drbd: Work on the Ahead -> SyncSource transition

The test if rs_pending_cnt == 0 was too weak. Using Test for
unacked_cnt == 0 instead. Moved that into the worker.

Since unacked_cnt gets already increased when an P_RS_DATA_REQ
comes in.

Also using a timer to make Ahead -> SyncSource -> Ahead cycles
slower...
Signed-off-by: NPhilipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: NLars Ellenberg <lars.ellenberg@linbit.com>

drivers/block/drbd/drbd_int.h

@@ -850,6 +850,7 @@ enum {
 	GOT_PING_ACK,		/* set when we receive a ping_ack packet, misc wait gets woken */
 	NEW_CUR_UUID,		/* Create new current UUID when thawing IO */
 	AL_SUSPENDED,		/* Activity logging is currently suspended. */
+	AHEAD_TO_SYNC_SOURCE,   /* Ahead -> SyncSource queued */
 };
 
 struct drbd_bitmap; /* opaque for drbd_conf */
@@ -961,6 +962,7 @@ struct drbd_conf {
 			  start_resync_work;
 	struct timer_list resync_timer;
 	struct timer_list md_sync_timer;
+	struct timer_list start_resync_timer;
 #ifdef DRBD_DEBUG_MD_SYNC
 	struct {
 		unsigned int line;
@@ -1544,6 +1546,7 @@ extern int w_send_oos(struct drbd_conf *, struct drbd_work *, int);
 extern int w_start_resync(struct drbd_conf *, struct drbd_work *, int);
 
 extern void resync_timer_fn(unsigned long data);
+extern void start_resync_timer_fn(unsigned long data);
 
 /* drbd_receiver.c */
 extern int drbd_rs_should_slow_down(struct drbd_conf *mdev, sector_t sector);

drivers/block/drbd/drbd_main.c

@@ -2984,12 +2984,16 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 	mdev->go_diskless.cb  = w_go_diskless;
 	mdev->md_sync_work.cb = w_md_sync;
 	mdev->bm_io_work.w.cb = w_bitmap_io;
+	mdev->start_resync_work.cb = w_start_resync;
 	init_timer(&mdev->resync_timer);
 	init_timer(&mdev->md_sync_timer);
+	init_timer(&mdev->start_resync_timer);
 	mdev->resync_timer.function = resync_timer_fn;
 	mdev->resync_timer.data = (unsigned long) mdev;
 	mdev->md_sync_timer.function = md_sync_timer_fn;
 	mdev->md_sync_timer.data = (unsigned long) mdev;
+	mdev->start_resync_timer.function = start_resync_timer_fn;
+	mdev->start_resync_timer.data = (unsigned long) mdev;
 
 	init_waitqueue_head(&mdev->misc_wait);
 	init_waitqueue_head(&mdev->state_wait);

drivers/block/drbd/drbd_receiver.c

@@ -4392,11 +4392,9 @@ static int got_BarrierAck(struct drbd_conf *mdev, struct p_header80 *h)
 
 	if (mdev->state.conn == C_AHEAD &&
 	    atomic_read(&mdev->ap_in_flight) == 0 &&
-	    atomic_read(&mdev->rs_pending_cnt) == 0 &&
-	    list_empty(&mdev->start_resync_work.list)) {
-		    struct drbd_work *w = &mdev->start_resync_work;
-		    w->cb = w_start_resync;
-		    drbd_queue_work(&mdev->data.work, w);
+	    !test_and_set_bit(AHEAD_TO_SYNC_SOURCE, &mdev->current_epoch->flags)) {
+		mdev->start_resync_timer.expires = jiffies + HZ;
+		add_timer(&mdev->start_resync_timer);
 	}
 
 	return true;

drivers/block/drbd/drbd_worker.c

@@ -712,10 +712,24 @@ static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int ca
 }
 
 
+void start_resync_timer_fn(unsigned long data)
+{
+	struct drbd_conf *mdev = (struct drbd_conf *) data;
+
+	drbd_queue_work(&mdev->data.work, &mdev->start_resync_work);
+}
+
 int w_start_resync(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 {
-	drbd_start_resync(mdev, C_SYNC_SOURCE);
+	if (atomic_read(&mdev->unacked_cnt) || atomic_read(&mdev->rs_pending_cnt)) {
+		dev_warn(DEV, "w_start_resync later...\n");
+		mdev->start_resync_timer.expires = jiffies + HZ/10;
+		add_timer(&mdev->start_resync_timer);
+		return 1;
+	}
 
+	drbd_start_resync(mdev, C_SYNC_SOURCE);
+	clear_bit(AHEAD_TO_SYNC_SOURCE, &mdev->current_epoch->flags);
 	return 1;
 }