diff mercurial/exchange.py @ 26644:74de1c59f71c

clonebundles: filter on bundle specification

Not all clients are capable of reading every bundle. Currently, content
negotiation to ensure a server sends a client a compatible bundle
format is performed at request time. The response bundle is dynamically
generated at request time, so this works fine.

Clone bundles are statically generated *before* the request. This means
that a modern server could produce bundles that a legacy client isn't
capable of reading. Without some kind of "type hint" in the clone
bundles manifest, a client may attempt to download an incompatible
bundle. Furthermore, a client may not realize a bundle is incompatible
until it has processed part of the bundle (imagine consuming a 1 GB
changegroup bundle2 part only to discover the bundle2 part afterwards is
incompatibl). This would waste time and resources. And it isn't very
user friendly.

Clone bundle manifests thus need to advertise the *exact* format of the
hosted bundles so clients may filter out entries that they don't know
how to read. This patch introduces that mechanism.

We introduce the BUNDLESPEC attribute to declare the "bundle
specification" of the entry. Bundle specifications are parsed using
exchange.parsebundlespecification, which uses the same strings as the
"--type" argument to `hg bundle`. The supported bundle specifications
are well defined and backwards compatible.

When a client encounters a BUNDLESPEC that is invalid or unsupported, it
silently ignores the entry.

--- a/mercurial/exchange.py	Tue Oct 13 10:41:54 2015 -0700
+++ b/mercurial/exchange.py	Tue Oct 13 11:45:30 2015 -0700
@@ -1599,15 +1599,26 @@
 
     res = remote._call('clonebundles')
     entries = parseclonebundlesmanifest(res)
-
-    # TODO filter entries by supported features.
-    # TODO sort entries by user preferences.
-
     if not entries:
         repo.ui.note(_('no clone bundles available on remote; '
                        'falling back to regular clone\n'))
         return
 
+    entries = filterclonebundleentries(repo, entries)
+    if not entries:
+        # There is a thundering herd concern here. However, if a server
+        # operator doesn't advertise bundles appropriate for its clients,
+        # they deserve what's coming. Furthermore, from a client's
+        # perspective, no automatic fallback would mean not being able to
+        # clone!
+        repo.ui.warn(_('no compatible clone bundles available on server; '
+                       'falling back to regular clone\n'))
+        repo.ui.warn(_('(you may want to report this to the server '
+                       'operator)\n'))
+        return
+
+    # TODO sort entries by user preferences.
+
     url = entries[0]['URL']
     repo.ui.status(_('applying clone bundle from %s\n') % url)
     if trypullbundlefromurl(repo.ui, repo, url):
@@ -1644,6 +1655,25 @@
 
     return m
 
+def filterclonebundleentries(repo, entries):
+    newentries = []
+    for entry in entries:
+        spec = entry.get('BUNDLESPEC')
+        if spec:
+            try:
+                parsebundlespec(repo, spec, strict=True)
+            except error.InvalidBundleSpecification as e:
+                repo.ui.debug(str(e) + '\n')
+                continue
+            except error.UnsupportedBundleSpecification as e:
+                repo.ui.debug('filtering %s because unsupported bundle '
+                              'spec: %s\n' % (entry['URL'], str(e)))
+                continue
+
+        newentries.append(entry)
+
+    return newentries
+
 def trypullbundlefromurl(ui, repo, url):
     """Attempt to apply a bundle from a URL."""
     lock = repo.lock()