Clean up direct mode cache and mapping info when dropping keys.

These files were left behind, and made getKeysPresent find keys that were
not present. It would be expensive to make getKeysPresent check that the
actual key files are present (it just lists the directories). But that's not
needed if we just clean up the stale cache and mapping files.

To handle systems that were in direct mode and got switched back with stale
direct mode files, made cleanObjectLoc remove all files in the key's directory.

git annex unused will still list keys that are gone but for which the stale
direct mode files exists. To deal with that, made dropunused remove the key's
directory even if the key does not seem to be present.

Annex/Content.hs

@@ -28,6 +28,7 @@ module Annex.Content (
 	freezeContent,
 	thawContent,
 	replaceFile,
+	cleanObjectLoc,
 ) where
 
 import System.IO.Unsafe (unsafeInterleaveIO)
@@ -334,7 +335,12 @@ withObjectLoc key indirect direct = ifM isDirect
 cleanObjectLoc :: Key -> Annex ()
 cleanObjectLoc key = do
 	file <- inRepo $ gitAnnexLocation key
-	liftIO $ removeparents file (3 :: Int)
+	liftIO $ do
+		let dir = parentDir file
+		void $ catchMaybeIO $ do
+			allowWrite dir
+			removeDirectoryRecursive dir
+		removeparents dir (2 :: Int)
   where
 	removeparents _ 0 = noop
 	removeparents file n = do
@@ -356,8 +362,8 @@ removeAnnex key = withObjectLoc key remove removedirect
 		cleanObjectLoc key
 	removedirect fs = do
 		cache <- recordedCache key
-		removeCache key
 		mapM_ (resetfile cache) fs
+		cleanObjectLoc key
 	resetfile cache f = whenM (compareCache f cache) $ do
 		l <- calcGitLink f key
 		top <- fromRepo Git.repoPath

Annex/Content/Direct.hs

@@ -15,7 +15,6 @@ module Annex.Content.Direct (
 	recordedCache,
 	compareCache,
 	writeCache,
-	removeCache,
 	genCache,
 	toCache,
 	Cache(..),
@@ -129,12 +128,6 @@ writeCache key cache = withCacheFile key $ \cachefile -> do
 	createContentDir cachefile
 	liftIO $ writeFile cachefile $ showCache cache
 
-{- Removes a cache. -}
-removeCache :: Key -> Annex ()
-removeCache key = withCacheFile key $ \f -> do
-	createContentDir f -- also thaws directory
-	liftIO $ nukeFile f
-
 {- Cache a file's inode, size, and modification time to determine if it's
  - been changed. -}
 data Cache = Cache FileID FileOffset EpochTime

Command/Drop.hs

@@ -60,7 +60,10 @@ performLocal key numcopies knownpresentremote = lockContent key $ do
 	untrusteduuids <- trustGet UnTrusted
 	let tocheck = Remote.remotesWithoutUUID remotes (trusteduuids'++untrusteduuids)
 	stopUnless (canDropKey key numcopies trusteduuids' tocheck []) $ do
-		whenM (inAnnex key) $ removeAnnex key
+		whenM (inAnnex key) $
+			removeAnnex key
+		{- Clean up stale direct mode files that may exist. -}
+		cleanObjectLoc key
 		next $ cleanupLocal key
 
 performRemote :: Key -> Maybe Int -> Remote -> CommandPerform

debian/changelog

@@ -13,6 +13,9 @@ git-annex (3.20130125) UNRELEASED; urgency=low
   * pre-commit: Update direct mode mappings. 
   * uninit, unannex --fast: If hard link creation fails, fall back to slow
     mode.
+  * Clean up direct mode cache and mapping info when dropping keys.
+  * dropunused: Clean up stale direct mode cache and mapping info not
+    removed before.
 
  -- Joey Hess <joeyh@debian.org>  Sat, 26 Jan 2013 15:48:40 +1100
 

doc/bugs/dropunused_doesn__39__t_work_in_my_case__63__.mdwn

@@ -56,3 +56,6 @@ What version of git-annex are you using? On what operating system?
 
 git-annex: 3.20130124
 Debian: sid 2013-02-01
+
+> unused being confused by stale data left when switching from direct mode.
+> I've made this be cleaned up. [[done]] --[[Joey]]