git-annex/Command/Migrate.hs

127 lines
4 KiB
Haskell
Raw Normal View History

{- git-annex command
-
- Copyright 2011 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
module Command.Migrate where
import Command
import Backend
import Types.Backend (canUpgradeKey, fastMigrate)
import Types.KeySource
2011-10-04 04:40:47 +00:00
import Annex.Content
import qualified Command.ReKey
import qualified Command.Fsck
import qualified Annex
import Logs.MetaData
import Logs.Web
import Utility.Metered
cmd :: Command
cmd = withAnnexOptions [backendOption, annexedMatchingOptions] $
command "migrate" SectionUtility
"switch data to different backend"
paramPaths (seek <$$> optParser)
data MigrateOptions = MigrateOptions
{ migrateThese :: CmdParams
, removeSize :: Bool
}
optParser :: CmdParamsDesc -> Parser MigrateOptions
optParser desc = MigrateOptions
<$> cmdParams desc
<*> switch
( long "remove-size"
<> help "remove size field from keys"
)
seek :: MigrateOptions -> CommandSeek
seek o = withFilesInGitAnnex ww seeker =<< workTreeItems ww (migrateThese o)
where
ww = WarnUnmatchLsFiles "migrate"
seeker = AnnexedFileSeeker
{ startAction = start o
, checkContentPresent = Nothing
, usesLocationLog = False
}
start :: MigrateOptions -> SeekInput -> RawFilePath -> Key -> CommandStart
start o si file key = do
forced <- Annex.getRead Annex.force
v <- Backend.getBackend (fromRawFilePath file) key
case v of
Nothing -> stop
Just oldbackend -> do
exists <- inAnnex key
newbackend <- chooseBackend file
if (newbackend /= oldbackend || upgradableKey oldbackend key || forced) && exists
then go False oldbackend newbackend
else if removeSize o && exists
then go True oldbackend oldbackend
else stop
where
go onlyremovesize oldbackend newbackend =
starting "migrate" (mkActionItem (key, file)) si $
perform onlyremovesize o file key oldbackend newbackend
{- Checks if a key is upgradable to a newer representation.
-
- Reasons for migration:
- - Ideally, all keys have file size metadata. Old keys may not.
- - Something has changed in the backend, such as a bug fix.
-}
upgradableKey :: Backend -> Key -> Bool
upgradableKey backend key = isNothing (fromKey keySize key) || backendupgradable
where
backendupgradable = maybe False (\a -> a key) (canUpgradeKey backend)
{- Store the old backend's key in the new backend
- The old backend's key is not dropped from it, because there may
- be other files still pointing at that key.
-
- To ensure that the data we have for the old key is valid, it's
- fscked here. First we generate the new key. This ensures that the
- data cannot get corrupted after the fsck but before the new key is
- generated.
-}
perform :: Bool -> MigrateOptions -> RawFilePath -> Key -> Backend -> Backend -> CommandPerform
perform onlyremovesize o file oldkey oldbackend newbackend = go =<< genkey (fastMigrate oldbackend)
2012-11-12 05:05:04 +00:00
where
go Nothing = stop
go (Just (newkey, knowngoodcontent))
| knowngoodcontent = finish (removesize newkey)
| otherwise = stopUnless checkcontent $
finish (removesize newkey)
checkcontent = Command.Fsck.checkBackend oldbackend oldkey KeyPresent afile
finish newkey = ifM (Command.ReKey.linkKey file oldkey newkey)
( do
2017-10-16 16:54:00 +00:00
_ <- copyMetaData oldkey newkey
-- If the old key had some associated urls, record them for
-- the new key as well.
urls <- getUrls oldkey
forM_ urls $ \url ->
setUrlPresent newkey url
include locked files in the keys database associated files Before only unlocked files were included. The initial scan now scans for locked as well as unlocked files. This does mean it gets a little bit slower, although I optimised it as well as I think it can be. reconcileStaged changed to diff from the current index to the tree of the previous index. This lets it handle deletions as well, removing associated files for both locked and unlocked files, which did not always happen before. On upgrade, there will be no recorded previous tree, so it will diff from the empty tree to current index, and so will fully populate the associated files, as well as removing any stale associated files that were present due to them not being removed before. reconcileStaged now does a bit more work. Most of the time, this will just be due to running more often, after some change is made to the index, and since there will be few changes since the last time, it will not be a noticable overhead. What may turn out to be a noticable slowdown is after changing to a branch, it has to go through the diff from the previous index to the new one, and if there are lots of changes, that could take a long time. Also, after adding a lot of files, or deleting a lot of files, or moving a large subdirectory, etc. Command.Lock used removeAssociatedFile, but now that's wrong because a newly locked file still needs to have its associated file tracked. Command.Rekey used removeAssociatedFile when the file was unlocked. It could remove it also when it's locked, but it is not really necessary, because it changes the index, and so the next time git-annex run and accesses the keys db, reconcileStaged will run and update it. There are probably several other places that use addAssociatedFile and don't need to any more for similar reasons. But there's no harm in keeping them, and it probably is a good idea to, if only to support mixing this with older versions of git-annex. However, mixing this and older versions does risk reconcileStaged not running, if the older version already ran it on a given index state. So it's not a good idea to mix versions. This problem could be dealt with by changing the name of the gitAnnexKeysDbIndexCache, but that would leave the old file dangling, or it would need to keep trying to remove it.
2021-05-21 19:47:37 +00:00
next $ Command.ReKey.cleanup file newkey
2018-10-16 19:52:40 +00:00
, giveup "failed creating link from old to new key"
)
genkey _ | onlyremovesize = return $ Just (oldkey, False)
genkey Nothing = do
content <- calcRepo $ gitAnnexLocation oldkey
let source = KeySource
2020-02-21 13:34:59 +00:00
{ keyFilename = file
, contentLocation = content
, inodeCache = Nothing
}
newkey <- fst <$> genKey source nullMeterUpdate newbackend
return $ Just (newkey, False)
genkey (Just fm) = fm oldkey newbackend afile >>= \case
Just newkey -> return (Just (newkey, True))
Nothing -> genkey Nothing
removesize k
| removeSize o = alterKey k $ \kd -> kd { keySize = Nothing }
| otherwise = k
afile = AssociatedFile (Just file)