finish bloom filters

Add tuning, docs, etc.

Not sure if status is the right place to remote size.. perhaps unused
should report the size and also warn if it sees more keys than the bloom
filter allows?

1 files changed, 18 insertions, 1 deletions

diff --git a/Command/Status.hs b/Command/Status.hs
index 0b1741dc0..eadb4f163 100644
--- a/Command/Status.hs
+++ b/Command/Status.hs
@@ -76,6 +76,7 @@ slow_stats =
 	, local_annex_size
 	, known_annex_keys
 	, known_annex_size
+	, bloom_info
 	, backend_usage
 	]
 
@@ -127,7 +128,7 @@ remote_list level desc = stat n $ nojson $ lift $ do
 	return $ if null s then "0" else show (length rs) ++ "\n" ++ beginning s
 	where
 		n = desc ++ " repositories"
-
+	
 local_annex_size :: Stat
 local_annex_size = stat "local annex size" $ json id $
 	showSizeKeys <$> cachedPresentData
@@ -136,6 +137,22 @@ local_annex_keys :: Stat
 local_annex_keys = stat "local annex keys" $ json show $
 	countKeys <$> cachedPresentData
 
+bloom_info :: Stat
+bloom_info = stat "bloom filter size" $ json id $ do
+	localkeys <- countKeys <$> cachedPresentData
+	capacity <- fromIntegral <$> lift Command.Unused.bloomCapacity
+	let note = aside $
+		if localkeys >= capacity
+		then "appears too small for this repository; adjust annex.bloomcapacity"
+		else "has room for " ++ show (capacity - localkeys) ++ " more local annex keys"
+
+	-- Two bloom filters are used at the same time, so double the size
+	-- of one.
+	size <- roughSize memoryUnits True . (* 2) . fromIntegral . fst <$>
+		lift Command.Unused.bloomBitsHashes
+
+	return $ size ++ note
+
 known_annex_size :: Stat
 known_annex_size = stat "known annex size" $ json id $
 	showSizeKeys <$> cachedReferencedData