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

11
Database/Benchmark.hs
View file

@ -16,7 +16,6 @@ import Types.Benchmark
import qualified Database.Keys.SQL as SQL
import qualified Database.Queue as H
import Database.Init
import Database.Types
import Utility.Tmp.Dir
import Git.FilePath
import Types.Key
@ -55,11 +54,11 @@ benchmarkDbs _ = error "not built with criterion, cannot benchmark"
getAssociatedFilesHitBench :: BenchDb -> Benchmark
getAssociatedFilesHitBench (BenchDb h num) = bench ("getAssociatedFiles from " ++ show num ++ " (hit)") $ nfIO $ do
n <- getStdRandom (randomR (1,num))
SQL.getAssociatedFiles (toIKey (keyN n)) (SQL.ReadHandle h)
SQL.getAssociatedFiles (keyN n) (SQL.ReadHandle h)
getAssociatedFilesMissBench :: BenchDb -> Benchmark
getAssociatedFilesMissBench (BenchDb h num) = bench ("getAssociatedFiles from " ++ show num ++ " (miss)") $ nfIO $
SQL.getAssociatedFiles (toIKey keyMiss) (SQL.ReadHandle h)
SQL.getAssociatedFiles keyMiss (SQL.ReadHandle h)
getAssociatedKeyHitBench :: BenchDb -> Benchmark
getAssociatedKeyHitBench (BenchDb h num) = bench ("getAssociatedKey from " ++ show num ++ " (hit)") $ nfIO $ do
@ -73,19 +72,19 @@ getAssociatedKeyMissBench (BenchDb h num) = bench ("getAssociatedKey from " ++ s
addAssociatedFileOldBench :: BenchDb -> Benchmark
addAssociatedFileOldBench (BenchDb h num) = bench ("addAssociatedFile to " ++ show num ++ " (old)") $ nfIO $ do
n <- getStdRandom (randomR (1,num))
SQL.addAssociatedFile (toIKey (keyN n)) (fileN n) (SQL.WriteHandle h)
SQL.addAssociatedFile (keyN n) (fileN n) (SQL.WriteHandle h)
H.flushDbQueue h
addAssociatedFileNewBench :: BenchDb -> Benchmark
addAssociatedFileNewBench (BenchDb h num) = bench ("addAssociatedFile to " ++ show num ++ " (new)") $ nfIO $ do
n <- getStdRandom (randomR (1,num))
SQL.addAssociatedFile (toIKey (keyN n)) (fileN (n+1)) (SQL.WriteHandle h)
SQL.addAssociatedFile (keyN n) (fileN (n+1)) (SQL.WriteHandle h)
H.flushDbQueue h
populateAssociatedFiles :: H.DbQueue -> Int -> IO ()
populateAssociatedFiles h num = do
forM_ [1..num] $ \n ->
SQL.addAssociatedFile (toIKey (keyN n)) (fileN n) (SQL.WriteHandle h)
SQL.addAssociatedFile (keyN n) (fileN n) (SQL.WriteHandle h)
H.flushDbQueue h
keyN :: Int -> Key