#At file:///media/sdb2/hezx/work/mysql/bzrwork/b41188/6.0-rpl/
2773 He Zhenxing 2008-12-29
BUG#41188 rpl_ndb_denote_gap fails sporadically: wrong Last_IO_Error
When master shuts down, the slave I/O thread can fail due to
various reasons, and result in various error code and message,
for example:
1) reconnect error
2) error in get_master_version_and_clock
3) error in register_slave_on_master
The actual situation can be more complicated than this.
There are some other problems with this test case:
1) in include/wait_until_disconnected.inc, which set the
mysql_errno to a wrong value
2) waiting for reconnection on the wrong host
3) did not start slave after slave stops, and the reason why it
worked was because when SHOW SLAVE STATUS says I/O slave is
not running, it can be RUN_NOT_CONNECT and reconnecting, so
when the master later comes up soon enough, it will
reconnect to the master.
This patch fixes the problem by:
1) removing I/O thread error code and message because they
varies and are not important to this test
2) adding missing --connection master before waiting
reconnection to master
3) starting slave IO thread before waiting for SQL thread to
stop
4) adding warning suppression for slave I/O thread
modified:
mysql-test/suite/rpl/t/rpl_slave_status.test
mysql-test/suite/rpl_ndb/r/rpl_ndb_denote_gap.result
mysql-test/suite/rpl_ndb/t/rpl_ndb_denote_gap.test
per-file messages:
mysql-test/suite/rpl/t/rpl_slave_status.test
wait slave I/O to stop before show status
mysql-test/suite/rpl_ndb/r/rpl_ndb_denote_gap.result
update result
mysql-test/suite/rpl_ndb/t/rpl_ndb_denote_gap.test
Add missing --connection master before waiting reconnection to
master
Start slave IO thread before waiting for SQL thread to stop
Remove showing the error code and message after master shutdown
because they can vary and are not neccessary for this
=== modified file 'mysql-test/suite/rpl/t/rpl_slave_status.test'
--- a/mysql-test/suite/rpl/t/rpl_slave_status.test 2008-12-24 10:48:24 +0000
+++ b/mysql-test/suite/rpl/t/rpl_slave_status.test 2008-12-29 09:16:51 +0000
@@ -54,6 +54,7 @@ sync_slave_with_master;
source include/stop_slave.inc;
start slave;
source include/wait_for_slave_sql_to_start.inc;
+source include/wait_for_slave_io_to_stop.inc;
--echo ==== Verify that Slave_IO_Running = No ====
let $result= query_get_value("SHOW SLAVE STATUS", Slave_IO_Running, 1);
=== modified file 'mysql-test/suite/rpl_ndb/r/rpl_ndb_denote_gap.result'
--- a/mysql-test/suite/rpl_ndb/r/rpl_ndb_denote_gap.result 2008-09-09 18:47:34 +0000
+++ b/mysql-test/suite/rpl_ndb/r/rpl_ndb_denote_gap.result 2008-12-29 09:16:51 +0000
@@ -9,9 +9,8 @@ start slave;
* slave status*
Slave_IO_Running = No
Slave_SQL_Running = Yes
-Last_IO_Errno = 2013
-Last_IO_Error = error reconnecting to master
* start master *
+start slave io_thread;
* slave status *
Slave_IO_Running = Yes
Slave_SQL_Running = No
=== modified file 'mysql-test/suite/rpl_ndb/t/rpl_ndb_denote_gap.test'
--- a/mysql-test/suite/rpl_ndb/t/rpl_ndb_denote_gap.test 2008-09-09 18:47:34 +0000
+++ b/mysql-test/suite/rpl_ndb/t/rpl_ndb_denote_gap.test 2008-12-29 09:16:51 +0000
@@ -15,6 +15,18 @@
--source include/ndb_master-slave.inc
--echo
+# When master shuts down, the slave I/O thread can fail due to various
+# reasons, and result in various error code and message, for example:
+# 1) reconnect error
+# 2) error in get_master_version_and_clock
+# 3) error in register_slave_on_master
+# So add suppresions for these errors.
+--disable_query_log
+call mtr.add_suppression("slave I/O thread stops");
+call mtr.add_suppression("Slave I/O thread couldn't register on master");
+call mtr.add_suppression("Slave I/O: Master command COM_REGISTER_SLAVE failed");
+--enable_query_log
+
# Stop master mysql server
--echo * shutdown master *
--connection master
@@ -32,12 +44,6 @@ let $io_run= query_get_value("SHOW SLAVE
echo Slave_IO_Running = $io_run;
let $sql_run= query_get_value("SHOW SLAVE STATUS", Slave_SQL_Running, 1);
echo Slave_SQL_Running = $sql_run;
-let $errno= query_get_value("SHOW SLAVE STATUS", Last_IO_Errno, 1);
-echo Last_IO_Errno = $errno;
-let $error= query_get_value("SHOW SLAVE STATUS", Last_IO_Error, 1);
-#--eval SELECT SUBSTRING_INDEX('$error', 'master', -1)
-let $error= `SELECT SUBSTRING_INDEX("$error", "'", 1)`;
-echo Last_IO_Error = $error;
# Start master server again
--echo * start master *
@@ -46,11 +52,31 @@ restart
EOF
# Reconnect to master
+--connection master
--enable_reconnect
--source include/wait_until_connected_again.inc
-# Wait for stop slave SQL thread with error LOST EVENTS
--connection slave
+
+# restart the slave IO thread
+#
+# NOTE: wait_for_slave_io_to_stop.inc above only waits for the
+# Slave_IO_running of SHOW SLAVE STATUS to become 'No', but this does
+# not mean the slave I/O thread is truly stopped, it will try to
+# reconnect to master for 'master_retry_count' times before giving up,
+# so if later the master restarts quickly enough, the slave I/O thread
+# will automatically reconnect to master and running.
+#
+# So the slave I/O thread still be running and the following statement
+# can emit a warning.
+#
+# See BUG#41613, this restriction can be lifted if this bug is fixed.
+#
+--disable_warnings
+start slave io_thread;
+--enable_warnings
+
+# Wait for stop slave SQL thread with error LOST EVENTS
--source include/wait_for_slave_sql_to_stop.inc
--echo * slave status *
let $io_run= query_get_value("SHOW SLAVE STATUS", Slave_IO_Running, 1);
