NetWatcher: When dbus connection is lost, try to reconnect.

MountWatcher can't do this, because it uses the session dbus,
and won't have access to the new DBUS_SESSION_BUS_ADDRESS if a new session
is started.

Bumped dbus library version, FD leak in it is fixed.

Assistant/Threads/MountWatcher.hs

@@ -72,6 +72,11 @@ dbusThread st dstatus scanremotes = E.catch (runClient getSessionAddress go) one
 			)
 		onerr :: E.SomeException -> IO ()
 		onerr e = do
+			{- If the session dbus fails, the user probably
+			 - logged out of their desktop. Even if they log
+			 - back in, we won't have access to the dbus
+			 - session key, so polling is the best that can be
+			 - done in this situation. -}
 			runThreadState st $
 				warning $ "dbus failed; falling back to mtab polling (" ++ show e ++ ")"
 			pollinstead

Assistant/Threads/NetWatcher.hs

@@ -24,7 +24,6 @@ import Utility.DBus
 import DBus.Client
 import DBus
 import Data.Word (Word32)
-import qualified Control.Exception as E
 #else
 #warning Building without dbus support; will poll for network connection changes
 #endif
@@ -57,22 +56,24 @@ netWatcherFallbackThread st dstatus scanremotes = thread $
 #if WITH_DBUS
 
 dbusThread :: ThreadState -> DaemonStatusHandle -> ScanRemoteMap -> IO ()
-dbusThread st dstatus scanremotes = E.catch (runClient getSystemAddress go) onerr
+dbusThread st dstatus scanremotes = persistentClient getSystemAddress () onerr go
 	where
 		go client = ifM (checkNetMonitor client)
 			( do
-				listenNMConnections client handle
+				listenNMConnections client handleconn
-				listenWicdConnections client handle
+				listenWicdConnections client handleconn
 			, do
 				runThreadState st $
 					warning "No known network monitor available through dbus; falling back to polling"
 			)
-		onerr :: E.SomeException -> IO ()
+		handleconn = do
-		onerr e = runThreadState st $
-			warning $ "dbus failed; falling back to polling (" ++ show e ++ ")"
-		handle = do
 			debug thisThread ["detected network connection"]
 			handleConnection st dstatus scanremotes
+		onerr e _ = do
+			runThreadState st $
+				warning $ "lost dbus connection; falling back to polling (" ++ show e ++ ")"
+			{- Wait, in hope that dbus will come back -}
+			threadDelaySeconds (Seconds 60)
 
 {- Examine the list of services connected to dbus, to see if there
  - are any we can use to monitor network connections. -}

Utility/DBus.hs

@@ -5,7 +5,7 @@
  - Licensed under the GNU GPL version 3 or higher.
  -}
 
-{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE OverloadedStrings, ScopedTypeVariables #-}
 
 module Utility.DBus where
 
@@ -65,15 +65,15 @@ runClient getaddr clientaction = do
  - If the connection is lost, runs onretry, which can do something like
  - a delay, or printing a warning, and has a state value (useful for
  - exponential backoff). Once onretry returns, the connection is retried.
- - 
+ -}
- - Warning: Currently connectWith can throw a SocketError and leave behind
- - an open FD. So each retry leaks one FD. -}
 persistentClient :: IO (Maybe Address) -> v -> (SomeException -> v -> IO v) -> (Client -> IO ()) -> IO ()
-persistentClient getaddr v onretry clientaction = do
+persistentClient getaddr v onretry clientaction =
 	{- runClient can fail with not just ClientError, but also other
-	 - things, if dbus is not running. -}
+	 - things, if dbus is not running. Let async exceptions through. -}
-	r <- E.try (runClient getaddr clientaction) :: IO (Either SomeException ())
+	runClient getaddr clientaction `E.catches`
-	either retry return r
+		[ Handler (\ (e :: AsyncException) -> E.throw e)
+		, Handler (\ (e :: SomeException) -> retry e)
+		]
 	where
 		retry e = do
 			v' <- onretry e v

debian/changelog

@@ -24,6 +24,7 @@ git-annex (3.20121018) UNRELEASED; urgency=low
   * configure: Check that checksum programs produce correct checksums.
   * Re-enable dbus, using a new version of the library that fixes the memory
     leak.
+  * NetWatcher: When dbus connection is lost, try to reconnect.
   * Use USER and HOME environment when set, and only fall back to getpwent,
     which doesn't work with LDAP or NIS.
 

debian/control

@@ -22,7 +22,7 @@ Build-Depends:
 	libghc-edit-distance-dev,
 	libghc-hinotify-dev [linux-any],
 	libghc-stm-dev (>= 2.3),
-	libghc-dbus-dev [linux-any] (>= 0.10.2),
+	libghc-dbus-dev [linux-any] (>= 0.10.3),
 	libghc-yesod-dev [i386 amd64 kfreebsd-i386 kfreebsd-amd64],
 	libghc-yesod-static-dev [i386 amd64 kfreebsd-i386 kfreebsd-amd64],
 	libghc-yesod-default-dev [i386 amd64 kfreebsd-i386 kfreebsd-amd64],

git-annex.cabal

@@ -77,7 +77,7 @@ Executable git-annex
       C-Sources: Utility/libkqueue.c
 
   if os(linux) && flag(Dbus)
-    Build-Depends: dbus (>= 0.10.2)
+    Build-Depends: dbus (>= 0.10.3)
     CPP-Options: -DWITH_DBUS
 
   if flag(Webapp) && flag(Assistant)