sync: superproject performance changes.

After updating all project’s revsionIds with the SHAs from superproject,
write the updated manifest into superproject_override.xml file. Reload
that file for future Reloads. This file is created in exp-superproject
directory.

Moved most of the code that is superproject specific into
git_superproject.py and wrote test code.

If git pull fails, did a git clone of the superproject.

We saw performance gains for consecutive repo sync's. The time to sync
went down from around 120 secs to 40 secs when repo sync is executed
consecutively.

Tested the code with the following commands.

$ ./run_tests -v tests/test_git_superproject.py
$ ./run_tests -v

Tested the sync code by copying all the repo changes into my Android
AOSP checkout and doing a repo sync --use-superproject twice.

First run
$ time repo sync --use-superproject
...
real	21m3.745s
user	97m59.380s
sys	19m11.286s

After two consecutive sync runs
$ time repo sync -c -j8 --use-superproject
real	0m39.626s
user	0m29.937s
sys	0m38.155s

Bug: https://crbug.com/gerrit/13709
Bug: https://crbug.com/gerrit/13707
Tested-by: Raman Tenneti <rtenneti@google.com>

Change-Id: Id79a0d7c4d20babd65e9bd485196c6f8fbe9de5e
Reviewed-on: https://gerrit-review.googlesource.com/c/git-repo/+/296082
Reviewed-by: Ian Kasprzak <iankaz@google.com>
Tested-by: Raman Tenneti <rtenneti@google.com>

1 files changed, 45 insertions, 36 deletions

diff --git a/subcmds/sync.py b/subcmds/sync.py
index 225e565a..c0f605a8 100644
--- a/subcmds/sync.py
+++ b/subcmds/sync.py
@@ -56,7 +56,7 @@ import gitc_utils
 from project import Project
 from project import RemoteSpec
 from command import Command, MirrorSafeCommand
-from error import BUG_REPORT_URL, RepoChangedException, GitError, ManifestParseError
+from error import RepoChangedException, GitError, ManifestParseError
 import platform_utils
 from project import SyncBuffer
 from progress import Progress
@@ -271,6 +271,47 @@ later is required to fix a server side protocol bug.
                  dest='repo_upgraded', action='store_true',
                  help=SUPPRESS_HELP)
 
+  def _UpdateProjectsRevisionId(self, opt, args):
+    """Update revisionId of every project with the SHA from superproject.
+
+    This function updates each project's revisionId with SHA from superproject.
+    It writes the updated manifest into a file and reloads the manifest from it.
+
+    Args:
+      opt: Program options returned from optparse.  See _Options().
+      args: Arguments to pass to GetProjects. See the GetProjects
+          docstring for details.
+
+    Returns:
+      Returns path to the overriding manifest file.
+    """
+    if not self.manifest.superproject:
+      print('error: superproject tag is not defined in manifest.xml',
+            file=sys.stderr)
+      sys.exit(1)
+    print('WARNING: --use-superproject is experimental and not '
+          'for general use', file=sys.stderr)
+
+    superproject_url = self.manifest.superproject['remote'].url
+    if not superproject_url:
+      print('error: superproject URL is not defined in manifest.xml',
+            file=sys.stderr)
+      sys.exit(1)
+
+    superproject = git_superproject.Superproject(self.manifest.repodir)
+    all_projects = self.GetProjects(args,
+                                    missing_ok=True,
+                                    submodules_ok=opt.fetch_submodules)
+    manifest_path = superproject.UpdateProjectsRevisionId(self.manifest,
+                                                          all_projects,
+                                                          url=superproject_url)
+    if not manifest_path:
+      print('error: Update of revsionId from superproject has failed',
+            file=sys.stderr)
+      sys.exit(1)
+    self._ReloadManifest(manifest_path)
+    return manifest_path
+
   def _FetchProjectList(self, opt, projects, sem, *args, **kwargs):
     """Main function of the fetch threads.
 
@@ -859,6 +900,9 @@ later is required to fix a server side protocol bug.
     else:
       self._UpdateManifestProject(opt, mp, manifest_name)
 
+    if opt.use_superproject:
+      manifest_name = self._UpdateProjectsRevisionId(opt, args)
+
     if self.gitc_manifest:
       gitc_manifest_projects = self.GetProjects(args,
                                                 missing_ok=True)
@@ -898,41 +942,6 @@ later is required to fix a server side protocol bug.
                                     missing_ok=True,
                                     submodules_ok=opt.fetch_submodules)
 
-    if opt.use_superproject:
-      if not self.manifest.superproject:
-        print('error: superproject tag is not defined in manifest.xml',
-              file=sys.stderr)
-        sys.exit(1)
-      print('WARNING: --use-superproject is experimental and not '
-            'for general use', file=sys.stderr)
-      superproject_url = self.manifest.superproject['remote'].url
-      if not superproject_url:
-        print('error: superproject URL is not defined in manifest.xml',
-              file=sys.stderr)
-        sys.exit(1)
-      superproject = git_superproject.Superproject(self.manifest.repodir)
-      try:
-        superproject_shas = superproject.GetAllProjectsSHAs(url=superproject_url)
-      except Exception as e:
-        print('error: Cannot get project SHAs for %s: %s: %s' %
-              (superproject_url, type(e).__name__, str(e)),
-              file=sys.stderr)
-        sys.exit(1)
-      projects_missing_shas = []
-      for project in all_projects:
-        path = project.relpath
-        if not path:
-          continue
-        sha = superproject_shas.get(path)
-        if sha:
-          project.SetRevisionId(sha)
-        else:
-          projects_missing_shas.append(path)
-      if projects_missing_shas:
-        print('error: please file a bug using %s to report missing shas for: %s' %
-              (BUG_REPORT_URL, projects_missing_shas), file=sys.stderr)
-        sys.exit(1)
-
     err_network_sync = False
     err_update_projects = False
     err_checkout = False