Increased the default annex.bloomaccuracy from 1000 to 10000000
This makes git annex unused use around 48 mb more memory than it did before, but the massive increase in accuracy makes this worthwhile for all but the smallest systems. Also, I want to use the bloom filter for sync --all --content, to avoid dropping files that the preferred content doesn't want, and 1/1000 false positives would be far too many in that use case, even if it were acceptable for unused. Actual memory use numbers: 1000: 21.06user 3.42system 0:26.40elapsed 92%CPU (0avgtext+0avgdata 501552maxresident)k 1000000: 21.41user 3.55system 0:26.84elapsed 93%CPU (0avgtext+0avgdata 549496maxresident)k 10000000: 21.84user 3.52system 0:27.89elapsed 90%CPU (0avgtext+0avgdata 549920maxresident)k Based on these numbers, 10 million seemed a better pick than 1 million.
This commit is contained in:
parent
f7350b7c33
commit
8b74aec3ea
6 changed files with 76 additions and 56 deletions
|
@ -16,7 +16,6 @@ import Data.Tuple
|
|||
import Data.Ord
|
||||
|
||||
import Common.Annex
|
||||
import qualified Command.Unused
|
||||
import qualified Git
|
||||
import qualified Annex
|
||||
import qualified Remote
|
||||
|
@ -39,6 +38,8 @@ import Types.TrustLevel
|
|||
import Types.FileMatcher
|
||||
import qualified Limit
|
||||
import Messages.JSON (DualDisp(..))
|
||||
import Annex.BloomFilter
|
||||
import qualified Command.Unused
|
||||
|
||||
-- a named computation that produces a statistic
|
||||
type Stat = StatState (Maybe (String, StatState String))
|
||||
|
@ -330,17 +331,17 @@ key_name k = simpleStat "key" $ pure $ key2file k
|
|||
bloom_info :: Stat
|
||||
bloom_info = simpleStat "bloom filter size" $ do
|
||||
localkeys <- countKeys <$> cachedPresentData
|
||||
capacity <- fromIntegral <$> lift Command.Unused.bloomCapacity
|
||||
capacity <- fromIntegral <$> lift bloomCapacity
|
||||
let note = aside $
|
||||
if localkeys >= capacity
|
||||
then "appears too small for this repository; adjust annex.bloomcapacity"
|
||||
else showPercentage 1 (percentage capacity localkeys) ++ " full"
|
||||
|
||||
-- Two bloom filters are used at the same time, so double the size
|
||||
-- of one.
|
||||
-- Two bloom filters are used at the same time when running
|
||||
-- git-annex unused, so double the size of one.
|
||||
sizer <- lift mkSizer
|
||||
size <- sizer memoryUnits False . (* 2) . fromIntegral . fst <$>
|
||||
lift Command.Unused.bloomBitsHashes
|
||||
lift bloomBitsHashes
|
||||
|
||||
return $ size ++ note
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue