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
---
 Utility/ExternalSHA.hs |  3 ++-
 Utility/Hash.hs        | 29 +++++++++++++++++++++++++++++
 Utility/WebApp.hs      |  4 ++--
 3 files changed, 33 insertions(+), 3 deletions(-)
 create mode 100644 Utility/Hash.hs

(limited to 'Utility')

diff --git a/Utility/ExternalSHA.hs b/Utility/ExternalSHA.hs
index 21241d302..adbde795a 100644
--- a/Utility/ExternalSHA.hs
+++ b/Utility/ExternalSHA.hs
@@ -1,6 +1,7 @@
 {- Calculating a SHA checksum with an external command.
  -
- - This is often faster than using Haskell libraries.
+ - This is typically a bit faster than using Haskell libraries,
+ - by around 1% to 10%. Worth it for really big files.
  -
  - Copyright 2011-2013 Joey Hess <joey@kitenet.net>
  -
diff --git a/Utility/Hash.hs b/Utility/Hash.hs
new file mode 100644
index 000000000..31a36462c
--- /dev/null
+++ b/Utility/Hash.hs
@@ -0,0 +1,29 @@
+{- Convenience wrapper around cryptohash.
+ -
+ - The resulting Digests can be shown to get a canonical hash encoding. -}
+
+module Utility.Hash where
+
+import Crypto.Hash
+import qualified Data.ByteString.Lazy as L
+
+sha1 :: L.ByteString -> Digest SHA1
+sha1 = hashlazy
+
+sha224 :: L.ByteString -> Digest SHA224
+sha224 = hashlazy
+
+sha256 :: L.ByteString -> Digest SHA256
+sha256 = hashlazy
+
+sha384 :: L.ByteString -> Digest SHA384
+sha384 = hashlazy
+
+sha512 :: L.ByteString -> Digest SHA512
+sha512 = hashlazy
+
+-- sha3 is not yet fully standardized
+--sha3 :: L.ByteString -> Digest SHA3
+--sha3 = hashlazy
+
+
diff --git a/Utility/WebApp.hs b/Utility/WebApp.hs
index f3c0d3a6b..c078a5643 100644
--- a/Utility/WebApp.hs
+++ b/Utility/WebApp.hs
@@ -12,6 +12,7 @@ module Utility.WebApp where
 import Common
 import Utility.Tmp
 import Utility.FileMode
+import Utility.Hash
 
 import qualified Yesod
 import qualified Network.Wai as Wai
@@ -24,7 +25,6 @@ import qualified Data.CaseInsensitive as CI
 import Network.Socket
 import Control.Exception
 import Crypto.Random
-import Data.Digest.Pure.SHA
 import qualified Web.ClientSession as CS
 import qualified Data.ByteString.Lazy as L
 import qualified Data.ByteString.Lazy.UTF8 as L8
@@ -214,7 +214,7 @@ genRandomToken = do
 	return $
 		case genBytes 512 g of
 			Left e -> error $ "failed to generate secret token: " ++ show e
-			Right (s, _) -> showDigest $ sha512 $ L.fromChunks [s]
+			Right (s, _) -> show $ sha512 $ L.fromChunks [s]
 
 {- A Yesod isAuthorized method, which checks the auth cgi parameter
  - against a token extracted from the Yesod application.
-- 
cgit v1.2.3