mercurial/pushkey.py

setdiscovery: avoid a full changelog graph traversal

We were definitely being suboptimal here: we were constructing two full sets,
one with the full set of common nodes (i.e. a graph traversal) and one with all
nodes. Then we subtract one set from the other. This whole process is
O(commits) and causes discovery to be significantly slower than it should be.

Instead, keep track of common incrementally and keep undecided as small as
possible.

This makes discovery massively faster on large repos: on one such repo, 'hg
debugdiscovery' over SSH with one commit missing on the client and five on the
server went from 4.5 seconds to 1.5. (An 'hg debugdiscovery' with no commits
missing on the client, i.e. connection startup time, was 1.2 seconds.)

# pushkey.py - dispatching for pushing and pulling keys
#
# Copyright 2010 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.

import bookmarks, phases, obsolete, encoding

def _nslist(repo):
    n = {}
    for k in _namespaces:
        n[k] = ""
    if not obsolete.isenabled(repo, obsolete.exchangeopt):
        n.pop('obsolete')
    return n

_namespaces = {"namespaces": (lambda *x: False, _nslist),
               "bookmarks": (bookmarks.pushbookmark, bookmarks.listbookmarks),
               "phases": (phases.pushphase, phases.listphases),
               "obsolete": (obsolete.pushmarker, obsolete.listmarkers),
              }

def register(namespace, pushkey, listkeys):
    _namespaces[namespace] = (pushkey, listkeys)

def _get(namespace):
    return _namespaces.get(namespace, (lambda *x: False, lambda *x: {}))

def push(repo, namespace, key, old, new):
    '''should succeed iff value was old'''
    pk = _get(namespace)[0]
    return pk(repo, key, old, new)

def list(repo, namespace):
    '''return a dict'''
    lk = _get(namespace)[1]
    return lk(repo)

encode = encoding.fromlocal

decode = encoding.tolocal

def encodekeys(keys):
    """encode the content of a pushkey namespace for exchange over the wire"""
    return '\n'.join(['%s\t%s' % (encode(k), encode(v)) for k, v in keys])

def decodekeys(data):
    """decode the content of a pushkey namespace from exchange over the wire"""
    result = {}
    for l in data.splitlines():
        k, v = l.split('\t')
        result[decode(k)] = decode(v)
    return result