view tests/test-batching.py @ 23702:c48924787eaa

filectx.parents: enforce changeid of parent to be in own changectx ancestors Because of the way filenodes are computed, you can have multiple changesets "introducing" the same file revision. For example, in the changeset graph below, changeset 2 and 3 both change a file -to- and -from- the same content. o 3: content = new | | o 2: content = new |/ o 1: content = old In such cases, the file revision is create once, when 2 is added, and just reused for 3. So the file change in '3' (from "old" to "new)" has no linkrev pointing to it). We'll call this situation "linkrev-shadowing". As the linkrev is used for optimization purposes when walking a file history, the linkrev-shadowing results in an unexpected jump to another branch during such a walk.. This leads to multiple bugs with log, annotate and rename detection. One element to fix such bugs is to ensure that walking the file history sticks on the same topology as the changeset's history. For this purpose, we extend the logic in 'basefilectx.parents' so that it always defines the proper changeset to associate the parent file revision with. This "proper" changeset has to be an ancestor of the changeset associated with the child file revision. This logic is performed in the '_adjustlinkrev' function. This function is given the starting changeset and all the information regarding the parent file revision. If the linkrev for the file revision is an ancestor of the starting changeset, the linkrev is valid and will be used. If it is not, we detected a topological jump caused by linkrev shadowing, we are going to walk the ancestors of the starting changeset until we find one setting the file to the revision we are trying to create. The performance impact appears acceptable: - We are walking the changelog once for each filelog traversal (as there should be no overlap between searches), - changelog traversal itself is fairly cheap, compared to what is likely going to be perform on the result on the filelog traversal, - We only touch the manifest for ancestors touching the file, And such changesets are likely to be the one introducing the file. (except in pathological cases involving merge), - We use manifest diff instead of full manifest unpacking to check manifest content, so it does not involve applying multiple diffs in most case. - linkrev shadowing is not the common case. Tests for fixed issues in log, annotate and rename detection have been added. But this changeset does not solve all problems. It fixes -ancestry- computation, but if the linkrev-shadowed changesets is the starting one, we'll still get things wrong. We'll have to fix the bootstrapping of such operations in a later changeset. Also, the usage of `hg log FILE` without --follow still has issues with linkrev pointing to hidden changesets, because it relies on the `filelog` revset which implement its own traversal logic that is still to be fixed. Thanks goes to: - Matt Mackall: for nudging me in the right direction - Julien Cristau and RĂ©mi Cardona: for keep telling me linkrev bug were an evolution show stopper for 3 years. - Durham Goode: for finding a new linkrev issue every few weeks - Mads Kiilerich: for that last rename bug who raise this topic over my anoyance limit.
author Pierre-Yves David <pierre-yves.david@fb.com>
date Tue, 23 Dec 2014 15:30:38 -0800
parents a7d5816087a9
children cbbdd085c991
line wrap: on
line source

# test-batching.py - tests for transparent command batching
#
# Copyright 2011 Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial.wireproto import localbatch, remotebatch, batchable, future

# equivalent of repo.repository
class thing(object):
    def hello(self):
        return "Ready."

# equivalent of localrepo.localrepository
class localthing(thing):
    def foo(self, one, two=None):
        if one:
            return "%s and %s" % (one, two,)
        return "Nope"
    def bar(self, b, a):
        return "%s und %s" % (b, a,)
    def greet(self, name=None):
        return "Hello, %s" % name
    def batch(self):
        '''Support for local batching.'''
        return localbatch(self)

# usage of "thing" interface
def use(it):

    # Direct call to base method shared between client and server.
    print it.hello()

    # Direct calls to proxied methods. They cause individual roundtrips.
    print it.foo("Un", two="Deux")
    print it.bar("Eins", "Zwei")

    # Batched call to a couple of (possibly proxied) methods.
    batch = it.batch()
    # The calls return futures to eventually hold results.
    foo = batch.foo(one="One", two="Two")
    foo2 = batch.foo(None)
    bar = batch.bar("Eins", "Zwei")
    # We can call non-batchable proxy methods, but the break the current batch
    # request and cause additional roundtrips.
    greet = batch.greet(name="John Smith")
    # We can also add local methods into the mix, but they break the batch too.
    hello = batch.hello()
    bar2 = batch.bar(b="Uno", a="Due")
    # Only now are all the calls executed in sequence, with as few roundtrips
    # as possible.
    batch.submit()
    # After the call to submit, the futures actually contain values.
    print foo.value
    print foo2.value
    print bar.value
    print greet.value
    print hello.value
    print bar2.value

# local usage
mylocal = localthing()
print
print "== Local"
use(mylocal)

# demo remoting; mimicks what wireproto and HTTP/SSH do

# shared

def escapearg(plain):
    return (plain
            .replace(':', '::')
            .replace(',', ':,')
            .replace(';', ':;')
            .replace('=', ':='))
def unescapearg(escaped):
    return (escaped
            .replace(':=', '=')
            .replace(':;', ';')
            .replace(':,', ',')
            .replace('::', ':'))

# server side

# equivalent of wireproto's global functions
class server(object):
    def __init__(self, local):
        self.local = local
    def _call(self, name, args):
        args = dict(arg.split('=', 1) for arg in args)
        return getattr(self, name)(**args)
    def perform(self, req):
        print "REQ:", req
        name, args = req.split('?', 1)
        args = args.split('&')
        vals = dict(arg.split('=', 1) for arg in args)
        res = getattr(self, name)(**vals)
        print "  ->", res
        return res
    def batch(self, cmds):
        res = []
        for pair in cmds.split(';'):
            name, args = pair.split(':', 1)
            vals = {}
            for a in args.split(','):
                if a:
                    n, v = a.split('=')
                    vals[n] = unescapearg(v)
            res.append(escapearg(getattr(self, name)(**vals)))
        return ';'.join(res)
    def foo(self, one, two):
        return mangle(self.local.foo(unmangle(one), unmangle(two)))
    def bar(self, b, a):
        return mangle(self.local.bar(unmangle(b), unmangle(a)))
    def greet(self, name):
        return mangle(self.local.greet(unmangle(name)))
myserver = server(mylocal)

# local side

# equivalent of wireproto.encode/decodelist, that is, type-specific marshalling
# here we just transform the strings a bit to check we're properly en-/decoding
def mangle(s):
    return ''.join(chr(ord(c) + 1) for c in s)
def unmangle(s):
    return ''.join(chr(ord(c) - 1) for c in s)

# equivalent of wireproto.wirerepository and something like http's wire format
class remotething(thing):
    def __init__(self, server):
        self.server = server
    def _submitone(self, name, args):
        req = name + '?' + '&'.join(['%s=%s' % (n, v) for n, v in args])
        return self.server.perform(req)
    def _submitbatch(self, cmds):
        req = []
        for name, args in cmds:
            args = ','.join(n + '=' + escapearg(v) for n, v in args)
            req.append(name + ':' + args)
        req = ';'.join(req)
        res = self._submitone('batch', [('cmds', req,)])
        return res.split(';')

    def batch(self):
        return remotebatch(self)

    @batchable
    def foo(self, one, two=None):
        if not one:
            yield "Nope", None
        encargs = [('one', mangle(one),), ('two', mangle(two),)]
        encresref = future()
        yield encargs, encresref
        yield unmangle(encresref.value)

    @batchable
    def bar(self, b, a):
        encresref = future()
        yield [('b', mangle(b),), ('a', mangle(a),)], encresref
        yield unmangle(encresref.value)

    # greet is coded directly. It therefore does not support batching. If it
    # does appear in a batch, the batch is split around greet, and the call to
    # greet is done in its own roundtrip.
    def greet(self, name=None):
        return unmangle(self._submitone('greet', [('name', mangle(name),)]))

# demo remote usage

myproxy = remotething(myserver)
print
print "== Remote"
use(myproxy)