BUG#37717: rpl.rpl_stm_until 'stmt' fails sporadically on pushbuild

Problem: After START SLAVE, the Slave_IO_Status column of
SHOW SLAVE STATUS goes from No to Yes asynchronously. That
caused sporadic failures on pushbuild in rpl_stm_until since
the test contains SHOW SLAVE STATUS right after START SLAVE.
Fix: Wait until Slave_IO_Status becomes Yes after each
START SLAVE.

mysql-test/include/wait_for_slave_io_to_start.inc

@@ -0,0 +1,19 @@
+# ==== Purpose ====
+#
+# Waits until the IO thread of the current connection has started and
+# connected to the master (i.e., until SHOW SLAVE STATUS returns Yes
+# in the Slave_IO_Running field), or until a timeout is reached.
+#
+# ==== Usage ====
+#
+# source include/wait_for_slave_io_to_start.inc;
+#
+# Parameters to this macro are $slave_timeout and
+# $slave_keep_connection. See wait_for_slave_param.inc for
+# descriptions.
+
+let $slave_param= Slave_IO_Running;
+let $slave_param_value= Yes;
+let $slave_error_message= Failed while waiting for slave IO thread to start;
+source include/wait_for_slave_param.inc;
+let $slave_error_message= ;

mysql-test/suite/rpl/r/rpl_stm_until.result

@@ -4,7 +4,10 @@ reset master;
 reset slave;
 drop table if exists t1,t2,t3,t4,t5,t6,t7,t8,t9;
 start slave;
+[on slave]
 include/stop_slave.inc
+==== Create some events on master ====
+[on master]
 create table t1(n int not null auto_increment primary key);
 insert into t1 values (1),(2),(3),(4);
 drop table t1;
@@ -12,6 +15,8 @@ create table t2(n int not null auto_increment primary key);
 insert into t2 values (1),(2);
 insert into t2 values (3),(4);
 drop table t2;
+==== Replicate one event at a time on slave ====
+[on slave]
 start slave until master_log_file='master-bin.000001', master_log_pos=323;
 select * from t1;
 n
@@ -149,6 +154,8 @@ Last_IO_Error	#
 Last_SQL_Errno	0
 Last_SQL_Error	
 start slave;
+[on master]
+[on slave]
 include/stop_slave.inc
 start slave until master_log_file='master-bin.000001', master_log_pos=776;
 SHOW SLAVE STATUS;
@@ -190,6 +197,7 @@ Last_IO_Errno	#
 Last_IO_Error	#
 Last_SQL_Errno	0
 Last_SQL_Error	
+==== Test various error conditions ====
 start slave until master_log_file='master-bin', master_log_pos=561;
 ERROR HY000: Incorrect parameter or combination of parameters for START SLAVE UNTIL
 start slave until master_log_file='master-bin.000001', master_log_pos=561, relay_log_pos=12;

mysql-test/suite/rpl/t/rpl_stm_until.test

@@ -1,18 +1,37 @@
+# ==== Purpose ====
+#
+# Verify that START SLAVE UNTIL replicates until the given binlog
+# position but not longer.  Verify that START SLAVE UNTIL with various
+# incorrect arguments gives an error.
+#
+# ==== Method ====
+#
+# On master, create a table and insert some rows.  On slave, START
+# SLAVE UNTIL so that it reads one event at a time, and check the
+# table and the slave status each time.
+#
+# Then, on slave, run START SLAVE UNTIL with incorrect arguments and
+# verify that it gives an error.
+#
+# ==== Related bugs ====
+#
+# Bug in this test: BUG#37717: rpl.rpl_stm_until 'stmt' fails sporadically on pushbuild
+
 -- source include/have_binlog_format_mixed_or_statement.inc
 -- source include/master-slave.inc
 
 # Test is dependent on binlog positions
 
-# prepare version for substitutions
-let $VERSION=`select version()`;
-
-# stop slave before he will start replication also sync with master
-# for avoiding undetermenistic behaviour
+# Stop slave before it starts replication.  Also sync with master
+# to avoid nondeterministic behaviour.
+--echo [on slave]
 sync_slave_with_master;
 --source include/stop_slave.inc
 
+--echo ==== Create some events on master ====
+
+--echo [on master]
 connection master;
-# create some events on master
 create table t1(n int not null auto_increment primary key);
 insert into t1 values (1),(2),(3),(4);
 drop table t1;
@@ -21,9 +40,13 @@ insert into t2 values (1),(2);
 insert into t2 values (3),(4);
 drop table t2;
 
+--echo ==== Replicate one event at a time on slave ====
+
 # try to replicate all queries until drop of t1
+--echo [on slave]
 connection slave;
 start slave until master_log_file='master-bin.000001', master_log_pos=323;
+--source include/wait_for_slave_io_to_start.inc
 --source include/wait_for_slave_sql_to_stop.inc
 # here table should be still not deleted
 select * from t1;
@@ -31,6 +54,7 @@ source include/show_slave_status2.inc;
 
 # this should fail right after start
 start slave until master_log_file='master-no-such-bin.000001', master_log_pos=291;
+--source include/wait_for_slave_io_to_start.inc
 --source include/wait_for_slave_sql_to_stop.inc
 # again this table should be still not deleted
 select * from t1;
@@ -38,24 +62,28 @@ source include/show_slave_status2.inc;
 
 # try replicate all up to and not including the second insert to t2;
 start slave until relay_log_file='slave-relay-bin.000004', relay_log_pos=746;
+--source include/wait_for_slave_io_to_start.inc
 --source include/wait_for_slave_sql_to_stop.inc
 select * from t2;
 source include/show_slave_status2.inc;
 
 # clean up
 start slave;
+--echo [on master]
 connection master;
+--echo [on slave]
 sync_slave_with_master;
 --source include/stop_slave.inc
 
 # this should stop immediately as we are already there
 start slave until master_log_file='master-bin.000001', master_log_pos=776;
+--source include/wait_for_slave_io_to_start.inc
 --source include/wait_for_slave_sql_to_stop.inc
-# here the sql slave thread should be stopped
 --replace_result bin.000005 bin.000004 bin.000006 bin.000004 bin.000007 bin.000004
 source include/show_slave_status2.inc;
 
-#testing various error conditions
+--echo ==== Test various error conditions ====
+
 --error 1277
 start slave until master_log_file='master-bin', master_log_pos=561;
 --error 1277
@@ -70,4 +98,3 @@ start slave until relay_log_file='slave-relay-bin.000002', master_log_pos=561;
 start slave sql_thread;
 start slave until master_log_file='master-bin.000001', master_log_pos=776;
 
-# End of 4.1 tests