog2.index[rev2]
            # rev numbers - in revlog2, very different from self.rev
            _start, _csize, _rsize, _base, linkrev, p1rev, p2rev, node = rev

            if linkmapper is None: # link is to same revlog
                assert linkrev == rev2 # we never link back
                link = n
            else: # rev must be mapped from repo2 cl to unified cl by linkmapper
                link = linkmapper(linkrev)

            if node in self.nodemap:
                # this happens for the common revlog revisions
                self.bundlerevs.add(self.nodemap[node])
                continue

            p1node = self.revlog2.node(p1rev)
            p2node = self.revlog2.node(p2rev)

            e = (None, None, None, None,
                 link, self.rev(p1node), self.rev(p2node), node)
            self.index.insert(-1, e)
            self.nodemap[node] = n
            self.bundlerevs.add(n)
            n += 1

    def _chunk(self, rev):
        if rev <= self.repotiprev:
            return revlog.revlog._chunk(self, rev)
        return self.revlog2._chunk(self.node(rev))

    def revdiff(self, rev1, rev2):
        """return or calculate a delta between two revisions"""
        if rev1 > self.repotiprev and rev2 > self.repotiprev:
            return self.revlog2.revdiff(
                self.revlog2.rev(self.node(rev1)),
                self.revlog2.rev(self.node(rev2)))
        elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
            return self.baserevdiff(rev1, rev2)

        return mdiff.textdiff(self.revision(self.node(rev1)),
                              self.revision(self.node(rev2)))

    def revision(self, nodeorrev):
        """return an uncompressed revision of a given node or revision
        number.
        """
        if isinstance(nodeorrev, int):
            rev = nodeorrev
            node = self.node(rev)
        else:
            node = nodeorrev
            rev = self.rev(node)

        if node == nullid:
            return ""

        if rev > self.repotiprev:
            text = self.revlog2.revision(node)
            self._cache = (node, rev, text)
        else:
            text = self.baserevision(rev)
            # already cached
        return text

    def baserevision(self, nodeorrev):
        # Revlog subclasses may override 'revision' method to modify format of
        # content retrieved from revlog. To use unionrevlog with such class one
        # needs to override 'baserevision' and make more specific call here.
        return revlog.revlog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        # Exists for the same purpose as baserevision.
        return revlog.revlog.revdiff(self, rev1, rev2)

    def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
        raise NotImplementedError
    def addgroup(self, revs, linkmapper, transaction):
        raise NotImplementedError
    def strip(self, rev, minlink):
        raise NotImplementedError
    def checksize(self):
        raise NotImplementedError

class unionchangelog(unionrevlog, changelog.changelog):
    def __init__(self, opener, opener2):
        changelog.changelog.__init__(self, opener)
        linkmapper = None
        changelog2 = changelog.changelog(opener2)
        unionrevlog.__init__(self, opener, self.indexfile, changelog2,
                             linkmapper)

    def baserevision(self, nodeorrev):
        # Although changelog doesn't override 'revision' method, some extensions
        # may replace this class with another that does. Same story with
        # manifest and filelog classes.
        return changelog.changelog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return changelog.changelog.revdiff(self, rev1, rev2)

class unionmanifest(unionrevlog, manifest.manifest):
    def __init__(self, opener, opener2, linkmapper):
        manifest.manifest.__init__(self, opener)
        manifest2 = manifest.manifest(opener2)
        unionrevlog.__init__(self, opener, self.indexfile, manifest2,
                             linkmapper)

    def baserevision(self, nodeorrev):
        return manifest.manifest.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return manifest.manifest.revdiff(self, rev1, rev2)

class unionfilelog(unionrevlog, filelog.filelog):
    def __init__(self, opener, path, opener2, linkmapper, repo):
        filelog.filelog.__init__(self, opener, path)
        filelog2 = filelog.filelog(opener2, path)
        unionrevlog.__init__(self, opener, self.indexfile, filelog2,
                             linkmapper)
        self._repo = repo

    def baserevision(self, nodeorrev):
        return filelog.filelog.revision(self, nodeorrev)

    def baserevdiff(self, rev1, rev2):
        return filelog.filelog.revdiff(self, rev1, rev2)

    def _file(self, f):
        self._repo.file(f)

class unionpeer(localrepo.localpeer):
    def canpush(self):
        return False

class unionrepository(localrepo.localrepository):
    def __init__(self, ui, path, path2):
        localrepo.localrepository.__init__(self, ui, path)
        self.ui.setconfig('phases', 'publish', False, 'unionrepo')

        self._url = 'union:%s+%s' % (util.expandpath(path),
                                     util.expandpath(path2))
        self.repo2 = localrepo.localrepository(ui, path2)

    @localrepo.unfilteredpropertycache
    def changelog(self):
        return unionchangelog(self.sopener, self.repo2.sopener)

    def _clrev(self, rev2):
        """map from repo2 changelog rev to temporary rev in self.changelog"""
        node = self.repo2.changelog.node(rev2)
        return self.changelog.rev(node)

    @localrepo.unfilteredpropertycache
    def manifest(self):
        return unionmanifest(self.sopener, self.repo2.sopener,
                             self._clrev)

    def url(self):
        return self._url

    def file(self, f):
        return unionfilelog(self.sopener, f, self.repo2.sopener,
                            self._clrev, self)

    def close(self):
        self.repo2.close()

    def cancopy(self):
        return False

    def peer(self):
        return unionpeer(self)

    def getcwd(self):
        return os.getcwd() # always outside the repo

def instance(ui, path, create):
    if create:
        raise util.Abort(_('cannot create new union repository'))
    parentpath = ui.config("bundle", "mainreporoot", "")
    if not parentpath:
        # try to find the correct path to the working directory repo
        parentpath = cmdutil.findrepo(os.getcwd())
        if parentpath is None:
            parentpath = ''
    if parentpath:
        # Try to make the full path relative so we get a nice, short URL.
        # In particular, we don't want temp dir names in test outputs.
        cwd = os.getcwd()
        if parentpath == cwd:
            parentpath = ''
        else:
            cwd = os.path.join(cwd,'')
            if parentpath.startswith(cwd):
                parentpath = parentpath[len(cwd):]
    if path.startswith('union:'):
        s = path.split(":", 1)[1].split("+", 1)
        if len(s) == 1:
            repopath, repopath2 = parentpath, s[0]
        else:
            repopath, repopath2 = s
    else:
        repopath, repopath2 = parentpath, path
    return unionrepository(ui, repopath, repopath2)