- developers - lists.mariadb.org

[Maria-developers] Updated (by Serg): support many clustered keys per table (113)
by worklog-noreply＠askmonty.org 10 May '10

10 May '10

----------------------------------------------------------------------- WORKLOG TASK -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- TASK...........: support many clustered keys per table CREATION DATE..: Sun, 25 Apr 2010, 16:23 SUPERVISOR.....: Sergei IMPLEMENTOR....: COPIES TO......: CATEGORY.......: Server-Sprint TASK ID........: 113 (http://askmonty.org/worklog/?tid=113) VERSION........: Server-5.3 STATUS.........: Un-Assigned PRIORITY.......: 60 WORKED HOURS...: 0 ESTIMATE.......: 0 (hours remain) ORIG. ESTIMATE.: 0 PROGRESS NOTES: -=-=(Serg - Mon, 10 May 2010, 14:35)=-=- Version updated. --- /tmp/wklog.113.old.7105 2010-05-10 14:35:25.000000000 +0000 +++ /tmp/wklog.113.new.7105 2010-05-10 14:35:25.000000000 +0000 @@ -1 +1 @@ -Server-9.x +Server-5.3 DESCRIPTION: The server now assumes that there can be only one clustered key per table, and only primary key can be clustered. It's not true for certain storage engines, we need to remove this limitation ESTIMATED WORK TIME ESTIMATED COMPLETION DATE ----------------------------------------------------------------------- WorkLog (v3.5.9)

1 0

[Maria-developers] bzr commit into MariaDB 5.1, with Maria 1.5:maria branch (knielsen:2860)
by knielsen＠knielsen-hq.org 10 May '10

10 May '10

#At lp:maria 2860 knielsen(a)knielsen-hq.org 2010-05-10 [merge] Automerge MariaDB 5.1.44b release. modified: mysql-test/r/grant.result mysql-test/t/grant.test sql/mysql_priv.h sql/partition_info.cc sql/sql_parse.cc sql/sql_table.cc sql/sql_yacc.yy sql/table.cc tests/mysql_client_test.c === modified file 'mysql-test/r/grant.result' --- a/mysql-test/r/grant.result 2010-01-29 10:42:31 +0000 +++ b/mysql-test/r/grant.result 2010-05-09 19:30:06 +0000 @@ -1413,3 +1413,19 @@ DROP USER 'user1'; DROP USER 'user1'@'localhost'; DROP USER 'user2'; DROP DATABASE db1; +CREATE DATABASE db1; +CREATE DATABASE db2; +GRANT SELECT ON db1.* to 'testbug'@localhost; +USE db2; +CREATE TABLE t1 (a INT); +USE test; +SELECT * FROM `../db2/tb2`; +ERROR 42S02: Table 'db1.../db2/tb2' doesn't exist +SELECT * FROM `../db2`.tb2; +ERROR 42000: SELECT command denied to user 'testbug'@'localhost' for table 'tb2' +SELECT * FROM `#mysql50#/../db2/tb2`; +ERROR 42S02: Table 'db1.#mysql50#/../db2/tb2' doesn't exist +DROP USER 'testbug'@localhost; +DROP TABLE db2.t1; +DROP DATABASE db1; +DROP DATABASE db2; === modified file 'mysql-test/t/grant.test' --- a/mysql-test/t/grant.test 2010-01-29 10:42:31 +0000 +++ b/mysql-test/t/grant.test 2010-05-09 19:30:06 +0000 @@ -1525,5 +1525,30 @@ DROP USER 'user1'@'localhost'; DROP USER 'user2'; DROP DATABASE db1; + +# +# Bug #53371: COM_FIELD_LIST can be abused to bypass table level grants. +# + +CREATE DATABASE db1; +CREATE DATABASE db2; +GRANT SELECT ON db1.* to 'testbug'@localhost; +USE db2; +CREATE TABLE t1 (a INT); +USE test; +connect (con1,localhost,testbug,,db1); +--error ER_NO_SUCH_TABLE +SELECT * FROM `../db2/tb2`; +--error ER_TABLEACCESS_DENIED_ERROR +SELECT * FROM `../db2`.tb2; +--error ER_NO_SUCH_TABLE +SELECT * FROM `#mysql50#/../db2/tb2`; +connection default; +disconnect con1; +DROP USER 'testbug'@localhost; +DROP TABLE db2.t1; +DROP DATABASE db1; +DROP DATABASE db2; + # Wait till we reached the initial number of concurrent sessions --source include/wait_until_count_sessions.inc === modified file 'sql/mysql_priv.h' --- a/sql/mysql_priv.h 2010-04-28 12:52:24 +0000 +++ b/sql/mysql_priv.h 2010-05-10 07:34:49 +0000 @@ -2289,7 +2289,7 @@ void update_create_info_from_table(HA_CR int rename_file_ext(const char * from,const char * to,const char * ext); bool check_db_name(LEX_STRING *db); bool check_column_name(const char *name); -bool check_table_name(const char *name, uint length); +bool check_table_name(const char *name, uint length, bool check_for_path_chars); char *get_field(MEM_ROOT *mem, Field *field); bool get_field(MEM_ROOT *mem, Field *field, class String *res); int wild_case_compare(CHARSET_INFO *cs, const char *str,const char *wildstr); === modified file 'sql/partition_info.cc' --- a/sql/partition_info.cc 2009-12-03 11:19:05 +0000 +++ b/sql/partition_info.cc 2010-05-09 19:30:06 +0000 @@ -972,7 +972,7 @@ bool partition_info::check_partition_inf part_elem->engine_type= default_engine_type; } if (check_table_name(part_elem->partition_name, - strlen(part_elem->partition_name))) + strlen(part_elem->partition_name), FALSE)) { my_error(ER_WRONG_PARTITION_NAME, MYF(0)); goto end; @@ -990,7 +990,7 @@ bool partition_info::check_partition_inf { sub_elem= sub_it++; if (check_table_name(sub_elem->partition_name, - strlen(sub_elem->partition_name))) + strlen(sub_elem->partition_name), FALSE)) { my_error(ER_WRONG_PARTITION_NAME, MYF(0)); goto end; === modified file 'sql/sql_parse.cc' --- a/sql/sql_parse.cc 2010-04-30 04:23:39 +0000 +++ b/sql/sql_parse.cc 2010-05-10 07:34:49 +0000 @@ -1334,6 +1334,11 @@ bool dispatch_command(enum enum_server_c system_charset_info, packet, db_length, thd->charset(), &dummy_errors); db_buff[db_length]= '\0'; + if (check_table_name(db_buff, db_length, FALSE)) + { + my_error(ER_WRONG_TABLE_NAME, MYF(0), db_buff); + break; + } table_list.alias= table_list.table_name= db_buff; if (!(fields= (char *) thd->memdup(wildcard, query_length + 1))) break; @@ -6298,7 +6303,7 @@ TABLE_LIST *st_select_lex::add_table_to_ DBUG_RETURN(0); // End of memory alias_str= alias ? alias->str : table->table.str; if (!test(table_options & TL_OPTION_ALIAS) && - check_table_name(table->table.str, table->table.length)) + check_table_name(table->table.str, table->table.length, FALSE)) { my_error(ER_WRONG_TABLE_NAME, MYF(0), table->table.str); DBUG_RETURN(0); === modified file 'sql/sql_table.cc' --- a/sql/sql_table.cc 2010-04-28 12:52:24 +0000 +++ b/sql/sql_table.cc 2010-05-10 07:34:49 +0000 @@ -435,7 +435,21 @@ uint tablename_to_filename(const char *f DBUG_PRINT("enter", ("from '%s'", from)); if ((length= check_n_cut_mysql50_prefix(from, to, to_length))) + { + /* + Check if the name supplied is a valid mysql 5.0 name and + make the name a zero length string if it's not. + Note that just returning zero length is not enough : + a lot of places don't check the return value and expect + a zero terminated string. + */ + if (check_table_name(to, length, TRUE)) + { + to[0]= 0; + length= 0; + } DBUG_RETURN(length); + } length= strconvert(system_charset_info, from, &my_charset_filename, to, to_length, &errors); if (check_if_legal_tablename(to) && === modified file 'sql/sql_yacc.yy' --- a/sql/sql_yacc.yy 2010-04-28 12:52:24 +0000 +++ b/sql/sql_yacc.yy 2010-05-10 07:34:49 +0000 @@ -6149,7 +6149,7 @@ alter_list_item: { MYSQL_YYABORT; } - if (check_table_name($3->table.str,$3->table.length) || + if (check_table_name($3->table.str,$3->table.length, FALSE) || ($3->db.str && check_db_name(&$3->db))) { my_error(ER_WRONG_TABLE_NAME, MYF(0), $3->table.str); === modified file 'sql/table.cc' --- a/sql/table.cc 2010-04-28 12:52:24 +0000 +++ b/sql/table.cc 2010-05-10 07:34:49 +0000 @@ -494,6 +494,19 @@ inline bool is_system_table_name(const c } +/** + Check if a string contains path elements +*/ + +static inline bool has_disabled_path_chars(const char *str) +{ + for (; *str; str++) + if (*str == FN_EXTCHAR || *str == '/' || *str == '\\' || *str == '~' || *str == '@') + return TRUE; + return FALSE; +} + + /* Read table definition from a binary / text based .frm file @@ -548,7 +561,8 @@ int open_table_def(THD *thd, TABLE_SHARE This kind of tables must have been opened only by the my_open() above. */ - if (strchr(share->table_name.str, '@') || + if (has_disabled_path_chars(share->table_name.str) || + has_disabled_path_chars(share->db.str) || !strncmp(share->db.str, MYSQL50_TABLE_NAME_PREFIX, MYSQL50_TABLE_NAME_PREFIX_LENGTH) || !strncmp(share->table_name.str, MYSQL50_TABLE_NAME_PREFIX, @@ -2718,7 +2732,6 @@ bool check_db_name(LEX_STRING *org_name) (name_length > NAME_CHAR_LEN)); /* purecov: inspected */ } - /* Allow anything as a table name, as long as it doesn't contain an ' ' at the end @@ -2726,7 +2739,7 @@ bool check_db_name(LEX_STRING *org_name) */ -bool check_table_name(const char *name, uint length) +bool check_table_name(const char *name, uint length, bool check_for_path_chars) { uint name_length= 0; // name length in symbols const char *end= name+length; @@ -2753,6 +2766,9 @@ bool check_table_name(const char *name, continue; } } + if (check_for_path_chars && + (*name == '/' || *name == '\\' || *name == '~' || *name == FN_EXTCHAR)) + return 1; #endif name++; name_length++; === modified file 'tests/mysql_client_test.c' --- a/tests/mysql_client_test.c 2010-01-11 13:15:28 +0000 +++ b/tests/mysql_client_test.c 2010-05-09 19:30:06 +0000 @@ -18092,6 +18092,50 @@ static void test_bug44495() DBUG_VOID_RETURN; } +static void test_bug53371() +{ + int rc; + MYSQL_RES *result; + + myheader("test_bug53371"); + + rc= mysql_query(mysql, "DROP TABLE IF EXISTS t1"); + myquery(rc); + rc= mysql_query(mysql, "DROP DATABASE IF EXISTS bug53371"); + myquery(rc); + rc= mysql_query(mysql, "DROP USER 'testbug'@localhost"); + + rc= mysql_query(mysql, "CREATE TABLE t1 (a INT)"); + myquery(rc); + rc= mysql_query(mysql, "CREATE DATABASE bug53371"); + myquery(rc); + rc= mysql_query(mysql, "GRANT SELECT ON bug53371.* to 'testbug'@localhost"); + myquery(rc); + + rc= mysql_change_user(mysql, "testbug", NULL, "bug53371"); + myquery(rc); + + rc= mysql_query(mysql, "SHOW COLUMNS FROM client_test_db.t1"); + DIE_UNLESS(rc); + DIE_UNLESS(mysql_errno(mysql) == 1142); + + result= mysql_list_fields(mysql, "../client_test_db/t1", NULL); + DIE_IF(result); + + result= mysql_list_fields(mysql, "#mysql50#/../client_test_db/t1", NULL); + DIE_IF(result); + + rc= mysql_change_user(mysql, opt_user, opt_password, current_db); + myquery(rc); + rc= mysql_query(mysql, "DROP TABLE t1"); + myquery(rc); + rc= mysql_query(mysql, "DROP DATABASE bug53371"); + myquery(rc); + rc= mysql_query(mysql, "DROP USER 'testbug'@localhost"); + myquery(rc); +} + + /* Read and parse arguments and MySQL options from my.cnf */ @@ -18401,6 +18445,7 @@ static struct my_tests_st my_tests[]= { { "test_bug30472", test_bug30472 }, { "test_bug20023", test_bug20023 }, { "test_bug45010", test_bug45010 }, + { "test_bug53371", test_bug53371 }, { "test_bug31418", test_bug31418 }, { "test_bug31669", test_bug31669 }, { "test_bug28386", test_bug28386 },

1 0

[Maria-developers] bzr commit into MariaDB 5.1, with Maria 1.5:maria branch (knielsen:2859)
by knielsen＠knielsen-hq.org 10 May '10

10 May '10

#At lp:maria 2859 knielsen(a)knielsen-hq.org 2010-05-10 Suppress a safemutex warning pending fix of MBug#578117. modified: mysql-test/suite/pbxt/r/pbxt_xa.result mysql-test/suite/pbxt/t/pbxt_xa.test === modified file 'mysql-test/suite/pbxt/r/pbxt_xa.result' --- a/mysql-test/suite/pbxt/r/pbxt_xa.result 2010-03-24 22:12:39 +0000 +++ b/mysql-test/suite/pbxt/r/pbxt_xa.result 2010-05-10 07:29:30 +0000 @@ -1,4 +1,5 @@ drop table if exists t1, t2; +CALL mtr.add_suppression("Found wrong usage of mutex 'LOCK_sync' and 'LOCK_active'"); CREATE TABLE t1 (a INT PRIMARY KEY) ENGINE=innodb; CREATE TABLE t2 (b INT PRIMARY KEY) ENGINE=pbxt; BEGIN; === modified file 'mysql-test/suite/pbxt/t/pbxt_xa.test' --- a/mysql-test/suite/pbxt/t/pbxt_xa.test 2010-03-24 22:12:39 +0000 +++ b/mysql-test/suite/pbxt/t/pbxt_xa.test 2010-05-10 07:29:30 +0000 @@ -4,6 +4,11 @@ drop table if exists t1, t2; --enable_warnings +# This warning is indication of a real bug, MBug#578117. +# But it is not a regression, so we suppress it to get a clean test run. +# This suppression must be removed as part of MBug#578117 fix. +CALL mtr.add_suppression("Found wrong usage of mutex 'LOCK_sync' and 'LOCK_active'"); + # # bug lp:544173, xa crash with two 2pc-capable storage engines without binlog #

1 0

[Maria-developers] bzr commit into MariaDB 5.1, with Maria 1.5:maria branch (knielsen:2834) Bug#53371
by knielsen＠knielsen-hq.org 09 May '10

09 May '10

#At lp:maria 2834 knielsen(a)knielsen-hq.org 2010-05-09 Cherry-pick fix for Bug#53371, security hole with bypassing grants using special path in db/table names. Bump MariaDB version for security fix release. modified: configure.in mysql-test/r/grant.result mysql-test/t/grant.test sql/mysql_priv.h sql/partition_info.cc sql/sql_parse.cc sql/sql_table.cc sql/sql_yacc.yy sql/table.cc tests/mysql_client_test.c === modified file 'configure.in' --- a/configure.in 2010-04-29 07:57:25 +0000 +++ b/configure.in 2010-05-09 19:30:06 +0000 @@ -7,7 +7,7 @@ AC_PREREQ(2.59) # Remember to also update version.c in ndb. # When changing major version number please also check switch statement # in mysqlbinlog::check_master_version(). -AC_INIT([MariaDB Server], [5.1.44a-MariaDB], [], [mysql]) +AC_INIT([MariaDB Server], [5.1.44b-MariaDB], [], [mysql]) AC_CONFIG_SRCDIR([sql/mysqld.cc]) AC_CANONICAL_SYSTEM # USTAR format gives us the possibility to store longer path names in === modified file 'mysql-test/r/grant.result' --- a/mysql-test/r/grant.result 2010-01-29 10:42:31 +0000 +++ b/mysql-test/r/grant.result 2010-05-09 19:30:06 +0000 @@ -1413,3 +1413,19 @@ DROP USER 'user1'; DROP USER 'user1'@'localhost'; DROP USER 'user2'; DROP DATABASE db1; +CREATE DATABASE db1; +CREATE DATABASE db2; +GRANT SELECT ON db1.* to 'testbug'@localhost; +USE db2; +CREATE TABLE t1 (a INT); +USE test; +SELECT * FROM `../db2/tb2`; +ERROR 42S02: Table 'db1.../db2/tb2' doesn't exist +SELECT * FROM `../db2`.tb2; +ERROR 42000: SELECT command denied to user 'testbug'@'localhost' for table 'tb2' +SELECT * FROM `#mysql50#/../db2/tb2`; +ERROR 42S02: Table 'db1.#mysql50#/../db2/tb2' doesn't exist +DROP USER 'testbug'@localhost; +DROP TABLE db2.t1; +DROP DATABASE db1; +DROP DATABASE db2; === modified file 'mysql-test/t/grant.test' --- a/mysql-test/t/grant.test 2010-01-29 10:42:31 +0000 +++ b/mysql-test/t/grant.test 2010-05-09 19:30:06 +0000 @@ -1525,5 +1525,30 @@ DROP USER 'user1'@'localhost'; DROP USER 'user2'; DROP DATABASE db1; + +# +# Bug #53371: COM_FIELD_LIST can be abused to bypass table level grants. +# + +CREATE DATABASE db1; +CREATE DATABASE db2; +GRANT SELECT ON db1.* to 'testbug'@localhost; +USE db2; +CREATE TABLE t1 (a INT); +USE test; +connect (con1,localhost,testbug,,db1); +--error ER_NO_SUCH_TABLE +SELECT * FROM `../db2/tb2`; +--error ER_TABLEACCESS_DENIED_ERROR +SELECT * FROM `../db2`.tb2; +--error ER_NO_SUCH_TABLE +SELECT * FROM `#mysql50#/../db2/tb2`; +connection default; +disconnect con1; +DROP USER 'testbug'@localhost; +DROP TABLE db2.t1; +DROP DATABASE db1; +DROP DATABASE db2; + # Wait till we reached the initial number of concurrent sessions --source include/wait_until_count_sessions.inc === modified file 'sql/mysql_priv.h' --- a/sql/mysql_priv.h 2010-03-04 08:03:07 +0000 +++ b/sql/mysql_priv.h 2010-05-09 19:30:06 +0000 @@ -2300,7 +2300,7 @@ void update_create_info_from_table(HA_CR int rename_file_ext(const char * from,const char * to,const char * ext); bool check_db_name(LEX_STRING *db); bool check_column_name(const char *name); -bool check_table_name(const char *name, uint length); +bool check_table_name(const char *name, uint length, bool check_for_path_chars); char *get_field(MEM_ROOT *mem, Field *field); bool get_field(MEM_ROOT *mem, Field *field, class String *res); int wild_case_compare(CHARSET_INFO *cs, const char *str,const char *wildstr); === modified file 'sql/partition_info.cc' --- a/sql/partition_info.cc 2009-12-03 11:19:05 +0000 +++ b/sql/partition_info.cc 2010-05-09 19:30:06 +0000 @@ -972,7 +972,7 @@ bool partition_info::check_partition_inf part_elem->engine_type= default_engine_type; } if (check_table_name(part_elem->partition_name, - strlen(part_elem->partition_name))) + strlen(part_elem->partition_name), FALSE)) { my_error(ER_WRONG_PARTITION_NAME, MYF(0)); goto end; @@ -990,7 +990,7 @@ bool partition_info::check_partition_inf { sub_elem= sub_it++; if (check_table_name(sub_elem->partition_name, - strlen(sub_elem->partition_name))) + strlen(sub_elem->partition_name), FALSE)) { my_error(ER_WRONG_PARTITION_NAME, MYF(0)); goto end; === modified file 'sql/sql_parse.cc' --- a/sql/sql_parse.cc 2010-04-29 07:57:25 +0000 +++ b/sql/sql_parse.cc 2010-05-09 19:30:06 +0000 @@ -1334,6 +1334,11 @@ bool dispatch_command(enum enum_server_c system_charset_info, packet, db_length, thd->charset(), &dummy_errors); db_buff[db_length]= '\0'; + if (check_table_name(db_buff, db_length, FALSE)) + { + my_error(ER_WRONG_TABLE_NAME, MYF(0), db_buff); + break; + } table_list.alias= table_list.table_name= db_buff; if (!(fields= (char *) thd->memdup(wildcard, query_length + 1))) break; @@ -6298,7 +6303,7 @@ TABLE_LIST *st_select_lex::add_table_to_ DBUG_RETURN(0); // End of memory alias_str= alias ? alias->str : table->table.str; if (!test(table_options & TL_OPTION_ALIAS) && - check_table_name(table->table.str, table->table.length)) + check_table_name(table->table.str, table->table.length, FALSE)) { my_error(ER_WRONG_TABLE_NAME, MYF(0), table->table.str); DBUG_RETURN(0); === modified file 'sql/sql_table.cc' --- a/sql/sql_table.cc 2010-03-04 08:03:07 +0000 +++ b/sql/sql_table.cc 2010-05-09 19:30:06 +0000 @@ -434,7 +434,21 @@ uint tablename_to_filename(const char *f DBUG_PRINT("enter", ("from '%s'", from)); if ((length= check_n_cut_mysql50_prefix(from, to, to_length))) + { + /* + Check if the name supplied is a valid mysql 5.0 name and + make the name a zero length string if it's not. + Note that just returning zero length is not enough : + a lot of places don't check the return value and expect + a zero terminated string. + */ + if (check_table_name(to, length, TRUE)) + { + to[0]= 0; + length= 0; + } DBUG_RETURN(length); + } length= strconvert(system_charset_info, from, &my_charset_filename, to, to_length, &errors); if (check_if_legal_tablename(to) && === modified file 'sql/sql_yacc.yy' --- a/sql/sql_yacc.yy 2010-03-04 08:03:07 +0000 +++ b/sql/sql_yacc.yy 2010-05-09 19:30:06 +0000 @@ -6149,7 +6149,7 @@ alter_list_item: { MYSQL_YYABORT; } - if (check_table_name($3->table.str,$3->table.length) || + if (check_table_name($3->table.str,$3->table.length, FALSE) || ($3->db.str && check_db_name(&$3->db))) { my_error(ER_WRONG_TABLE_NAME, MYF(0), $3->table.str); === modified file 'sql/table.cc' --- a/sql/table.cc 2010-03-10 10:32:14 +0000 +++ b/sql/table.cc 2010-05-09 19:30:06 +0000 @@ -494,6 +494,19 @@ inline bool is_system_table_name(const c } +/** + Check if a string contains path elements +*/ + +static inline bool has_disabled_path_chars(const char *str) +{ + for (; *str; str++) + if (*str == FN_EXTCHAR || *str == '/' || *str == '\\' || *str == '~' || *str == '@') + return TRUE; + return FALSE; +} + + /* Read table definition from a binary / text based .frm file @@ -548,7 +561,8 @@ int open_table_def(THD *thd, TABLE_SHARE This kind of tables must have been opened only by the my_open() above. */ - if (strchr(share->table_name.str, '@') || + if (has_disabled_path_chars(share->table_name.str) || + has_disabled_path_chars(share->db.str) || !strncmp(share->db.str, MYSQL50_TABLE_NAME_PREFIX, MYSQL50_TABLE_NAME_PREFIX_LENGTH) || !strncmp(share->table_name.str, MYSQL50_TABLE_NAME_PREFIX, @@ -2718,7 +2732,6 @@ bool check_db_name(LEX_STRING *org_name) (name_length > NAME_CHAR_LEN)); /* purecov: inspected */ } - /* Allow anything as a table name, as long as it doesn't contain an ' ' at the end @@ -2726,7 +2739,7 @@ bool check_db_name(LEX_STRING *org_name) */ -bool check_table_name(const char *name, uint length) +bool check_table_name(const char *name, uint length, bool check_for_path_chars) { uint name_length= 0; // name length in symbols const char *end= name+length; @@ -2753,6 +2766,9 @@ bool check_table_name(const char *name, continue; } } + if (check_for_path_chars && + (*name == '/' || *name == '\\' || *name == '~' || *name == FN_EXTCHAR)) + return 1; #endif name++; name_length++; === modified file 'tests/mysql_client_test.c' --- a/tests/mysql_client_test.c 2010-01-11 13:15:28 +0000 +++ b/tests/mysql_client_test.c 2010-05-09 19:30:06 +0000 @@ -18092,6 +18092,50 @@ static void test_bug44495() DBUG_VOID_RETURN; } +static void test_bug53371() +{ + int rc; + MYSQL_RES *result; + + myheader("test_bug53371"); + + rc= mysql_query(mysql, "DROP TABLE IF EXISTS t1"); + myquery(rc); + rc= mysql_query(mysql, "DROP DATABASE IF EXISTS bug53371"); + myquery(rc); + rc= mysql_query(mysql, "DROP USER 'testbug'@localhost"); + + rc= mysql_query(mysql, "CREATE TABLE t1 (a INT)"); + myquery(rc); + rc= mysql_query(mysql, "CREATE DATABASE bug53371"); + myquery(rc); + rc= mysql_query(mysql, "GRANT SELECT ON bug53371.* to 'testbug'@localhost"); + myquery(rc); + + rc= mysql_change_user(mysql, "testbug", NULL, "bug53371"); + myquery(rc); + + rc= mysql_query(mysql, "SHOW COLUMNS FROM client_test_db.t1"); + DIE_UNLESS(rc); + DIE_UNLESS(mysql_errno(mysql) == 1142); + + result= mysql_list_fields(mysql, "../client_test_db/t1", NULL); + DIE_IF(result); + + result= mysql_list_fields(mysql, "#mysql50#/../client_test_db/t1", NULL); + DIE_IF(result); + + rc= mysql_change_user(mysql, opt_user, opt_password, current_db); + myquery(rc); + rc= mysql_query(mysql, "DROP TABLE t1"); + myquery(rc); + rc= mysql_query(mysql, "DROP DATABASE bug53371"); + myquery(rc); + rc= mysql_query(mysql, "DROP USER 'testbug'@localhost"); + myquery(rc); +} + + /* Read and parse arguments and MySQL options from my.cnf */ @@ -18401,6 +18445,7 @@ static struct my_tests_st my_tests[]= { { "test_bug30472", test_bug30472 }, { "test_bug20023", test_bug20023 }, { "test_bug45010", test_bug45010 }, + { "test_bug53371", test_bug53371 }, { "test_bug31418", test_bug31418 }, { "test_bug31669", test_bug31669 }, { "test_bug28386", test_bug28386 },

1 0

[Maria-developers] BuildBot Outage
by Adam M. Dutko 08 May '10

08 May '10

The following buildbots will be unavailable until May 12th: adutko-centos5-amd64 adutko-ultrasparc3 mariadb-brs Sorry for the inconvenience. -Adam

1 0

Re: [Maria-developers] [Drizzle-discuss] Learning Storage Engine API
by Venu Kalyan 08 May '10

08 May '10

Hi You should check this link, as it has everything on storage engine API: http://forge.mysql.com/wiki/MySQL_Internals_Custom_Engine Also; you should check the example storage engine source code (storage/example) for bootstrapping, so that you can get your dummy storage engine ready in few minutes. Once you start, it will be real fun and easy to start though... Have fun Venu On Mon, Apr 19, 2010 at 1:35 PM, Igor K <igor175(a)gmail.com> wrote: > Dear all, > > I am new to the community and would like to ask a question: > > What is the best approach, in your opinion, to start learning storage > engine API? So that one can write a dummy storage engine in no time. > > Advices from the experts as well as various experiences from life are > welcomed. > > Igor Kozachenko > University of California, Berkeley > > _______________________________________________ > Mailing list: https://launchpad.net/~drizzle-discuss<https://launchpad.net/%7Edrizzle-discuss> > Post to : drizzle-discuss(a)lists.launchpad.net > Unsubscribe : https://launchpad.net/~drizzle-discuss<https://launchpad.net/%7Edrizzle-discuss> > More help : https://help.launchpad.net/ListHelp >

4 4

[Maria-developers] MariaDB Release Process
by Daniel Bartholomew 05 May '10

05 May '10

FYI: I just updated the Release Process page on the wiki. I removed some outdated information and added some new information (such as sending a note to maria-docs(a)lists.launchpad.net when a tree is ready for release instead of to docs(a)askmonty.org) http://askmonty.org/wiki/Release_Process Take a look if you are interested and let me know of any errors or omissions. Thanks. -- Daniel Bartholomew Monty Program - http://askmonty.org

1 0

Re: [Maria-developers] [Commits] bzr commit into MariaDB 5.1, with Maria 1.5:maria branch (knielsen:2851)
by Sergei Golubchik 05 May '10

05 May '10

Hi, knielsen! On May 05, knielsen(a)knielsen-hq.org wrote: > #At lp:maria > > 2851 knielsen(a)knielsen-hq.org 2010-05-05 > Change commit mails to go to commits(a)mariadb.org > modified: > .bzr-mysql/default.conf > > === modified file '.bzr-mysql/default.conf' > --- a/.bzr-mysql/default.conf 2010-03-04 08:03:07 +0000 > +++ b/.bzr-mysql/default.conf 2010-05-05 12:58:26 +0000 > @@ -1,6 +1,6 @@ > [MYSQL] > tree_location = lp:maria > -post_commit_to = maria-developers(a)lists.launchpad.net > +post_commit_to = commits(a)mariadb.org > post_commit_url = lp:maria > tree_name = maria > project_name = "MariaDB 5.1, with Maria 1.5" Don't bother chaning it - it only affects internal MySQL bzr plugin, we do not (and can not) use it. Regards, Sergei

1 0

[Maria-developers] Progress (by Knielsen): Store in binlog text of statements that caused RBR events (47)
by worklog-noreply＠askmonty.org 05 May '10

05 May '10

----------------------------------------------------------------------- WORKLOG TASK -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- TASK...........: Store in binlog text of statements that caused RBR events CREATION DATE..: Sat, 15 Aug 2009, 23:48 SUPERVISOR.....: Monty IMPLEMENTOR....: COPIES TO......: Knielsen, Serg CATEGORY.......: Server-Sprint TASK ID........: 47 (http://askmonty.org/worklog/?tid=47) VERSION........: Server-9.x STATUS.........: Code-Review PRIORITY.......: 60 WORKED HOURS...: 29 ESTIMATE.......: 6 (hours remain) ORIG. ESTIMATE.: 35 PROGRESS NOTES: -=-=(Knielsen - Wed, 05 May 2010, 13:53)=-=- Review of fixes to first review done. No new issues found. Worked 2 hours and estimate 6 hours remain (original estimate unchanged). -=-=(Knielsen - Fri, 23 Apr 2010, 12:51)=-=- Status updated. --- /tmp/wklog.47.old.28747 2010-04-23 12:51:36.000000000 +0000 +++ /tmp/wklog.47.new.28747 2010-04-23 12:51:36.000000000 +0000 @@ -1 +1 @@ -In-Progress +Code-Review -=-=(Knielsen - Tue, 06 Apr 2010, 15:26)=-=- Code review (mailed to maria-developers@). Worked 7 hours and estimate 8 hours remain (original estimate unchanged). -=-=(Knielsen - Tue, 06 Apr 2010, 15:25)=-=- Status updated. --- /tmp/wklog.47.old.12734 2010-04-06 15:25:54.000000000 +0000 +++ /tmp/wklog.47.new.12734 2010-04-06 15:25:54.000000000 +0000 @@ -1 +1 @@ -Code-Review +In-Progress -=-=(Knielsen - Mon, 29 Mar 2010, 10:59)=-=- Status updated. --- /tmp/wklog.47.old.27790 2010-03-29 10:59:53.000000000 +0000 +++ /tmp/wklog.47.new.27790 2010-03-29 10:59:53.000000000 +0000 @@ -1 +1 @@ -In-Progress +Code-Review -=-=(Alexi - Thu, 18 Feb 2010, 19:29)=-=- Worked 20 hours (alexi) Worked 20 hours and estimate 15 hours remain (original estimate unchanged). -=-=(Serg - Fri, 05 Feb 2010, 14:04)=-=- Observers changed: Knielsen,Serg -=-=(Guest - Fri, 05 Feb 2010, 13:40)=-=- Category updated. --- /tmp/wklog.47.old.9197 2010-02-05 13:40:36.000000000 +0200 +++ /tmp/wklog.47.new.9197 2010-02-05 13:40:36.000000000 +0200 @@ -1 +1 @@ -Server-RawIdeaBin +Server-Sprint -=-=(Guest - Fri, 05 Feb 2010, 13:40)=-=- Status updated. --- /tmp/wklog.47.old.9197 2010-02-05 13:40:36.000000000 +0200 +++ /tmp/wklog.47.new.9197 2010-02-05 13:40:36.000000000 +0200 @@ -1 +1 @@ -Un-Assigned +In-Progress -=-=(Alexi - Thu, 04 Feb 2010, 09:54)=-=- Low Level Design modified. --- /tmp/wklog.47.old.16174 2010-02-04 09:54:13.000000000 +0200 +++ /tmp/wklog.47.new.16174 2010-02-04 09:54:13.000000000 +0200 @@ -171,35 +171,20 @@ 5. How slave IO thread requests Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -When requesting an event, the slave should inform the master whether -it should send Annotate_rows events or not. To that end we add a new -BINLOG_SEND_ANNOTATE_ROWS_EVENT flag used when requesting an event: +If the replicate-annotate-rows-events option is not set on a slave, there +is no need for master to send Annotate_rows events to this slave. The slave +(or mysqlbinlog in remote case), before requesting binlog dump via the +COM_BINLOG_DUMP command, informs the master whether it should send these +events by executing the newly added COM_BINLOG_DUMP_OPTIONS_EXT server +command: + + case COM_BINLOG_DUMP_OPTIONS_EXT: + thd->binlog_dump_flags_ext= packet[0]; + my_ok(thd); + break; - #define BINLOG_DUMP_NON_BLOCK 1 - #define BINLOG_SEND_ANNOTATE_ROWS_EVENT 2 - - pthread_handler_t handle_slave_io(void *arg) - { ... - request_dump(mysql, ...); - ... - } - - int request_dump(MYSQL* mysql, ...) - { ... - if (opt_log_slave_updates && - mi->io_thd->variables.binlog_annotate_rows_events) - binlog_flags|= BINLOG_SEND_ANNOTATE_ROWS_EVENT; - ... - int2store(buf + 4, binlog_flags); - ... - simple_command(mysql, COM_BINLOG_DUMP, buf, ...); - ... - } - -NOTE. mysqlbinlog, when remotely requesting BINLOG_DUMP by calling the -simple_command() function, should also use this flag if it wants (in case -of the --print-annotate-rows-events option set) to recieve Annotate_rows -events. +Note. We add this new command and don't use COM_BINLOG_DUMP to avoid possible +conflicts with MySQL/Sun. 6. How master executes the request ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -338,10 +323,4 @@ to internals(a)lists.mysql.com about this and suggesting to reserve the event number. -Also we should notice the introduction of the BINLOG_SEND_ANNOTATE_ROWS_EVENT -flag taking into account that MySQL/Sun may also introduce a flag with the -same value to be used in the request_dump-mysql_binlog_send interface. -But this is mainly the question of merging: if a conflict concerning this -flag occur, we may simply change the BINLOG_SEND_ANNOTATE_ROWS_EVENT value -(this does not require additional changes in the code). ------------------------------------------------------------ -=-=(View All Progress Notes, 29 total)=-=- http://askmonty.org/worklog/index.pl?tid=47&nolimit=1 DESCRIPTION: Store in binlog (and show in mysqlbinlog output) texts of statements that caused RBR events This is needed for (list from Monty): - Easier to understand why updates happened - Would make it easier to find out where in application things went wrong (as you can search for exact strings) - Allow one to filter things based on comments in the statement. The cost of this can be that the binlog will be approximately 2x in size (especially insert of big blob's would be a bit painful), so this should be an optional feature. HIGH-LEVEL SPECIFICATION: Content ~~~~~~~ 1. Annotate_rows_log_event 2. Server option: --binlog-annotate-rows-events 3. Server option: --replicate-annotate-rows-events 4. mysqlbinlog option: --print-annotate-rows-events 5. mysqlbinlog output 1. Annotate_rows_log_event [ ANNOTATE_ROWS_EVENT ] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Describes the query which caused the corresponding rows events. Has empty post-header and contains the query text in its data part. Example: ************************ ANNOTATE_ROWS_EVENT ************************ 00000220 | B6 A0 2C 4B | time_when = 1261215926 00000224 | 33 | event_type = 51 00000225 | 64 00 00 00 | server_id = 100 00000229 | 36 00 00 00 | event_len = 54 0000022D | 56 02 00 00 | log_pos = 00000256 00000231 | 00 00 | flags = <none> ------------------------ 00000233 | 49 4E 53 45 | query = "INSERT INTO t1 VALUES (1), (2), (3)" 00000237 | 52 54 20 49 | 0000023B | 4E 54 4F 20 | 0000023F | 74 31 20 56 | 00000243 | 41 4C 55 45 | 00000247 | 53 20 28 31 | 0000024B | 29 2C 20 28 | 0000024F | 32 29 2C 20 | 00000253 | 28 33 29 | ************************ In binary log, Annotate_rows event follows the (possible) 'BEGIN' Query event and precedes the first of Table map events which accompany the corresponding rows events. (See example in the "mysqlbinlog output" section below.) 2. Server option: --binlog-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tells the master to write Annotate_rows events to the binary log. * Variable Name: binlog_annotate_rows_events * Scope: Global & Session * Access Type: Dynamic * Data Type: bool * Default Value: OFF NOTE. Session values allows to annotate only some selected statements: ... SET SESSION binlog_annotate_rows_events=ON; ... statements to be annotated ... SET SESSION binlog_annotate_rows_events=OFF; ... statements not to be annotated ... 3. Server option: --replicate-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tells the slave to reproduce Annotate_rows events recieved from the master in its own binary log (sensible only in pair with log-slave-updates option). * Variable Name: replicate_annotate_rows_events * Scope: Global * Access Type: Read only * Data Type: bool * Default Value: OFF NOTE. Why do we additionally need this 'replicate' option? Why not to make the slave to reproduce this events when its binlog-annotate-rows-events global value is ON? Well, because, for example, we may want to configure the slave which should reproduce Annotate_rows events but has global binlog-annotate-rows-events = OFF meaning this to be the default value for the client threads (see also "How slave treats replicate-annotate-rows-events option" in LLD part). 4. mysqlbinlog option: --print-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ With this option, mysqlbinlog prints the content of Annotate_rows events (if the binary log does contain them). Without this option (i.e. by default), mysqlbinlog skips Annotate_rows events. 5. mysqlbinlog output ~~~~~~~~~~~~~~~~~~~~~ With --print-annotate-rows-events, mysqlbinlog outputs Annotate_rows events in a form like this: ... # at 1646 #091219 12:45:26 server id 100 end_log_pos 1714 Query thread_id=1 exec_time=0 error_code=0 SET TIMESTAMP=1261215926/*!*/; BEGIN /*!*/; # at 1714 # at 1812 # at 1853 # at 1894 # at 1938 #091219 12:45:26 server id 100 end_log_pos 1812 Query: `DELETE t1, t2 FROM t1 INNER JOIN t2 INNER JOIN t3 WHERE t1.a=t2.a AND t2.a=t3.a` #091219 12:45:26 server id 100 end_log_pos 1853 Table_map: `test`.`t1` mapped to number 16 #091219 12:45:26 server id 100 end_log_pos 1894 Table_map: `test`.`t2` mapped to number 17 #091219 12:45:26 server id 100 end_log_pos 1938 Delete_rows: table id 16 #091219 12:45:26 server id 100 end_log_pos 1982 Delete_rows: table id 17 flags: STMT_END_F ... LOW-LEVEL DESIGN: Content ~~~~~~~ 1. Annotate_rows event number 2. Outline of Annotate_rows event behavior 3. How Master writes Annotate_rows events to the binary log 4. How slave treats replicate-annotate-rows-events option 5. How slave IO thread requests Annotate_rows events 6. How master executes the request 7. How slave SQL thread processes Annotate_rows events 8. General remarks 1. Annotate_rows event number ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ To avoid possible event numbers conflict with MySQL/Sun, we leave a gap between the last MySQL event number and the Annotate_rows event number: enum Log_event_type { ... INCIDENT_EVENT= 26, // New MySQL event numbers are to be added here MYSQL_EVENTS_END, MARIA_EVENTS_BEGIN= 51, // New Maria event numbers start from here ANNOTATE_ROWS_EVENT= 51, ENUM_END_EVENT }; together with the corresponding extension of 'post_header_len' array in the Format description event. (This extension does not affect the compatibility of the binary log). Here is how Format description event looks like with this extension: ************************ FORMAT_DESCRIPTION_EVENT ************************ 00000004 | A1 A0 2C 4B | time_when = 1261215905 00000008 | 0F | event_type = 15 00000009 | 64 00 00 00 | server_id = 100 0000000D | 7F 00 00 00 | event_len = 127 00000011 | 83 00 00 00 | log_pos = 00000083 00000015 | 01 00 | flags = LOG_EVENT_BINLOG_IN_USE_F ------------------------ 00000017 | 04 00 | binlog_ver = 4 00000019 | 35 2E 32 2E | server_ver = 5.2.0-MariaDB-alpha-debug-log ..... ... 0000004B | A1 A0 2C 4B | time_created = 1261215905 0000004F | 13 | common_header_len = 19 ------------------------ post_header_len ------------------------ 00000050 | 38 | 56 - START_EVENT_V3 [1] ..... ... 00000069 | 02 | 2 - INCIDENT_EVENT [26] 0000006A | 00 | 0 - RESERVED [27] ..... ... 00000081 | 00 | 0 - RESERVED [50] 00000082 | 00 | 0 - ANNOTATE_ROWS_EVENT [51] ************************ 2. Outline of Annotate_rows event behavior ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Each Annotate_rows_log_event object has two private members describing the corresponding query: char *m_query_txt; uint m_query_len; When the object is created for writing to a binary log, this query is taken from 'thd' (for short, below we omit the 'Annotate_rows_log_event::' prefix as well as other implementation details): Annotate_rows_log_event(THD *thd) { m_query_txt = thd->query(); m_query_len = thd->query_length(); } When the object is read from a binary log, the query is taken from the buffer containing the binary log representation of the event (this buffer is allocated in Log_event object from which all Log events are derived): Annotate_rows_log_event(char *buf, uint event_len, Format_description_log_event *desc) { m_query_len = event_len - desc->common_header_len; m_query_txt = buf + desc->common_header_len; } The events are written to the binary log by the Log_event::write() member which calls virtual write_data_header() and write_data_body() members ("data header" and "post header" are synonym in replication terminology). In our case, data header is empty and data body is just the query: bool write_data_body(IO_CACHE *file) { return my_b_safe_write(file, (uchar*) m_query_txt, m_query_len); } Printing the event is just printing the query: void Annotate_rows_log_event::print(FILE *file, PRINT_EVENT_INFO *pinfo) { my_b_printf(&pinfo->head_cache, "\tQuery: `%s`\n", m_query_txt); } 3. How Master writes Annotate_rows events to the binary log ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The event is written to the binary log just before the group of Table_map events which precede corresponding Rows events (one query may generate several Table map events in the binary log, but the corresponding Annotate_rows event must be written only once before the first Table map event; hence the boolean variable 'with_annotate' below): int write_locked_table_maps(THD *thd) { ... bool with_annotate= thd->variables.binlog_annotate_rows_events; ... for (uint i= 0; i < ... <number of tables> ...; ++i) { ... thd->binlog_write_table_map(table, ..., with_annotate); with_annotate= 0; // write Annotate_event not more than once ... } ... } int THD::binlog_write_table_map(TABLE *table, ..., bool with_annotate) { ... Table_map_log_event the_event(...); ... if (with_annotate) { Annotate_rows_log_event anno(this); mysql_bin_log.write(&anno); } mysql_bin_log.write(&the_event); ... } 4. How slave treats replicate-annotate-rows-events option ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The replicate-annotate-rows-events option is treated just as the session value of the binlog_annotate_rows_events variable for the slave IO and SQL threads. This setting is done during initialization of these threads: pthread_handler_t handle_slave_io(void *arg) { THD *thd= new THD; ... init_slave_thread(thd, SLAVE_THD_IO); ... } pthread_handler_t handle_slave_sql(void *arg) { THD *thd= new THD; ... init_slave_thread(thd, SLAVE_THD_SQL); ... } int init_slave_thread(THD* thd, SLAVE_THD_TYPE thd_type) { ... thd->variables.binlog_annotate_rows_events= opt_replicate_annotate_rows_events; ... } 5. How slave IO thread requests Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If the replicate-annotate-rows-events option is not set on a slave, there is no need for master to send Annotate_rows events to this slave. The slave (or mysqlbinlog in remote case), before requesting binlog dump via the COM_BINLOG_DUMP command, informs the master whether it should send these events by executing the newly added COM_BINLOG_DUMP_OPTIONS_EXT server command: case COM_BINLOG_DUMP_OPTIONS_EXT: thd->binlog_dump_flags_ext= packet[0]; my_ok(thd); break; Note. We add this new command and don't use COM_BINLOG_DUMP to avoid possible conflicts with MySQL/Sun. 6. How master executes the request ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ case COM_BINLOG_DUMP: { ... flags= uint2korr(packet + 4); ... mysql_binlog_send(thd, ..., flags); ... } void mysql_binlog_send(THD* thd, ..., ushort flags) { ... Log_event::read_log_event(&log, packet, ...); ... if ((*packet)[EVENT_TYPE_OFFSET + 1] != ANNOTATE_ROWS_EVENT || flags & BINLOG_SEND_ANNOTATE_ROWS_EVENT) { my_net_write(net, packet->ptr(), packet->length()); } ... } 7. How slave SQL thread processes Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The slave processes each recieved event by "applying" it, i.e. by calling the Log_event::apply_event() function which in turn calls the virtual do_apply_event() member specific for each type of the event. int exec_relay_log_event(THD* thd, Relay_log_info* rli) { ... Log_event *ev = next_event(rli); ... apply_event_and_update_pos(ev, ...); if (ev->get_type_code() != FORMAT_DESCRIPTION_EVENT) delete ev; ... } int apply_event_and_update_pos(Log_event *ev, ...) { ... ev->apply_event(...); ... } int Log_event::apply_event(...) { return do_apply_event(...); } What does it mean to "apply" an Annotate_rows event? It means to set current thd query to that of the described by the event, i.e. to the query which caused the subsequent Rows events (see "How Master writes Annotate_rows events to the binary log" to follow what happens further when the subsequent Rows events are applied): int Annotate_rows_log_event::do_apply_event(...) { thd->set_query(m_query_txt, m_query_len); } NOTE. I am not sure, but possibly current values of thd->query and thd->query_length should be saved before calling set_query() and to be restored on the Annotate_rows_log_event object deletion. Is it really needed ? After calling this do_apply_event() function we may not delete the Annotate_rows_log_event object immediatedly (see exec_relay_log_event() above) because thd->query now points to the string inside this object. We may keep the pointer to this object in the Relay_log_info: class Relay_log_info { public: ... void set_annotate_event(Annotate_rows_log_event*); Annotate_rows_log_event* get_annotate_event(); void free_annotate_event(); ... private: Annotate_rows_log_event* m_annotate_event; }; The saved Annotate_rows object should be deleted when all corresponding Rows events will be processed: int exec_relay_log_event(THD* thd, Relay_log_info* rli) { ... Log_event *ev= next_event(rli); ... apply_event_and_update_pos(ev, ...); if (rli->get_annotate_event() && is_last_rows_event(ev)) rli->free_annotate_event(); else if (ev->get_type_code() == ANNOTATE_ROWS_EVENT) rli->set_annotate_event((Annotate_rows_log_event*) ev); else if (ev->get_type_code() != FORMAT_DESCRIPTION_EVENT) delete ev; ... } where bool is_last_rows_event(Log_event* ev) { Log_event_type type= ev->get_type_code(); if (IS_ROWS_EVENT_TYPE(type)) { Rows_log_event* rows= (Rows_log_event*)ev; return rows->get_flags(Rows_log_event::STMT_END_F); } return 0; } #define IS_ROWS_EVENT_TYPE(type) ((type) == WRITE_ROWS_EVENT || \ (type) == UPDATE_ROWS_EVENT || \ (type) == DELETE_ROWS_EVENT) 8. General remarks ~~~~~~~~~~~~~~~~~~ Kristian noticed that introducing new log event type should be coordinated somehow with MySQL/Sun: Kristian: The numeric code for this event must be assigned carefully. It should be coordinated with MySQL/Sun, otherwise we can get into a situation where MySQL uses the same numeric code for one event that MariaDB uses for ANNOTATE_ROWS_EVENT, which would make merging the two impossible. Alex: I reserved about 20 numbers not to have possible conflicts with MySQL. Kristian: Still, I think it would be appropriate to send a polite email to internals(a)lists.mysql.com about this and suggesting to reserve the event number. ESTIMATED WORK TIME ESTIMATED COMPLETION DATE ----------------------------------------------------------------------- WorkLog (v3.5.9)

1 0

[Maria-developers] Progress (by Knielsen): Store in binlog text of statements that caused RBR events (47)
by worklog-noreply＠askmonty.org 05 May '10

05 May '10

----------------------------------------------------------------------- WORKLOG TASK -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- TASK...........: Store in binlog text of statements that caused RBR events CREATION DATE..: Sat, 15 Aug 2009, 23:48 SUPERVISOR.....: Monty IMPLEMENTOR....: COPIES TO......: Knielsen, Serg CATEGORY.......: Server-Sprint TASK ID........: 47 (http://askmonty.org/worklog/?tid=47) VERSION........: Server-9.x STATUS.........: Code-Review PRIORITY.......: 60 WORKED HOURS...: 29 ESTIMATE.......: 6 (hours remain) ORIG. ESTIMATE.: 35 PROGRESS NOTES: -=-=(Knielsen - Wed, 05 May 2010, 13:53)=-=- Review of fixes to first review done. No new issues found. Worked 2 hours and estimate 6 hours remain (original estimate unchanged). -=-=(Knielsen - Fri, 23 Apr 2010, 12:51)=-=- Status updated. --- /tmp/wklog.47.old.28747 2010-04-23 12:51:36.000000000 +0000 +++ /tmp/wklog.47.new.28747 2010-04-23 12:51:36.000000000 +0000 @@ -1 +1 @@ -In-Progress +Code-Review -=-=(Knielsen - Tue, 06 Apr 2010, 15:26)=-=- Code review (mailed to maria-developers@). Worked 7 hours and estimate 8 hours remain (original estimate unchanged). -=-=(Knielsen - Tue, 06 Apr 2010, 15:25)=-=- Status updated. --- /tmp/wklog.47.old.12734 2010-04-06 15:25:54.000000000 +0000 +++ /tmp/wklog.47.new.12734 2010-04-06 15:25:54.000000000 +0000 @@ -1 +1 @@ -Code-Review +In-Progress -=-=(Knielsen - Mon, 29 Mar 2010, 10:59)=-=- Status updated. --- /tmp/wklog.47.old.27790 2010-03-29 10:59:53.000000000 +0000 +++ /tmp/wklog.47.new.27790 2010-03-29 10:59:53.000000000 +0000 @@ -1 +1 @@ -In-Progress +Code-Review -=-=(Alexi - Thu, 18 Feb 2010, 19:29)=-=- Worked 20 hours (alexi) Worked 20 hours and estimate 15 hours remain (original estimate unchanged). -=-=(Serg - Fri, 05 Feb 2010, 14:04)=-=- Observers changed: Knielsen,Serg -=-=(Guest - Fri, 05 Feb 2010, 13:40)=-=- Category updated. --- /tmp/wklog.47.old.9197 2010-02-05 13:40:36.000000000 +0200 +++ /tmp/wklog.47.new.9197 2010-02-05 13:40:36.000000000 +0200 @@ -1 +1 @@ -Server-RawIdeaBin +Server-Sprint -=-=(Guest - Fri, 05 Feb 2010, 13:40)=-=- Status updated. --- /tmp/wklog.47.old.9197 2010-02-05 13:40:36.000000000 +0200 +++ /tmp/wklog.47.new.9197 2010-02-05 13:40:36.000000000 +0200 @@ -1 +1 @@ -Un-Assigned +In-Progress -=-=(Alexi - Thu, 04 Feb 2010, 09:54)=-=- Low Level Design modified. --- /tmp/wklog.47.old.16174 2010-02-04 09:54:13.000000000 +0200 +++ /tmp/wklog.47.new.16174 2010-02-04 09:54:13.000000000 +0200 @@ -171,35 +171,20 @@ 5. How slave IO thread requests Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -When requesting an event, the slave should inform the master whether -it should send Annotate_rows events or not. To that end we add a new -BINLOG_SEND_ANNOTATE_ROWS_EVENT flag used when requesting an event: +If the replicate-annotate-rows-events option is not set on a slave, there +is no need for master to send Annotate_rows events to this slave. The slave +(or mysqlbinlog in remote case), before requesting binlog dump via the +COM_BINLOG_DUMP command, informs the master whether it should send these +events by executing the newly added COM_BINLOG_DUMP_OPTIONS_EXT server +command: + + case COM_BINLOG_DUMP_OPTIONS_EXT: + thd->binlog_dump_flags_ext= packet[0]; + my_ok(thd); + break; - #define BINLOG_DUMP_NON_BLOCK 1 - #define BINLOG_SEND_ANNOTATE_ROWS_EVENT 2 - - pthread_handler_t handle_slave_io(void *arg) - { ... - request_dump(mysql, ...); - ... - } - - int request_dump(MYSQL* mysql, ...) - { ... - if (opt_log_slave_updates && - mi->io_thd->variables.binlog_annotate_rows_events) - binlog_flags|= BINLOG_SEND_ANNOTATE_ROWS_EVENT; - ... - int2store(buf + 4, binlog_flags); - ... - simple_command(mysql, COM_BINLOG_DUMP, buf, ...); - ... - } - -NOTE. mysqlbinlog, when remotely requesting BINLOG_DUMP by calling the -simple_command() function, should also use this flag if it wants (in case -of the --print-annotate-rows-events option set) to recieve Annotate_rows -events. +Note. We add this new command and don't use COM_BINLOG_DUMP to avoid possible +conflicts with MySQL/Sun. 6. How master executes the request ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -338,10 +323,4 @@ to internals(a)lists.mysql.com about this and suggesting to reserve the event number. -Also we should notice the introduction of the BINLOG_SEND_ANNOTATE_ROWS_EVENT -flag taking into account that MySQL/Sun may also introduce a flag with the -same value to be used in the request_dump-mysql_binlog_send interface. -But this is mainly the question of merging: if a conflict concerning this -flag occur, we may simply change the BINLOG_SEND_ANNOTATE_ROWS_EVENT value -(this does not require additional changes in the code). ------------------------------------------------------------ -=-=(View All Progress Notes, 29 total)=-=- http://askmonty.org/worklog/index.pl?tid=47&nolimit=1 DESCRIPTION: Store in binlog (and show in mysqlbinlog output) texts of statements that caused RBR events This is needed for (list from Monty): - Easier to understand why updates happened - Would make it easier to find out where in application things went wrong (as you can search for exact strings) - Allow one to filter things based on comments in the statement. The cost of this can be that the binlog will be approximately 2x in size (especially insert of big blob's would be a bit painful), so this should be an optional feature. HIGH-LEVEL SPECIFICATION: Content ~~~~~~~ 1. Annotate_rows_log_event 2. Server option: --binlog-annotate-rows-events 3. Server option: --replicate-annotate-rows-events 4. mysqlbinlog option: --print-annotate-rows-events 5. mysqlbinlog output 1. Annotate_rows_log_event [ ANNOTATE_ROWS_EVENT ] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Describes the query which caused the corresponding rows events. Has empty post-header and contains the query text in its data part. Example: ************************ ANNOTATE_ROWS_EVENT ************************ 00000220 | B6 A0 2C 4B | time_when = 1261215926 00000224 | 33 | event_type = 51 00000225 | 64 00 00 00 | server_id = 100 00000229 | 36 00 00 00 | event_len = 54 0000022D | 56 02 00 00 | log_pos = 00000256 00000231 | 00 00 | flags = <none> ------------------------ 00000233 | 49 4E 53 45 | query = "INSERT INTO t1 VALUES (1), (2), (3)" 00000237 | 52 54 20 49 | 0000023B | 4E 54 4F 20 | 0000023F | 74 31 20 56 | 00000243 | 41 4C 55 45 | 00000247 | 53 20 28 31 | 0000024B | 29 2C 20 28 | 0000024F | 32 29 2C 20 | 00000253 | 28 33 29 | ************************ In binary log, Annotate_rows event follows the (possible) 'BEGIN' Query event and precedes the first of Table map events which accompany the corresponding rows events. (See example in the "mysqlbinlog output" section below.) 2. Server option: --binlog-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tells the master to write Annotate_rows events to the binary log. * Variable Name: binlog_annotate_rows_events * Scope: Global & Session * Access Type: Dynamic * Data Type: bool * Default Value: OFF NOTE. Session values allows to annotate only some selected statements: ... SET SESSION binlog_annotate_rows_events=ON; ... statements to be annotated ... SET SESSION binlog_annotate_rows_events=OFF; ... statements not to be annotated ... 3. Server option: --replicate-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tells the slave to reproduce Annotate_rows events recieved from the master in its own binary log (sensible only in pair with log-slave-updates option). * Variable Name: replicate_annotate_rows_events * Scope: Global * Access Type: Read only * Data Type: bool * Default Value: OFF NOTE. Why do we additionally need this 'replicate' option? Why not to make the slave to reproduce this events when its binlog-annotate-rows-events global value is ON? Well, because, for example, we may want to configure the slave which should reproduce Annotate_rows events but has global binlog-annotate-rows-events = OFF meaning this to be the default value for the client threads (see also "How slave treats replicate-annotate-rows-events option" in LLD part). 4. mysqlbinlog option: --print-annotate-rows-events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ With this option, mysqlbinlog prints the content of Annotate_rows events (if the binary log does contain them). Without this option (i.e. by default), mysqlbinlog skips Annotate_rows events. 5. mysqlbinlog output ~~~~~~~~~~~~~~~~~~~~~ With --print-annotate-rows-events, mysqlbinlog outputs Annotate_rows events in a form like this: ... # at 1646 #091219 12:45:26 server id 100 end_log_pos 1714 Query thread_id=1 exec_time=0 error_code=0 SET TIMESTAMP=1261215926/*!*/; BEGIN /*!*/; # at 1714 # at 1812 # at 1853 # at 1894 # at 1938 #091219 12:45:26 server id 100 end_log_pos 1812 Query: `DELETE t1, t2 FROM t1 INNER JOIN t2 INNER JOIN t3 WHERE t1.a=t2.a AND t2.a=t3.a` #091219 12:45:26 server id 100 end_log_pos 1853 Table_map: `test`.`t1` mapped to number 16 #091219 12:45:26 server id 100 end_log_pos 1894 Table_map: `test`.`t2` mapped to number 17 #091219 12:45:26 server id 100 end_log_pos 1938 Delete_rows: table id 16 #091219 12:45:26 server id 100 end_log_pos 1982 Delete_rows: table id 17 flags: STMT_END_F ... LOW-LEVEL DESIGN: Content ~~~~~~~ 1. Annotate_rows event number 2. Outline of Annotate_rows event behavior 3. How Master writes Annotate_rows events to the binary log 4. How slave treats replicate-annotate-rows-events option 5. How slave IO thread requests Annotate_rows events 6. How master executes the request 7. How slave SQL thread processes Annotate_rows events 8. General remarks 1. Annotate_rows event number ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ To avoid possible event numbers conflict with MySQL/Sun, we leave a gap between the last MySQL event number and the Annotate_rows event number: enum Log_event_type { ... INCIDENT_EVENT= 26, // New MySQL event numbers are to be added here MYSQL_EVENTS_END, MARIA_EVENTS_BEGIN= 51, // New Maria event numbers start from here ANNOTATE_ROWS_EVENT= 51, ENUM_END_EVENT }; together with the corresponding extension of 'post_header_len' array in the Format description event. (This extension does not affect the compatibility of the binary log). Here is how Format description event looks like with this extension: ************************ FORMAT_DESCRIPTION_EVENT ************************ 00000004 | A1 A0 2C 4B | time_when = 1261215905 00000008 | 0F | event_type = 15 00000009 | 64 00 00 00 | server_id = 100 0000000D | 7F 00 00 00 | event_len = 127 00000011 | 83 00 00 00 | log_pos = 00000083 00000015 | 01 00 | flags = LOG_EVENT_BINLOG_IN_USE_F ------------------------ 00000017 | 04 00 | binlog_ver = 4 00000019 | 35 2E 32 2E | server_ver = 5.2.0-MariaDB-alpha-debug-log ..... ... 0000004B | A1 A0 2C 4B | time_created = 1261215905 0000004F | 13 | common_header_len = 19 ------------------------ post_header_len ------------------------ 00000050 | 38 | 56 - START_EVENT_V3 [1] ..... ... 00000069 | 02 | 2 - INCIDENT_EVENT [26] 0000006A | 00 | 0 - RESERVED [27] ..... ... 00000081 | 00 | 0 - RESERVED [50] 00000082 | 00 | 0 - ANNOTATE_ROWS_EVENT [51] ************************ 2. Outline of Annotate_rows event behavior ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Each Annotate_rows_log_event object has two private members describing the corresponding query: char *m_query_txt; uint m_query_len; When the object is created for writing to a binary log, this query is taken from 'thd' (for short, below we omit the 'Annotate_rows_log_event::' prefix as well as other implementation details): Annotate_rows_log_event(THD *thd) { m_query_txt = thd->query(); m_query_len = thd->query_length(); } When the object is read from a binary log, the query is taken from the buffer containing the binary log representation of the event (this buffer is allocated in Log_event object from which all Log events are derived): Annotate_rows_log_event(char *buf, uint event_len, Format_description_log_event *desc) { m_query_len = event_len - desc->common_header_len; m_query_txt = buf + desc->common_header_len; } The events are written to the binary log by the Log_event::write() member which calls virtual write_data_header() and write_data_body() members ("data header" and "post header" are synonym in replication terminology). In our case, data header is empty and data body is just the query: bool write_data_body(IO_CACHE *file) { return my_b_safe_write(file, (uchar*) m_query_txt, m_query_len); } Printing the event is just printing the query: void Annotate_rows_log_event::print(FILE *file, PRINT_EVENT_INFO *pinfo) { my_b_printf(&pinfo->head_cache, "\tQuery: `%s`\n", m_query_txt); } 3. How Master writes Annotate_rows events to the binary log ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The event is written to the binary log just before the group of Table_map events which precede corresponding Rows events (one query may generate several Table map events in the binary log, but the corresponding Annotate_rows event must be written only once before the first Table map event; hence the boolean variable 'with_annotate' below): int write_locked_table_maps(THD *thd) { ... bool with_annotate= thd->variables.binlog_annotate_rows_events; ... for (uint i= 0; i < ... <number of tables> ...; ++i) { ... thd->binlog_write_table_map(table, ..., with_annotate); with_annotate= 0; // write Annotate_event not more than once ... } ... } int THD::binlog_write_table_map(TABLE *table, ..., bool with_annotate) { ... Table_map_log_event the_event(...); ... if (with_annotate) { Annotate_rows_log_event anno(this); mysql_bin_log.write(&anno); } mysql_bin_log.write(&the_event); ... } 4. How slave treats replicate-annotate-rows-events option ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The replicate-annotate-rows-events option is treated just as the session value of the binlog_annotate_rows_events variable for the slave IO and SQL threads. This setting is done during initialization of these threads: pthread_handler_t handle_slave_io(void *arg) { THD *thd= new THD; ... init_slave_thread(thd, SLAVE_THD_IO); ... } pthread_handler_t handle_slave_sql(void *arg) { THD *thd= new THD; ... init_slave_thread(thd, SLAVE_THD_SQL); ... } int init_slave_thread(THD* thd, SLAVE_THD_TYPE thd_type) { ... thd->variables.binlog_annotate_rows_events= opt_replicate_annotate_rows_events; ... } 5. How slave IO thread requests Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If the replicate-annotate-rows-events option is not set on a slave, there is no need for master to send Annotate_rows events to this slave. The slave (or mysqlbinlog in remote case), before requesting binlog dump via the COM_BINLOG_DUMP command, informs the master whether it should send these events by executing the newly added COM_BINLOG_DUMP_OPTIONS_EXT server command: case COM_BINLOG_DUMP_OPTIONS_EXT: thd->binlog_dump_flags_ext= packet[0]; my_ok(thd); break; Note. We add this new command and don't use COM_BINLOG_DUMP to avoid possible conflicts with MySQL/Sun. 6. How master executes the request ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ case COM_BINLOG_DUMP: { ... flags= uint2korr(packet + 4); ... mysql_binlog_send(thd, ..., flags); ... } void mysql_binlog_send(THD* thd, ..., ushort flags) { ... Log_event::read_log_event(&log, packet, ...); ... if ((*packet)[EVENT_TYPE_OFFSET + 1] != ANNOTATE_ROWS_EVENT || flags & BINLOG_SEND_ANNOTATE_ROWS_EVENT) { my_net_write(net, packet->ptr(), packet->length()); } ... } 7. How slave SQL thread processes Annotate_rows events ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The slave processes each recieved event by "applying" it, i.e. by calling the Log_event::apply_event() function which in turn calls the virtual do_apply_event() member specific for each type of the event. int exec_relay_log_event(THD* thd, Relay_log_info* rli) { ... Log_event *ev = next_event(rli); ... apply_event_and_update_pos(ev, ...); if (ev->get_type_code() != FORMAT_DESCRIPTION_EVENT) delete ev; ... } int apply_event_and_update_pos(Log_event *ev, ...) { ... ev->apply_event(...); ... } int Log_event::apply_event(...) { return do_apply_event(...); } What does it mean to "apply" an Annotate_rows event? It means to set current thd query to that of the described by the event, i.e. to the query which caused the subsequent Rows events (see "How Master writes Annotate_rows events to the binary log" to follow what happens further when the subsequent Rows events are applied): int Annotate_rows_log_event::do_apply_event(...) { thd->set_query(m_query_txt, m_query_len); } NOTE. I am not sure, but possibly current values of thd->query and thd->query_length should be saved before calling set_query() and to be restored on the Annotate_rows_log_event object deletion. Is it really needed ? After calling this do_apply_event() function we may not delete the Annotate_rows_log_event object immediatedly (see exec_relay_log_event() above) because thd->query now points to the string inside this object. We may keep the pointer to this object in the Relay_log_info: class Relay_log_info { public: ... void set_annotate_event(Annotate_rows_log_event*); Annotate_rows_log_event* get_annotate_event(); void free_annotate_event(); ... private: Annotate_rows_log_event* m_annotate_event; }; The saved Annotate_rows object should be deleted when all corresponding Rows events will be processed: int exec_relay_log_event(THD* thd, Relay_log_info* rli) { ... Log_event *ev= next_event(rli); ... apply_event_and_update_pos(ev, ...); if (rli->get_annotate_event() && is_last_rows_event(ev)) rli->free_annotate_event(); else if (ev->get_type_code() == ANNOTATE_ROWS_EVENT) rli->set_annotate_event((Annotate_rows_log_event*) ev); else if (ev->get_type_code() != FORMAT_DESCRIPTION_EVENT) delete ev; ... } where bool is_last_rows_event(Log_event* ev) { Log_event_type type= ev->get_type_code(); if (IS_ROWS_EVENT_TYPE(type)) { Rows_log_event* rows= (Rows_log_event*)ev; return rows->get_flags(Rows_log_event::STMT_END_F); } return 0; } #define IS_ROWS_EVENT_TYPE(type) ((type) == WRITE_ROWS_EVENT || \ (type) == UPDATE_ROWS_EVENT || \ (type) == DELETE_ROWS_EVENT) 8. General remarks ~~~~~~~~~~~~~~~~~~ Kristian noticed that introducing new log event type should be coordinated somehow with MySQL/Sun: Kristian: The numeric code for this event must be assigned carefully. It should be coordinated with MySQL/Sun, otherwise we can get into a situation where MySQL uses the same numeric code for one event that MariaDB uses for ANNOTATE_ROWS_EVENT, which would make merging the two impossible. Alex: I reserved about 20 numbers not to have possible conflicts with MySQL. Kristian: Still, I think it would be appropriate to send a polite email to internals(a)lists.mysql.com about this and suggesting to reserve the event number. ESTIMATED WORK TIME ESTIMATED COMPLETION DATE ----------------------------------------------------------------------- WorkLog (v3.5.9)

1 0