From ca7695f9e746ef0d9cc70ffed6c2590dba29db79 Mon Sep 17 00:00:00 2001
From: Joey Hess <joey@kitenet.net>
Date: Sun, 22 Sep 2013 19:45:08 -0400
Subject: 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
---
 Remote/Bup.hs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'Remote')

diff --git a/Remote/Bup.hs b/Remote/Bup.hs
index 960ed4ada..16fe8c8c5 100644
--- a/Remote/Bup.hs
+++ b/Remote/Bup.hs
@@ -10,6 +10,7 @@ module Remote.Bup (remote) where
 import qualified Data.ByteString.Lazy as L
 import qualified Data.Map as M
 import System.Process
+import Data.ByteString.Lazy.UTF8 (fromString)
 
 import Common.Annex
 import Types.Remote
@@ -25,8 +26,7 @@ import Remote.Helper.Ssh
 import Remote.Helper.Special
 import Remote.Helper.Encryptable
 import Crypto
-import Data.ByteString.Lazy.UTF8 (fromString)
-import Data.Digest.Pure.SHA
+import Utility.Hash
 import Utility.UserInfo
 import Annex.Content
 import Annex.UUID
@@ -277,7 +277,7 @@ bup2GitRemote r
 bupRef :: Key -> String
 bupRef k
 	| Git.Ref.legal True shown = shown
-	| otherwise = "git-annex-" ++ showDigest (sha256 (fromString shown))
+	| otherwise = "git-annex-" ++ show (sha256 (fromString shown))
   where
 	shown = key2file k
 
-- 
cgit v1.2.3