################################################################################ # Validate that the replication asynchronous connection failover feature for # Managed_type 'GroupReplication', when a group member becomes UNREACHABLE and # return without starting Group Replication is not considered healthy, even when # it has the highest weight. # # Test: # 0. The test requires 4 servers: # server1: group primary # server2: group secondary # server3: group secondary # server4: replica server # 1. Deploy a 3 members group in single primary mode. # Set group_replication_member_expel_timeout to 3600, so # that a UNREACHABLE member is only expelled after 1 hour. # 2. Configure replica to manage the asynchronous connection # to group. # 3. Create and start the managed channel connected to server1. # 4. Kill server1. # Server will return without starting Group Replication. # 5. Validate that replica is connected to server2 or server3. # Server1 is back and has the highest weight, but since it # is not part of the group it cannot be selected as the sender. # 6. Wait 30 seconds and validate that replica is still connected # to server2 or server3. # 7. Assert that group information did not change, since the # missing member is UNREACHABLE # 8. Revert group_replication_member_expel_timeout to the # default value on server2 and server3, which will cause # server1 to be expelled. # 9. server1 was removed from performance_schema.replication_asynchronous_connection_failover table. # server4 is connected to the group primary. # 10. Clean up. ################################################################################ --source include/big_test.inc --source include/not_valgrind.inc --source include/have_group_replication_plugin.inc --let $rpl_skip_group_replication_start= 1 --let $rpl_server_count= 4 --let $group_replication_group_name= aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa --source include/group_replication.inc --echo --echo ############################################################ --echo # 1. Deploy a 3 members group in single primary mode. --echo # Set group_replication_member_expel_timeout to 3600, so --echo # that a UNREACHABLE member is only expelled after 1 hour. --let $rpl_connection_name= server1 --source include/rpl_connection.inc --let $server1_uuid= `SELECT @@server_uuid` SET GLOBAL group_replication_member_expel_timeout = 3600; --source include/start_and_bootstrap_group_replication.inc --let $rpl_connection_name= server2 --source include/rpl_connection.inc --let $server2_uuid= `SELECT @@server_uuid` SET GLOBAL group_replication_member_expel_timeout = 3600; --source include/start_group_replication.inc --let $rpl_connection_name= server3 --source include/rpl_connection.inc --let $server3_uuid= `SELECT @@server_uuid` SET GLOBAL group_replication_member_expel_timeout = 3600; --source include/start_group_replication.inc --echo --echo ############################################################ --echo # 2. Configure replica to manage the asynchronous connection --echo # to group. --let $rpl_connection_name= server4 --source include/rpl_connection.inc --replace_result $SERVER_MYPORT_1 SERVER_MYPORT_1 $group_replication_group_name GROUP_NAME --eval SELECT asynchronous_connection_failover_add_managed('ch1', 'GroupReplication', '$group_replication_group_name', '127.0.0.1', $SERVER_MYPORT_1, '', 90, 70); --let $assert_text= 'There is one row in performance_schema.replication_asynchronous_connection_failover for server1' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover WHERE port=$SERVER_MYPORT_1, count, 1] = 1 --source include/assert.inc --let $assert_text= 'There is one row in performance_schema.replication_asynchronous_connection_failover_managed for server1' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover_managed WHERE managed_name="$group_replication_group_name", count, 1] = 1 --source include/assert.inc --echo --echo ############################################################ --echo # 3. Create and start the managed channel connected to server1. --let $rpl_connection_name= server4 --source include/rpl_connection.inc --replace_result $SERVER_MYPORT_1 SERVER_1_PORT --eval CHANGE REPLICATION SOURCE TO SOURCE_HOST='127.0.0.1', SOURCE_USER='root', SOURCE_AUTO_POSITION=1, SOURCE_CONNECTION_AUTO_FAILOVER=1, SOURCE_PORT=$SERVER_MYPORT_1, SOURCE_RETRY_COUNT=1, SOURCE_CONNECT_RETRY=1 FOR CHANNEL 'ch1' --let $rpl_channel_name='ch1' --source include/start_slave.inc --let $rpl_channel_name= --let $assert_text= Verify channel ch1 IO_THREAD is ON and connected to server1 --let $assert_cond= "[SELECT SERVICE_STATE FROM performance_schema.replication_connection_status WHERE channel_name=\'ch1\' AND source_uuid=\'$server1_uuid\', SERVICE_STATE, 1]" = "ON" --source include/assert.inc --let $wait_condition= SELECT COUNT(*)=3 FROM performance_schema.replication_asynchronous_connection_failover --source include/wait_condition.inc --echo --echo ############################################################ --echo # 4. Kill server1. --echo # Server will return without starting Group Replication. --let $rpl_connection_name= server1 --source include/rpl_connection.inc --source include/kill_and_restart_mysqld.inc --let $rpl_server_number= 1 --source include/rpl_reconnect.inc --let $rpl_connection_name= server2 --source include/rpl_connection.inc --let $group_replication_member_state= UNREACHABLE --let $group_replication_member_id= $server1_uuid --source include/gr_wait_for_member_state.inc --let $rpl_connection_name= server3 --source include/rpl_connection.inc --let $group_replication_member_state= UNREACHABLE --let $group_replication_member_id= $server1_uuid --source include/gr_wait_for_member_state.inc --echo --echo ############################################################ --echo # 5. Validate that replica is connected to server2 or server3. --echo # Server1 is back and has the highest weight, but since it --echo # is not part of the group it cannot be selected as the sender. --let $rpl_connection_name= server4 --source include/rpl_connection.inc --echo Wait until ch1 IO_THREAD is connected to server2 or server3 --let $wait_condition= SELECT service_state="ON" FROM performance_schema.replication_connection_status WHERE channel_name="ch1" AND source_uuid="$server2_uuid" OR source_uuid="$server3_uuid" --source include/wait_condition.inc --echo --echo ############################################################ --echo # 6. Wait 30 seconds and validate that replica is still connected --echo # to server2 or server3. --let $rpl_connection_name= server4 --source include/rpl_connection.inc --sleep 30 --let $assert_text= Verify channel ch1 IO_THREAD is ON and connected to server2 or server3 --let $assert_cond= "[SELECT SERVICE_STATE FROM performance_schema.replication_connection_status WHERE channel_name=\'ch1\' AND source_uuid=\'$server2_uuid\' OR source_uuid=\'$server3_uuid\', SERVICE_STATE, 1]" = "ON" --source include/assert.inc --echo --echo ############################################################ --echo # 7. Assert that group information did not change, since the --echo # missing member is UNREACHABLE --let $rpl_connection_name= server4 --source include/rpl_connection.inc --let $assert_text= 'There are 3 rows in performance_schema.replication_asynchronous_connection_failover' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover, count, 1] = 3 --source include/assert.inc --echo --echo ############################################################ --echo # 8. Revert group_replication_member_expel_timeout to the --echo # default value on server2 and server3, which will cause --echo # server1 to be expelled. --let $rpl_connection_name= server2 --source include/rpl_connection.inc SET GLOBAL group_replication_member_expel_timeout = DEFAULT; --let $rpl_connection_name= server3 --source include/rpl_connection.inc SET GLOBAL group_replication_member_expel_timeout = DEFAULT; --let $wait_condition=SELECT COUNT(*)=2 FROM performance_schema.replication_group_members --source include/wait_condition.inc --echo --echo ############################################################ --echo # 9. server1 was removed from performance_schema.replication_asynchronous_connection_failover table. --echo # server4 is connected to the group primary. --let $primary_uuid= query_get_value(SELECT MEMBER_ID FROM performance_schema.replication_group_members where member_role='PRIMARY', MEMBER_ID, 1) --let $rpl_connection_name= server4 --source include/rpl_connection.inc --let $wait_condition= SELECT COUNT(*)=2 FROM performance_schema.replication_asynchronous_connection_failover --source include/wait_condition.inc --let $assert_text= 'There is no row in performance_schema.replication_asynchronous_connection_failover for server1' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover WHERE port=$SERVER_MYPORT_1, count, 1] = 0 --source include/assert.inc --echo Wait until ch1 IO_THREAD is connected to the group primary --let $wait_condition= SELECT service_state="ON" FROM performance_schema.replication_connection_status WHERE channel_name="ch1" AND source_uuid="$primary_uuid" --source include/wait_condition.inc --echo --echo ############################################################ --echo # 10. Clean up. --let $rpl_connection_name= server4 --source include/rpl_connection.inc --let $rpl_channel_name='ch1' --source include/stop_slave.inc --let $rpl_reset_slave_all= 1 --let $rpl_multi_source= 1 --source include/rpl_reset_slave.inc --let $rpl_channel_name= --let $rpl_reset_slave_all= --let $rpl_multi_source= --replace_result $group_replication_group_name GROUP_NAME --eval SELECT asynchronous_connection_failover_delete_managed('ch1', '$group_replication_group_name') --let $assert_text= 'There are no rows in performance_schema.replication_asynchronous_connection_failover' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover, count, 1] = 0 --source include/assert.inc --let $assert_text= 'There are no rows in performance_schema.replication_asynchronous_connection_failover_managed' --let $assert_cond= [SELECT COUNT(*) count FROM performance_schema.replication_asynchronous_connection_failover_managed, count, 1] = 0 --source include/assert.inc SET SESSION sql_log_bin = 0; call mtr.add_suppression("The source .* for channel 'ch1' has joined the group .*, and so added its entry into replication_asynchronous_connection_failover table."); call mtr.add_suppression("The master's UUID has changed, although this should not happen unless you have changed it manually.*"); call mtr.add_suppression("The Monitor IO thread detected that the source .* does not belong to the group majority, thence the channel .* will try to connect to another source.*"); call mtr.add_suppression("The IO thread detected that the source .* does not belong to the group majority, thence the channel .* will try to connect to another source."); call mtr.add_suppression("The source .* for channel 'ch1' has left the group .*, and so removed its entry from replication_asynchronous_connection_failover table."); call mtr.add_suppression("The group .* for the channel .* has been removed, and so removed its entry from replication_asynchronous_connection_failover_managed and all the group members from replication_asynchronous_connection_failover table."); call mtr.add_suppression("The group .* for the channel .* has been added, and so added its entry in replication_asynchronous_connection_failover_managed and source to replication_asynchronous_connection_failover table."); call mtr.add_suppression("The Monitor IO thread failed to connect to the source .* for channel .*, thence it will try to connect to another source."); SET SESSION sql_log_bin = 1; --let $rpl_connection_name= server3 --source include/rpl_connection.inc --source include/stop_group_replication.inc --let $rpl_connection_name= server2 --source include/rpl_connection.inc --source include/stop_group_replication.inc --let $rpl_connection_name= server1 --source include/rpl_connection.inc SET GLOBAL group_replication_member_expel_timeout = DEFAULT; --source include/group_replication_end.inc