Merge 10.6 into 10.9

Author: dr-m

.gitlab-ci.yml

@@ -42,7 +42,7 @@ variables:
   CMAKE_FLAGS: "-DWITH_SSL=system -DPLUGIN_COLUMNSTORE=NO -DPLUGIN_ROCKSDB=NO -DPLUGIN_S3=NO -DPLUGIN_MROONGA=NO -DPLUGIN_CONNECT=NO -DPLUGIN_MROONGA=NO -DPLUGIN_TOKUDB=NO -DPLUGIN_PERFSCHEMA=NO -DWITH_WSREP=OFF"
   # Major version dictates which branches share the same ccache. E.g. 10.6-abc
   # and 10.6-xyz will have the same cache.
-  MARIADB_MAJOR_VERSION: "10.8"
+  MARIADB_MAJOR_VERSION: "10.9"
   # NOTE! Currently ccache is only used on the Centos8 build. As each job has
   # sufficiently different environments they are unable to benefit from each
   # other's ccaches. As each build generates about 1 GB of ccache, having

include/mysql/service_wsrep.h

@@ -57,6 +57,7 @@ extern struct wsrep_service_st {
   my_bool                     (*wsrep_on_func)(const MYSQL_THD thd);
   bool                        (*wsrep_prepare_key_for_innodb_func)(MYSQL_THD thd, const unsigned char*, size_t, const unsigned char*, size_t, struct wsrep_buf*, size_t*);
   void                        (*wsrep_thd_LOCK_func)(const MYSQL_THD thd);
+  int                         (*wsrep_thd_TRYLOCK_func)(const MYSQL_THD thd);
   void                        (*wsrep_thd_UNLOCK_func)(const MYSQL_THD thd);
   const char *                (*wsrep_thd_query_func)(const MYSQL_THD thd);
   int                         (*wsrep_thd_retry_counter_func)(const MYSQL_THD thd);
@@ -89,7 +90,6 @@ extern struct wsrep_service_st {
   ulong                       (*wsrep_OSU_method_get_func)(const MYSQL_THD thd);
   my_bool                     (*wsrep_thd_has_ignored_error_func)(const MYSQL_THD thd);
   void                        (*wsrep_thd_set_ignored_error_func)(MYSQL_THD thd, my_bool val);
-  bool                        (*wsrep_thd_set_wsrep_aborter_func)(MYSQL_THD bf_thd, MYSQL_THD thd);
   void                        (*wsrep_report_bf_lock_wait_func)(const MYSQL_THD thd,
                                                                 unsigned long long trx_id);
   void                        (*wsrep_thd_kill_LOCK_func)(const MYSQL_THD thd);
@@ -111,6 +111,7 @@ extern struct wsrep_service_st {
 #define wsrep_on(thd) (thd) && WSREP_ON && wsrep_service->wsrep_on_func(thd)
 #define wsrep_prepare_key_for_innodb(A,B,C,D,E,F,G) wsrep_service->wsrep_prepare_key_for_innodb_func(A,B,C,D,E,F,G)
 #define wsrep_thd_LOCK(T) wsrep_service->wsrep_thd_LOCK_func(T)
+#define wsrep_thd_TRYLOCK(T) wsrep_service->wsrep_thd_TRYLOCK_func(T)
 #define wsrep_thd_UNLOCK(T) wsrep_service->wsrep_thd_UNLOCK_func(T)
 #define wsrep_thd_kill_LOCK(T) wsrep_service->wsrep_thd_kill_LOCK_func(T)
 #define wsrep_thd_kill_UNLOCK(T) wsrep_service->wsrep_thd_kill_UNLOCK_func(T)
@@ -141,7 +142,6 @@ extern struct wsrep_service_st {
 #define wsrep_OSU_method_get(T) wsrep_service->wsrep_OSU_method_get_func(T)
 #define wsrep_thd_has_ignored_error(T) wsrep_service->wsrep_thd_has_ignored_error_func(T)
 #define wsrep_thd_set_ignored_error(T,V) wsrep_service->wsrep_thd_set_ignored_error_func(T,V)
-#define wsrep_thd_set_wsrep_aborter(T) wsrep_service->wsrep_thd_set_wsrep_aborter_func(T1, T2)
 #define wsrep_report_bf_lock_wait(T,I) wsrep_service->wsrep_report_bf_lock_wait(T,I)
 #define wsrep_thd_set_PA_unsafe(T) wsrep_service->wsrep_thd_set_PA_unsafe_func(T)
 #else
@@ -175,6 +175,8 @@ void wsrep_set_data_home_dir(const char *data_dir);
 extern "C" my_bool wsrep_on(const MYSQL_THD thd);
 /* Lock thd wsrep lock */
 extern "C" void wsrep_thd_LOCK(const MYSQL_THD thd);
+/* Try thd wsrep lock. Return non-zero if lock could not be taken. */
+extern "C" int wsrep_thd_TRYLOCK(const MYSQL_THD thd);
 /* Unlock thd wsrep lock */
 extern "C" void wsrep_thd_UNLOCK(const MYSQL_THD thd);
 
@@ -197,8 +199,6 @@ extern "C" my_bool wsrep_thd_is_local(const MYSQL_THD thd);
 /* Return true if thd is in high priority mode */
 /* todo: rename to is_high_priority() */
 extern "C" my_bool wsrep_thd_is_applying(const MYSQL_THD thd);
-/* set wsrep_aborter for the target THD */
-extern "C" bool wsrep_thd_set_wsrep_aborter(MYSQL_THD bf_thd, MYSQL_THD victim_thd);
 /* Return true if thd is in TOI mode */
 extern "C" my_bool wsrep_thd_is_toi(const MYSQL_THD thd);
 /* Return true if thd is in replicating TOI mode */
@@ -249,7 +249,6 @@ extern "C" my_bool wsrep_thd_is_applying(const MYSQL_THD thd);
 extern "C" ulong wsrep_OSU_method_get(const MYSQL_THD thd);
 extern "C" my_bool wsrep_thd_has_ignored_error(const MYSQL_THD thd);
 extern "C" void wsrep_thd_set_ignored_error(MYSQL_THD thd, my_bool val);
-extern "C" bool wsrep_thd_set_wsrep_aborter(MYSQL_THD bf_thd, MYSQL_THD victim_thd);
 extern "C" void wsrep_report_bf_lock_wait(const THD *thd,
                                           unsigned long long trx_id);
 /* declare parallel applying unsafety for the THD */

mysql-test/suite/galera/disabled.def

@@ -27,3 +27,5 @@ galera_bf_kill_debug : timeout after 900 seconds
 galera_ssl_upgrade : [Warning] Failed to load slave replication state from table mysql.gtid_slave_pos: 130: Incorrect file format 'gtid_slave_pos'
 galera_parallel_simple : timeout related to wsrep_sync_wait
 galera_insert_bulk : MDEV-30536 no expected deadlock in galera_insert_bulk test
+MDEV-27713 : test is using get_lock(), which is now rejected in cluster
+galera_bf_abort_group_commit : MDEV-30855 PR to remove the test exists

mysql-test/suite/galera/r/MDEV-29293.result

@@ -0,0 +1,21 @@
+connection node_2;
+connection node_1;
+connect node_1a, 127.0.0.1, root, , test, $NODE_MYPORT_1;
+connect node_1b, 127.0.0.1, root, , test, $NODE_MYPORT_1;
+set wsrep_sync_wait = 0;
+CREATE TABLE t1(a int not null primary key auto_increment, b int) engine=InnoDB;
+INSERT INTO t1 VALUES (1,2);
+connection node_1a;
+BEGIN;
+UPDATE t1 SET b=3 WHERE a=1;
+connection node_1;
+set debug_sync='wsrep_kill_before_awake_no_mutex SIGNAL before_kill WAIT_FOR continue';
+connection node_1b;
+set debug_sync= 'now WAIT_FOR before_kill';
+connection node_2;
+UPDATE t1 SET b=7 WHERE a=1;
+connection node_1b;
+set debug_sync= 'now SIGNAL continue';
+connection node_1;
+DROP TABLE t1;
+SET DEBUG_SYNC= 'RESET';

mysql-test/suite/galera/r/galera_create_table_as_select.result

@@ -82,6 +82,7 @@ connect node_1a, 127.0.0.1, root, , test, $NODE_MYPORT_1;
 LOCK TABLE t2 WRITE;
 connection node_1;
 CREATE TABLE t1 AS SELECT * FROM t2;;
+connection node_1a;
 connection node_2;
 SELECT COUNT(*) = 5 FROM t2;
 COUNT(*) = 5

mysql-test/suite/galera/r/galera_gcache_recover_manytrx.result

@@ -134,6 +134,3 @@ connection node_1;
 call mtr.add_suppression("Error in Log_event::read_log_event():.*");
 CALL mtr.add_suppression("conflict state 7 after post commit");
 CALL mtr.add_suppression("Skipped GCache ring buffer recovery");
-connection node_2;
-call mtr.add_suppression("Error in Log_event::read_log_event():.*");
-CALL mtr.add_suppression("Skipped GCache ring buffer recovery");

mysql-test/suite/galera/r/galera_kill_group_commit.result

@@ -0,0 +1,27 @@
+connection node_2;
+connection node_1;
+connect node_1_kill, 127.0.0.1, root, , test, $NODE_MYPORT_1;
+connect node_1_ctrl, 127.0.0.1, root, , test, $NODE_MYPORT_1;
+SET SESSION wsrep_sync_wait = 0;
+connect node_1_follower, 127.0.0.1, root, , test, $NODE_MYPORT_1;
+SET SESSION wsrep_sync_wait = 0;
+connection node_1;
+CREATE TABLE t1 (f1 INT PRIMARY KEY) ENGINE=InnoDB;
+SET SESSION DEBUG_SYNC = "commit_before_enqueue SIGNAL leader_before_enqueue_reached WAIT_FOR leader_before_enqueue_continue";
+INSERT INTO t1 VALUES (1);
+connection node_1_ctrl;
+SET DEBUG_SYNC = "now WAIT_FOR leader_before_enqueue_reached";
+connection node_1_follower;
+INSERT INTO t1 VALUES (2);;
+connection node_1_ctrl;
+connection node_1_kill;
+# Execute KILL QUERY for group commit follower
+SET DEBUG_SYNC = "now SIGNAL leader_before_enqueue_continue";
+connection node_1_follower;
+connection node_1;
+SELECT * FROM t1;
+f1
+1
+2
+SET DEBUG_SYNC = "RESET";
+DROP TABLE t1;

mysql-test/suite/galera/r/galera_var_retry_autocommit.result

@@ -36,7 +36,10 @@ SET DEBUG_SYNC = 'now SIGNAL wsrep_retry_autocommit_continue';
 connection node_1;
 SELECT COUNT(*) FROM t1;
 COUNT(*)
-1
+connection node_1;
+SELECT COUNT(*) FROM t1;
+COUNT(*)
+0
 SET DEBUG_SYNC = 'RESET';
 SET GLOBAL debug_dbug = NULL;
 DROP TABLE t1;

mysql-test/suite/galera/t/MDEV-29293.test

@@ -0,0 +1,41 @@
+--source include/galera_cluster.inc
+--source include/have_innodb.inc
+--source include/have_debug_sync.inc
+--source include/galera_have_debug_sync.inc
+
+--connect node_1a, 127.0.0.1, root, , test, $NODE_MYPORT_1
+--connect node_1b, 127.0.0.1, root, , test, $NODE_MYPORT_1
+set wsrep_sync_wait = 0;
+
+CREATE TABLE t1(a int not null primary key auto_increment, b int) engine=InnoDB;
+INSERT INTO t1 VALUES (1,2); 
+
+--connection node_1a
+--let $victim_id = `SELECT CONNECTION_ID()`
+BEGIN;
+UPDATE t1 SET b=3 WHERE a=1;
+
+--connection node_1
+set debug_sync='wsrep_kill_before_awake_no_mutex SIGNAL before_kill WAIT_FOR continue';
+--disable_query_log
+--disable_result_log
+--send_eval KILL CONNECTION $victim_id 
+--enable_result_log
+--enable_query_log
+
+--connection node_1b
+set debug_sync= 'now WAIT_FOR before_kill';
+
+--connection node_2
+UPDATE t1 SET b=7 WHERE a=1;
+
+--connection node_1b 
+--let $wait_condition = SELECT COUNT(*) = 1 FROM INFORMATION_SCHEMA.PROCESSLIST WHERE User = 'system user' AND  State LIKE 'Update_rows_log_event%'; 
+--source include/wait_condition.inc
+set debug_sync= 'now SIGNAL continue'; 
+
+--connection node_1
+--reap 
+DROP TABLE t1;
+SET DEBUG_SYNC= 'RESET';
+

mysql-test/suite/galera/t/galera_create_table_as_select.test

@@ -113,6 +113,10 @@ LOCK TABLE t2 WRITE;
 --connection node_1
 --send CREATE TABLE t1 AS SELECT * FROM t2;
 
+--connection node_1a
+--let $wait_condition = SELECT COUNT(*) = 1 FROM information_schema.processlist WHERE STATE LIKE 'Waiting for table metadata lock%'
+--source include/wait_condition.inc
+
 --connection node_2
 SELECT COUNT(*) = 5 FROM t2;
 CREATE TABLE t1 AS SELECT * FROM t2;
@@ -121,7 +125,7 @@ CREATE TABLE t1 AS SELECT * FROM t2;
 UNLOCK TABLES;
 
 --connection node_1
---error ER_TABLE_EXISTS_ERROR,ER_LOCK_DEADLOCK
+--error ER_TABLE_EXISTS_ERROR,ER_QUERY_INTERRUPTED
 --reap
 
 DROP TABLE t1, t2;

mysql-test/suite/galera/t/galera_kill_group_commit.cnf

@@ -0,0 +1,5 @@
+!include ../galera_2nodes.cnf
+
+[mysqld]
+log-bin
+log-slave-updates

mysql-test/suite/galera/t/galera_kill_group_commit.test

@@ -0,0 +1,69 @@
+#
+# Verify that transaction which has reached group commit queue
+# cannot be killed. If the kill succeeds, assertion for
+# wsrep transaction state will fail.
+#
+# If the bug is present, i.e. wsrep transaction gets killed during
+# group commit wait, this test is enough to reproduce the crash
+# most of the time.
+#
+
+--source include/have_innodb.inc
+--source include/have_debug_sync.inc
+--source include/galera_cluster.inc
+
+# Connection for KILL commands
+--connect node_1_kill, 127.0.0.1, root, , test, $NODE_MYPORT_1
+# Connection for sync point control
+--connect node_1_ctrl, 127.0.0.1, root, , test, $NODE_MYPORT_1
+SET SESSION wsrep_sync_wait = 0;
+# Connection for group commit follower
+--connect node_1_follower, 127.0.0.1, root, , test, $NODE_MYPORT_1
+# Need to disable sync wait to reach commit queue when leader
+# is blocked.
+SET SESSION wsrep_sync_wait = 0;
+--let $follower_id = `SELECT CONNECTION_ID()`
+
+--connection node_1
+CREATE TABLE t1 (f1 INT PRIMARY KEY) ENGINE=InnoDB;
+
+SET SESSION DEBUG_SYNC = "commit_before_enqueue SIGNAL leader_before_enqueue_reached WAIT_FOR leader_before_enqueue_continue";
+--send INSERT INTO t1 VALUES (1)
+
+--connection node_1_ctrl
+SET DEBUG_SYNC = "now WAIT_FOR leader_before_enqueue_reached";
+
+--connection node_1_follower
+# SET SESSION DEBUG_SYNC = "group_commit_waiting_for_prior SIGNAL follower_waiting_for_prior_reached WAIT_FOR follower_waiting_for_prior_continue";
+--send INSERT INTO t1 VALUES (2);
+
+--connection node_1_ctrl
+# TODO: Is it possible to use sync points to enforce group commit to happen?
+# The leader will hold commit monitor in commit_before_enqueue sync point,
+# which prevents the follower to reach the group commit wait state.
+# We now sleep and expect the follower to reach group commit, but this
+# may cause false negatives.
+--sleep 1
+
+--connection node_1_kill
+--echo # Execute KILL QUERY for group commit follower
+--disable_query_log
+--disable_result_log
+# Because it is currently impossible to verify that the
+# follower has reached group commit queue, the KILL may
+# sometimes return success.
+--error 0,ER_KILL_DENIED_ERROR
+--eval KILL QUERY $follower_id
+--enable_result_log
+--enable_query_log
+
+SET DEBUG_SYNC = "now SIGNAL leader_before_enqueue_continue";
+--connection node_1_follower
+--reap
+
+--connection node_1
+--reap
+SELECT * FROM t1;
+
+SET DEBUG_SYNC = "RESET";
+DROP TABLE t1;

mysql-test/suite/galera/t/galera_var_retry_autocommit.test

@@ -64,6 +64,7 @@ SELECT COUNT(*) FROM t1;
 SET DEBUG_SYNC = 'now SIGNAL wsrep_retry_autocommit_continue';
 
 --connection node_1
+--error 0,ER_LOCK_DEADLOCK
 --reap
 SELECT COUNT(*) FROM t1;