MDEV-9519: Data corruption will happen on the Galera cluster size change

If we have a 2+ node cluster which is replicating from an async master
and the binlog_format is set to STATEMENT and multi-row inserts are executed
on a table with an auto_increment column such that values are automatically
generated by MySQL, then the server node generates wrong auto_increment
values, which are different from what was generated on the async master.

In the title of the MDEV-9519 it was proposed to ban start slave on a Galera
if master binlog_format = statement and wsrep_auto_increment_control = 1,
but the problem can be solved without such a restriction.

The causes and fixes:

1. We need to improve processing of changing the auto-increment values
after changing the cluster size.

2. If wsrep auto_increment_control switched on during operation of
the node, then we should immediately update the auto_increment_increment
and auto_increment_offset global variables, without waiting of the next
invocation of the wsrep_view_handler_cb() callback. In the current version
these variables retain its initial values if wsrep_auto_increment_control
is switched on during operation of the node, which leads to inconsistent
results on the different nodes in some scenarios.

3. If wsrep auto_increment_control switched off during operation of the node,
then we must return the original values of the auto_increment_increment and
auto_increment_offset global variables, as the user has set. To make this
possible, we need to add a "shadow copies" of these variables (which stores
the latest values set by the user).

https://jira.mariadb.org/browse/MDEV-9519

1 files changed, 3 insertions, 0 deletions

diff --git a/include/mysql/service_wsrep.h b/include/mysql/service_wsrep.h
index b51f154422f..267c8cb4e90 100644
--- a/include/mysql/service_wsrep.h
+++ b/include/mysql/service_wsrep.h
@@ -107,6 +107,7 @@ extern struct wsrep_service_st {
   bool                        (*wsrep_thd_ignore_table_func)(THD *thd);
   long long                   (*wsrep_thd_trx_seqno_func)(THD *thd);
   struct wsrep_ws_handle *    (*wsrep_thd_ws_handle_func)(THD *thd);
+  void                        (*wsrep_thd_auto_increment_variables_func)(THD *thd, unsigned long long *offset, unsigned long long *increment);
   int                         (*wsrep_trx_is_aborting_func)(MYSQL_THD thd);
   int                         (*wsrep_trx_order_before_func)(MYSQL_THD, MYSQL_THD);
   void                        (*wsrep_unlock_rollback_func)();
@@ -149,6 +150,7 @@ extern struct wsrep_service_st {
 #define wsrep_thd_ignore_table(T) wsrep_service->wsrep_thd_ignore_table_func(T)
 #define wsrep_thd_trx_seqno(T) wsrep_service->wsrep_thd_trx_seqno_func(T)
 #define wsrep_thd_ws_handle(T) wsrep_service->wsrep_thd_ws_handle_func(T)
+#define wsrep_thd_auto_increment_variables(T,O,I) wsrep_service->wsrep_thd_auto_increment_variables_func(T,O,I)
 #define wsrep_trx_is_aborting(T) wsrep_service->wsrep_trx_is_aborting_func(T)
 #define wsrep_trx_order_before(T1,T2) wsrep_service->wsrep_trx_order_before_func(T1,T2)
 #define wsrep_unlock_rollback() wsrep_service->wsrep_unlock_rollback_func()
@@ -201,6 +203,7 @@ my_bool wsrep_thd_is_BF(MYSQL_THD thd, my_bool sync);
 my_bool wsrep_thd_is_wsrep(MYSQL_THD thd);
 struct wsrep *get_wsrep();
 struct wsrep_ws_handle *wsrep_thd_ws_handle(THD *thd);
+void wsrep_thd_auto_increment_variables(THD *thd, unsigned long long *offset, unsigned long long *increment);
 void wsrep_aborting_thd_enqueue(THD *thd);
 void wsrep_lock_rollback();
 void wsrep_post_commit(THD* thd, bool all);