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.

Assistant/Alert.hs

@@ -214,10 +214,10 @@ syncAlert rs = baseActivityAlert
 	, alertPriority = Low
         }
 
-scanAlert :: Remote -> Alert
+scanAlert :: [Remote] -> Alert
-scanAlert r = baseActivityAlert
+scanAlert rs = baseActivityAlert
 	{ alertHeader = Just $ tenseWords
-		[Tensed "Scanning" "Scanned", showRemotes [r]]
+		[Tensed "Scanning" "Scanned", showRemotes rs]
 	, alertBlockDisplay = True
 	, alertPriority = Low
 	}

Assistant/ScanRemotes.hs

@@ -26,21 +26,15 @@ type ScanRemoteMap = TMVar (M.Map Remote ScanInfo)
 newScanRemoteMap :: IO ScanRemoteMap
 newScanRemoteMap = atomically newEmptyTMVar
 
-{- Blocks until there is a remote that needs to be scanned.
+{- Blocks until there is a remote or remotes that need to be scanned.
- - Processes higher priority remotes first. -}
+ -
-getScanRemote :: ScanRemoteMap -> IO (Remote, ScanInfo)
+ - The list has higher priority remotes listed first. -}
-getScanRemote v = atomically $ do
+getScanRemote :: ScanRemoteMap -> IO [(Remote, ScanInfo)]
-	m <- takeTMVar v
+getScanRemote v = atomically $
-	let l = reverse $ sortBy (compare `on` scanPriority . snd) $ M.toList m
+	reverse . sortBy (compare `on` scanPriority . snd) . M.toList
-	case l of
+		<$> takeTMVar v
-		[] -> retry -- should never happen
-		(ret@(r, _):_) -> do
-			let m' = M.delete r m
-			unless (M.null m') $
-				putTMVar v m'
-			return ret
 
-{- Adds new remotes that need scanning to the map. -}
+{- Adds new remotes that need scanning. -}
 addScanRemotes :: ScanRemoteMap -> Bool -> [Remote] -> IO ()
 addScanRemotes _ _ [] = noop
 addScanRemotes v full rs = atomically $ do

Assistant/Sync.hs

@@ -28,8 +28,8 @@ import qualified Data.Map as M
  - 
  - First gets git in sync, and then prepares any necessary file transfers.
  -
- - An expensive full scan is queued when the git-annex branches of the
+ - An expensive full scan is queued when the git-annex branches of some of
- - remotes have diverged from the local git-annex branch. Otherwise,
+ - the remotes have diverged from the local git-annex branch. Otherwise,
  - it's sufficient to requeue failed transfers.
  -}
 reconnectRemotes :: ThreadName -> ThreadState -> DaemonStatusHandle -> ScanRemoteMap -> [Remote] -> IO ()

Assistant/Threads/TransferScanner.hs

@@ -36,13 +36,13 @@ transferScannerThread st dstatus scanremotes transferqueue = do
 	where
 		go scanned = do
 			threadDelaySeconds (Seconds 2)
-			(r, info) <- getScanRemote scanremotes
+			(rs, infos) <- unzip <$> getScanRemote scanremotes
-			if fullScan info || not (S.member r scanned)
+			if any fullScan infos || any (`S.notMember` scanned) rs
 				then do
-					expensiveScan st dstatus transferqueue r
+					expensiveScan st dstatus transferqueue rs
-					go (S.insert r scanned)
+					go (S.union scanned (S.fromList rs))
 				else do
-					failedTransferScan st dstatus transferqueue r
+					mapM_ (failedTransferScan st dstatus transferqueue) rs
 					go scanned
 		{- All available remotes are scanned in full on startup,
 		 - for multiple reasons, including:
@@ -92,39 +92,39 @@ failedTransferScan st dstatus transferqueue r = do
 		dequeue t = void $ runThreadState st $ inRepo $
 			liftIO . tryIO . removeFile . failedTransferFile t
 
-{- This is a expensive scan through the full git work tree.
+{- This is a expensive scan through the full git work tree, finding
+ - files to download from or upload to any of the remotes.
  - 
  - The scan is blocked when the transfer queue gets too large. -}
-expensiveScan :: ThreadState -> DaemonStatusHandle -> TransferQueue -> Remote -> IO ()
+expensiveScan :: ThreadState -> DaemonStatusHandle -> TransferQueue -> [Remote] -> IO ()
-expensiveScan st dstatus transferqueue r = do
+expensiveScan st dstatus transferqueue rs = do
-	liftIO $ debug thisThread ["starting scan of", show r]
+	liftIO $ debug thisThread ["starting scan of", show rs]
-	void $ alertWhile dstatus (scanAlert r) $ do
+	void $ alertWhile dstatus (scanAlert rs) $ do
 		g <- runThreadState st $ fromRepo id
 		files <- LsFiles.inRepo [] g
 		go files
 		return True
-	liftIO $ debug thisThread ["finished scan of", show r]
+	liftIO $ debug thisThread ["finished scan of", show rs]
 	where
 		go [] = noop
 		go (f:fs) = do
-			v <- runThreadState st $ whenAnnexed check f
+			mapM_ (enqueue f) =<< catMaybes <$> runThreadState st
-			case v of
+				(ifAnnexed f findtransfers $ return [])
-				Nothing -> noop
-				Just t -> do
-					debug thisThread ["queuing", show t]
-					enqueue f t
 			go fs
-			where
+		enqueue f (r, t) = do
-				check _ (key, _) = ifM (inAnnex key)
+			debug thisThread ["queuing", show t]
-					( helper key Upload False =<< remoteHas r key
+			queueTransferWhenSmall transferqueue dstatus (Just f) t r
-					, helper key Download True =<< remoteHas r key
+		findtransfers (key, _) = do
-					)
+			locs <- loggedLocations key
-				helper key direction x y
+			let use a = return $ map (a key locs) rs
-					| x == y = return $ Just $
+			ifM (inAnnex key)
-						Transfer direction (Remote.uuid r) key
+				( use $ check Upload False
-					| otherwise = return Nothing
+				, use $ check Download True
-				
+				)
-		enqueue f t = queueTransferWhenSmall transferqueue dstatus (Just f) t r
+		check direction want key locs r
+			| (Remote.uuid r `elem` locs) == want = Just $
+				(r, Transfer direction (Remote.uuid r) key)
+			| otherwise = Nothing
 
 remoteHas :: Remote -> Key -> Annex Bool
 remoteHas r key = elem