use InodeCache when dropping a key to see if a pointer file can be safely reset

The Keys database can hold multiple inode caches for a given key. One for
the annex object, and one for each pointer file, which may not be hard
linked to it.

Inode caches for a key are recorded when its content is added to the annex,
but only if it has known pointer files. This is to avoid the overhead of
maintaining the database when not needed.

When the smudge filter outputs a file's content, the inode cache is not
updated, because git's smudge interface doesn't let us write the file. So,
dropping will fall back to doing an expensive verification then. Ideally,
git's interface would be improved, and then the inode cache could be
updated then too.

Annex/Action.hs

@@ -17,6 +17,7 @@ import System.Posix.Signals
 import Common.Annex
 import qualified Annex
 import Annex.Content
+import qualified Database.Keys
 
 {- Actions to perform each time ran. -}
 startup :: Annex ()
@@ -32,4 +33,5 @@ shutdown :: Bool -> Annex ()
 shutdown nocommit = do
 	saveState nocommit
 	sequence_ =<< M.elems <$> Annex.getState Annex.cleanup
+	Database.Keys.shutdown
 	liftIO reapZombies -- zombies from long-running git processes

Annex/Content.hs

@@ -451,7 +451,9 @@ moveAnnex key src = withObjectLoc key storeobject storedirect
 			fs <- Database.Keys.getAssociatedFiles key
 			if null fs
 				then freezeContent dest
-				else mapM_ (populatePointerFile key dest) fs
+				else do
+					mapM_ (populatePointerFile key dest) fs
+					Database.Keys.storeInodeCaches key (dest:fs)
 		)
 	storeindirect = storeobject =<< calcRepo (gitAnnexLocation key)
 
@@ -505,7 +507,9 @@ linkAnnex key src = do
 		( return LinkAnnexNoop
 		, modifyContent dest $
 			ifM (liftIO $ createLinkOrCopy src dest)
-				( return LinkAnnexOk
+				( do
+					Database.Keys.storeInodeCaches key [dest, src]
+					return LinkAnnexOk
 				, return LinkAnnexFailed
 				)
 		)
@@ -601,6 +605,7 @@ removeAnnex (ContentRemovalLock key) = withObjectLoc key remove removedirect
 		removeInodeCache key
 		mapM_ (void . tryIO . resetPointerFile key)
 			=<< Database.Keys.getAssociatedFiles key
+		Database.Keys.removeInodeCaches key
 	removedirect fs = do
 		cache <- recordedInodeCache key
 		removeInodeCache key
@@ -613,8 +618,7 @@ removeAnnex (ContentRemovalLock key) = withObjectLoc key remove removedirect
 {- To safely reset a pointer file, it has to be the unmodified content of
  - the key. The expensive way to tell is to do a verification of its content.
  - The cheaper way is to see if the InodeCache for the key matches the
- - file.
- -}
+ - file. -}
 resetPointerFile :: Key -> FilePath -> Annex ()
 resetPointerFile key f = go =<< geti
   where
@@ -624,10 +628,14 @@ resetPointerFile key f = go =<< geti
 			secureErase f
 			liftIO $ nukeFile f
 			liftIO $ writeFile f (formatPointer key)
-		, noop
+		-- Can't delete the pointer file.
+		-- If it was a hard link to the annex object,
+		-- that object might have been frozen as part of the
+		-- removal process, so thaw it.
+		, thawContent f
 		)
-	cheapcheck fc = maybe (return False) (compareInodeCaches fc)
-		=<< Database.Keys.getInodeCache key
+	cheapcheck fc = anyM (compareInodeCaches fc)
+		=<< Database.Keys.getInodeCaches key
 	expensivecheck fc = ifM (verifyKeyContent AlwaysVerify Types.Remote.UnVerified key f)
 		-- The file could have been modified while it was
 		-- being verified. Detect that.

Command/Smudge.hs

@@ -48,7 +48,7 @@ smudge file = do
 	case parseLinkOrPointer b of
 		Nothing -> liftIO $ B.putStr b
 		Just k -> do
-			updateAssociatedFiles k file
+			Database.Keys.addAssociatedFile k file
 			content <- calcRepo (gitAnnexLocation k)
 			liftIO $ B.hPut stdout . fromMaybe b
 				=<< catchMaybeIO (B.readFile content)
@@ -65,7 +65,7 @@ clean file = do
 		else ifM (shouldAnnex file)
 			( do
 				k <- ingest file
-				updateAssociatedFiles k file
+				Database.Keys.addAssociatedFile k file
 				liftIO $ emitPointer k
 			, liftIO $ B.hPut stdout b
 			)
@@ -100,8 +100,3 @@ ingest file = do
 
 emitPointer :: Key -> IO ()
 emitPointer = putStrLn . formatPointer
-
-updateAssociatedFiles :: Key -> FilePath -> Annex ()
-updateAssociatedFiles k f = do
-	Database.Keys.addAssociatedFile k f
-	Database.Keys.flushDb

Database/Keys.hs

@@ -13,15 +13,17 @@
 module Database.Keys (
 	DbHandle,
 	openDb,
-	flushDb,
 	closeDb,
+	shutdown,
 	addAssociatedFile,
 	getAssociatedFiles,
 	removeAssociatedFile,
-	setInodeCache,
-	getInodeCache,
+	storeInodeCaches,
+	addInodeCaches,
+	getInodeCaches,
+	removeInodeCaches,
 	AssociatedId,
-	DataId,
+	ContentId,
 ) where
 
 import Database.Types
@@ -35,6 +37,7 @@ import Annex.Perms
 import Annex.LockFile
 import Messages
 import Utility.InodeCache
+import Annex.InodeSentinal
 
 import Database.Persist.TH
 import Database.Esqueleto hiding (Key)
@@ -44,10 +47,10 @@ Associated
   key SKey
   file FilePath
   KeyFileIndex key file
-Data
+Content
   key SKey
-  inodeCache SInodeCache
-  KeyIndex key
+  cache SInodeCache
+  KeyCacheIndex key cache
 |]
 
 {- Opens the database, creating it if it doesn't exist yet. -}
@@ -62,7 +65,7 @@ openDb = withExclusiveLock gitAnnexKeysDbLock $ do
 				runMigrationSilent migrateKeysDb
 		setAnnexDirPerm dbdir
 		setAnnexFilePerm db
-	h <- liftIO $ H.openDb db "data"
+	h <- liftIO $ H.openDb db "content"
 
 	-- work around https://github.com/yesodweb/persistent/issues/474
 	liftIO setConsoleEncoding
@@ -85,9 +88,12 @@ dbHandle = maybe startup return =<< Annex.getState Annex.keysdbhandle
 		Annex.changeState $ \s -> s { Annex.keysdbhandle = Just h }
 		return h
 
-{- Flushes any changes made to the database. -}
-flushDb :: Annex ()
-flushDb = withDbHandle H.flushQueueDb
+shutdown :: Annex ()
+shutdown = maybe noop go =<< Annex.getState Annex.keysdbhandle
+  where
+	go h = do
+		Annex.changeState $ \s -> s { Annex.keysdbhandle = Nothing }
+		liftIO $ closeDb h
 
 addAssociatedFile :: Key -> FilePath -> Annex ()
 addAssociatedFile k f = withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $ do
@@ -113,21 +119,35 @@ getAssociatedFiles' sk = do
 	return $ map unValue l
 
 removeAssociatedFile :: Key -> FilePath -> Annex ()
-removeAssociatedFile k f =  withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $
+removeAssociatedFile k f = withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $
 	delete $ from $ \r -> do
 		where_ (r ^. AssociatedKey ==. val sk &&. r ^. AssociatedFile ==. val f)
   where
 	sk = toSKey k
 
-setInodeCache :: Key -> InodeCache -> Annex ()
-setInodeCache k i = withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $
-	void $ upsert (Data (toSKey k) (toSInodeCache i)) []
+{- Stats the files, and stores their InodeCaches. -}
+storeInodeCaches :: Key -> [FilePath] -> Annex ()
+storeInodeCaches k fs = withTSDelta $ \d ->
+	addInodeCaches k . catMaybes =<< liftIO (mapM (`genInodeCache` d) fs)
 
-getInodeCache :: Key -> Annex (Maybe (InodeCache))
-getInodeCache k = withDbHandle $ \h -> H.queryDb h $ do
+addInodeCaches :: Key -> [InodeCache] -> Annex ()
+addInodeCaches k is = withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $
+	forM_ is $ \i -> insertUnique $ Content (toSKey k) (toSInodeCache i)
+
+{- A key may have multiple InodeCaches; one for the annex object, and one
+ - for each pointer file that is a copy of it. -}
+getInodeCaches :: Key -> Annex [InodeCache]
+getInodeCaches k = withDbHandle $ \h -> H.queryDb h $ do
 	l <- select $ from $ \r -> do
-		where_ (r ^. DataKey ==. val sk)
-		return (r ^. DataInodeCache)
-	return $ headMaybe $ map (fromSInodeCache . unValue) l
+		where_ (r ^. ContentKey ==. val sk)
+		return (r ^. ContentCache)
+	return $ map (fromSInodeCache . unValue) l
+  where
+	sk = toSKey k
+
+removeInodeCaches :: Key -> Annex ()
+removeInodeCaches k = withDbHandle $ \h -> H.queueDb h (\_ _ -> pure True) $
+	delete $ from $ \r -> do
+		where_ (r ^. ContentKey ==. val sk)
   where
 	sk = toSKey k

Utility/InodeCache.hs

@@ -1,7 +1,7 @@
 {- Caching a file's inode, size, and modification time
  - to see when it's changed.
  -
- - Copyright 2013, 2014 Joey Hess <id@joeyh.name>
+ - Copyright 2013-2014 Joey Hess <id@joeyh.name>
  -
  - License: BSD-2-clause
  -}

doc/todo/smudge.mdwn

@@ -328,6 +328,8 @@ files to be unlocked, while the indirect upgrades don't touch the files.
 * inAnnex check should fail in the case where an annexed object is unlocked
   and has had its content changed. Could use an InodeCache for
   such objects. This parallels how inAnnex checks work for direct mode.
+* Also, Annex.Content.prepSendAnnex should check the InodeCache for
+  changes.
 * Reconcile staged changes into the associated files database, whenever
   the database is queried.
 * See if the cases where the associated files database is not used can be
@@ -338,17 +340,6 @@ files to be unlocked, while the indirect upgrades don't touch the files.
   (when not in direct mode).
   However, beware over-optimisation breaking the assistant or perhaps other
   long-lived processes.
-* Update pointer files when dropping the content of a key.
-  - Check the associated files database to find associated files for the key.
-  - Verify that worktree files are not modified from the annexed object.
-    How? InodeCache could be maintained, but the smudge filer interface
-    wouldn't let it be updated when smudging a file. May need to take
-    an expensive path:
-    1. stat object file
-    2. stat worktree file
-    3. if same stat, ok else hash worktree file
-    4. stat worktree file again after checking hash; make sure it's
-       unchanged from earlier stat
 * Convert `git annex unlock` to stage a pointer file, and hard link to the
   annexed object (or write pointer file if annexed object not present).
   - Also needs to thaw annex object file