Commit 5052fee2 authored by Lars Ellenberg's avatar Lars Ellenberg Committed by Jens Axboe

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: default avatarPhilipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: default avatarLars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent 505675f9
...@@ -770,10 +770,18 @@ static bool lazy_bitmap_update_due(struct drbd_device *device) ...@@ -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) static void maybe_schedule_on_disk_bitmap_update(struct drbd_device *device, bool rs_done)
{ {
if (rs_done) 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); set_bit(RS_DONE, &device->flags);
/* and also set RS_PROGRESS below */ /* and also set RS_PROGRESS below */
else if (!lazy_bitmap_update_due(device))
/* 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; return;
drbd_device_post_work(device, RS_PROGRESS); drbd_device_post_work(device, RS_PROGRESS);
......
...@@ -2102,13 +2102,22 @@ static inline void _sub_unacked(struct drbd_device *device, int n, const char *f ...@@ -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); 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) static inline bool is_sync_state(enum drbd_conns connection_state)
{ {
return return is_sync_source_state(connection_state) ||
(connection_state == C_SYNC_SOURCE is_sync_target_state(connection_state);
|| connection_state == C_SYNC_TARGET
|| connection_state == C_PAUSED_SYNC_S
|| connection_state == C_PAUSED_SYNC_T);
} }
/** /**
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment