From 6a2a7d99f7cdf22eda7b2832e64557f7715d20e3 Mon Sep 17 00:00:00 2001
From: Christian Kellner <christian@kellner.me>
Date: Tue, 18 Feb 2020 09:57:00 +0100
Subject: [PATCH] objectstore: unify commit and snapshot code paths

As a result of the previous commits that implement copy on write
semantics, `commit` can now be used to create snapshots. Whenever
an Object is committed, its tree is moved to the store and it is
being reset, i.e. a new clean workdir is created and the old one
discarded. The moved tree is then set as the base of the reset
Object. On the next call to `write` the moved tree will be copied
over and forms the basis of the Object again. Should nobody want
to write to Object after the snapshot, i.e. the `commit`, no copy
will be made.
NB: snapshots/commits will act now act as synchronization points:
if a object with the same treesum, i.e. the very same content
already exists, the move (i.e. `store_tree`) will gracefully fail
and the existing content will be set as the base for Object.
---
 osbuild/objectstore.py   | 27 +++++++++------------------
 osbuild/pipeline.py      |  2 +-
 test/test_objectstore.py |  2 +-
 3 files changed, 11 insertions(+), 20 deletions(-)

diff --git a/osbuild/objectstore.py b/osbuild/objectstore.py
index d760ce00..b70e4ce5 100644
--- a/osbuild/objectstore.py
+++ b/osbuild/objectstore.py
@@ -188,24 +188,6 @@ class ObjectStore:
             # left to do is to commit it to the object store
             self.commit(obj, object_id)
 
-    def snapshot(self, obj: str, object_id: str) -> str:
-        """Commit `obj` to store and ref it as `object_id`
-
-        Create a snapshot of the object `obj` and store it via
-        its content hash in the object directory; additionally
-        create a new reference to it via `object_id` in the
-        reference directory.
-
-        Returns: The treesum of the snapshot
-        """
-        # Make a new temporary directory and Object; initialize
-        # the latter with the contents of `obj.path` and commit
-        # it to the store
-        with Object(self) as tmp:
-            tmp.base_path = obj.path
-            tmp.init()
-            return self.commit(tmp, object_id)
-
     def commit(self, obj: Object, object_id: str) -> str:
         """Commits a Object to the object store
 
@@ -235,4 +217,13 @@ class ObjectStore:
             os.symlink(f"../objects/{treesum_hash}", link)
             os.replace(link, self.resolve_ref(object_id))
 
+        # the reference that is pointing to `treesum_hash` is now the base
+        # of `obj`. It is not actively initialized but any subsequent calls
+        # to `obj.write()` or `obj.path`will initialize it again
+        # NB: in the case that an object with the same treesum as `obj`
+        # already existed in the store obj.store_tree() will not actually
+        # have written anything to the store. In this case `obj` will then
+        # be initialized with the content of the already existing object.
+        obj.base_path = self.resolve_ref(object_id)
+
         return treesum_hash
diff --git a/osbuild/pipeline.py b/osbuild/pipeline.py
index 8071fac6..067d1abf 100644
--- a/osbuild/pipeline.py
+++ b/osbuild/pipeline.py
@@ -281,7 +281,7 @@ class Pipeline:
                                               var=store,
                                               secrets=secrets)
                                 if stage.checkpoint:
-                                    object_store.snapshot(tree, stage.id)
+                                    object_store.commit(tree, stage.id)
                                 results["stages"].append(r.as_dict())
                     except BuildError as err:
                         results["stages"].append(err.as_dict())
diff --git a/test/test_objectstore.py b/test/test_objectstore.py
index c33e4fbc..0ab585b1 100644
--- a/test/test_objectstore.py
+++ b/test/test_objectstore.py
@@ -77,7 +77,7 @@ class TestObjectStore(unittest.TestCase):
             path = tree.write()
             p = Path(f"{path}/A")
             p.touch()
-            object_store.snapshot(tree, "a")
+            object_store.commit(tree, "a")
             path = tree.write()
             p = Path(f"{path}/B")
             p.touch()