drbd: finish resync on sync source only by notification from sync target

If the replication link breaks exactly during "resync finished" detection,
finishing too early on the sync source could again lead to UUIDs rotated
too fast, and potentially a spurious full resync on next handshake.

Always wait for explicit resync finished state change notification from
the sync target.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 265b2b6..cafa9c4 100644 (file)
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -770,10 +770,18 @@ static bool lazy_bitmap_update_due(struct drbd_device *device)
 
 static void maybe_schedule_on_disk_bitmap_update(struct drbd_device *device, bool rs_done)
 {
-       if (rs_done)
-               set_bit(RS_DONE, &device->flags);
-               /* and also set RS_PROGRESS below */
-       else if (!lazy_bitmap_update_due(device))
+       if (rs_done) {
+               struct drbd_connection *connection = first_peer_device(device)->connection;
+               if (connection->agreed_pro_version <= 95 ||
+                   is_sync_target_state(device->state.conn))
+                       set_bit(RS_DONE, &device->flags);
+                       /* and also set RS_PROGRESS below */
+
+               /* Else: rather wait for explicit notification via receive_state,
+                * to avoid uuids-rotated-too-fast causing full resync
+                * in next handshake, in case the replication link breaks
+                * at the most unfortunate time... */
+       } else if (!lazy_bitmap_update_due(device))
                return;
 
        drbd_device_post_work(device, RS_PROGRESS);

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9c68ec5..c5dbc85 100644 (file)
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -2102,13 +2102,22 @@ static inline void _sub_unacked(struct drbd_device *device, int n, const char *f
        ERR_IF_CNT_IS_NEGATIVE(unacked_cnt, func, line);
 }
 
+static inline bool is_sync_target_state(enum drbd_conns connection_state)
+{
+       return  connection_state == C_SYNC_TARGET ||
+               connection_state == C_PAUSED_SYNC_T;
+}
+
+static inline bool is_sync_source_state(enum drbd_conns connection_state)
+{
+       return  connection_state == C_SYNC_SOURCE ||
+               connection_state == C_PAUSED_SYNC_S;
+}
+
 static inline bool is_sync_state(enum drbd_conns connection_state)
 {
-       return
-          (connection_state == C_SYNC_SOURCE
-       ||  connection_state == C_SYNC_TARGET
-       ||  connection_state == C_PAUSED_SYNC_S
-       ||  connection_state == C_PAUSED_SYNC_T);
+       return  is_sync_source_state(connection_state) ||
+               is_sync_target_state(connection_state);
 }
 
 /**