sync: superproject - support for switching hosts and switching branches.

+ superproject will be fetched into a directory with the name
  “<remote name>-superproject.git” instead of the current
  “superproject.git” folder.

+ Deleted  _Clone method and added _Init method.

+ _Init method will do “git init --bare <remote>-superproject.git”.
  It will create the folder and set up a bare repository in
  <remote>-superproject.git folder.

+ _Fetch method, will pass <remote url>, <branch> arguments.
  Moved the --filter argument from “git clone” to “git fetch”.
  _Fetch method will execute the following command to fetch
  superproject. Added --no-tags argument.

  master:  git fetch <remote url> --force --no-tags --filter blob:none
  branch:  git fetch <remote url> --force --no-tags --filter blob:none \
           <branch>:<branch>

+ Performance improvements for aosp-master
  ++ repo init performance improved from 35 seconds to 17 seconds.
  ++ repo init --use-superproject is around 5 to 7 secsonds slower.
  ++ repo sync --use-superproject is around 3 to 4 minutes faster.

Tested the code with the following commands.

$ ./run_tests -v

Tested the sync code by using repo_dev alias and pointing to this CL.

$ time repo_dev init -u sso://android.git.corp.google.com/platform/manifest -b master --partial-clone --clone-filter=blob:limit=10M --repo-rev=main --use-superproject
...
  real	0m20.648s
  user	0m8.046s
  sys	0m3.271s

+ Without superproject
$ time repo init -u sso://android.git.corp.google.com/platform/manifest -b master --partial-clone --clone-filter=blob:limit=10M --repo-rev=main
  real	0m13.078s
  user	0m9.783s
  sys	0m2.528s

$ time repo_dev sync -c -j32 --use-superproject
...
  real	15m7.072s
  user	110m7.216s
  sys	20m17.559s

+ Without superproject
$ time repo sync -c -j32
...
  real	19m25.644s
  user	91m56.331s
  sys	20m59.170s

Bug: [google internal] b/180492484
Bug: [google internal] b/179470886
Bug: [google internal] b/180124069
Bug: https://crbug.com/gerrit/13709
Bug: https://crbug.com/gerrit/13707

Change-Id: Ib04bd7f1e25ceb75532643e58ad0129300ba3299
Reviewed-on: https://gerrit-review.googlesource.com/c/git-repo/+/297702
Reviewed-by: Mike Frysinger <vapier@google.com>
Tested-by: Raman Tenneti <rtenneti@google.com>

1 files changed, 32 insertions, 38 deletions

diff --git a/git_superproject.py b/git_superproject.py
index 471dadc4..a09edc15 100644
--- a/git_superproject.py
+++ b/git_superproject.py
@@ -22,13 +22,13 @@ Examples:
   project_commit_ids = superproject.UpdateProjectsRevisionId(projects)
 """
 
+import hashlib
 import os
 import sys
 
 from error import BUG_REPORT_URL
 from git_command import GitCommand
 from git_refs import R_HEADS
-import platform_utils
 
 _SUPERPROJECT_GIT_NAME = 'superproject.git'
 _SUPERPROJECT_MANIFEST_NAME = 'superproject_override.xml'
@@ -37,9 +37,9 @@ _SUPERPROJECT_MANIFEST_NAME = 'superproject_override.xml'
 class Superproject(object):
   """Get commit ids from superproject.
 
-  It does a 'git clone' of superproject and 'git ls-tree' to get list of commit ids
-  for all projects. It contains project_commit_ids which is a dictionary with
-  project/commit id entries.
+  Initializes a local copy of a superproject for the manifest. This allows
+  lookup of commit ids for all projects. It contains _project_commit_ids which
+  is a dictionary with project/commit id entries.
   """
   def __init__(self, manifest, repodir, superproject_dir='exp-superproject'):
     """Initializes superproject.
@@ -58,8 +58,12 @@ class Superproject(object):
     self._superproject_path = os.path.join(self._repodir, superproject_dir)
     self._manifest_path = os.path.join(self._superproject_path,
                                        _SUPERPROJECT_MANIFEST_NAME)
-    self._work_git = os.path.join(self._superproject_path,
-                                  _SUPERPROJECT_GIT_NAME)
+    git_name = ''
+    if self._manifest.superproject:
+      remote_name = self._manifest.superproject['remote'].name
+      git_name = hashlib.md5(remote_name.encode('utf8')).hexdigest() + '-'
+    self._work_git_name = git_name + _SUPERPROJECT_GIT_NAME
+    self._work_git = os.path.join(self._superproject_path, self._work_git_name)
 
   @property
   def project_commit_ids(self):
@@ -77,20 +81,15 @@ class Superproject(object):
       branch = branch[len(R_HEADS):]
     return branch
 
-  def _Clone(self, url):
-    """Do a 'git clone' for the given url.
-
-    Args:
-      url: superproject's url to be passed to git clone.
+  def _Init(self):
+    """Sets up a local Git repository to get a copy of a superproject.
 
     Returns:
-      True if git clone is successful, or False.
+      True if initialization is successful, or False.
     """
     if not os.path.exists(self._superproject_path):
       os.mkdir(self._superproject_path)
-    cmd = ['clone', url, '--filter', 'blob:none', '--bare']
-    if self._branch:
-      cmd += ['--branch', self._branch]
+    cmd = ['init', '--bare', self._work_git_name]
     p = GitCommand(None,
                    cmd,
                    cwd=self._superproject_path,
@@ -98,24 +97,27 @@ class Superproject(object):
                    capture_stderr=True)
     retval = p.Wait()
     if retval:
-      # `git clone` is documented to produce an exit status of `128` if
-      # the requested url or branch are not present in the configuration.
-      print('repo: error: git clone call failed with return code: %r, stderr: %r' %
+      print('repo: error: git init call failed with return code: %r, stderr: %r' %
             (retval, p.stderr), file=sys.stderr)
       return False
     return True
 
-  def _Fetch(self):
-    """Do a 'git fetch' to to fetch the latest content.
+  def _Fetch(self, url):
+    """Fetches a local copy of a superproject for the manifest based on url.
+
+    Args:
+      url: superproject's url.
 
     Returns:
-      True if 'git fetch' is successful, or False.
+      True if fetch is successful, or False.
     """
     if not os.path.exists(self._work_git):
       print('git fetch missing drectory: %s' % self._work_git,
             file=sys.stderr)
       return False
-    cmd = ['fetch', 'origin', '+refs/heads/*:refs/heads/*', '--prune']
+    cmd = ['fetch', url, '--force', '--no-tags', '--filter', 'blob:none']
+    if self._branch:
+      cmd += [self._branch + ':' + self._branch]
     p = GitCommand(None,
                    cmd,
                    cwd=self._work_git,
@@ -129,7 +131,7 @@ class Superproject(object):
     return True
 
   def _LsTree(self):
-    """Returns the data from 'git ls-tree ...'.
+    """Gets the commit ids for all projects.
 
     Works only in git repositories.
 
@@ -153,14 +155,12 @@ class Superproject(object):
     if retval == 0:
       data = p.stdout
     else:
-      # `git clone` is documented to produce an exit status of `128` if
-      # the requested url or branch are not present in the configuration.
       print('repo: error: git ls-tree call failed with return code: %r, stderr: %r' % (
           retval, p.stderr), file=sys.stderr)
     return data
 
   def Sync(self):
-    """Sync superproject either by git clone/fetch.
+    """Gets a local copy of a superproject for the manifest.
 
     Returns:
       True if sync of superproject is successful, or False.
@@ -179,17 +179,10 @@ class Superproject(object):
             file=sys.stderr)
       return False
 
-    do_clone = True
-    if os.path.exists(self._superproject_path):
-      if not self._Fetch():
-        # If fetch fails due to a corrupted git directory, then do a git clone.
-        platform_utils.rmtree(self._superproject_path)
-      else:
-        do_clone = False
-    if do_clone:
-      if not self._Clone(url):
-        print('error: git clone failed for url: %s' % url, file=sys.stderr)
-        return False
+    if not self._Init():
+      return False
+    if not self._Fetch(url):
+      return False
     return True
 
   def _GetAllProjectsCommitIds(self):
@@ -203,7 +196,8 @@ class Superproject(object):
 
     data = self._LsTree()
     if not data:
-      print('error: git ls-tree failed for superproject', file=sys.stderr)
+      print('error: git ls-tree failed to return data for superproject',
+            file=sys.stderr)
       return None
 
     # Parse lines like the following to select lines starting with '160000' and