From 748addbe05c378b0fdca320d9d5720fe7768524f Mon Sep 17 00:00:00 2001 From: Joey Hess Date: Fri, 30 Jul 2021 17:46:11 -0400 Subject: [PATCH] remove second pass in scanAnnexedFiles The pass was needed to populate files when annex.thin was set, but in commit 73e0cbbb19703f08daf783d8788370726f852162, reconcileStaged started to do that. So, this second pass is not needed any longer. --- Annex/Init.hs | 2 +- Annex/WorkTree.hs | 91 +++++------------------------------------------ Command/Smudge.hs | 2 +- Upgrade/V5.hs | 2 +- 4 files changed, 11 insertions(+), 86 deletions(-) diff --git a/Annex/Init.hs b/Annex/Init.hs index 962eae26eb..adbee09333 100644 --- a/Annex/Init.hs +++ b/Annex/Init.hs @@ -135,7 +135,7 @@ initialize' mversion = checkInitializeAllowed $ do then configureSmudgeFilter else deconfigureSmudgeFilter unlessM isBareRepo $ do - scanAnnexedFiles True + scanAnnexedFiles hookWrite postCheckoutHook hookWrite postMergeHook AdjustedBranch.checkAdjustedClone >>= \case diff --git a/Annex/WorkTree.hs b/Annex/WorkTree.hs index 60b460e813..7bb4b9fe00 100644 --- a/Annex/WorkTree.hs +++ b/Annex/WorkTree.hs @@ -8,24 +8,10 @@ module Annex.WorkTree where import Annex.Common -import qualified Annex import Annex.Link import Annex.CatFile -import Annex.Content -import Annex.ReplaceFile import Annex.CurrentBranch -import Annex.InodeSentinal -import Utility.InodeCache -import Git.FilePath -import Git.CatFile -import qualified Git.Ref -import qualified Git.LsTree -import qualified Git.Types import qualified Database.Keys -import Config -import qualified Utility.RawFilePath as R - -import qualified Data.ByteString.Lazy as L {- Looks up the key corresponding to an annexed file in the work tree, - by examining what the file links to. @@ -69,74 +55,13 @@ ifAnnexed file yes no = maybe no yes =<< lookupKey file {- Find all annexed files and update the keys database for them. - - - This is expensive, and so normally the associated files are updated - - incrementally when changes are noticed. So, this only needs to be done - - when initializing/upgrading a repository. - - - - Also, the content for an unlocked file may already be present as - - an annex object. If so, populate the pointer file with it. - - But if worktree file does not have a pointer file's content, it is left - - as-is. + - Normally the keys database is updated incrementally when it's being + - opened, and changes are noticed. Calling this explicitly allows + - running the update at an earlier point. -} -scanAnnexedFiles :: Bool -> Annex () -scanAnnexedFiles initscan = do - -- This gets the keys database populated with all annexed files, - -- by running Database.Keys.reconcileStaged. +scanAnnexedFiles :: Annex () +scanAnnexedFiles = + -- All that needs to be done is to open the database, + -- that will result in Database.Keys.reconcileStaged + -- running, and doing the work. Database.Keys.runWriter (const noop) - -- The above tries to populate pointer files, but one thing it - -- is not able to handle is populating a pointer file when the - -- annex object file already exists, but its inode is not yet - -- cached and annex.thin is set. So, the rest of this makes - -- another pass over the tree to do that. - whenM - ( pure initscan - <&&> annexThin <$> Annex.getGitConfig - <&&> inRepo Git.Ref.headExists - <&&> not <$> isBareRepo - ) $ do - g <- Annex.gitRepo - (l, cleanup) <- inRepo $ Git.LsTree.lsTree - Git.LsTree.LsTreeRecursive - (Git.LsTree.LsTreeLong True) - Git.Ref.headRef - catObjectStreamLsTree l want g go - liftIO $ void cleanup - where - -- Want to process symlinks, and regular files. - want i = case Git.Types.toTreeItemType (Git.LsTree.mode i) of - Just Git.Types.TreeSymlink -> Just (i, False) - Just Git.Types.TreeFile -> checkfilesize i - Just Git.Types.TreeExecutable -> checkfilesize i - _ -> Nothing - - -- Avoid processing files that are too large to be pointer files. - checkfilesize i = case Git.LsTree.size i of - Just n | n < maxPointerSz -> Just (i, True) - _ -> Nothing - - go getnext = liftIO getnext >>= \case - Just ((i, isregfile), Just c) -> do - maybe noop (add i isregfile) - (parseLinkTargetOrPointer (L.toStrict c)) - go getnext - _ -> return () - - add i isregfile k = do - let tf = Git.LsTree.file i - whenM (pure isregfile <&&> inAnnex k) $ do - f <- fromRepo $ fromTopFilePath tf - liftIO (isPointerFile f) >>= \case - Just k' | k' == k -> do - destmode <- liftIO $ catchMaybeIO $ - fileMode <$> R.getFileStatus f - ic <- replaceWorkTreeFile (fromRawFilePath f) $ \tmp -> do - let tmp' = toRawFilePath tmp - linkFromAnnex' k tmp' destmode >>= \case - LinkAnnexOk -> - withTSDelta (liftIO . genInodeCache tmp') - LinkAnnexNoop -> return Nothing - LinkAnnexFailed -> liftIO $ do - writePointerFile tmp' k destmode - return Nothing - maybe noop (restagePointerFile (Restage True) f) ic - _ -> noop diff --git a/Command/Smudge.hs b/Command/Smudge.hs index 70fc9235ad..c242b7e1b5 100644 --- a/Command/Smudge.hs +++ b/Command/Smudge.hs @@ -267,7 +267,7 @@ update = do -- point to refresh the keys database for changes to annexed files. -- Doing it explicitly here avoids a later pause in the middle of -- some other action. - scanAnnexedFiles False + scanAnnexedFiles updateSmudged (Restage True) stop diff --git a/Upgrade/V5.hs b/Upgrade/V5.hs index 22200b0c80..2db92d57f9 100644 --- a/Upgrade/V5.hs +++ b/Upgrade/V5.hs @@ -47,7 +47,7 @@ upgrade automatic = flip catchNonAsync onexception $ do , do checkGitVersionForIndirectUpgrade ) - scanAnnexedFiles True + scanAnnexedFiles configureSmudgeFilter -- Inode sentinal file was only used in direct mode and when -- locking down files as they were added. In v6, it's used more