Made --timer work
mtr_cases.pl:
Added option --reorder to get less server restarts
mysql-test-run.pl:
Added option --reorder to get less server restarts
Moved do_before_start_master() not to remove binlog files unless restarted
Made --timer work
Slave was incorrectly writing log to error log
"Warnings on 'drop procedure' platform-specific").
In mysqltest we should not issue "SHOW WARNINGS" until we have not
read results from all statements in multi-statement.
Otherwise such "SHOW WARNINGS" will either cause "Packets out of order"
error and thus will ruin current connection (but we may not notice this as
it happened in sp.test because we ignore errors from such auxilary
SHOW WARNINGS and use auto-reconnecting connections) or will
succeed but consume first packet from next statement in multi-statement
sequence (this happens if "SHOW WARNINGS" is issued when this packet
is already received by client. Packet is thrown away by net_clear()
call which is issued when "SHOW WARNINGS" is sent to server).
In our case sp.test failed because usually we had first situation
but sometimes second situation occured causing warning to pop-up.
Windows to call CreateFileMapping() with correct arguments, and
propogating the introduction of query_id_t to everywhere query ids are
passed around. (Bug #8826)
First one is related to Bug#7905. One should not be allowed to
create new user with password without UPDATE privilege to
MySQL database. Furthermore, executing the same GRANT statement
twice would actually crash the server and corrupt privilege database.
Other bug was that one could update a column, using the existing
value as basis to calculate the new value (e.g. UPDATE t1 SET a=a+1)
without SELECT privilege to the field (a in the above example)
Fixed tests grant.pl and grant2, which were wrong.
Added a test for bug #8615.
sql_select.cc:
Fixed bug #8615.
This fix only removed the cause of the reported crash.
It does not resolve other problems of rollup queries
with DISTINCT. They were fixed in the previous patch
for bug 8616.
Enabled VARCHAR testing for innodb
NOTE: innodb.test currently fails becasue of a bug in InnoDB.
I have informed Heikki about this and expect him to fix this ASAP