git-annex/Assistant/ScanRemotes.hs
Joey Hess ae52efc673 scan multiple remotes in one pass
The expensive transfer scan now scans a whole set of remotes in one pass.
So at startup, or when network comes up, it will run only once.

Note that this can result in transfers from/to higher cost remotes being
queued before other transfers of other content from/to lower cost remotes.
Before, low cost remotes were scanned first and all their transfers came
first. When multiple transfers are queued for a key, the lower cost ones
are still queued first. However, this could result in transfers from slow
remotes running for a long time while transfers of other data from faster
remotes waits.

I expect to make the transfer queue smarter about ordering
and/or make it allow multiple transfers at a time, which should eliminate
this annoyance. (Also, it was already possible to get into that situation,
for example if the network was up, lots of transfers from slow remotes
might be queued, and then a disk is mounted and its faster transfers have
to wait.)

Also note that this means I don't need to improve the code in
Assistant.Sync that currently checks if any of the reconnected remotes
have diverged, and if so, queues scans of all of them. That had been very
innefficient, but now doesn't matter.
2012-08-26 14:09:02 -04:00

48 lines
1.4 KiB
Haskell

{- git-annex assistant remotes needing scanning
-
- Copyright 2012 Joey Hess <joey@kitenet.net>
-
- Licensed under the GNU GPL version 3 or higher.
-}
module Assistant.ScanRemotes where
import Common.Annex
import qualified Types.Remote as Remote
import Data.Function
import Control.Concurrent.STM
import qualified Data.Map as M
data ScanInfo = ScanInfo
{ scanPriority :: Int
, fullScan :: Bool
}
type ScanRemoteMap = TMVar (M.Map Remote ScanInfo)
{- The TMVar starts empty, and is left empty when there are no remotes
- to scan. -}
newScanRemoteMap :: IO ScanRemoteMap
newScanRemoteMap = atomically newEmptyTMVar
{- Blocks until there is a remote or remotes that need to be scanned.
-
- The list has higher priority remotes listed first. -}
getScanRemote :: ScanRemoteMap -> IO [(Remote, ScanInfo)]
getScanRemote v = atomically $
reverse . sortBy (compare `on` scanPriority . snd) . M.toList
<$> takeTMVar v
{- Adds new remotes that need scanning. -}
addScanRemotes :: ScanRemoteMap -> Bool -> [Remote] -> IO ()
addScanRemotes _ _ [] = noop
addScanRemotes v full rs = atomically $ do
m <- fromMaybe M.empty <$> tryTakeTMVar v
putTMVar v $ M.unionWith merge (M.fromList $ zip rs (map info rs)) m
where
info r = ScanInfo (-1 * Remote.cost r) full
merge x y = ScanInfo
{ scanPriority = max (scanPriority x) (scanPriority y)
, fullScan = fullScan x || fullScan y
}