- developers - lists.mariadb.org

[Maria-developers] GSoC Introduction
by Rucha Deodhar 27 May '19

27 May '19

Hello, I am Rucha Deodhar. I am a GSoC student and will implement INSERT...RETURNING. In the first week I plan to extend the parser. Approximately the next 2 months, I plan to make changes the in the codes in insert.cc and other files related to the project, and remaining time for testing. As suggested, I am allotting 40% of the time for testing.This is my approximate plan, Regards, Rucha.

2 1

Re: [Maria-developers] Regarding approach used for Early NULL filtering in the range optimizer(MDEV-15777)
by Sergey Petrunia 24 May '19

24 May '19

On Fri, May 24, 2019 at 10:08:04AM -0700, Igor Babaev wrote: > On 05/24/2019 04:03 AM, Varun Gupta wrote: > > Hi Igor, > > After discussing with Sergey, we came up with these conclusions as to > > why we used the approach of going through all the keyuses in the KEYUSE > > array > > > > Cases to consider: > > we have an index on column a > > > > 1) a OP const > > where OP can be (</<=/=/between/ etc on which we do range analysis) . > > This case is already handled by the range optimizer. We do not create a > > NULL rejecting predicate for such conditions. > > > > 2) eq_join conditions (tbl1.a = tbl2.col2) > > This is the specific case we have tried to implement in MDEV-15777, we > > create NULL rejecting predicates for the keyuses for each table and then > > feed these predicates to range optimizer > There is no logical explanation for checking null rejection of fields used > in equalities with the help of array keyuse. The logic here is as follows: We already collect the set of KEYUSE::null_rejecting attributes. Its meaning is very close to what the patch needs. Because of this, the part of the patch for MDEV-15777 which analyzes the KEYUSE array is very small: 122 lines including the comment (I counted make_null_rejecting_conds() and add_cond()). I think, the CPU overhead is small, too. > > > > 3) a < func(b,c) > > we do not handle this case, because: > > > > a) It is harder to process. We would need to process the whole WHERE > > clause to infer > > non-nullability of the condition. Example: > > > > (t1.f2+1 < t1.f1+t1.f3) OR ... OR t1.f1 is null > > > > here the left part of the OR condition doesn't allow f1 to be NULL, but > > the > > right condition allows it. We would also need to take into account tables > > inside outer joins. We would need to go through Item classes and add code > > which say "Item_xxx() will compute to false when its argument Y is null" > > (there is item->not_null_tables() currently, but not not_null_columns()). > Have you actually looked at the implementations of the virtual function > not_null_tables()? > Do you need me to provide the implementation of the virtual function > not_null_columns()? It will require multiple implementations. At the moment we have: nm mysqld --demangle | grep 'Item.*::not_null_tables' | wc -l 21 Another question: do you intend to collect not_null_columns() for all columns, or just columns that are a part of some index? What would a good data structure to store a set of tablename.column_name ? > > > > b) the conditions in form of arbitrary functions are not as frequently > > used as > > ref access conditions. > > > > to sum up a) and b) - doable but will require a lot of effort. > > > > Do you have any specific practically relevant example in mind that we > > should > > handle? BR Sergei -- Sergei Petrunia, Software Developer MariaDB Corporation | Skype: sergefp | Blog: http://s.petrunia.net/blog

1 0

[Maria-developers] Regarding approach used for Early NULL filtering in the range optimizer(MDEV-15777)
by Varun Gupta 24 May '19

24 May '19

Hi Igor, After discussing with Sergey, we came up with these conclusions as to why we used the approach of going through all the keyuses in the KEYUSE array Cases to consider: we have an index on column a 1) a OP const where OP can be (</<=/=/between/ etc on which we do range analysis) . This case is already handled by the range optimizer. We do not create a NULL rejecting predicate for such conditions. 2) eq_join conditions (tbl1.a = tbl2.col2) This is the specific case we have tried to implement in MDEV-15777, we create NULL rejecting predicates for the keyuses for each table and then feed these predicates to range optimizer 3) a < func(b,c) we do not handle this case, because: a) It is harder to process. We would need to process the whole WHERE clause to infer non-nullability of the condition. Example: (t1.f2+1 < t1.f1+t1.f3) OR ... OR t1.f1 is null here the left part of the OR condition doesn't allow f1 to be NULL, but the right condition allows it. We would also need to take into account tables inside outer joins. We would need to go through Item classes and add code which say "Item_xxx() will compute to false when its argument Y is null" (there is item->not_null_tables() currently, but not not_null_columns()). b) the conditions in form of arbitrary functions are not as frequently used as ref access conditions. to sum up a) and b) - doable but will require a lot of effort. Do you have any specific practically relevant example in mind that we should handle? Regards, Varun and Sergey

1 0

[Maria-developers] Review for: b4696ee97e684 : MDEV-15777: Support Early NULLs filtering-like restrictions in the range optimizer
by Sergey Petrunia 23 May '19

23 May '19

Hi Varun, Please find review input below. Only cosmetic changes are requested. I also assume that after this is pushed - we add a optimizer trace printout into 10.4 - the feature is enabled by default in 10.5 ? (do we need separate MDEVs for this?) One final question is the choice of name for @@optimizer_switch flag. Let me get back to you on this. > commit b4696ee97e6846ba49ef203cfc7189f50c1e53a7 > Author: Varun Gupta <varun.gupta(a)mariadb.com> > Date: Mon May 20 15:14:30 2019 +0530 > > MDEV-15777: Support Early NULLs filtering-like restrictions in the range optimizer > > For eqjoin conditions, we add a NOT NULL predicate so as to allow the range optimizer > to use the predicate and possibly create a range access on the given table. > > Example: > select * from t1,t2 where t1.a=t2.a; we have KEY(a) on t1 > we would inject a NOT NULL predicate t1.a IS NOT NULL for table t1 > this would allow the range optimizer to create ranges and we get a > range access on table t1, then we will be able > to do an early NULL filtering for ranges too. > > diff --git a/mysql-test/main/range.result b/mysql-test/main/range.result > index 32e0cf2868c..d75d6734277 100644 > --- a/mysql-test/main/range.result > +++ b/mysql-test/main/range.result > @@ -3024,3 +3024,151 @@ drop table t1; > # > # End of 10.2 tests > # > +# > +# MDEV-15777: Support Early NULLs filtering-like restrictions in the range optimizer > +# > +set @save_optimizer_switch= @@optimizer_switch; > +set @@optimizer_switch='null_rejecting_for_ranges=on'; > +create table ten(a int); > +insert into ten values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9); > +create table one_k(a int); > +insert into one_k select A.a + B.a* 10 + C.a * 100 from ten A, ten B, ten C; Did we abandon the convention of naming the tables t1,t2,t3,... ? If not, please rename. > +create table t1 ( > +id int(10) unsigned NOT NULL, > +subset_id int(11) DEFAULT NULL, > +PRIMARY KEY (id), > +KEY t1_subset_id (subset_id)); ... > diff --git a/sql/opt_range.cc b/sql/opt_range.cc > index ec7b3dbbd7a..cb7800d1ba6 100644 > --- a/sql/opt_range.cc > +++ b/sql/opt_range.cc > @@ -2539,6 +2546,42 @@ int SQL_SELECT::test_quick_select(THD *thd, key_map keys_to_use, > TRP_GROUP_MIN_MAX *group_trp; > double best_read_time= read_time; > > + /* > + For the range optimizer, null_rejecting_conds are just an extra condition > + on which one can use index to create ranges. > + > + Also here we try to allow consider range access for a column involed in a > + null rejecting predicate only if it is the first keypart of an index. > + Let try to make it clear with examples: > + > + Query 1 > + select * from t1,t2 where t1.a=2 and t1.b=t2.b; > + and we have a key(a,b) > + So lets consider range access for table t1: > + Null rejecting predicate : t1.b IS NOT NULL > + but the column t1.b is NOT the first keypart in the index, > + so we don't consider it while building ranges > + > + Query 2 > + select * from t1,t2 where t1.a=t2.a and t1.b=t2.b; > + and we have a key (a,b) > + > + So lets consider range access for table t1: > + Null rejecting predicate : t1.a IS NOT NULL AND t1.b IS NOT NULL > + so here t1.a is the first keypart in the index, so we consider > + the predicate for building the ranges. > + > + The first keypart prerequisite is made as we try to reuse range > + estimates (because they are more accurate) at different places > + and we needed to make sure that correct/accurate estimates are used there. > + */ > + > + if (null_rejecting_conds) > + not_null_cond_tree= null_rejecting_conds->get_mm_tree(&param, > + &null_rejecting_conds); Please fix indentation and fit within 80 chars. ^ And also use curly braces as the code inside if doesn't fit on one line. > + if (not_null_cond_tree) > + remove_nonrange_trees(&param, not_null_cond_tree); > + > if (cond) > { > if ((tree= cond->get_mm_tree(&param, &cond))) > @@ -2557,6 +2600,7 @@ int SQL_SELECT::test_quick_select(THD *thd, key_map keys_to_use, > tree= NULL; > } > } > + tree= tree_and(&param, tree, not_null_cond_tree); > > /* > Try to construct a QUICK_GROUP_MIN_MAX_SELECT. > @@ -4422,6 +4466,128 @@ static bool create_partition_index_description(PART_PRUNE_PARAM *ppar) > return FALSE; > } > > +inline void add_cond(THD *thd, Item **e1, Item *e2) > +{ > + if (*e1) > + { > + if (!e2) > + return; > + Item *res; > + if ((res= new (thd->mem_root) Item_cond_and(thd, *e1, e2))) > + { > + res->fix_fields(thd, 0); > + res->update_used_tables(); > + *e1= res; > + } > + } > + else > + *e1= e2; > +} > + > +/* > + Create null rejecting conditions for a table, for all the equalites > + present in the WHERE clause of a query. > + > + SYNOPSIS > + make_null_rejecting_conds() > + @param TABLE - Keys of this table will participate in null > + rejecting conditions > + @param keyuse_array - array that has all the equalites of the > + WHERE clasuse The above doesn't match the function's definition. Out of date comment? > + > + DESCRIPTION > + This function creates null rejecting conditions for a table. These > + conditions are created to do range analysis on them , the conditions > + are of the form tbl.key.keypart IS NOT NULL. > + > + IMPLEMENTATION > + Lookup in the keyuse array to check if it has equalites that belong > + to the given table. If yes then find out if the conditions are null > + rejecting and accordingly create all the condition for the keys of a > + given table and AND them. > + > + > + RETURN > + NOT NULL - Found null rejecting conditions for the given table > + NULL - No null rejecting conditions for the given table The above doesn't match the function's definition. Out of date comment? > +*/ > + > +void make_null_rejecting_conds(THD *thd, JOIN_TAB *tab) > +{ > + KEY *keyinfo; > + Item *cond= NULL; > + KEYUSE* keyuse; > + TABLE *table= tab->table; > + key_map *const_keys= &tab->const_keys; ^ Does it make sense to introduce a variable if it is only used once? > + > + /* > + No need to add NOT NULL condition for materialized derived tables > + or materialized subqueries as we do not run the range optimizer > + on their conditions > + */ > + > + if (!optimizer_flag(thd, OPTIMIZER_SWITCH_NULL_REJECTING_FOR_RANGES)) > + return; > + > + if (tab->table->is_filled_at_execution() || > + (tab->table->pos_in_table_list->derived && > + tab->table->pos_in_table_list->is_materialized_derived())) > + return; > + > + Field_map not_null_keypart_map; > + > + /* > + The null rejecting conds added will be on the keypart of a key, so for > + that we need the table to atleast have a key. > + */ > + if (!table->s->keys || table->null_rejecting_conds || !tab->keyuse) > + return; > + > + for(keyuse= tab->keyuse; keyuse->table == table; keyuse++) > + { Please add space, "for ". > + /* > + No null rejecting conds for a hash key or full-text keys > + */ > + if (keyuse->key == MAX_KEY || keyuse->keypart == FT_KEYPART) > + continue; > + keyinfo= keyuse->table->key_info + keyuse->key; > + Field *field= keyinfo->key_part[keyuse->keypart].field; > + > + if (not_null_keypart_map.is_set(field->field_index)) > + continue; > + > + /* > + No need to add null-rejecting condition if we have a > + keyuse element as > + - table.key.keypart= const > + - (table.key.keypart= tbl.otherfield or table.key.keypart IS NULL) > + - table.key.keypart IS NOT NULLABLE > + */ > + > + if (keyuse->val->const_item() || > + !(keyuse->null_rejecting && field->maybe_null()) || > + keyuse->optimize & KEY_OPTIMIZE_REF_OR_NULL) > + continue; > + > + Item_field *field_item= new (thd->mem_root)Item_field(thd, field); > + Item* not_null_item= new (thd->mem_root)Item_func_isnotnull(thd, field_item); > + > + /* > + adding the key to const keys as we have the condition > + as key.keypart IS NOT NULL > + */ > + > + const_keys->set_bit(keyuse->key); > + not_null_item->fix_fields(thd, 0); ^^ please change 0 to &not_null_item. > + not_null_item->update_used_tables(); > + add_cond(thd, &cond, not_null_item); > + not_null_keypart_map.set_bit(field->field_index); > + } > + DBUG_EXECUTE("where", print_where(cond, "Early Null Filtering", > + QT_ORDINARY);); > + table->null_rejecting_conds= cond; > +} > + > > #ifndef DBUG_OFF > ... > diff --git a/sql/sql_select.cc b/sql/sql_select.cc > index 8cdcf3afc8b..140ceed5c2d 100644 > --- a/sql/sql_select.cc > +++ b/sql/sql_select.cc > @@ -5510,15 +5512,30 @@ add_key_field(JOIN *join, > If the condition has form "tbl.keypart = othertbl.field" and > othertbl.field can be NULL, there will be no matches if othertbl.field > has NULL value. > - We use null_rejecting in add_not_null_conds() to add > - 'othertbl.field IS NOT NULL' to tab->select_cond. > + > + The field KEY_FIELD::null_rejecting is set to TRUE if either > + the left or the right hand side of the equality is NULLABLE > + > + null_rejecting is used > + - by add_not_null_conds(), to add "othertbl.field IS NOT NULL" to > + othertbl's tab->select_cond. (This is called "Early NULLs filtering") > + > + - by make_null_rejecting_conds(), to provide range optimizer with > + additional "tbl.keypart IS NOT NULL" condition. > */ > { > Item *real= (*value)->real_item(); > - if (((cond->functype() == Item_func::EQ_FUNC) || > - (cond->functype() == Item_func::MULT_EQUAL_FUNC)) && > - (real->type() == Item::FIELD_ITEM) && > - ((Item_field*)real)->field->maybe_null()) > + if (( > + (cond->functype() == Item_func::EQ_FUNC) || > + (cond->functype() == Item_func::MULT_EQUAL_FUNC) > + ) && > + ( > + ( > + (real->type() == Item::FIELD_ITEM) && > + ((Item_field*)real)->field->maybe_null() > + ) || > + (field->maybe_null()) > + )) > (*key_fields)->null_rejecting= true; > else > (*key_fields)->null_rejecting= false; > @@ -9982,8 +9999,12 @@ static bool create_ref_for_key(JOIN *join, JOIN_TAB *j, > uint maybe_null= MY_TEST(keyinfo->key_part[i].null_bit); > j->ref.items[i]=keyuse->val; // Save for cond removal > j->ref.cond_guards[i]= keyuse->cond_guard; > - if (keyuse->null_rejecting) > + Item *real= (keyuse->val)->real_item(); > + if (keyuse->null_rejecting && > + (real->type() == Item::FIELD_ITEM) && > + ((Item_field*)real)->field->maybe_null()) This code looks as if if keyuse->val->maybe_null() != keyuse->val->real_item()->maybe_null() do you have any specific case in mind or this is just to match the code in add_key_field? > j->ref.null_rejecting|= (key_part_map)1 << i; > + > keyuse_uses_no_tables= keyuse_uses_no_tables && !keyuse->used_tables; > /* > We don't want to compute heavy expressions in EXPLAIN, an example would BR Sergei -- Sergei Petrunia, Software Developer MariaDB Corporation | Skype: sergefp | Blog: http://s.petrunia.net/blog

2 1

Re: [Maria-developers] [Commits] 53d0e921794: MDEV-11094: Blackhole table updates on slave fail when row annotation is enabled
by andrei.elkin＠pp.inet.fi 22 May '19

22 May '19

Sujatha, salute! Thanks for a detailed description! I would add up to it a minor piece > revision-id: 53d0e9217943719b806ef9fa1cac0a699df4839c (mariadb-10.1.39-31-g53d0e921794) > parent(s): 47637a3dd13d19e897a7cbfd1499f1bf3b2fdb2a > author: Sujatha > committer: Sujatha > timestamp: 2019-05-17 13:11:49 +0530 > message: > > MDEV-11094: Blackhole table updates on slave fail when row annotation is enabled > > Problem: > ======= > rpl_blackhole.test fails when executed with following options > mysqld=--binlog_annotate_row_events=1, mysqld=--replicate_annotate_row_events=1 > > Test output: > ------------ > worker[1] Using MTR_BUILD_THREAD 300, with reserved ports 16000..16019 > rpl.rpl_blackhole_bug 'mix' [ pass ] 791 > rpl.rpl_blackhole_bug 'row' [ fail ] > Replicate_Wild_Ignore_Table > Last_Errno 1032 > Last_Error Could not execute Update_rows_v1 event on table test.t1; Can't find > record in 't1', Error_code: 1032; handler error HA_ERR_END_OF_FILE; the event's > master log master-bin.000001, end_log_pos 1510 > > Analysis: > ========= > Enabling "replicate_annotate_row_events" on slave, Tells the slave to write > annotate rows events received from the master to its own binary log. The > received annotate events are applied after the Gtid event as shown below. > thd->query() will be set to the actual query received from the master, through > annotate event. Annotate_rows event should not be deleted after the event is > applied as the thd->query will be used to generate new Annotate_rows event > during applying the subsequent Rows events. [ here ] The Table_map and Rows_log_event that follow do not touch thd->query(). Notice that the being suggested sentence is sufficient to explain the not-NULL without the sentence below (fill free to remove then): > After the last Rows event has been > applied, the saved Annotate_rows event (if any) will be deleted. > > master-bin.000001 | 457 | Gtid | BEGIN GTID 0-1-2 > master-bin.000001 | 495 | Annotate_rows | insert into t values (10) > master-bin.000001 | 539 | Table_map | table_id: 19 (test.t) > master-bin.000001 | 579 | Write_rows_v1 | table_id: 19 flags: STMT_END_F > master-bin.000001 | 613 | Xid | COMMIT /* xid=7 */ > > In balckhole engine all the DML operations are noops as they donot store any > data. They simply return success without doing any operation. But the existing > strictly expects thd->query() to be 'NULL' to identify that row based > replication is in use. This assumption will fail when row annotations are > enabled as the query is not 'NULL'. Hence various row based operations like > 'update', 'delete', 'index lookup' will fail when row annotations are enabled. > > Fix: > === > Extend the row based replication check to include row annotations as well. > i.e Either the thd->query() is NULL or thd->query() points to query and row > annotations are in use. This works, but the check does not really refers to the Annotate. So in principle thd->query() may turn in not-NULL of different reasons. Besides the check is multiplied over few places (again hopefully covering all). We can do it simpler actually: Rows_log_event::do_apply_event() { ... do { /* in_use can have been set to NULL in close_tables_for_reopen */ THD* old_thd= table->in_use; if (!table->in_use) table->in_use= thd; --> add a check whether Annotate has been done and when so store/restore --> thd->query() like `old_thd` above/below, and pass it as NULL (thd->reset_query()) to the following: error= do_exec_row(rgi); if (error) DBUG_PRINT("info", ("error: %s", HA_ERR(error))); DBUG_ASSERT(error != HA_ERR_RECORD_DELETED); table->in_use = old_thd; I also suggest to check out mysqlbinlog run. There seems to be no test for that though, so one needs to be written. The goal would be to prove a created binlog output is as expected (e.g to include Annotate). Cheers, Andrei > > --- > mysql-test/suite/rpl/t/rpl_blackhole-master.opt | 1 + > mysql-test/suite/rpl/t/rpl_blackhole-slave.opt | 1 + > storage/blackhole/ha_blackhole.cc | 28 +++++++++++++++++++------ > 3 files changed, 24 insertions(+), 6 deletions(-) > > diff --git a/mysql-test/suite/rpl/t/rpl_blackhole-master.opt b/mysql-test/suite/rpl/t/rpl_blackhole-master.opt > new file mode 100644 > index 00000000000..1ad0b884c60 > --- /dev/null > +++ b/mysql-test/suite/rpl/t/rpl_blackhole-master.opt > @@ -0,0 +1 @@ > +--binlog_annotate_row_events > diff --git a/mysql-test/suite/rpl/t/rpl_blackhole-slave.opt b/mysql-test/suite/rpl/t/rpl_blackhole-slave.opt > new file mode 100644 > index 00000000000..7ac6a84faa7 > --- /dev/null > +++ b/mysql-test/suite/rpl/t/rpl_blackhole-slave.opt > @@ -0,0 +1 @@ > +--binlog_annotate_row_events --replicate_annotate_row_events > diff --git a/storage/blackhole/ha_blackhole.cc b/storage/blackhole/ha_blackhole.cc > index 01aaa9ea15f..43bcdc541a1 100644 > --- a/storage/blackhole/ha_blackhole.cc > +++ b/storage/blackhole/ha_blackhole.cc > @@ -25,6 +25,16 @@ > #include "ha_blackhole.h" > #include "sql_class.h" // THD, SYSTEM_THREAD_SLAVE_SQL > > +static bool is_row_based_replication(THD *thd) > +{ > + /* > + A row event which has its thd->query() == NULL or a row event which has > + replicate_annotate_row_events enabled. In the later case the thd->query() > + will be pointing to the query, received through replicated annotate event > + from master. > + */ > + return ((thd->query() == NULL) || thd->variables.binlog_annotate_row_events); > +} > /* Static declarations for handlerton */ > > static handler *blackhole_create_handler(handlerton *hton, > @@ -109,7 +119,8 @@ int ha_blackhole::update_row(const uchar *old_data, uchar *new_data) > { > DBUG_ENTER("ha_blackhole::update_row"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > DBUG_RETURN(0); > DBUG_RETURN(HA_ERR_WRONG_COMMAND); > } > @@ -118,7 +129,8 @@ int ha_blackhole::delete_row(const uchar *buf) > { > DBUG_ENTER("ha_blackhole::delete_row"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > DBUG_RETURN(0); > DBUG_RETURN(HA_ERR_WRONG_COMMAND); > } > @@ -135,7 +147,8 @@ int ha_blackhole::rnd_next(uchar *buf) > int rc; > DBUG_ENTER("ha_blackhole::rnd_next"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > rc= 0; > else > rc= HA_ERR_END_OF_FILE; > @@ -220,7 +233,8 @@ int ha_blackhole::index_read_map(uchar * buf, const uchar * key, > int rc; > DBUG_ENTER("ha_blackhole::index_read"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > rc= 0; > else > rc= HA_ERR_END_OF_FILE; > @@ -235,7 +249,8 @@ int ha_blackhole::index_read_idx_map(uchar * buf, uint idx, const uchar * key, > int rc; > DBUG_ENTER("ha_blackhole::index_read_idx"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > rc= 0; > else > rc= HA_ERR_END_OF_FILE; > @@ -249,7 +264,8 @@ int ha_blackhole::index_read_last_map(uchar * buf, const uchar * key, > int rc; > DBUG_ENTER("ha_blackhole::index_read_last"); > THD *thd= ha_thd(); > - if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL) > + if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && > + is_row_based_replication(thd)) > rc= 0; > else > rc= HA_ERR_END_OF_FILE; > _______________________________________________ > commits mailing list > commits(a)mariadb.org > https://lists.askmonty.org/cgi-bin/mailman/listinfo/commits

1 0

Re: [Maria-developers] 9e176e81b72: MDEV-18531 : Use WolfSSL instead of YaSSL as "bundled" SSL/encryption library
by Sergei Golubchik 21 May '19

21 May '19

Hi, Vladislav! It's good to see how small the patch is, and that wolfssl is more OpenSSL compatible than YaSSL. Few comments below. On May 19, Vladislav Vaintroub wrote: > revision-id: 9e176e81b72 (mariadb-10.4.4-61-g9e176e81b72) > parent(s): ea679c88c32 > author: Vladislav Vaintroub <wlad(a)mariadb.com> > committer: Vladislav Vaintroub <wlad(a)mariadb.com> > timestamp: 2019-05-01 11:28:56 +0100 > message: > > MDEV-18531 : Use WolfSSL instead of YaSSL as "bundled" SSL/encryption library > > - Add new submodule for WolfSSL > - Build and use wolfssl and wolfcrypt instead of yassl/taocrypt > - Use HAVE_WOLFSSL instead of HAVE_YASSL > - Increase MY_AES_CTX_SIZE, to avoid compile time asserts in my_crypt.cc > (sizeof(EVP_CIPHER_CTX) is larger on WolfSSL) > > diff --git a/cmake/ssl.cmake b/cmake/ssl.cmake > index aa42333a5c8..79a531ec323 100644 > --- a/cmake/ssl.cmake > +++ b/cmake/ssl.cmake > @@ -48,29 +48,19 @@ MACRO (CHANGE_SSL_SETTINGS string) > ENDMACRO() > > MACRO (MYSQL_USE_BUNDLED_SSL) > - SET(INC_DIRS > - ${CMAKE_SOURCE_DIR}/extra/yassl/include > - ${CMAKE_SOURCE_DIR}/extra/yassl/taocrypt/include > + SET(INC_DIRS > + ${CMAKE_SOURCE_DIR}/extra/wolfssl/wolfssl > + ${CMAKE_SOURCE_DIR}/extra/wolfssl/wolfssl/wolfssl > + #${CMAKE_SOURCE_DIR}/extra/wolfssl/taocrypt/include don't you want to remove these (and many below) commented lines? > ) > - SET(SSL_LIBRARIES yassl taocrypt) > + SET(SSL_LIBRARIES wolfssl wolfcrypt) > SET(SSL_INCLUDE_DIRS ${INC_DIRS}) > - SET(SSL_INTERNAL_INCLUDE_DIRS ${CMAKE_SOURCE_DIR}/extra/yassl/taocrypt/mySTL) > + SET(SSL_DEFINES "-DHAVE_OPENSSL -DHAVE_WOLFSSL -DOPENSSL_ALL -DWOLFSSL_MYSQL_COMPATIBLE -DWC_NO_HARDEN") > - SET(SSL_DEFINES "-DHAVE_YASSL -DYASSL_PREFIX -DHAVE_OPENSSL -DMULTI_THREADED") > - SET(HAVE_ERR_remove_thread_state OFF CACHE INTERNAL "yassl doesn't have ERR_remove_thread_state") > - SET(HAVE_EncryptAes128Ctr OFF CACHE INTERNAL "yassl doesn't support AES-CTR") > - SET(HAVE_EncryptAes128Gcm OFF CACHE INTERNAL "yassl doesn't support AES-GCM") > + SET(HAVE_ERR_remove_thread_state ON CACHE INTERNAL "wolfssl doesn't have ERR_remove_thread_state") > + SET(HAVE_EncryptAes128Ctr ON CACHE INTERNAL "wolfssl does support AES-CTR") > + SET(HAVE_EncryptAes128Gcm OFF CACHE INTERNAL "wolfssl does not support AES-GCM") > CHANGE_SSL_SETTINGS("bundled") > - ADD_SUBDIRECTORY(extra/yassl) > - ADD_SUBDIRECTORY(extra/yassl/taocrypt) > - GET_TARGET_PROPERTY(src yassl SOURCES) > - FOREACH(file ${src}) > - SET(SSL_SOURCES ${SSL_SOURCES} ${CMAKE_SOURCE_DIR}/extra/yassl/${file}) > - ENDFOREACH() > - GET_TARGET_PROPERTY(src taocrypt SOURCES) > - FOREACH(file ${src}) > - SET(SSL_SOURCES ${SSL_SOURCES} > - ${CMAKE_SOURCE_DIR}/extra/yassl/taocrypt/${file}) > - ENDFOREACH() > + ADD_SUBDIRECTORY(extra/wolfssl) > MESSAGE_ONCE(SSL_LIBRARIES "SSL_LIBRARIES = ${SSL_LIBRARIES}") > ENDMACRO() > > diff --git a/extra/wolfssl/CMakeLists.txt b/extra/wolfssl/CMakeLists.txt > new file mode 100644 > index 00000000000..c1165ad6c72 > --- /dev/null > +++ b/extra/wolfssl/CMakeLists.txt > @@ -0,0 +1,119 @@ > +# CMakeLists.txt > +# > +# Copyright (C) 2006-2015 wolfSSL Inc. > +# > +# This file is part of wolfSSL. (formerly known as CyaSSL) > +# > +# wolfSSL is free software; you can redistribute it and/or modify > +# it under the terms of the GNU General Public License as published by > +# the Free Software Foundation; either version 2 of the License, or > +# (at your option) any later version. > +# > +# wolfSSL is distributed in the hope that it will be useful, > +# but WITHOUT ANY WARRANTY; without even the implied warranty of > +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > +# GNU General Public License for more details. > +# > +# You should have received a copy of the GNU General Public License > +# along with this program; if not, write to the Free Software > +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA > + > +SET(WOLFSSL_SRCDIR ${CMAKE_CURRENT_SOURCE_DIR}/wolfssl/src) > +ADD_DEFINITIONS(${SSL_DEFINES}) > +ADD_DEFINITIONS( > + -DWOLFSSL_MYSQL_COMPATIBLE > + -DHAVE_ECC > + -DECC_TIMING_RESISTANT > + -DBUILDING_WOLFSSL > + -DHAVE_HASHDRBG > + -DWOLFSSL_AES_DIRECT > + -DWOLFSSL_SHA384 > + -DWOLFSSL_SHA512 > + -DWOLFSSL_SHA224 > + -DSESSION_CERT > + -DKEEP_OUR_CERT > + -DWOLFSSL_STATIC_RSA > + -DWC_RSA_BLINDING > + -DHAVE_TLS_EXTENSIONS > + -DHAVE_AES_ECB > + -DWOLFSSL_AES_COUNTER > + -DNO_WOLFSSL_STUB) > + > +SET(WOLFSSL_SOURCES > + ${WOLFSSL_SRCDIR}/crl.c > + ${WOLFSSL_SRCDIR}/internal.c > + ${WOLFSSL_SRCDIR}/keys.c > + ${WOLFSSL_SRCDIR}/tls.c > + ${WOLFSSL_SRCDIR}/wolfio.c > + ${WOLFSSL_SRCDIR}/ocsp.c > + ${WOLFSSL_SRCDIR}/ssl.c) > +ADD_DEFINITIONS(-DWOLFSSL_LIB) > +INCLUDE_DIRECTORIES(BEFORE ${CMAKE_CURRENT_SOURCE_DIR}/wolfssl) > +IF(MSVC) > + # size_t to long truncation warning > + ADD_DEFINITIONS(-wd4267) > +ENDIF() > + > + > +ADD_CONVENIENCE_LIBRARY(wolfssl ${WOLFSSL_SOURCES}) > + > +# Workaround linker crash with older Ubuntu binutils > +# e.g aborting at ../../bfd/merge.c line 873 in _bfd_merged_section_offset > +IF((CMAKE_SYSTEM_NAME MATCHES "Linux") AND (CMAKE_LINKER STREQUAL "/usr/bin/ld")) > + EXECUTE_PROCESS(COMMAND ${CMAKE_LINKER} -v OUTPUT_VARIABLE LINKER_VERSION_STR) > + STRING(REGEX MATCH "[0-9]+\\.[0-9]+" LINKER_VERSION > + "${LINKER_VERSION_STR}") > + IF(LINKER_VERSION AND (LINKER_VERSION VERSION_LESS 2.25)) > + STRING(REPLACE "-g " "-g1 " CMAKE_C_FLAGS_RELWITHDEBINFO > + ${CMAKE_C_FLAGS_RELWITHDEBINFO}) > + STRING(REPLACE "-g " "-g1 " CMAKE_C_FLAGS_DEBUG > + ${CMAKE_C_FLAGS_DEBUG}) > + STRING(REPLACE "-ggdb3 " " " CMAKE_C_FLAGS_RELWITHDEBINFO > + ${CMAKE_C_FLAGS_RELWITHDEBINFO}) > + STRING(REPLACE "-ggdb3 " " " CMAKE_C_FLAGS_DEBUG > + ${CMAKE_C_FLAGS_DEBUG}) > + ENDIF() > +ENDIF() I would've just disabled -g\w+ unconditionally, for a simpler CMakeLists.txt We aren't going to debug wolfssl anyway (and if I'd need to debug it, for some weird reason, I know how to enable debugging temporarily) > + > + > +SET(WOLFCRYPT_SRCDIR ${CMAKE_CURRENT_SOURCE_DIR}/wolfssl/wolfcrypt/src) > +SET(WOLFCRYPT_SOURCES > +${WOLFCRYPT_SRCDIR}/aes.c > +${WOLFCRYPT_SRCDIR}/arc4.c > +${WOLFCRYPT_SRCDIR}/asn.c > +#${WOLFCRYPT_SRCDIR}/blake2b.c > +#${WOLFCRYPT_SRCDIR}/camellia.c > +#${WOLFCRYPT_SRCDIR}/chacha.c > +${WOLFCRYPT_SRCDIR}/coding.c > +#${WOLFCRYPT_SRCDIR}/compress.c > +${WOLFCRYPT_SRCDIR}/des3.c > +${WOLFCRYPT_SRCDIR}/dh.c > +${WOLFCRYPT_SRCDIR}/dsa.c > +${WOLFCRYPT_SRCDIR}/ecc.c > +${WOLFCRYPT_SRCDIR}/error.c > +#${WOLFCRYPT_SRCDIR}/hc128.c > +${WOLFCRYPT_SRCDIR}/hmac.c > +${WOLFCRYPT_SRCDIR}/integer.c > +${WOLFCRYPT_SRCDIR}/logging.c > +#${WOLFCRYPT_SRCDIR}/md2.c > +${WOLFCRYPT_SRCDIR}/md4.c > +${WOLFCRYPT_SRCDIR}/md5.c > +${WOLFCRYPT_SRCDIR}/memory.c > +#${WOLFCRYPT_SRCDIR}/pkcs7.c > +${WOLFCRYPT_SRCDIR}/pkcs12.c > +#${WOLFCRYPT_SRCDIR}/poly1305.c > +${WOLFCRYPT_SRCDIR}/pwdbased.c > +${WOLFCRYPT_SRCDIR}/rabbit.c > +${WOLFCRYPT_SRCDIR}/random.c > +#${WOLFCRYPT_SRCDIR}/ripemd.c > +${WOLFCRYPT_SRCDIR}/rsa.c > +${WOLFCRYPT_SRCDIR}/sha.c > +${WOLFCRYPT_SRCDIR}/sha256.c > +${WOLFCRYPT_SRCDIR}/sha512.c > +#${WOLFCRYPT_SRCDIR}/tfm.c > +${WOLFCRYPT_SRCDIR}/wc_port.c > +${WOLFCRYPT_SRCDIR}/wc_encrypt.c > +${WOLFCRYPT_SRCDIR}/hash.c > +${WOLFCRYPT_SRCDIR}/wolfmath.c) > +ADD_CONVENIENCE_LIBRARY(wolfcrypt ${WOLFCRYPT_SOURCES}) > + > diff --git a/extra/wolfssl/wolfssl b/extra/wolfssl/wolfssl > new file mode 160000 > index 00000000000..dc313ccf6ee > --- /dev/null > +++ b/extra/wolfssl/wolfssl > @@ -0,0 +1 @@ > +Subproject commit dc313ccf6ee0e99fb5a13793b82e412f396e11c6 I think we should only use wolfssl (any external project, actually) only at release points, not at intermediate commits. 4.0.0-stable should be ok, I guess. And, generaly, pefer to use system globally installed library, if available. Although in case of wolfssl (and libmarias3) I would not bother. > diff --git a/include/ssl_compat.h b/include/ssl_compat.h > index c94b9671d5f..105405efff2 100644 > --- a/include/ssl_compat.h > +++ b/include/ssl_compat.h > @@ -17,9 +17,9 @@ > #include <openssl/opensslv.h> > > /* OpenSSL version specific definitions */ > -#if !defined(HAVE_YASSL) && defined(OPENSSL_VERSION_NUMBER) > +#if defined(OPENSSL_VERSION_NUMBER) > > -#if OPENSSL_VERSION_NUMBER >= 0x10002000L && !defined(LIBRESSL_VERSION_NUMBER) > +#if (OPENSSL_VERSION_NUMBER >= 0x10002000L && !defined(LIBRESSL_VERSION_NUMBER)) || defined (HAVE_WOLFSSL) What's OPENSSL_VERSION_NUMBER in wolfssl? > #define HAVE_X509_check_host 1 May be move it to ssl.cmake? Where other such defines are. > #endif > > diff --git a/include/sslopt-case.h b/include/sslopt-case.h > index 4a8c65948cb..b129a97cc76 100644 > --- a/include/sslopt-case.h > +++ b/include/sslopt-case.h > @@ -29,8 +29,8 @@ > One can disable SSL later by using --skip-ssl or --ssl=0 > */ > opt_use_ssl= 1; > - /* crl has no effect in yaSSL */ > -#ifdef HAVE_YASSL > +#ifdef HAVE_WOLFSSL > + /* CRL does not work with WolfSSL */ Still? > opt_ssl_crl= NULL; > opt_ssl_crlpath= NULL; > #endif > diff --git a/mysys_ssl/my_crypt.cc b/mysys_ssl/my_crypt.cc > index 2d6f5188034..1ce0c6bbc03 100644 > --- a/mysys_ssl/my_crypt.cc > +++ b/mysys_ssl/my_crypt.cc > @@ -18,14 +18,10 @@ > #include <my_global.h> > #include <string.h> > > -#ifdef HAVE_YASSL > -#include "yassl.cc" delete yassl.cc file, perhaps? > -#else > #include <openssl/evp.h> > #include <openssl/aes.h> > #include <openssl/err.h> > #include <openssl/rand.h> > -#endif > > #include <my_crypt.h> > #include <ssl_compat.h> > @@ -70,8 +66,24 @@ class MyCTX > } > virtual int finish(uchar *dst, uint *dlen) > { > +#ifdef HAVE_WOLFSSL > + /* > + Bug in WolfSSL - sometimes EVP_CipherFinal_ex > + returns success without setting destination length > + when it should return error. > + We catch it by presetting invalid value for length, > + and checking if it has changed after the call. > + > + See https://github.com/wolfSSL/wolfssl/issues/2092 > + */ > + *dlen= UINT_MAX; > +#endif I suppose you can remove it. This is fixed as of 4.0.0-stable tag. > if (!EVP_CipherFinal_ex(ctx, dst, (int*)dlen)) > return MY_AES_BAD_DATA; > +#ifdef HAVE_WOLFSSL > + if (*dlen == UINT_MAX) > + return MY_AES_BAD_DATA; > +#endif > return MY_AES_OK; > } > }; > diff --git a/plugin/file_key_management/parser.cc b/plugin/file_key_management/parser.cc > index 13a9dfa0cb6..27277f62994 100644 > --- a/plugin/file_key_management/parser.cc > +++ b/plugin/file_key_management/parser.cc > @@ -103,7 +103,6 @@ openssl enc -aes-256-cbc -md sha1 -k "secret" -in keys.txt -out keys.enc > EVP_BytesToKey(EVP_aes_256_cbc(), EVP_sha1(), salt, > secret, strlen(secret), 1, key, iv); > > - but alas! we want to support yassl too does wolfssl have an equivalent of EVP_BytesToKey? if not, the comment still holds. > */ > > void Parser::bytes_to_key(const unsigned char *salt, const char *input, > diff --git a/sql/mysqld.cc b/sql/mysqld.cc > index bfa03aa57c1..8c3a59c55d1 100644 > --- a/sql/mysqld.cc > +++ b/sql/mysqld.cc > @@ -7317,13 +7315,13 @@ static int show_ssl_get_verify_mode(THD *thd, SHOW_VAR *var, char *buff, > { > var->type= SHOW_LONG; > var->value= buff; > -#ifndef HAVE_YASSL > +#ifndef HAVE_WOLFSSL > if( thd->net.vio && thd->net.vio->ssl_arg ) > *((long *)buff)= (long)SSL_get_verify_mode((SSL*)thd->net.vio->ssl_arg); no SSL_get_verify_mode or an analog in wolfssl? I'm asking, as I see it has gone a long way towards OpenSSL compatibility > else > *((long *)buff)= 0; > #else > - *((long *)buff) = 0; > + *((long *)buff)= 0; > #endif > return 0; > } Regards, Sergei Chief Architect MariaDB and security(a)mariadb.org

2 2

Re: [Maria-developers] ddec45aa50e: MDEV-16932: ASAN heap-use-after-free in my_charlen_utf8 / my_well_formed_char_length_utf8 on 2nd execution of SP with ALTER trying to add bad CHECK
by Sergei Golubchik 20 May '19

20 May '19

Hi, Oleksandr! On May 20, Oleksandr Byelkin wrote: > Alter table will trigger recompilation of the SP (as I remember all SPs) I've run this test, it complains about duplicate constraint name. > > What about this: > > > > CREATE TABLE t1 (a INT); > > CREATE PROCEDURE sp() ALTER TABLE t1 ADD CONSTRAINT CHECK (b > 0); > > --error ER_BAD_FIELD_ERROR > > CALL sp; > > alter table t1 add column b int, add constraint check (b < 10); > > CALL sp; > > > > ? > > second CALL will not regenerate the name of the constraint. > > Regards, Sergei Chief Architect MariaDB and security(a)mariadb.org

1 0

Re: [Maria-developers] ddec45aa50e: MDEV-16932: ASAN heap-use-after-free in my_charlen_utf8 / my_well_formed_char_length_utf8 on 2nd execution of SP with ALTER trying to add bad CHECK
by Sergei Golubchik 20 May '19

20 May '19

Hi, Oleksandr! On May 20, Oleksandr Byelkin wrote: > On Mon, May 20, 2019 at 3:11 PM Sergei Golubchik <serg(a)mariadb.org> wrote: > > On May 20, Oleksandr Byelkin wrote: > > > revision-id: ddec45aa50e (mariadb-10.2.24-11-gddec45aa50e) > > > parent(s): 50999738eae > > > author: Oleksandr Byelkin <sanja(a)mariadb.com> > > > committer: Oleksandr Byelkin <sanja(a)mariadb.com> > > > timestamp: 2019-05-14 14:01:15 +0200 > > > message: > > > > > > MDEV-16932: ASAN heap-use-after-free in my_charlen_utf8 / > > > my_well_formed_char_length_utf8 on 2nd execution of SP with ALTER > > > trying to add bad CHECK > > > > > > In case of error the SP can be executed without re-comilation and so > > > will reuse constructed constaint name, so the name should be allocated > > > in the statement memory. > > > > Is that right? You're saying that the "unique constraint name" will be > > generated once and reused? > > > > But on the second SP invocation is might no longer be unique. I'd think > > that `ALTER TABLE t1 ADD CONSTRAINT CHECK (x > 0)` should add a new > > constraint, not "add a new contraint with the name that used to be > > unique when the SP was invoked for the first time". > > With the second call we have 2 possibility: > > 1) first execution failed and so we can reuse the name > 2) first execution succeed and we will re-compile SP or re-prepare PS and > so will generate new name (that is why we mostly had no problems) What about this: CREATE TABLE t1 (a INT); CREATE PROCEDURE sp() ALTER TABLE t1 ADD CONSTRAINT CHECK (b > 0); --error ER_BAD_FIELD_ERROR CALL sp; alter table t1 add column b int, add constraint check (b < 10); CALL sp; ? second CALL will not regenerate the name of the constraint. Regards, Sergei Chief Architect MariaDB and security(a)mariadb.org

1 0

Re: [Maria-developers] ddec45aa50e: MDEV-16932: ASAN heap-use-after-free in my_charlen_utf8 / my_well_formed_char_length_utf8 on 2nd execution of SP with ALTER trying to add bad CHECK
by Sergei Golubchik 20 May '19

20 May '19

Hi, Oleksandr! On May 20, Oleksandr Byelkin wrote: > revision-id: ddec45aa50e (mariadb-10.2.24-11-gddec45aa50e) > parent(s): 50999738eae > author: Oleksandr Byelkin <sanja(a)mariadb.com> > committer: Oleksandr Byelkin <sanja(a)mariadb.com> > timestamp: 2019-05-14 14:01:15 +0200 > message: > > MDEV-16932: ASAN heap-use-after-free in my_charlen_utf8 / > my_well_formed_char_length_utf8 on 2nd execution of SP with ALTER > trying to add bad CHECK > > In case of error the SP can be executed without re-comilation and so > will reuse constructed constaint name, so the name should be allocated > in the statement memory. Is that right? You're saying that the "unique constraint name" will be generated once and reused? But on the second SP invocation is might no longer be unique. I'd think that `ALTER TABLE t1 ADD CONSTRAINT CHECK (x > 0)` should add a new constraint, not "add a new contraint with the name that used to be unique when the SP was invoked for the first time". > diff --git a/sql/sql_table.cc b/sql/sql_table.cc > index 3df877792cc..ecd5de3a09d 100644 > --- a/sql/sql_table.cc > +++ b/sql/sql_table.cc > @@ -4185,9 +4185,15 @@ mysql_prepare_create_table(THD *thd, HA_CREATE_INFO *create_info, > while ((check= c_it++)) > { > if (!check->name.length) > + { > + Query_arena backup; > + Query_arena *arena= thd->activate_stmt_arena_if_needed(&backup); > make_unique_constraint_name(thd, &check->name, > &alter_info->check_constraint_list, > &nr); > + if (arena) > + thd->restore_active_arena(arena, &backup); > + } > { > /* Check that there's no repeating constraint names. */ > List_iterator_fast<Virtual_column_info> Regards, Sergei Chief Architect MariaDB and security(a)mariadb.org

1 0

Re: [Maria-developers] [Commits] 66349551bf3: MDEV-16214: Incorrect plan taken by the optimizer , uses INDEX instead of ref access with ORDER BY
by Sergey Petrunia 19 May '19

19 May '19

Hi Varun, The patch is mostly fine. Please find some input on the comments / coding style below. Ok to push after it is addressed. On Fri, May 17, 2019 at 01:44:36PM +0530, Varun wrote: > revision-id: 66349551bf3a266fbefaebfe044abd05108723c2 (mariadb-10.3.12-205-g66349551bf3) > parent(s): 3d56adbfac394b2b3ffd22a89fe7c2978ed9a505 > author: Varun Gupta > committer: Varun Gupta > timestamp: 2019-05-17 13:44:05 +0530 > message: > > MDEV-16214: Incorrect plan taken by the optimizer , uses INDEX instead of ref access with ORDER BY > > The issue in this case is that we take in account the estimates from quick keys instead of rec_per_key. > The estimates for quick keys are better than rec_per_key only if we have ref(const), so we need to check > that all keyparts in the ref key are of the type ref(const). > > --- > mysql-test/main/order_by.result | 57 +++++++++++++++++++++++++++++++++++++++++ > mysql-test/main/order_by.test | 37 ++++++++++++++++++++++++++ > sql/sql_select.cc | 42 ++++++++++++++++++++---------- > 3 files changed, 122 insertions(+), 14 deletions(-) ... > diff --git a/sql/sql_select.cc b/sql/sql_select.cc > index f36a68bc7ae..8cdcf3afc8b 100644 > --- a/sql/sql_select.cc > +++ b/sql/sql_select.cc > @@ -9986,31 +9986,35 @@ static bool create_ref_for_key(JOIN *join, JOIN_TAB *j, > j->ref.null_rejecting|= (key_part_map)1 << i; > keyuse_uses_no_tables= keyuse_uses_no_tables && !keyuse->used_tables; > /* > - Todo: we should remove this check for thd->lex->describe on the next > - line. With SHOW EXPLAIN code, EXPLAIN printout code no longer depends > - on it. However, removing the check caused change in lots of query > - plans! Does the optimizer depend on the contents of > - table_ref->key_copy ? If yes, do we produce incorrect EXPLAINs? > + We don't want to compute heavy expressions in EXPLAIN, an example would > + select * from t1 where t1.key=(select thats very heavy); > + > + (select thats very heavy) => is a constant here > + eg: (select avg(order_cost) from orders) => constant but expensive > */ > if (!keyuse->val->used_tables() && !thd->lex->describe) > { // Compare against constant > - store_key_item tmp(thd, > + store_key_item tmp(thd, > keyinfo->key_part[i].field, > key_buff + maybe_null, > maybe_null ? key_buff : 0, > keyinfo->key_part[i].length, > keyuse->val, > FALSE); > - if (unlikely(thd->is_fatal_error)) > - DBUG_RETURN(TRUE); > - tmp.copy(); > + if (unlikely(thd->is_fatal_error)) > + DBUG_RETURN(TRUE); > + tmp.copy(); > j->ref.const_ref_part_map |= key_part_map(1) << i ; > } > else > - *ref_key++= get_store_key(thd, > - keyuse,join->const_table_map, > - &keyinfo->key_part[i], > - key_buff, maybe_null); > + { > + *ref_key++= get_store_key(thd, > + keyuse,join->const_table_map, > + &keyinfo->key_part[i], > + key_buff, maybe_null); > + if (!keyuse->val->used_tables()) > + j->ref.const_ref_part_map |= key_part_map(1) << i ; > + } > /* > Remember if we are going to use REF_OR_NULL > But only if field _really_ can be null i.e. we force JT_REF > @@ -25256,6 +25260,8 @@ bool JOIN_TAB::save_explain_data(Explain_table_access *eta, > { > if (!(eta->ref_list.append_str(thd->mem_root, "const"))) > return 1; > + if (thd->lex->describe) > + key_ref++; This is very cryptic. Please provide an explanation, something like: create_ref_for_key() handles keypart=const equalities as follows: - non-EXPLAIN execution will copy the "const" to lookup tuple immediately and will not add an element to ref.key_copy - EXPLAIN will put an element into ref.key_copy. Since we've just printed "const" for it, we should skip it here. > } > else > { > @@ -26921,7 +26927,15 @@ test_if_cheaper_ordering(const JOIN_TAB *tab, ORDER *order, TABLE *table, > */ > if (ref_key >= 0 && ref_key != MAX_KEY && tab->type == JT_REF) > { > - if (table->quick_keys.is_set(ref_key)) > + /* > + For all the parts of the ref key we check if all of them belong > + to the type ref(const). This is done because if all parts of the ref > + key are of type ref(const), then we are sure that the estimates > + provides by quick keys is better than that provide by rec_per_key. The above is hard to read and has typos. Here's a shorter variant: If ref access uses keypart=const for all its key parts, and quick select uses the same # of key parts, then they are equivalent. Reuse #rows estimate from quick select as it is more precise. > + */ > + if (tab->ref.const_ref_part_map == make_prev_keypart_map(tab->ref.key_parts) && > + table->quick_keys.is_set(ref_key) && > + table->quick_key_parts[ref_key] == tab->ref.key_parts) Please fix indetation; One of the lines is too long. > refkey_rows_estimate= table->quick_rows[ref_key]; > else > { BR Sergei -- Sergei Petrunia, Software Developer MariaDB Corporation | Skype: sergefp | Blog: http://s.petrunia.net/blog

1 0