tests/wireprotosimplecache.py

commit: improve the files field of changelog for merges

Currently, the files list of merge commits repeats all the deletions
(either actual deletions, or files that got renamed) that happened
between base and p2 of the merge. If p2 is the main branch, the list
can easily be much bigger than the change being merged.

This results in various problems worth improving:
- changelog is bigger than necessary
- `hg log directory` lists many unrelated merge commits, and `hg log
  -v -r commit` frequently fills multiple screens worth of files
- it possibly slows down adjustlinkrev, by forcing it to read more
  manifests, and that function can certainly be a bottleneck
- the server side of pulls can waste a lot of time simply opening the
  filelogs for pointless files (the constant factors for opening even
  a tiny filelog is apparently pretty bad)

So stop listing such files as described in the code.  Impacted merge
commits and their descendants get a different hash than they would
have without this. This doesn't seem problematic, except for
convert. The previous commit helped with that in the hg->hg case (but
if you do svn->hg twice from scratch, hashes can still change).

The rest of the description is numbers. I don't have much to report,
because recreating the files list of existing repositories is not
easy:
- debugupgradeformat and bundle/unbundle don't recreate the list
- export/import tends to choke quickly applying patches or on
  description that contain diffs,
- merge commits from the convert extension don't have the right files
  list for reasons orthogonal to the current commit
- replaying the merge with hg update/hg merge/hg revert --all/hg
  commit can end up failing in hg revert
- I wasn't sure that using debugsetparents + debugrebuilddirstate
  would really build the right thing

I measured commit time before and after this change, in a case with no
files filtered out, several files filtered out (no difference) and 5k
files filtered out (+1% time).

Recreating the 100 more recent merges in a private repo, the
concatenated uncompressed files lists goes from 1.12MB to
0.52MB. Excluding 3 merges that are not representative, then the size
goes from 570k to 15k.
I converted part of mozilla-central, and observed file list shrinking
quite a bit too, starting at the very first merge, 733641d9feaf, going
from 550 files to 10 files (although they have relatively few merges,
so they probably wouldn't care).

Differential Revision: https://phab.mercurial-scm.org/D6613

# wireprotosimplecache.py - Extension providing in-memory wire protocol cache
#
# Copyright 2018 Gregory Szorc <[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 mercurial import (
    extensions,
    registrar,
    repository,
    util,
    wireprotoserver,
    wireprototypes,
    wireprotov2server,
)
from mercurial.utils import (
    interfaceutil,
    stringutil,
)

CACHE = None

configtable = {}
configitem = registrar.configitem(configtable)

configitem(b'simplecache', b'cacheapi',
           default=False)
configitem(b'simplecache', b'cacheobjects',
           default=False)
configitem(b'simplecache', b'redirectsfile',
           default=None)

# API handler that makes cached keys available.
def handlecacherequest(rctx, req, res, checkperm, urlparts):
    if rctx.repo.ui.configbool(b'simplecache', b'cacheobjects'):
        res.status = b'500 Internal Server Error'
        res.setbodybytes(b'cacheobjects not supported for api server')
        return

    if not urlparts:
        res.status = b'200 OK'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(b'simple cache server')
        return

    key = b'/'.join(urlparts)

    if key not in CACHE:
        res.status = b'404 Not Found'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(b'key not found in cache')
        return

    res.status = b'200 OK'
    res.headers[b'Content-Type'] = b'application/mercurial-cbor'
    res.setbodybytes(CACHE[key])

def cachedescriptor(req, repo):
    return {}

wireprotoserver.API_HANDLERS[b'simplecache'] = {
    b'config': (b'simplecache', b'cacheapi'),
    b'handler': handlecacherequest,
    b'apidescriptor': cachedescriptor,
}

@interfaceutil.implementer(repository.iwireprotocolcommandcacher)
class memorycacher(object):
    def __init__(self, ui, command, encodefn, redirecttargets, redirecthashes,
                 req):
        self.ui = ui
        self.encodefn = encodefn
        self.redirecttargets = redirecttargets
        self.redirecthashes = redirecthashes
        self.req = req
        self.key = None
        self.cacheobjects = ui.configbool(b'simplecache', b'cacheobjects')
        self.cacheapi = ui.configbool(b'simplecache', b'cacheapi')
        self.buffered = []

        ui.log(b'simplecache', b'cacher constructed for %s\n', command)

    def __enter__(self):
        return self

    def __exit__(self, exctype, excvalue, exctb):
        if exctype:
            self.ui.log(b'simplecache', b'cacher exiting due to error\n')

    def adjustcachekeystate(self, state):
        # Needed in order to make tests deterministic. Don't copy this
        # pattern for production caches!
        del state[b'repo']

    def setcachekey(self, key):
        self.key = key
        return True

    def lookup(self):
        if self.key not in CACHE:
            self.ui.log(b'simplecache', b'cache miss for %s\n', self.key)
            return None

        entry = CACHE[self.key]
        self.ui.log(b'simplecache', b'cache hit for %s\n', self.key)

        redirectable = True

        if not self.cacheapi:
            redirectable = False
        elif not self.redirecttargets:
            redirectable = False
        else:
            clienttargets = set(self.redirecttargets)
            ourtargets = set(t[b'name'] for t in loadredirecttargets(self.ui))

            # We only ever redirect to a single target (for now). So we don't
            # need to store which target matched.
            if not clienttargets & ourtargets:
                redirectable = False

        if redirectable:
            paths = self.req.dispatchparts[:-3]
            paths.append(b'simplecache')
            paths.append(self.key)

            url = b'%s/%s' % (self.req.baseurl, b'/'.join(paths))

            #url = b'http://example.com/%s' % self.key
            self.ui.log(b'simplecache', b'sending content redirect for %s to '
                                        b'%s\n', self.key, url)
            response = wireprototypes.alternatelocationresponse(
                url=url,
                mediatype=b'application/mercurial-cbor')

            return {b'objs': [response]}

        if self.cacheobjects:
            return {
                b'objs': entry,
            }
        else:
            return {
                b'objs': [wireprototypes.encodedresponse(entry)],
            }

    def onobject(self, obj):
        if self.cacheobjects:
            self.buffered.append(obj)
        else:
            self.buffered.extend(self.encodefn(obj))

        yield obj

    def onfinished(self):
        self.ui.log(b'simplecache', b'storing cache entry for %s\n', self.key)
        if self.cacheobjects:
            CACHE[self.key] = self.buffered
        else:
            CACHE[self.key] = b''.join(self.buffered)

        return []

def makeresponsecacher(orig, repo, proto, command, args, objencoderfn,
                       redirecttargets, redirecthashes):
    return memorycacher(repo.ui, command, objencoderfn, redirecttargets,
                        redirecthashes, proto._req)

def loadredirecttargets(ui):
    path = ui.config(b'simplecache', b'redirectsfile')
    if not path:
        return []

    with open(path, 'rb') as fh:
        s = fh.read()

    return stringutil.evalpythonliteral(s)

def getadvertisedredirecttargets(orig, repo, proto):
    return loadredirecttargets(repo.ui)

def extsetup(ui):
    global CACHE

    CACHE = util.lrucachedict(10000)

    extensions.wrapfunction(wireprotov2server, b'makeresponsecacher',
                            makeresponsecacher)
    extensions.wrapfunction(wireprotov2server, b'getadvertisedredirecttargets',
                            getadvertisedredirecttargets)