exchangev2: fetch and apply phases data

Now that the server supports emitting phases data, we can request it
and apply it on the client.

Because we may receive phases-only updates from the server, we no
longer conditionally perform the "changesetdata" command depending
on whether there are revisions to fetch. In the previous wire
protocol, this case would result in us falling back to performing
"listkeys" commands to look up phases, bookmarks, etc data. But
since "changesetdata" is smart enough to handle metadata only
fetches, we can keep things consistent.

It's worth noting that because of the unified approach to changeset
data retrieval, phase handling code in wire proto v2 exchange is
drastically simpler. Contrast with all the code in exchange.py
dealing with all the variations for obtaining phases data.

Differential Revision: https://phab.mercurial-scm.org/D4484

mercurial/exchangev2.py

@@ -1,138 +1,167 b''
 # exchangev2.py - repository exchange for wire protocol version 2
 #
 # 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
 
 import weakref
 
 from .i18n import _
 from .node import (
     nullid,
     short,
 )
 from . import (
     mdiff,
+    phases,
     pycompat,
     setdiscovery,
 )
 
 def pull(pullop):
     """Pull using wire protocol version 2."""
     repo = pullop.repo
     remote = pullop.remote
     tr = pullop.trmanager.transaction()
 
     # Figure out what needs to be fetched.
     common, fetch, remoteheads = _pullchangesetdiscovery(
         repo, remote, pullop.heads, abortwhenunrelated=pullop.force)
 
+    # And fetch the data.
     pullheads = pullop.heads or remoteheads
-    _fetchchangesets(repo, tr, remote, common, fetch, pullheads)
+    csetres = _fetchchangesets(repo, tr, remote, common, fetch, pullheads)
+
+    # New revisions are written to the changelog. But all other updates
+    # are deferred. Do those now.
+
+    # Ensure all new changesets are draft by default. If the repo is
+    # publishing, the phase will be adjusted by the loop below.
+    if csetres['added']:
+        phases.registernew(repo, tr, phases.draft, csetres['added'])
+
+    # And adjust the phase of all changesets accordingly.
+    for phase in phases.phasenames:
+        if phase == b'secret' or not csetres['nodesbyphase'][phase]:
+            continue
+
+        phases.advanceboundary(repo, tr, phases.phasenames.index(phase),
+                               csetres['nodesbyphase'][phase])
 
 def _pullchangesetdiscovery(repo, remote, heads, abortwhenunrelated=True):
     """Determine which changesets need to be pulled."""
 
     if heads:
         knownnode = repo.changelog.hasnode
         if all(knownnode(head) for head in heads):
             return heads, False, heads
 
     # TODO wire protocol version 2 is capable of more efficient discovery
     # than setdiscovery. Consider implementing something better.
     common, fetch, remoteheads = setdiscovery.findcommonheads(
         repo.ui, repo, remote, abortwhenunrelated=abortwhenunrelated)
 
     common = set(common)
     remoteheads = set(remoteheads)
 
     # If a remote head is filtered locally, put it back in the common set.
     # See the comment in exchange._pulldiscoverychangegroup() for more.
 
     if fetch and remoteheads:
         nodemap = repo.unfiltered().changelog.nodemap
 
         common |= {head for head in remoteheads if head in nodemap}
 
         if set(remoteheads).issubset(common):
             fetch = []
 
     common.discard(nullid)
 
     return common, fetch, remoteheads
 
 def _fetchchangesets(repo, tr, remote, common, fetch, remoteheads):
-    if not fetch:
-        return
-
     # TODO consider adding a step here where we obtain the DAG shape first
     # (or ask the server to slice changesets into chunks for us) so that
     # we can perform multiple fetches in batches. This will facilitate
     # resuming interrupted clones, higher server-side cache hit rates due
     # to smaller segments, etc.
     with remote.commandexecutor() as e:
         objs = e.callcommand(b'changesetdata', {
             b'noderange': [sorted(common), sorted(remoteheads)],
-            b'fields': {b'parents', b'revision'},
+            b'fields': {b'parents', b'phase', b'revision'},
         }).result()
 
         # The context manager waits on all response data when exiting. So
         # we need to remain in the context manager in order to stream data.
         return _processchangesetdata(repo, tr, objs)
 
 def _processchangesetdata(repo, tr, objs):
     repo.hook('prechangegroup', throw=True,
               **pycompat.strkwargs(tr.hookargs))
 
     urepo = repo.unfiltered()
     cl = urepo.changelog
 
     cl.delayupdate(tr)
 
     # The first emitted object is a header describing the data that
     # follows.
     meta = next(objs)
 
     progress = repo.ui.makeprogress(_('changesets'),
                                     unit=_('chunks'),
                                     total=meta.get(b'totalitems'))
 
     def linkrev(node):
         repo.ui.debug('add changeset %s\n' % short(node))
         # Linkrev for changelog is always self.
         return len(cl)
 
     def onchangeset(cl, node):
         progress.increment()
 
+    nodesbyphase = {phase: set() for phase in phases.phasenames}
+
     # addgroup() expects a 7-tuple describing revisions. This normalizes
     # the wire data to that format.
+    #
+    # This loop also aggregates non-revision metadata, such as phase
+    # data.
     def iterrevisions():
         for cset in objs:
-            assert b'revisionsize' in cset
+            node = cset[b'node']
+
+            if b'phase' in cset:
+                nodesbyphase[cset[b'phase']].add(node)
+
+            # Some entries might only be metadata only updates.
+            if b'revisionsize' not in cset:
+                continue
+
             data = next(objs)
 
             yield (
-                cset[b'node'],
+                node,
                 cset[b'parents'][0],
                 cset[b'parents'][1],
                 # Linknode is always itself for changesets.
                 cset[b'node'],
                 # We always send full revisions. So delta base is not set.
                 nullid,
                 mdiff.trivialdiffheader(len(data)) + data,
                 # Flags not yet supported.
                 0,
             )
 
     added = cl.addgroup(iterrevisions(), linkrev, weakref.proxy(tr),
                         addrevisioncb=onchangeset)
 
     progress.complete()
 
     return {
         'added': added,
+        'nodesbyphase': nodesbyphase,
     }

tests/test-wireproto-exchangev2.t

@@ -1,214 +1,277 b''
 Tests for wire protocol version 2 exchange.
 Tests in this file should be folded into existing tests once protocol
 v2 has enough features that it can be enabled via #testcase in existing
 tests.
 
   $ . $TESTDIR/wireprotohelpers.sh
   $ enablehttpv2client
 
   $ hg init server-simple
   $ enablehttpv2 server-simple
   $ cd server-simple
   $ cat >> .hg/hgrc << EOF
   > [phases]
   > publish = false
   > EOF
   $ echo a0 > a
   $ echo b0 > b
   $ hg -q commit -A -m 'commit 0'
 
   $ echo a1 > a
   $ hg commit -m 'commit 1'
   $ hg phase --public -r .
   $ echo a2 > a
   $ hg commit -m 'commit 2'
 
   $ hg -q up -r 0
   $ echo b1 > b
   $ hg -q commit -m 'head 2 commit 1'
   $ echo b2 > b
   $ hg -q commit -m 'head 2 commit 2'
 
   $ hg serve -p $HGPORT -d --pid-file hg.pid -E error.log
   $ cat hg.pid > $DAEMON_PIDS
 
   $ cd ..
 
 Test basic clone
 
   $ hg --debug clone -U http://localhost:$HGPORT client-simple
   using http://localhost:$HGPORT/
   sending capabilities command
   query 1; heads
   sending 2 commands
   sending command heads: {}
   sending command known: {
     'nodes': []
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
   received frame(size=43; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   received frame(size=11; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=1; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=3; stream=2; streamflags=; type=command-response; flags=eos)
   sending 1 commands
   sending command changesetdata: {
     'fields': set([
       'parents',
+      'phase',
       'revision'
     ]),
     'noderange': [
       [],
       [
         '\xca\xa2\xa4eE\x1d\xd1\xfa\xcd\xa0\xf5\xb1#\x12\xc3UXA\x88\xa1',
         '\xcd%4vk\xec\xe18\xc7\xc1\xaf\xdch%0/\x0fb\xd8\x1f'
       ]
     ]
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
-  received frame(size=809; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=871; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   add changeset 3390ef850073
   add changeset 4432d83626e8
   add changeset cd2534766bec
   add changeset e96ae20f4188
   add changeset caa2a465451d
   updating the branch cache
-  new changesets 3390ef850073:caa2a465451d
+  new changesets 3390ef850073:caa2a465451d (3 drafts)
 
 All changesets should have been transferred
 
   $ hg -R client-simple debugindex -c
      rev linkrev nodeid       p1           p2
        0       0 3390ef850073 000000000000 000000000000
        1       1 4432d83626e8 3390ef850073 000000000000
        2       2 cd2534766bec 4432d83626e8 000000000000
        3       3 e96ae20f4188 3390ef850073 000000000000
        4       4 caa2a465451d e96ae20f4188 000000000000
 
   $ hg -R client-simple log -G -T '{rev} {node} {phase}\n'
-  o  4 caa2a465451dd1facda0f5b12312c355584188a1 public
+  o  4 caa2a465451dd1facda0f5b12312c355584188a1 draft
   |
-  o  3 e96ae20f4188487b9ae4ef3941c27c81143146e5 public
+  o  3 e96ae20f4188487b9ae4ef3941c27c81143146e5 draft
   |
-  | o  2 cd2534766bece138c7c1afdc6825302f0f62d81f public
+  | o  2 cd2534766bece138c7c1afdc6825302f0f62d81f draft
   | |
   | o  1 4432d83626e8a98655f062ec1f2a43b07f7fbbb0 public
   |/
   o  0 3390ef850073fbc2f0dfff2244342c8e9229013a public
   
 
 Cloning only a specific revision works
 
   $ hg --debug clone -U -r 4432d83626e8 http://localhost:$HGPORT client-singlehead
   using http://localhost:$HGPORT/
   sending capabilities command
   sending 1 commands
   sending command lookup: {
     'key': '4432d83626e8'
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
   received frame(size=21; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   query 1; heads
   sending 2 commands
   sending command heads: {}
   sending command known: {
     'nodes': []
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
   received frame(size=43; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   received frame(size=11; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=1; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=3; stream=2; streamflags=; type=command-response; flags=eos)
   sending 1 commands
   sending command changesetdata: {
     'fields': set([
       'parents',
+      'phase',
       'revision'
     ]),
     'noderange': [
       [],
       [
         'D2\xd86&\xe8\xa9\x86U\xf0b\xec\x1f*C\xb0\x7f\x7f\xbb\xb0'
       ]
     ]
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
-  received frame(size=327; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=353; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   add changeset 3390ef850073
   add changeset 4432d83626e8
   updating the branch cache
   new changesets 3390ef850073:4432d83626e8
 
   $ cd client-singlehead
 
   $ hg log -G -T '{rev} {node} {phase}\n'
   o  1 4432d83626e8a98655f062ec1f2a43b07f7fbbb0 public
   |
   o  0 3390ef850073fbc2f0dfff2244342c8e9229013a public
   
 
 Incremental pull works
 
   $ hg --debug pull
   pulling from http://localhost:$HGPORT/
   using http://localhost:$HGPORT/
   sending capabilities command
   query 1; heads
   sending 2 commands
   sending command heads: {}
   sending command known: {
     'nodes': [
       'D2\xd86&\xe8\xa9\x86U\xf0b\xec\x1f*C\xb0\x7f\x7f\xbb\xb0'
     ]
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
   received frame(size=43; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   received frame(size=11; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=2; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=3; stream=2; streamflags=; type=command-response; flags=eos)
   searching for changes
   all local heads known remotely
   sending 1 commands
   sending command changesetdata: {
     'fields': set([
       'parents',
+      'phase',
       'revision'
     ]),
     'noderange': [
       [
         'D2\xd86&\xe8\xa9\x86U\xf0b\xec\x1f*C\xb0\x7f\x7f\xbb\xb0'
       ],
       [
         '\xca\xa2\xa4eE\x1d\xd1\xfa\xcd\xa0\xf5\xb1#\x12\xc3UXA\x88\xa1',
         '\xcd%4vk\xec\xe18\xc7\xc1\xaf\xdch%0/\x0fb\xd8\x1f'
       ]
     ]
   }
   received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
-  received frame(size=495; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=571; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
   received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
   add changeset cd2534766bec
   add changeset e96ae20f4188
   add changeset caa2a465451d
   updating the branch cache
-  new changesets cd2534766bec:caa2a465451d
+  new changesets cd2534766bec:caa2a465451d (3 drafts)
+  (run 'hg update' to get a working copy)
+
+  $ hg log -G -T '{rev} {node} {phase}\n'
+  o  4 caa2a465451dd1facda0f5b12312c355584188a1 draft
+  |
+  o  3 e96ae20f4188487b9ae4ef3941c27c81143146e5 draft
+  |
+  | o  2 cd2534766bece138c7c1afdc6825302f0f62d81f draft
+  | |
+  | o  1 4432d83626e8a98655f062ec1f2a43b07f7fbbb0 public
+  |/
+  o  0 3390ef850073fbc2f0dfff2244342c8e9229013a public
+  
+
+Phase-only update works
+
+  $ hg -R ../server-simple phase --public -r caa2a465451dd
+  $ hg --debug pull
+  pulling from http://localhost:$HGPORT/
+  using http://localhost:$HGPORT/
+  sending capabilities command
+  query 1; heads
+  sending 2 commands
+  sending command heads: {}
+  sending command known: {
+    'nodes': [
+      '\xcd%4vk\xec\xe18\xc7\xc1\xaf\xdch%0/\x0fb\xd8\x1f',
+      '\xca\xa2\xa4eE\x1d\xd1\xfa\xcd\xa0\xf5\xb1#\x12\xc3UXA\x88\xa1'
+    ]
+  }
+  received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
+  received frame(size=43; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
+  received frame(size=11; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=3; request=3; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=0; request=3; stream=2; streamflags=; type=command-response; flags=eos)
+  searching for changes
+  all remote heads known locally
+  sending 1 commands
+  sending command changesetdata: {
+    'fields': set([
+      'parents',
+      'phase',
+      'revision'
+    ]),
+    'noderange': [
+      [
+        '\xca\xa2\xa4eE\x1d\xd1\xfa\xcd\xa0\xf5\xb1#\x12\xc3UXA\x88\xa1',
+        '\xcd%4vk\xec\xe18\xc7\xc1\xaf\xdch%0/\x0fb\xd8\x1f'
+      ],
+      [
+        '\xca\xa2\xa4eE\x1d\xd1\xfa\xcd\xa0\xf5\xb1#\x12\xc3UXA\x88\xa1',
+        '\xcd%4vk\xec\xe18\xc7\xc1\xaf\xdch%0/\x0fb\xd8\x1f'
+      ]
+    ]
+  }
+  received frame(size=11; request=1; stream=2; streamflags=stream-begin; type=command-response; flags=continuation)
+  received frame(size=92; request=1; stream=2; streamflags=; type=command-response; flags=continuation)
+  received frame(size=0; request=1; stream=2; streamflags=; type=command-response; flags=eos)
+  2 local changesets published
   (run 'hg update' to get a working copy)
 
   $ hg log -G -T '{rev} {node} {phase}\n'
   o  4 caa2a465451dd1facda0f5b12312c355584188a1 public
   |
   o  3 e96ae20f4188487b9ae4ef3941c27c81143146e5 public
   |
-  | o  2 cd2534766bece138c7c1afdc6825302f0f62d81f public
+  | o  2 cd2534766bece138c7c1afdc6825302f0f62d81f draft
   | |
   | o  1 4432d83626e8a98655f062ec1f2a43b07f7fbbb0 public
   |/
   o  0 3390ef850073fbc2f0dfff2244342c8e9229013a public
   
 
   $ cd ..