diff mercurial/discovery.py @ 14164:cb98fed52495

discovery: add new set-based discovery Adds a new discovery method based on repeatedly sampling the still undecided subset of the local node graph to determine the set of nodes common to both the client and the server. For small differences between client and server, it uses about the same or slightly fewer roundtrips than the old tree-based discovery. For larger differences, it typically reduces the number of roundtrips drastically (from 150 to 4, for instance). The old discovery code now lives in treediscovery.py, the new code is in setdiscovery.py. Still missing is a hook for extensions to contribute nodes to the initial sample. For instance, Augie's remotebranches could contribute the last known state of the server's heads. Credits for the actual sampler and computing common heads instead of bases go to Benoit Boissinot.
author Peter Arrenbrecht <peter.arrenbrecht@gmail.com>
date Mon, 02 May 2011 19:21:30 +0200
parents 72c84f24b420
children 4ab6e2d597cc
line wrap: on
line diff
--- a/mercurial/discovery.py	Mon May 02 19:21:30 2011 +0200
+++ b/mercurial/discovery.py	Mon May 02 19:21:30 2011 +0200
@@ -7,7 +7,7 @@
 
 from node import nullid, short
 from i18n import _
-import util, error
+import util, error, setdiscovery, treediscovery
 
 def findcommonincoming(repo, remote, heads=None, force=False):
     """Return a tuple (common, anyincoming, heads) used to identify the common
@@ -20,145 +20,28 @@
       changegroupsubset. No code except for pull should be relying on this fact
       any longer.
     "heads" is either the supplied heads, or else the remote's heads.
+
+    If you pass heads and they are all known locally, the reponse lists justs
+    these heads in "common" and in "heads".
     """
 
-    m = repo.changelog.nodemap
-    search = []
-    fetch = set()
-    seen = set()
-    seenbranch = set()
-    base = set()
-
-    if not heads:
-        heads = remote.heads()
-
-    if repo.changelog.tip() == nullid:
-        base.add(nullid)
-        if heads != [nullid]:
-            return [nullid], [nullid], list(heads)
-        return [nullid], [], []
-
-    # assume we're closer to the tip than the root
-    # and start by examining the heads
-    repo.ui.status(_("searching for changes\n"))
-
-    if remote.capable('getbundle'):
-        myheads = repo.heads()
-        known = remote.known(myheads)
-        if util.all(known):
-            hasincoming = set(heads).difference(set(myheads)) and True
-            return myheads, hasincoming, heads
-
-    unknown = []
-    for h in heads:
-        if h not in m:
-            unknown.append(h)
-        else:
-            base.add(h)
-
-    heads = unknown
-    if not unknown:
-        return list(base), [], []
-
-    req = set(unknown)
-    reqcnt = 0
-
-    # search through remote branches
-    # a 'branch' here is a linear segment of history, with four parts:
-    # head, root, first parent, second parent
-    # (a branch always has two parents (or none) by definition)
-    unknown = remote.branches(unknown)
-    while unknown:
-        r = []
-        while unknown:
-            n = unknown.pop(0)
-            if n[0] in seen:
-                continue
+    if not remote.capable('getbundle'):
+        return treediscovery.findcommonincoming(repo, remote, heads, force)
 
-            repo.ui.debug("examining %s:%s\n"
-                          % (short(n[0]), short(n[1])))
-            if n[0] == nullid: # found the end of the branch
-                pass
-            elif n in seenbranch:
-                repo.ui.debug("branch already found\n")
-                continue
-            elif n[1] and n[1] in m: # do we know the base?
-                repo.ui.debug("found incomplete branch %s:%s\n"
-                              % (short(n[0]), short(n[1])))
-                search.append(n[0:2]) # schedule branch range for scanning
-                seenbranch.add(n)
-            else:
-                if n[1] not in seen and n[1] not in fetch:
-                    if n[2] in m and n[3] in m:
-                        repo.ui.debug("found new changeset %s\n" %
-                                      short(n[1]))
-                        fetch.add(n[1]) # earliest unknown
-                    for p in n[2:4]:
-                        if p in m:
-                            base.add(p) # latest known
-
-                for p in n[2:4]:
-                    if p not in req and p not in m:
-                        r.append(p)
-                        req.add(p)
-            seen.add(n[0])
-
-        if r:
-            reqcnt += 1
-            repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
-            repo.ui.debug("request %d: %s\n" %
-                        (reqcnt, " ".join(map(short, r))))
-            for p in xrange(0, len(r), 10):
-                for b in remote.branches(r[p:p + 10]):
-                    repo.ui.debug("received %s:%s\n" %
-                                  (short(b[0]), short(b[1])))
-                    unknown.append(b)
+    if heads:
+        allknown = True
+        nm = repo.changelog.nodemap
+        for h in heads:
+            if nm.get(h) is None:
+                allknown = False
+                break
+        if allknown:
+            return (heads, False, heads)
 
-    # do binary search on the branches we found
-    while search:
-        newsearch = []
-        reqcnt += 1
-        repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
-        for n, l in zip(search, remote.between(search)):
-            l.append(n[1])
-            p = n[0]
-            f = 1
-            for i in l:
-                repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
-                if i in m:
-                    if f <= 2:
-                        repo.ui.debug("found new branch changeset %s\n" %
-                                          short(p))
-                        fetch.add(p)
-                        base.add(i)
-                    else:
-                        repo.ui.debug("narrowed branch search to %s:%s\n"
-                                      % (short(p), short(i)))
-                        newsearch.append((p, i))
-                    break
-                p, f = i, f * 2
-            search = newsearch
-
-    # sanity check our fetch list
-    for f in fetch:
-        if f in m:
-            raise error.RepoError(_("already have changeset ")
-                                  + short(f[:4]))
-
-    base = list(base)
-    if base == [nullid]:
-        if force:
-            repo.ui.warn(_("warning: repository is unrelated\n"))
-        else:
-            raise util.Abort(_("repository is unrelated"))
-
-    repo.ui.debug("found new changesets starting at " +
-                 " ".join([short(f) for f in fetch]) + "\n")
-
-    repo.ui.progress(_('searching'), None)
-    repo.ui.debug("%d total queries\n" % reqcnt)
-
-    return base, list(fetch), heads
+    res = setdiscovery.findcommonheads(repo.ui, repo, remote,
+                                       abortwhenunrelated=not force)
+    common, anyinc, srvheads = res
+    return (list(common), anyinc, heads or list(srvheads))
 
 def prepush(repo, remote, force, revs, newbranch):
     '''Analyze the local and remote repositories and determine which
@@ -174,9 +57,7 @@
     changegroup is a readable file-like object whose read() returns
     successive changegroup chunks ready to be sent over the wire and
     remoteheads is the list of remote heads.'''
-    remoteheads = remote.heads()
-    common, inc, _rheads = findcommonincoming(repo, remote, heads=remoteheads,
-                                              force=force)
+    common, inc, remoteheads = findcommonincoming(repo, remote, force=force)
 
     cl = repo.changelog
     outg = cl.findmissing(common, revs)