database/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-07-29 05:21:33 +03:00
Code Activity

MDEV-371 Unique Index for long columns

Browse Source 
This patch implements engine independent unique hash index.

Usage:- Unique HASH index can be created automatically for blob/varchar/test column whose key
 length > handler->max_key_length()
or it can be explicitly specified.

  Automatic Creation:-
   Create TABLE t1 (a blob unique);
  Explicit Creation:-
   Create TABLE t1 (a int , unique(a) using HASH);

Internal KEY_PART Representations:-
 Long unique key_info will have 2 representations.
 (lets understand this with an example create table t1(a blob, b blob , unique(a, b)); )

 1. User Given Representation:- key_info->key_part array will be similar to what user has defined.
 So in case of example it will have 2 key_parts (a, b)

 2. Storage Engine Representation:- In this case there will be only one key_part and it will point to
 HASH_FIELD. This key_part will be always after user defined key_parts.

 So:- User Given Representation          [a] [b] [hash_key_part]
                  key_info->key_part ----^
  Storage Engine Representation          [a] [b] [hash_key_part]
                  key_info->key_part ------------^

 Table->s->key_info will have User Given Representation, While table->key_info will have Storage Engine
 Representation.Representation can be changed into each other by calling re/setup_keyinfo_hash function.

Working:-

1. So when user specifies HASH_INDEX or key_length is > handler->max_key_length(), In mysql_prepare_create_table
One extra vfield is added (for each long unique key). And key_info->algorithm is set to HA_KEY_ALG_LONG_HASH.

2. In init_from_binary_frm_image values for hash_keypart is set (like fieldnr , field and flags)

3. In parse_vcol_defs, HASH_FIELD->vcol_info is created. Item_func_hash is used with list of Item_fields,
   When Explicit length is given by user then Item_left is used to concatenate Item_field values.

4. In ha_write_row/ha_update_row check_duplicate_long_entry_key is called which will create the hash key from
table->record[0] and then call ha_index_read_map , if we found duplicated hash , we will compare the result
field by field.
This commit is contained in:
Sachin
2019-02-20 02:53:08 +05:30
committed by Sergei Golubchik
parent 5b4d6595d2
commit d00f19e832
46 changed files with 4118 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
mysql-test/main/long_unique_debug.test Normal file
View File

@ -0,0 +1,91 @@
--source include/have_debug.inc
--source include/have_innodb.inc
--echo #In this test case we will check what will happen in the case of hash collision
SET debug_dbug="d,same_long_unique_hash";
create table t1(a blob unique);
FLUSH STATUS;
insert into t1 values('xyz');
insert into t1 values('abc');
insert into t1 values('sachin');
--error ER_DUP_ENTRY
insert into t1 values('sachin');
insert into t1 values('maria');
--error ER_DUP_ENTRY
insert into t1 values('maria');
drop table t1;
SHOW STATUS LIKE 'handler_read_next';
SET debug_dbug="";
create table t1(a blob unique);
FLUSH STATUS;
insert into t1 values('xyz');
insert into t1 values('abc');
insert into t1 values('sachin');
--error ER_DUP_ENTRY
insert into t1 values('sachin');
insert into t1 values('maria');
--error ER_DUP_ENTRY
insert into t1 values('maria');
drop table t1;
SHOW STATUS LIKE 'handler_read_next';
SET debug_dbug="d,same_long_unique_hash";
create table t1(a blob unique, b blob unique);
insert into t1 values('xyz', 11);
insert into t1 values('abc', 22);
insert into t1 values('sachin', 1);
--error ER_DUP_ENTRY
insert into t1 values('sachin', 4);
insert into t1 values('maria', 2);
--error ER_DUP_ENTRY
insert into t1 values('maria', 3);
drop table t1;
create table t1(a blob , b blob , unique(a,b));
insert into t1 values('xyz', 11);
insert into t1 values('abc', 22);
insert into t1 values('sachin', 1);
--error ER_DUP_ENTRY
insert into t1 values('sachin', 1);
insert into t1 values('maria', 2);
--error ER_DUP_ENTRY
insert into t1 values('maria', 2);
drop table t1;
--echo ##Internal State of long unique tables
SET debug_dbug="d,print_long_unique_internal_state";
create table t1 ( a blob unique);
SET debug_dbug="";
drop table t1;
SET debug_dbug="d,print_long_unique_internal_state";
create table t1 ( a blob unique, b blob unique , c blob unique);
SET debug_dbug="";
drop table t1;
SET debug_dbug="d,print_long_unique_internal_state";
create table t1 ( a blob , b blob , c blob , d blob , unique (a,b), unique(c, d));
SET debug_dbug="";
drop table t1;
SET debug_dbug="d,print_long_unique_internal_state";
create table t1(a int primary key, b blob unique , c blob unique not null);
SET debug_dbug="";
drop table t1;
--echo ##Using hash
SET debug_dbug="d,print_long_unique_internal_state";
create table t1(a int ,b int , c int, unique(a, b, c) using hash);
SET debug_dbug="";
drop table t1;
--echo ##Using hash but with memory engine so no long unique column
SET debug_dbug="d,print_long_unique_internal_state";
create table t1(a int ,b int , c int, unique(a, b, c) using hash) engine=memory;
SET debug_dbug="";
drop table t1;