clone: disable pull during hgsql streaming clones

Summary:
hgsql depends on repositories being byte for byte identical, but the
current pull after a streaming clone can cause the repository to be different
(like if different delta decisions were made, or the commits were ordered
slightly differently). Let's disable that pull when the repository is an hgsql
repo.

Reviewed By: ryanmce

Differential Revision: D7925300

fbshipit-source-id: 6eba7ad4ccdd37f6d7c5090522867d1a54f722b7

hgext/hgsql.py

@@ -121,6 +121,7 @@ def uisetup(ui):
 
     wrapcommand(commands.table, 'bookmark', bookmarkcommand)
     wrapfunction(exchange, '_localphasemove', _localphasemove)
+    wrapfunction(exchange.pulloperation, '__init__', pullop_init)
     wrapfunction(exchange, 'push', push)
 
     # Enable SQL for remote commands that write to the repository
@@ -252,6 +253,11 @@ def pull(orig, *args, **kwargs):
     else:
         return orig(*args, **kwargs)
 
+def pullop_init(orig, self, repo, *args, **kwargs):
+    if issqlrepo(repo) or 'hgsql' in repo.requirements:
+        kwargs['exactbyteclone'] = True
+    return orig(self, repo, *args, **kwargs)
+
 def push(orig, *args, **kwargs):
     repo = args[0]
     if issqlrepo(repo):

mercurial/exchange.py

@@ -1194,7 +1194,8 @@ class pulloperation(object):
     """
 
     def __init__(self, repo, remote, heads=None, force=False, bookmarks=(),
-                 remotebookmarks=None, streamclonerequested=None):
+                 remotebookmarks=None, streamclonerequested=None,
+                 exactbyteclone=False):
         # repo we pull into
         self.repo = repo
         # repo we pull from
@@ -1224,6 +1225,9 @@ class pulloperation(object):
         self.stepsdone = set()
         # Whether we attempted a clone from pre-generated bundles.
         self.clonebundleattempted = False
+        # Whether clones should do an exact byte clone. This is used for hgsql
+        # to avoid the extra semantic pull after a streaming clone.
+        self.exactbyteclone = exactbyteclone
 
     @util.propertycache
     def pulledsubset(self):
@@ -1336,14 +1340,19 @@ def pull(repo, remote, heads=None, force=False, bookmarks=(), opargs=None,
         # This should ideally be in _pullbundle2(). However, it needs to run
         # before discovery to avoid extra work.
         _maybeapplyclonebundle(pullop)
-        streamclone.maybeperformlegacystreamclone(pullop)
-        _pulldiscovery(pullop)
-        if pullop.canusebundle2:
-            _pullbundle2(pullop)
-        _pullchangeset(pullop)
-        _pullphase(pullop)
-        _pullbookmarks(pullop)
-        _pullobsolete(pullop)
+        cloned = streamclone.maybeperformlegacystreamclone(pullop)
+
+        # hgsql needs byte-for-byte identical clones, so let's skip the semantic
+        # pull stage since it can result in different bytes (different deltas,
+        # etc).
+        if not (cloned and pullop.exactbyteclone):
+            _pulldiscovery(pullop)
+            if pullop.canusebundle2:
+                _pullbundle2(pullop)
+            _pullchangeset(pullop)
+            _pullphase(pullop)
+            _pullbookmarks(pullop)
+            _pullobsolete(pullop)
         pullop.trmanager.close()
     finally:
         lockmod.release(pullop.trmanager, lock, wlock)

mercurial/streamclone.py

@@ -115,11 +115,13 @@ def maybeperformlegacystreamclone(pullop):
 
     A legacy stream clone will not be performed if a bundle2 stream clone is
     supported.
+
+    Returns True if a clone was performed.
     """
     supported, requirements = canperformstreamclone(pullop)
 
     if not supported:
-        return
+        return False
 
     repo = pullop.repo
     remote = pullop.remote
@@ -169,6 +171,8 @@ def maybeperformlegacystreamclone(pullop):
 
         repo.invalidate()
 
+    return True
+
 def allowservergeneration(repo):
     """Whether streaming clones are allowed from the server."""
     if not repo.ui.configbool('server', 'uncompressed', untrusted=True):

tests/test-hgsql-requires.t

@@ -41,3 +41,10 @@ Ensure streaming clones to non-hgsql repos work
   $ hg clone --config extensions.hgsql=! --config ui.ssh='python "$TESTDIR/dummyssh"' --uncompressed ssh://user@dummy/master client2 | grep "streaming all changes"
   streaming all changes
 
+Ensure streaming clones to hgsql repos work
+  $ hg clone --config extensions.hgsql= --config ui.ssh='python "$TESTDIR/dummyssh"' --uncompressed ssh://user@dummy/master client3
+  streaming all changes
+  3 files to transfer, 294 bytes of data
+  transferred 294 bytes in * seconds (*) (glob)
+  updating to branch default
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved