view mercurial/bundlerepo.py @ 29861:2f6d5c60f6fc stable

annotate: pre-calculate the "needed" dictionary (issue5360)

The "needed" dict is used as a reference counter to free items in the giant
"hist" dict. However, currently it is not very accurate and can lead to
dropping "hist" items unnecessarily, for example, with the following DAG,

       -3-
      /   \
  0--1--2--4--

The current algorithm will visit and calculate rev 1 twice, undesired. And
it tries to be smart by clearing rev 1's parents: "pcache[1] = []" at the
time hist[1] being accessed (note: hist[1] needs to be used twice, by rev 2
and rev 3). It can result in incorrect results if p1 of rev 4 deletes chunks
belonging to rev 0.

However, simply removing "needed" is not okay, because it will consume 10x
memory:

  # without any change
  % HGRCPATH= lrun ./hg annotate mercurial/commands.py -r d130a38 3>&2 [1]
  MEMORY   49074176
  CPUTIME  9.213
  REALTIME 9.270

  # with "needed" removed
  MEMORY   637673472
  CPUTIME  8.164
  REALTIME 8.249

This patch moves "needed" (and "pcache") calculation to a separate DFS to
address the issue. It improves perf and fixes issue5360 by correctly reusing
hist, while maintaining low memory usage. Some additional attempt has been
made to further reduce memory usage, like changing "pcache[f] = []" to "del
pcache[f]". Therefore the result can be both faster and lower memory usage:

  # with this patch applied
  MEMORY   47575040
  CPUTIME  7.870
  REALTIME 7.926

[1]: lrun is a lightweight sandbox built on Linux cgroup and namespace. It's
     used to measure CPU and memory usage here. Source code is available at
     github.com/quark-zju/lrun.

# bundlerepo.py - repository class for viewing uncompressed bundles
#
# Copyright 2006, 2007 Benoit Boissinot <[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 viewing uncompressed bundles.

This provides a read-only repository interface to bundles as if they
were part of the actual repository.
"""

from __future__ import absolute_import

import os
import shutil
import tempfile

from .i18n import _
from .node import nullid

from . import (
    bundle2,
    changegroup,
    changelog,
    cmdutil,
    discovery,
    error,
    exchange,
    filelog,
    localrepo,
    manifest,
    mdiff,
    node as nodemod,
    pathutil,
    phases,
    revlog,
    scmutil,
    util,
)

class bundlerevlog(revlog.revlog):
    def __init__(self, opener, indexfile, bundle, linkmapper):
        # How it works:
        # To retrieve a revision, we need to know the offset of the revision in
        # the bundle (an unbundle object). We store this offset in the index
        # (start). The base of the delta is stored in the base field.
        #
        # To differentiate a rev in the bundle from a rev in the revlog, we
        # check revision against repotiprev.
        opener = scmutil.readonlyvfs(opener)
        revlog.revlog.__init__(self, opener, indexfile)
        self.bundle = bundle
        n = len(self)
        self.repotiprev = n - 1
        chain = None
        self.bundlerevs = set() # used by 'bundle()' revset expression
        while True:
            chunkdata = bundle.deltachunk(chain)
            if not chunkdata:
                break
            node = chunkdata['node']
            p1 = chunkdata['p1']
            p2 = chunkdata['p2']
            cs = chunkdata['cs']
            deltabase = chunkdata['deltabase']
            delta = chunkdata['delta']

            size = len(delta)
            start = bundle.tell() - size

            link = linkmapper(cs)
            if node in self.nodemap:
                # this can happen if two branches make the same change
                chain = node
                self.bundlerevs.add(self.nodemap[node])
                continue

            for p in (p1, p2):
                if p not in self.nodemap:
                    raise error.LookupError(p, self.indexfile,
                                            _("unknown parent"))

            if deltabase not in self.nodemap:
                raise LookupError(deltabase, self.indexfile,
                                  _('unknown delta base'))

            baserev = self.rev(deltabase)
            # start, size, full unc. size, base (unused), link, p1, p2, node
            e = (revlog.offset_type(start, 0), size, -1, baserev, link,
                 self.rev(p1), self.rev(p2), node)
            self.index.insert(-1, e)
            self.nodemap[node] = n
            self.bundlerevs.add(n)
            chain = node
            n += 1

    def _chunk(self, rev):
        # Warning: in case of bundle, the diff is against what we stored as
        # delta base, not against rev - 1
        # XXX: could use some caching
        if rev <= self.repotiprev:
            return revlog.revlog._chunk(self, rev)
        self.bundle.seek(self.start(rev))
        return self.bundle.read(self.length(rev))

    def revdiff(self, rev1, rev2):
        """return or calculate a delta between two revisions"""
        if rev1 > self.repotiprev and rev2 > self.repotiprev:
            # hot path for bundle
            revb = self.index[rev2][3]
            if revb == rev1:
                return self._chunk(rev2)
        elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
            return revlog.revlog.revdiff(self, 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 ""

        text = None
        chain = []
        iterrev = rev
        # reconstruct the revision if it is from a changegroup
        while iterrev > self.repotiprev:
            if self._cache and self._cache[1] == iterrev:
                text = self._cache[2]
                break
            chain.append(iterrev)
            iterrev = self.index[iterrev][3]
        if text is None:
            text = self.baserevision(iterrev)

        while chain:
            delta = self._chunk(chain.pop())
            text = mdiff.patches(text, [delta])

        self._checkhash(text, node, rev)
        self._cache = (node, rev, text)
        return text

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

    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 bundlechangelog(bundlerevlog, changelog.changelog):
    def __init__(self, opener, bundle):
        changelog.changelog.__init__(self, opener)
        linkmapper = lambda x: x
        bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                              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.

        # This bypasses filtering on changelog.node() and rev() because we need
        # revision text of the bundle base even if it is hidden.
        oldfilter = self.filteredrevs
        try:
            self.filteredrevs = ()
            return changelog.changelog.revision(self, nodeorrev)
        finally:
            self.filteredrevs = oldfilter

class bundlemanifest(bundlerevlog, manifest.manifest):
    def __init__(self, opener, bundle, linkmapper):
        manifest.manifest.__init__(self, opener)
        bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                              linkmapper)

    def baserevision(self, nodeorrev):
        node = nodeorrev
        if isinstance(node, int):
            node = self.node(node)

        if node in self._mancache:
            result = self._mancache[node][0].text()
        else:
            result = manifest.manifest.revision(self, nodeorrev)
        return result

class bundlefilelog(bundlerevlog, filelog.filelog):
    def __init__(self, opener, path, bundle, linkmapper):
        filelog.filelog.__init__(self, opener, path)
        bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                              linkmapper)

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

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

class bundlephasecache(phases.phasecache):
    def __init__(self, *args, **kwargs):
        super(bundlephasecache, self).__init__(*args, **kwargs)
        if util.safehasattr(self, 'opener'):
            self.opener = scmutil.readonlyvfs(self.opener)

    def write(self):
        raise NotImplementedError

    def _write(self, fp):
        raise NotImplementedError

    def _updateroots(self, phase, newroots, tr):
        self.phaseroots[phase] = newroots
        self.invalidate()
        self.dirty = True

class bundlerepository(localrepo.localrepository):
    def __init__(self, ui, path, bundlename):
        def _writetempbundle(read, suffix, header=''):
            """Write a temporary file to disk

            This is closure because we need to make sure this tracked by
            self.tempfile for cleanup purposes."""
            fdtemp, temp = self.vfs.mkstemp(prefix="hg-bundle-",
                                            suffix=".hg10un")
            self.tempfile = temp

            with os.fdopen(fdtemp, 'wb') as fptemp:
                fptemp.write(header)
                while True:
                    chunk = read(2**18)
                    if not chunk:
                        break
                    fptemp.write(chunk)

            return self.vfs.open(self.tempfile, mode="rb")
        self._tempparent = None
        try:
            localrepo.localrepository.__init__(self, ui, path)
        except error.RepoError:
            self._tempparent = tempfile.mkdtemp()
            localrepo.instance(ui, self._tempparent, 1)
            localrepo.localrepository.__init__(self, ui, self._tempparent)
        self.ui.setconfig('phases', 'publish', False, 'bundlerepo')

        if path:
            self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
        else:
            self._url = 'bundle:' + bundlename

        self.tempfile = None
        f = util.posixfile(bundlename, "rb")
        self.bundlefile = self.bundle = exchange.readbundle(ui, f, bundlename)

        if isinstance(self.bundle, bundle2.unbundle20):
            cgstream = None
            for part in self.bundle.iterparts():
                if part.type == 'changegroup':
                    if cgstream is not None:
                        raise NotImplementedError("can't process "
                                                  "multiple changegroups")
                    cgstream = part
                    version = part.params.get('version', '01')
                    if version not in changegroup.allsupportedversions(ui):
                        msg = _('Unsupported changegroup version: %s')
                        raise error.Abort(msg % version)
                    if self.bundle.compressed():
                        cgstream = _writetempbundle(part.read,
                                                    ".cg%sun" % version)

            if cgstream is None:
                raise error.Abort(_('No changegroups found'))
            cgstream.seek(0)

            self.bundle = changegroup.getunbundler(version, cgstream, 'UN')

        elif self.bundle.compressed():
            f = _writetempbundle(self.bundle.read, '.hg10un', header='HG10UN')
            self.bundlefile = self.bundle = exchange.readbundle(ui, f,
                                                                bundlename,
                                                                self.vfs)

        # dict with the mapping 'filename' -> position in the bundle
        self.bundlefilespos = {}

        self.firstnewrev = self.changelog.repotiprev + 1
        phases.retractboundary(self, None, phases.draft,
                               [ctx.node() for ctx in self[self.firstnewrev:]])

    @localrepo.unfilteredpropertycache
    def _phasecache(self):
        return bundlephasecache(self, self._phasedefaults)

    @localrepo.unfilteredpropertycache
    def changelog(self):
        # consume the header if it exists
        self.bundle.changelogheader()
        c = bundlechangelog(self.svfs, self.bundle)
        self.manstart = self.bundle.tell()
        return c

    @localrepo.unfilteredpropertycache
    def manifest(self):
        self.bundle.seek(self.manstart)
        # consume the header if it exists
        self.bundle.manifestheader()
        linkmapper = self.unfiltered().changelog.rev
        m = bundlemanifest(self.svfs, self.bundle, linkmapper)
        # XXX: hack to work with changegroup3, but we still don't handle
        # tree manifests correctly
        if self.bundle.version == "03":
            self.bundle.filelogheader()
        self.filestart = self.bundle.tell()
        return m

    @localrepo.unfilteredpropertycache
    def manstart(self):
        self.changelog
        return self.manstart

    @localrepo.unfilteredpropertycache
    def filestart(self):
        self.manifest
        return self.filestart

    def url(self):
        return self._url

    def file(self, f):
        if not self.bundlefilespos:
            self.bundle.seek(self.filestart)
            while True:
                chunkdata = self.bundle.filelogheader()
                if not chunkdata:
                    break
                fname = chunkdata['filename']
                self.bundlefilespos[fname] = self.bundle.tell()
                while True:
                    c = self.bundle.deltachunk(None)
                    if not c:
                        break

        if f in self.bundlefilespos:
            self.bundle.seek(self.bundlefilespos[f])
            linkmapper = self.unfiltered().changelog.rev
            return bundlefilelog(self.svfs, f, self.bundle, linkmapper)
        else:
            return filelog.filelog(self.svfs, f)

    def close(self):
        """Close assigned bundle file immediately."""
        self.bundlefile.close()
        if self.tempfile is not None:
            self.vfs.unlink(self.tempfile)
        if self._tempparent:
            shutil.rmtree(self._tempparent, True)

    def cancopy(self):
        return False

    def peer(self):
        return bundlepeer(self)

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

    # Check if parents exist in localrepo before setting
    def setparents(self, p1, p2=nullid):
        p1rev = self.changelog.rev(p1)
        p2rev = self.changelog.rev(p2)
        msg = _("setting parent to node %s that only exists in the bundle\n")
        if self.changelog.repotiprev < p1rev:
            self.ui.warn(msg % nodemod.hex(p1))
        if self.changelog.repotiprev < p2rev:
            self.ui.warn(msg % nodemod.hex(p2))
        return super(bundlerepository, self).setparents(p1, p2)

def instance(ui, path, create):
    if create:
        raise error.Abort(_('cannot create new bundle repository'))
    # internal config: bundle.mainreporoot
    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 = pathutil.normasprefix(cwd)
            if parentpath.startswith(cwd):
                parentpath = parentpath[len(cwd):]
    u = util.url(path)
    path = u.localpath()
    if u.scheme == 'bundle':
        s = path.split("+", 1)
        if len(s) == 1:
            repopath, bundlename = parentpath, s[0]
        else:
            repopath, bundlename = s
    else:
        repopath, bundlename = parentpath, path
    return bundlerepository(ui, repopath, bundlename)

class bundletransactionmanager(object):
    def transaction(self):
        return None

    def close(self):
        raise NotImplementedError

    def release(self):
        raise NotImplementedError

def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                     force=False):
    '''obtains a bundle of changes incoming from other

    "onlyheads" restricts the returned changes to those reachable from the
      specified heads.
    "bundlename", if given, stores the bundle to this file path permanently;
      otherwise it's stored to a temp file and gets deleted again when you call
      the returned "cleanupfn".
    "force" indicates whether to proceed on unrelated repos.

    Returns a tuple (local, csets, cleanupfn):

    "local" is a local repo from which to obtain the actual incoming
      changesets; it is a bundlerepo for the obtained bundle when the
      original "other" is remote.
    "csets" lists the incoming changeset node ids.
    "cleanupfn" must be called without arguments when you're done processing
      the changes; it closes both the original "other" and the one returned
      here.
    '''
    tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                       force=force)
    common, incoming, rheads = tmp
    if not incoming:
        try:
            if bundlename:
                os.unlink(bundlename)
        except OSError:
            pass
        return repo, [], other.close

    commonset = set(common)
    rheads = [x for x in rheads if x not in commonset]

    bundle = None
    bundlerepo = None
    localrepo = other.local()
    if bundlename or not localrepo:
        # create a bundle (uncompressed if other repo is not local)

        canbundle2 = (ui.configbool('experimental', 'bundle2-exp', True)
                      and other.capable('getbundle')
                      and other.capable('bundle2'))
        if canbundle2:
            kwargs = {}
            kwargs['common'] = common
            kwargs['heads'] = rheads
            kwargs['bundlecaps'] = exchange.caps20to10(repo)
            kwargs['cg'] = True
            b2 = other.getbundle('incoming', **kwargs)
            fname = bundle = changegroup.writechunks(ui, b2._forwardchunks(),
                                                     bundlename)
        else:
            if other.capable('getbundle'):
                cg = other.getbundle('incoming', common=common, heads=rheads)
            elif onlyheads is None and not other.capable('changegroupsubset'):
                # compat with older servers when pulling all remote heads
                cg = other.changegroup(incoming, "incoming")
                rheads = None
            else:
                cg = other.changegroupsubset(incoming, rheads, 'incoming')
            if localrepo:
                bundletype = "HG10BZ"
            else:
                bundletype = "HG10UN"
            fname = bundle = bundle2.writebundle(ui, cg, bundlename,
                                                     bundletype)
        # keep written bundle?
        if bundlename:
            bundle = None
        if not localrepo:
            # use the created uncompressed bundlerepo
            localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root,
                                                      fname)
            # this repo contains local and other now, so filter out local again
            common = repo.heads()
    if localrepo:
        # Part of common may be remotely filtered
        # So use an unfiltered version
        # The discovery process probably need cleanup to avoid that
        localrepo = localrepo.unfiltered()

    csets = localrepo.changelog.findmissing(common, rheads)

    if bundlerepo:
        reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev:]]
        remotephases = other.listkeys('phases')

        pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
        pullop.trmanager = bundletransactionmanager()
        exchange._pullapplyphases(pullop, remotephases)

    def cleanup():
        if bundlerepo:
            bundlerepo.close()
        if bundle:
            os.unlink(bundle)
        other.close()

    return (localrepo, csets, cleanup)