view mercurial/logexchange.py @ 35767:5f5fb279fd39

streamclone: also stream caches to the client

When stream clone is used over bundle2, relevant cache files are also streamed.
This is expected to be a massive performance win for clone since no important
cache will have to be recomputed.

Some performance numbers:

(All times are wall-clock times in seconds, 2 attempts per case.)

# Mozilla-Central

## Clone over ssh over lan
V1 streaming: 234.3 239.6
V2 streaming: 248.4 243.7

## Clone over ssh over Internet
V1 streaming: 175.5 110.9
V2 streaming: 109.1 111.0

## Clone over HTTP over lan
V1 streaming: 105.3 105.6
V2 streaming: 112.7 111.4

## Clone over HTTP over internet
V1 streaming: 105.6 114.6
V2 streaming: 226.7 225.9

## Hg tags
V1 streaming (no cache): 1.084 1.071
V2 streaming (cache):    0.312 0.325

## Hg branches
V1 streaming (no cache):   14.047 14.148
V2 streaming (with cache):  0.312  0.333

# Pypy

## Clone over ssh over internet
V1 streaming: 29.4 30.1
V2 streaming: 31.2 30.1

## Clone over http over internet
V1 streaming: 29.7 29.7
V2 streaming: 75.2 72.9

(since ssh and lan are not affected, there seems to be an issue with how we
read/write the http stream on connection with latency, unrelated to the format)

## Hg tags
V1 streaming (no cache):   1.752 1.664
V2 streaming (with cache): 0.274 0.260

## Hg branches
V1 streaming (no cache):   4.469 4.728
V2 streaming (with cache): 0.318 0.321

# Private repository:
    * 500K revision revisions
    * 11K topological heads
    * 28K branch heads

## hg tags
no cache:   1543.332
with cache:    4.900

## hg branches
no cache:   91.828
with cache:  2.955

# logexchange.py
#
# Copyright 2017 Augie Fackler <[e-mail]>
# Copyright 2017 Sean Farley <[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

from .node import hex

from . import (
    vfs as vfsmod,
)

# directory name in .hg/ in which remotenames files will be present
remotenamedir = 'logexchange'

def readremotenamefile(repo, filename):
    """
    reads a file from .hg/logexchange/ directory and yields it's content
    filename: the file to be read
    yield a tuple (node, remotepath, name)
    """

    vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
    if not vfs.exists(filename):
        return
    f = vfs(filename)
    lineno = 0
    for line in f:
        line = line.strip()
        if not line:
            continue
        # contains the version number
        if lineno == 0:
            lineno += 1
        try:
            node, remote, rname = line.split('\0')
            yield node, remote, rname
        except ValueError:
            pass

    f.close()

def readremotenames(repo):
    """
    read the details about the remotenames stored in .hg/logexchange/ and
    yields a tuple (node, remotepath, name). It does not yields information
    about whether an entry yielded is branch or bookmark. To get that
    information, call the respective functions.
    """

    for bmentry in readremotenamefile(repo, 'bookmarks'):
        yield bmentry
    for branchentry in readremotenamefile(repo, 'branches'):
        yield branchentry

def writeremotenamefile(repo, remotepath, names, nametype):
    vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
    f = vfs(nametype, 'w', atomictemp=True)
    # write the storage version info on top of file
    # version '0' represents the very initial version of the storage format
    f.write('0\n\n')

    olddata = set(readremotenamefile(repo, nametype))
    # re-save the data from a different remote than this one.
    for node, oldpath, rname in sorted(olddata):
        if oldpath != remotepath:
            f.write('%s\0%s\0%s\n' % (node, oldpath, rname))

    for name, node in sorted(names.iteritems()):
        if nametype == "branches":
            for n in node:
                f.write('%s\0%s\0%s\n' % (n, remotepath, name))
        elif nametype == "bookmarks":
            if node:
                f.write('%s\0%s\0%s\n' % (node, remotepath, name))

    f.close()

def saveremotenames(repo, remotepath, branches=None, bookmarks=None):
    """
    save remotenames i.e. remotebookmarks and remotebranches in their
    respective files under ".hg/logexchange/" directory.
    """
    wlock = repo.wlock()
    try:
        if bookmarks:
            writeremotenamefile(repo, remotepath, bookmarks, 'bookmarks')
        if branches:
            writeremotenamefile(repo, remotepath, branches, 'branches')
    finally:
        wlock.release()

def pullremotenames(localrepo, remoterepo):
    """
    pulls bookmarks and branches information of the remote repo during a
    pull or clone operation.
    localrepo is our local repository
    remoterepo is the peer instance
    """
    remotepath = remoterepo.url()
    bookmarks = remoterepo.listkeys('bookmarks')
    # on a push, we don't want to keep obsolete heads since
    # they won't show up as heads on the next pull, so we
    # remove them here otherwise we would require the user
    # to issue a pull to refresh the storage
    bmap = {}
    repo = localrepo.unfiltered()
    for branch, nodes in remoterepo.branchmap().iteritems():
        bmap[branch] = []
        for node in nodes:
            if node in repo and not repo[node].obsolete():
                bmap[branch].append(hex(node))

    saveremotenames(localrepo, remotepath, bmap, bookmarks)