add: Significantly speed up adding lots of non-large files to git

* add: Significantly speed up adding lots of non-large files to git,
  by disabling the annex smudge filter when running git add.
* add --force-small: Run git add rather than updating the index itself,
  so any other smudge filters than the annex one that may be enabled will
  be used.

Annex/GitOverlay.hs

@@ -20,6 +20,7 @@ import Git.Index
 import Git.Env
 import qualified Annex
 import qualified Annex.Queue
+import Config.Smudge
 
 {- Runs an action using a different git index file. -}
 withIndexFile :: AltIndexFile -> (FilePath -> Annex a) -> Annex a
@@ -67,16 +68,12 @@ withIndexFile i = withAltRepo usecachedgitenv restoregitenv
  - Smudge and clean filters are disabled in this work tree. -}
 withWorkTree :: FilePath -> Annex a -> Annex a
 withWorkTree d a = withAltRepo
-	(\g -> return $ (g { location = modlocation (location g), gitGlobalOpts = gitGlobalOpts g ++ disableSmudgeConfig }, ()))
+	(\g -> return $ (g { location = modlocation (location g), gitGlobalOpts = gitGlobalOpts g ++ bypassSmudgeConfig }, ()))
 	(\g g' -> g' { location = location g, gitGlobalOpts = gitGlobalOpts g })
 	(const a)
   where
 	modlocation l@(Local {}) = l { worktree = Just (toRawFilePath d) }
 	modlocation _ = error "withWorkTree of non-local git repo"
-	disableSmudgeConfig = map Param
-		[ "-c", "filter.annex.smudge="
-		, "-c", "filter.annex.clean="
-		]
 
 {- Runs an action with the git index file and HEAD, and a few other
  - files that are related to the work tree coming from an overlay

CHANGELOG

@@ -1,3 +1,13 @@
+git-annex (8.20201130) UNRELEASED; urgency=medium
+
+  * add: Significantly speed up adding lots of non-large files to git,
+    by disabling the annex smudge filter when running git add.
+  * add --force-small: Run git add rather than updating the index itself,
+    so any other smudge filters than the annex one that may be enabled will
+    be used.
+
+ -- Joey Hess <id@joeyh.name>  Mon, 04 Jan 2021 12:52:41 -0400
+
 git-annex (8.20201129) upstream; urgency=medium
 
   * New borg special remote. This is a new kind of remote, that examines

Command/Add.hs

@@ -1,6 +1,6 @@
 {- git-annex command
  -
- - Copyright 2010-2020 Joey Hess <id@joeyh.name>
+ - Copyright 2010-2021 Joey Hess <id@joeyh.name>
  -
  - Licensed under the GNU AGPL version 3 or higher.
  -}
@@ -17,13 +17,10 @@ import qualified Database.Keys
 import Annex.FileMatcher
 import Annex.Link
 import Annex.Tmp
-import Annex.HashObject
 import Messages.Progress
-import Git.Types
 import Git.FilePath
 import Config.GitConfig
-import qualified Git.UpdateIndex
-import Utility.FileMode
+import Config.Smudge
 import Utility.OptParse
 import qualified Utility.RawFilePath as R
 
@@ -119,37 +116,26 @@ startSmall o si file =
 addSmall :: CheckGitIgnore -> RawFilePath -> Annex Bool
 addSmall ci file = do
 	showNote "non-large file; adding content to git repository"
-	addFile ci file
+	addFile Small ci file
 
 startSmallOverridden :: AddOptions -> SeekInput -> RawFilePath -> CommandStart
 startSmallOverridden o si file = 
-	starting "add" (ActionItemWorkTreeFile file) si $
-		next $ addSmallOverridden o file
+	starting "add" (ActionItemWorkTreeFile file) si $ next $ do
+		showNote "adding content to git repository"
+		addFile Small (checkGitIgnoreOption o) file
 
-addSmallOverridden :: AddOptions -> RawFilePath -> Annex Bool
-addSmallOverridden o file = do
-	showNote "adding content to git repository"
-	s <- liftIO $ R.getSymbolicLinkStatus file
-	if not (isRegularFile s)
-		then addFile (checkGitIgnoreOption o) file
-		else do
-			-- Can't use addFile because the clean filter will
-			-- honor annex.largefiles and it has been overridden.
-			-- Instead, hash the file and add to the index.
-			sha <- hashFile file
-			let ty = if isExecutable (fileMode s)
-				then TreeExecutable
-				else TreeFile
-			Annex.Queue.addUpdateIndex =<<
-				inRepo (Git.UpdateIndex.stageFile sha ty (fromRawFilePath file))
-			return True
+data SmallOrLarge = Small | Large
 
-addFile :: CheckGitIgnore -> RawFilePath -> Annex Bool
-addFile ci file = do
+addFile :: SmallOrLarge -> CheckGitIgnore -> RawFilePath -> Annex Bool
+addFile smallorlarge ci file = do
 	ps <- gitAddParams ci
-	Annex.Queue.addCommand [] "add" (ps++[Param "--"])
+	Annex.Queue.addCommand cps "add" (ps++[Param "--"])
 		[fromRawFilePath file]
 	return True
+  where
+	cps = case smallorlarge of
+		Large -> []
+		Small -> bypassSmudgeConfig
 
 start :: AddOptions -> SeekInput -> RawFilePath -> AddUnlockedMatcher -> CommandStart
 start o si file addunlockedmatcher = do
@@ -164,7 +150,7 @@ start o si file addunlockedmatcher = do
 			| otherwise -> 
 				starting "add" (ActionItemWorkTreeFile file) si $
 					if isSymbolicLink s
-						then next $ addFile (checkGitIgnoreOption o) file
+						then next $ addFile Small (checkGitIgnoreOption o) file
 						else perform o file addunlockedmatcher
 	addpresent key = 
 		liftIO (catchMaybeIO $ R.getSymbolicLinkStatus file) >>= \case
@@ -180,7 +166,7 @@ start o si file addunlockedmatcher = do
 		starting "add" (ActionItemWorkTreeFile file) si $
 			addingExistingLink file key $ do
 				Database.Keys.addAssociatedFile key =<< inRepo (toTopFilePath file)
-				next $ addFile (checkGitIgnoreOption o) file
+				next $ addFile Large (checkGitIgnoreOption o) file
 
 perform :: AddOptions -> RawFilePath -> AddUnlockedMatcher -> CommandPerform
 perform o file addunlockedmatcher = withOtherTmp $ \tmpdir -> do

Config/Smudge.hs

@@ -60,3 +60,11 @@ deconfigureSmudgeFilter = do
 		filter (\l -> l `notElem` stdattr && not (null l)) ls
 	unsetConfig (ConfigKey "filter.annex.smudge")
 	unsetConfig (ConfigKey "filter.annex.clean")
+
+-- Params to pass to git to temporarily avoid using the smudge/clean
+-- filters.
+bypassSmudgeConfig :: [CommandParam]
+bypassSmudgeConfig = map Param
+	[ "-c", "filter.annex.smudge="
+	, "-c", "filter.annex.clean="
+	]

Database/Keys.hs

@@ -43,6 +43,7 @@ import Git.FilePath
 import Git.Command
 import Git.Types
 import Git.Index
+import Config.Smudge
 import qualified Utility.RawFilePath as R
 
 import qualified Data.ByteString as S
@@ -237,15 +238,14 @@ reconcileStaged qh = do
 		liftIO $ writeFile indexcache $ showInodeCache cur
 	
 	diff =
-		-- Avoid using external diff command, which would be slow.
-		-- (The -G option may make it be used otherwise.)
-		[ Param "-c", Param "diff.external="
 		-- Avoid running smudge or clean filters, since we want the
 		-- raw output, and they would block trying to access the
 		-- locked database. The --raw normally avoids git diff
 		-- running them, but older versions of git need this.
-		, Param "-c", Param "filter.annex.smudge="
-		, Param "-c", Param "filter.annex.clean="
+		bypassSmudgeConfig ++
+		-- Avoid using external diff command, which would be slow.
+		-- (The -G option may make it be used otherwise.)
+		[ Param "-c", Param "diff.external="
 		, Param "diff"
 		, Param "--cached"
 		, Param "--raw"

doc/todo/speed_up_git_annex_add_of_small_files.mdwn

@@ -14,3 +14,5 @@ with the existing `--force-small` too, but at least that's not the default.
 
 Possible alternate approach: Unsetting filter.annex.smudge and
 filter.annex.clean when running `git add`?
+
+> This approach is a winner! [[done]] --[[Joey]]