Use cryptohash rather than SHA for hashing.
This is a massive win on OSX, which doesn't have a sha256sum normally. Only use external hash commands when the file is > 1 mb, since cryptohash is quite close to them in speed. SHA is still used to calculate HMACs. I don't quite understand cryptohash's API for those. Used the following benchmark to arrive at the 1 mb number. 1 mb file: benchmarking sha256/internal mean: 13.86696 ms, lb 13.83010 ms, ub 13.93453 ms, ci 0.950 std dev: 249.3235 us, lb 162.0448 us, ub 458.1744 us, ci 0.950 found 5 outliers among 100 samples (5.0%) 4 (4.0%) high mild 1 (1.0%) high severe variance introduced by outliers: 10.415% variance is moderately inflated by outliers benchmarking sha256/external mean: 14.20670 ms, lb 14.17237 ms, ub 14.27004 ms, ci 0.950 std dev: 230.5448 us, lb 150.7310 us, ub 427.6068 us, ci 0.950 found 3 outliers among 100 samples (3.0%) 2 (2.0%) high mild 1 (1.0%) high severe 2 mb file: benchmarking sha256/internal mean: 26.44270 ms, lb 26.23701 ms, ub 26.63414 ms, ci 0.950 std dev: 1.012303 ms, lb 925.8921 us, ub 1.122267 ms, ci 0.950 variance introduced by outliers: 35.540% variance is moderately inflated by outliers benchmarking sha256/external mean: 26.84521 ms, lb 26.77644 ms, ub 26.91433 ms, ci 0.950 std dev: 347.7867 us, lb 210.6283 us, ub 571.3351 us, ci 0.950 found 6 outliers among 100 samples (6.0%) import Crypto.Hash import Data.ByteString.Lazy as L import Criterion.Main import Common testfile :: FilePath testfile = "/run/shm/data" -- on ram disk main = defaultMain [ bgroup "sha256" [ bench "internal" $ whnfIO internal , bench "external" $ whnfIO external ] ] sha256 :: L.ByteString -> Digest SHA256 sha256 = hashlazy internal :: IO String internal = show . sha256 <$> L.readFile testfile external :: IO String external = do s <- readProcess "sha256sum" [testfile] return $ fst $ separate (== ' ') s
This commit is contained in:
parent
4cee7cbac6
commit
7390f08ef9
8 changed files with 57 additions and 17 deletions
|
@ -18,7 +18,6 @@ module Git.CatFile (
|
|||
import System.IO
|
||||
import qualified Data.ByteString as S
|
||||
import qualified Data.ByteString.Lazy as L
|
||||
import Data.Digest.Pure.SHA
|
||||
import Data.Char
|
||||
import System.Process (std_out, std_err)
|
||||
import Numeric
|
||||
|
@ -31,6 +30,7 @@ import Git.Command
|
|||
import Git.Types
|
||||
import Git.FilePath
|
||||
import qualified Utility.CoProcess as CoProcess
|
||||
import Utility.Hash
|
||||
|
||||
data CatFileHandle = CatFileHandle CoProcess.CoProcessHandle Repo
|
||||
|
||||
|
@ -103,7 +103,7 @@ catObjectDetails (CatFileHandle hdl repo) object = CoProcess.query hdl send rece
|
|||
}
|
||||
fileEncoding h
|
||||
content <- L.hGetContents h
|
||||
let sha = (\s -> length s `seq` s) (showDigest $ sha1 content)
|
||||
let sha = (\s -> length s `seq` s) (show $ sha1 content)
|
||||
ok <- checkSuccessProcess pid
|
||||
return $ if ok
|
||||
then Just (content, Ref sha)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue