mirrors/git-annex
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity Actions

improve data types for sqlite

Browse source 
This is a non-backwards compatable change, so not suitable for merging
w/o a annex.version bump and transition code. Not yet tested.

This improves performance of git-annex benchmark --databases
across the board by 10-25%, since eg Key roundtrips as a ByteString.

(serializeKey' produces a lazy ByteString, so there is still a
copy involved in converting it to a strict ByteString. It may be faster
to switch to using bytestring-strict-builder.)

FilePath and Key are both stored as blobs. This avoids mojibake in some
situations. It would be possible to use varchar instead, if persistent
could avoid converting that to Text, but it seems there is no good
way to do so. See doc/todo/sqlite_database_improvements.mdwn

Eliminated some ugly artifacts of using Read/Show serialization;
constructors and quoted strings are no longer stored in sqlite.

Renamed SRef to SSha to reflect that it is only ever a git sha,
not a ref name. Since it is limited to the characters in a sha,
it is not affected by mojibake, so still uses String.
This commit is contained in:
Joey Hess 2019-10-29 12:28:01 -04:00
parent e1b21a0491
commit c35a9047d3
No known key found for this signature in database
GPG key ID: DB12DB0FF05F8F38
9 changed files with 135 additions and 189 deletions
Download patch file Download diff file Expand all files Collapse all files

14
Database/ContentIdentifier.hs
View file

@ -52,11 +52,11 @@ share [mkPersist sqlSettings, mkMigrate "migrateContentIdentifier"] [persistLowe
ContentIdentifiers
remote UUID
cid ContentIdentifier
key IKey
key Key
-- The last git-annex branch tree sha that was used to update
-- ContentIdentifiers
AnnexBranch
tree SRef
tree SSha
UniqueTree tree
|]
@ -92,13 +92,13 @@ flushDbQueue (ContentIdentifierHandle h) = H.flushDbQueue h
-- Be sure to also update the git-annex branch when using this.
recordContentIdentifier :: ContentIdentifierHandle -> RemoteStateHandle -> ContentIdentifier -> Key -> IO ()
recordContentIdentifier h (RemoteStateHandle u) cid k = queueDb h $ do
void $ insert_ $ ContentIdentifiers u cid (toIKey k)
void $ insert_ $ ContentIdentifiers u cid k
getContentIdentifiers :: ContentIdentifierHandle -> RemoteStateHandle -> Key -> IO [ContentIdentifier]
getContentIdentifiers (ContentIdentifierHandle h) (RemoteStateHandle u) k =
H.queryDbQueue h $ do
l <- selectList
[ ContentIdentifiersKey ==. toIKey k
[ ContentIdentifiersKey ==. k
, ContentIdentifiersRemote ==. u
] []
return $ map (contentIdentifiersCid . entityVal) l
@ -110,18 +110,18 @@ getContentIdentifierKeys (ContentIdentifierHandle h) (RemoteStateHandle u) cid =
[ ContentIdentifiersCid ==. cid
, ContentIdentifiersRemote ==. u
] []
return $ map (fromIKey . contentIdentifiersKey . entityVal) l
return $ map (contentIdentifiersKey . entityVal) l
recordAnnexBranchTree :: ContentIdentifierHandle -> Sha -> IO ()
recordAnnexBranchTree h s = queueDb h $ do
deleteWhere ([] :: [Filter AnnexBranch])
void $ insertUnique $ AnnexBranch $ toSRef s
void $ insertUnique $ AnnexBranch $ toSSha s
getAnnexBranchTree :: ContentIdentifierHandle -> IO Sha
getAnnexBranchTree (ContentIdentifierHandle h) = H.queryDbQueue h $ do
l <- selectList ([] :: [Filter AnnexBranch]) []
case l of
(s:[]) -> return $ fromSRef $ annexBranchTree $ entityVal s
(s:[]) -> return $ fromSSha $ annexBranchTree $ entityVal s
_ -> return emptyTree
{- Check if the git-annex branch has been updated and the database needs