fastannotate: process files as they arrive

peer.commandexecutor()'s context manager waits for all responses to
arrive in its __exit__() method. We want to process the results as
they arrive, so we should do that inside the context manager
scope. Note that the futures' result() methods have been replaced to
make sure that the command executor's sendcommands() method is called
when the first future's result is requested, so we don't need to do
that.

A minor side-effect is that we can no longer easily tell when the
server has started sending us responses, so that long statement was
lost.

Differential Revision: https://phab.mercurial-scm.org/D4666

hgext/fastannotate/protocol.py

@@ -1,228 +1,228 b''
 # Copyright 2016-present Facebook. All Rights Reserved.
 #
 # protocol: logic for a server providing fastannotate support
 #
 # 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
 
 import contextlib
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     extensions,
     hg,
     util,
     wireprotov1peer,
     wireprotov1server,
 )
 from . import context
 
 # common
 
 def _getmaster(ui):
     """get the mainbranch, and enforce it is set"""
     master = ui.config('fastannotate', 'mainbranch')
     if not master:
         raise error.Abort(_('fastannotate.mainbranch is required '
                             'for both the client and the server'))
     return master
 
 # server-side
 
 def _capabilities(orig, repo, proto):
     result = orig(repo, proto)
     result.append('getannotate')
     return result
 
 def _getannotate(repo, proto, path, lastnode):
     # output:
     #   FILE := vfspath + '\0' + str(size) + '\0' + content
     #   OUTPUT := '' | FILE + OUTPUT
     result = ''
     buildondemand = repo.ui.configbool('fastannotate', 'serverbuildondemand',
                                        True)
     with context.annotatecontext(repo, path) as actx:
         if buildondemand:
             # update before responding to the client
             master = _getmaster(repo.ui)
             try:
                 if not actx.isuptodate(master):
                     actx.annotate(master, master)
             except Exception:
                 # non-fast-forward move or corrupted. rebuild automically.
                 actx.rebuild()
                 try:
                     actx.annotate(master, master)
                 except Exception:
                     actx.rebuild() # delete files
             finally:
                 # although the "with" context will also do a close/flush, we
                 # need to do it early so we can send the correct respond to
                 # client.
                 actx.close()
         # send back the full content of revmap and linelog, in the future we
         # may want to do some rsync-like fancy updating.
         # the lastnode check is not necessary if the client and the server
         # agree where the main branch is.
         if actx.lastnode != lastnode:
             for p in [actx.revmappath, actx.linelogpath]:
                 if not os.path.exists(p):
                     continue
                 content = ''
                 with open(p, 'rb') as f:
                     content = f.read()
                 vfsbaselen = len(repo.vfs.base + '/')
                 relpath = p[vfsbaselen:]
                 result += '%s\0%d\0%s' % (relpath, len(content), content)
     return result
 
 def _registerwireprotocommand():
     if 'getannotate' in wireprotov1server.commands:
         return
     wireprotov1server.wireprotocommand(
         'getannotate', 'path lastnode')(_getannotate)
 
 def serveruisetup(ui):
     _registerwireprotocommand()
     extensions.wrapfunction(wireprotov1server, '_capabilities', _capabilities)
 
 # client-side
 
 def _parseresponse(payload):
     result = {}
     i = 0
     l = len(payload) - 1
     state = 0 # 0: vfspath, 1: size
     vfspath = size = ''
     while i < l:
         ch = payload[i]
         if ch == '\0':
             if state == 1:
                 result[vfspath] = buffer(payload, i + 1, int(size))
                 i += int(size)
                 state = 0
                 vfspath = size = ''
             elif state == 0:
                 state = 1
         else:
             if state == 1:
                 size += ch
             elif state == 0:
                 vfspath += ch
         i += 1
     return result
 
 def peersetup(ui, peer):
     class fastannotatepeer(peer.__class__):
         @wireprotov1peer.batchable
         def getannotate(self, path, lastnode=None):
             if not self.capable('getannotate'):
                 ui.warn(_('remote peer cannot provide annotate cache\n'))
                 yield None, None
             else:
                 args = {'path': path, 'lastnode': lastnode or ''}
                 f = wireprotov1peer.future()
                 yield args, f
                 yield _parseresponse(f.value)
     peer.__class__ = fastannotatepeer
 
 @contextlib.contextmanager
 def annotatepeer(repo):
     ui = repo.ui
 
     remotepath = ui.expandpath(
         ui.config('fastannotate', 'remotepath', 'default'))
     peer = hg.peer(ui, {}, remotepath)
 
     try:
         yield peer
     finally:
         peer.close()
 
 def clientfetch(repo, paths, lastnodemap=None, peer=None):
     """download annotate cache from the server for paths"""
     if not paths:
         return
 
     if peer is None:
         with annotatepeer(repo) as peer:
             return clientfetch(repo, paths, lastnodemap, peer)
 
     if lastnodemap is None:
         lastnodemap = {}
 
     ui = repo.ui
     results = []
     with peer.commandexecutor() as batcher:
         ui.debug('fastannotate: requesting %d files\n' % len(paths))
         for p in paths:
             results.append(batcher.callcommand(
                 'getannotate',
                 {'path': p, 'lastnode':lastnodemap.get(p)}))
 
-    ui.debug('fastannotate: server returned\n')
-    for result in results:
-        r = result.result()
-        # TODO: pconvert these paths on the server?
-        r = {util.pconvert(p): v for p, v in r.iteritems()}
-        for path in sorted(r):
-            # ignore malicious paths
-            if not path.startswith('fastannotate/') or '/../' in (path + '/'):
-                ui.debug('fastannotate: ignored malicious path %s\n' % path)
-                continue
-            content = r[path]
-            if ui.debugflag:
-                ui.debug('fastannotate: writing %d bytes to %s\n'
-                         % (len(content), path))
-            repo.vfs.makedirs(os.path.dirname(path))
-            with repo.vfs(path, 'wb') as f:
-                f.write(content)
+        for result in results:
+            r = result.result()
+            # TODO: pconvert these paths on the server?
+            r = {util.pconvert(p): v for p, v in r.iteritems()}
+            for path in sorted(r):
+                # ignore malicious paths
+                if (not path.startswith('fastannotate/')
+                    or '/../' in (path + '/')):
+                    ui.debug('fastannotate: ignored malicious path %s\n' % path)
+                    continue
+                content = r[path]
+                if ui.debugflag:
+                    ui.debug('fastannotate: writing %d bytes to %s\n'
+                             % (len(content), path))
+                repo.vfs.makedirs(os.path.dirname(path))
+                with repo.vfs(path, 'wb') as f:
+                    f.write(content)
 
 def _filterfetchpaths(repo, paths):
     """return a subset of paths whose history is long and need to fetch linelog
     from the server. works with remotefilelog and non-remotefilelog repos.
     """
     threshold = repo.ui.configint('fastannotate', 'clientfetchthreshold', 10)
     if threshold <= 0:
         return paths
 
     result = []
     for path in paths:
         try:
             if len(repo.file(path)) >= threshold:
                 result.append(path)
         except Exception: # file not found etc.
             result.append(path)
 
     return result
 
 def localreposetup(ui, repo):
     class fastannotaterepo(repo.__class__):
         def prefetchfastannotate(self, paths, peer=None):
             master = _getmaster(self.ui)
             needupdatepaths = []
             lastnodemap = {}
             try:
                 for path in _filterfetchpaths(self, paths):
                     with context.annotatecontext(self, path) as actx:
                         if not actx.isuptodate(master, strict=False):
                             needupdatepaths.append(path)
                             lastnodemap[path] = actx.lastnode
                 if needupdatepaths:
                     clientfetch(self, needupdatepaths, lastnodemap, peer)
             except Exception as ex:
                 # could be directory not writable or so, not fatal
                 self.ui.debug('fastannotate: prefetch failed: %r\n' % ex)
     repo.__class__ = fastannotaterepo
 
 def clientreposetup(ui, repo):
     _registerwireprotocommand()
     if repo.local():
         localreposetup(ui, repo)
     # TODO: this mutates global state, but only if at least one repo
     # has the extension enabled. This is probably bad for hgweb.
     if peersetup not in hg.wirepeersetupfuncs:
         hg.wirepeersetupfuncs.append(peersetup)

tests/test-fastannotate-protocol.t

@@ -1,215 +1,211 b''
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ssh = "$PYTHON" "$TESTDIR/dummyssh"
   > [extensions]
   > fastannotate=
   > [fastannotate]
   > mainbranch=@
   > EOF
 
   $ HGMERGE=true; export HGMERGE
 
 setup the server repo
 
   $ hg init repo-server
   $ cd repo-server
   $ cat >> .hg/hgrc << EOF
   > [fastannotate]
   > server=1
   > EOF
   $ for i in 1 2 3 4; do
   >   echo $i >> a
   >   hg commit -A -m $i a
   > done
   $ [ -d .hg/fastannotate ]
   [1]
   $ hg bookmark @
   $ cd ..
 
 setup the local repo
 
   $ hg clone 'ssh://user@dummy/repo-server' repo-local -q
   $ cd repo-local
   $ cat >> .hg/hgrc << EOF
   > [fastannotate]
   > client=1
   > clientfetchthreshold=0
   > EOF
   $ [ -d .hg/fastannotate ]
   [1]
   $ hg fastannotate a --debug
   running * (glob)
   sending hello command
   sending between command
   remote: * (glob) (?)
   remote: capabilities: * (glob)
   remote: * (glob) (?)
   sending protocaps command
   fastannotate: requesting 1 files
   sending getannotate command
-  fastannotate: server returned
   fastannotate: writing 112 bytes to fastannotate/default/a.l
   fastannotate: writing 94 bytes to fastannotate/default/a.m
   fastannotate: a: using fast path (resolved fctx: True)
   0: 1
   1: 2
   2: 3
   3: 4
 
 the cache could be reused and no download is necessary
 
   $ hg fastannotate a --debug
   fastannotate: a: using fast path (resolved fctx: True)
   0: 1
   1: 2
   2: 3
   3: 4
 
 if the client agrees where the head of the master branch is, no re-download
 happens even if the client has more commits
 
   $ echo 5 >> a
   $ hg commit -m 5
   $ hg bookmark -r 3 @ -f
   $ hg fastannotate a --debug
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 if the client has a different "@" (head of the master branch) and "@" is ahead
 of the server, the server can detect things are unchanged and does not return
 full contents (not that there is no "writing ... to fastannotate"), but the
 client can also build things up on its own (causing diverge)
 
   $ hg bookmark -r 4 @ -f
   $ hg fastannotate a --debug
   running * (glob)
   sending hello command
   sending between command
   remote: * (glob) (?)
   remote: capabilities: * (glob)
   remote: * (glob) (?)
   sending protocaps command
   fastannotate: requesting 1 files
   sending getannotate command
-  fastannotate: server returned
   fastannotate: a: 1 new changesets in the main branch
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 if the client has a different "@" which is behind the server. no download is
 necessary
 
   $ hg fastannotate a --debug --config fastannotate.mainbranch=2
   fastannotate: a: using fast path (resolved fctx: True)
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 define fastannotate on-disk paths
 
   $ p1=.hg/fastannotate/default
   $ p2=../repo-server/.hg/fastannotate/default
 
 revert bookmark change so the client is behind the server
 
   $ hg bookmark -r 2 @ -f
 
 in the "fctx" mode with the "annotate" command, the client also downloads the
 cache. but not in the (default) "fastannotate" mode.
 
   $ rm $p1/a.l $p1/a.m
   $ hg annotate a --debug | grep 'fastannotate: writing'
   [1]
   $ hg annotate a --config fastannotate.modes=fctx --debug | grep 'fastannotate: writing' | sort
   fastannotate: writing 112 bytes to fastannotate/default/a.l
   fastannotate: writing 94 bytes to fastannotate/default/a.m
 
 the fastannotate cache (built server-side, downloaded client-side) in two repos
 have the same content (because the client downloads from the server)
 
   $ diff $p1/a.l $p2/a.l
   $ diff $p1/a.m $p2/a.m
 
 in the "fctx" mode, the client could also build the cache locally
 
   $ hg annotate a --config fastannotate.modes=fctx --debug --config fastannotate.mainbranch=4 | grep fastannotate
   fastannotate: requesting 1 files
-  fastannotate: server returned
   fastannotate: a: 1 new changesets in the main branch
 
 the server would rebuild broken cache automatically
 
   $ cp $p2/a.m $p2/a.m.bak
   $ echo BROKEN1 > $p1/a.m
   $ echo BROKEN2 > $p2/a.m
   $ hg fastannotate a --debug | grep 'fastannotate: writing' | sort
   fastannotate: writing 112 bytes to fastannotate/default/a.l
   fastannotate: writing 94 bytes to fastannotate/default/a.m
   $ diff $p1/a.m $p2/a.m
   $ diff $p2/a.m $p2/a.m.bak
 
 use the "debugbuildannotatecache" command to build annotate cache
 
   $ rm -rf $p1 $p2
   $ hg --cwd ../repo-server debugbuildannotatecache a --debug
   fastannotate: a: 4 new changesets in the main branch
   $ hg --cwd ../repo-local debugbuildannotatecache a --debug
   running * (glob)
   sending hello command
   sending between command
   remote: * (glob) (?)
   remote: capabilities: * (glob)
   remote: * (glob) (?)
   sending protocaps command
   fastannotate: requesting 1 files
   sending getannotate command
-  fastannotate: server returned
   fastannotate: writing * (glob)
   fastannotate: writing * (glob)
   $ diff $p1/a.l $p2/a.l
   $ diff $p1/a.m $p2/a.m
 
 with the clientfetchthreshold config option, the client can build up the cache
 without downloading from the server
 
   $ rm -rf $p1
   $ hg fastannotate a --debug --config fastannotate.clientfetchthreshold=10
   fastannotate: a: 3 new changesets in the main branch
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 if the fastannotate directory is not writable, the fctx mode still works
 
   $ rm -rf $p1
   $ touch $p1
   $ hg annotate a --debug --traceback --config fastannotate.modes=fctx
   fastannotate: a: cache broken and deleted
   fastannotate: prefetch failed: * (glob)
   fastannotate: a: cache broken and deleted
   fastannotate: falling back to the vanilla annotate: * (glob)
   0: 1
   1: 2
   2: 3
   3: 4
   4: 5
 
 with serverbuildondemand=False, the server will not build anything
 
   $ cat >> ../repo-server/.hg/hgrc <<EOF
   > [fastannotate]
   > serverbuildondemand=False
   > EOF
   $ rm -rf $p1 $p2
   $ hg fastannotate a --debug | grep 'fastannotate: writing'
   [1]