Galera SST donation fails, FLUSH TABLES WITH READ LOCK times out

2020-05-13 10:18:44 139871772944128 [Note] WSREP: sst_donor_thread signaled with 0

2020-05-13 10:18:45 139871226160896 [Note] WSREP: Flushing tables for SST...

2020-05-13 10:18:46 139871226160896 [Warning] WSREP: Error executing 'FLUSH TABLES WITH READ LOCK': 1205 (Lock wait timeout exceeded; try restarting transaction)

2020-05-13 10:18:46 139871226160896 [ERROR] WSREP: Failed to flush and lock tables

# The test verifies that the FLUSH TABLES WITH READ LOCK does not

# time out if it needs to wait for another MDL lock for short duration

# during SST donation.

--source include/galera_cluster.inc

--let $node_1 = node_1

--let $node_2 = node_2

--source include/auto_increment_offset_save.inc

--let $galera_connection_name = node_1_ctrl

--let $galera_server_number = 1

--source include/galera_connect.inc

#

# Run UPDATE on node_1 and make it block before table locks are taken.

# This should block FTWRL.

#

--connection node_1

CREATE TABLE t1 (f1 INT PRIMARY KEY, f2 INT);

INSERT INTO t1 VALUES (1, 1);

SET DEBUG_SYNC = "before_lock_tables_takes_lock SIGNAL sync_point_reached WAIT_FOR sync_point_continue";

--send UPDATE t1 SET f2 = 2 WHERE f1 = 1

--connection node_1_ctrl

SET DEBUG_SYNC = "now WAIT_FOR sync_point_reached";

#

# Restart node_2, force SST.

#

--connection node_2

--source include/shutdown_mysqld.inc

--remove_file $MYSQLTEST_VARDIR/mysqld.2/data/grastate.dat

# Restart without waiting. The UPDATE should block FTWRL on node_1,

# so the SST cannot be completed and node_2 cannot join before

# UPDATE connection is signalled to continue.

--exec echo "restart:$start_mysqld_params" > $_expect_file_name

# If the bug is present, FTWRL times out on node_1 in couple of

# seconds and node_2 fails to join.

--sleep 10

--connection node_1_ctrl

SET DEBUG_SYNC = "now SIGNAL sync_point_continue";

--connection node_1

--reap

SET DEBUG_SYNC = "RESET";

--connection node_2

--enable_reconnect

--source include/wait_until_connected_again.inc

--connection node_1

DROP TABLE t1;

--source include/auto_increment_offset_restore.inc

    /* Check if the client is gone while we were waiting. */

    if (! thd_is_connected(m_owner->get_thd()))

    {

      /*

       * The client is disconnected. Don't wait forever:

       * assume it's the same as a wait timeout, this

       * ensures all error handling is correct.

       */

      wait_status= MDL_wait::TIMEOUT;

      break;

    }