use same hash directories for chunked key as are used for its parent

This avoids a proliferation of hash directories when using new-style
chunking, and should improve performance since chunks are accessed
in sequence and so should have a common locality.

Of course, when a chunked key is encrypted, its hash directories have no
relation to the parent key.

This commit was sponsored by Christian Kellermann.

3 files changed, 20 insertions, 2 deletions

diff --git a/Locations.hs b/Locations.hs
index d397a97be..0369c7a1c 100644
--- a/Locations.hs
+++ b/Locations.hs
@@ -421,6 +421,7 @@ keyPaths key = map (keyPath key) annexHashes
  - which do not allow using a directory "XX" when "xx" already exists.
  - To support that, most repositories use the lower case hash for new data. -}
 type Hasher = Key -> FilePath
+
 annexHashes :: [Hasher]
 annexHashes = [hashDirLower, hashDirMixed]
 
@@ -428,12 +429,12 @@ hashDirMixed :: Hasher
 hashDirMixed k = addTrailingPathSeparator $ take 2 dir </> drop 2 dir
   where
 	dir = take 4 $ display_32bits_as_dir =<< [a,b,c,d]
-	ABCD (a,b,c,d) = md5 $ md5FilePath $ key2file k
+	ABCD (a,b,c,d) = md5 $ md5FilePath $ key2file $ nonChunkKey k
 
 hashDirLower :: Hasher
 hashDirLower k = addTrailingPathSeparator $ take 3 dir </> drop 3 dir
   where
-	dir = take 6 $ md5s $ md5FilePath $ key2file k
+	dir = take 6 $ md5s $ md5FilePath $ key2file $ nonChunkKey k
 
 {- modified version of display_32bits_as_hex from Data.Hash.MD5
  -   Copyright (C) 2001 Ian Lynagh 
diff --git a/Types/Key.hs b/Types/Key.hs
index 90f66f23e..3015b1e86 100644
--- a/Types/Key.hs
+++ b/Types/Key.hs
@@ -13,6 +13,8 @@ module Types.Key (
 	stubKey,
 	key2file,
 	file2key,
+	isChunkKey,
+	nonChunkKey,
 
 	prop_idempotent_key_encode,
 	prop_idempotent_key_decode
@@ -47,6 +49,16 @@ stubKey = Key
 	, keyChunkNum = Nothing
 	}
 
+isChunkKey :: Key -> Bool 
+isChunkKey k = isJust (keyChunkSize k) && isJust (keyChunkNum k) 
+
+-- Gets the parent of a chunk key.
+nonChunkKey :: Key -> Key
+nonChunkKey k = k
+	{ keyChunkSize = Nothing
+	, keyChunkNum = Nothing
+	}
+
 fieldSep :: Char
 fieldSep = '-'
 
diff --git a/doc/internals/hashing.mdwn b/doc/internals/hashing.mdwn
index cc4bc6456..bdc259b63 100644
--- a/doc/internals/hashing.mdwn
+++ b/doc/internals/hashing.mdwn
@@ -36,3 +36,8 @@ string, but where that would normally encode the bits using the 16 characters
 0-9a-f, this instead uses the 32 characters "0123456789zqjxkmvwgpfZQJXKMVWGPF".
 The first 2 letters of the resulting string are the first directory, and the
 second 2 are the second directory.
+
+## chunk keys
+
+The same hash directory is used for a chunk key as would be used for the
+key that it's a chunk of.