mariadb/storage/myisammrg/ha_myisammrg.h
Monty b66cdbd1ea Changing all cost calculation to be given in milliseconds
This makes it easier to compare different costs and also allows
the optimizer to optimizer different storage engines more reliably.

- Added tests/check_costs.pl, a tool to verify optimizer cost calculations.
  - Most engine costs has been found with this program. All steps to
    calculate the new costs are documented in Docs/optimizer_costs.txt

- User optimizer_cost variables are given in microseconds (as individual
  costs can be very small). Internally they are stored in ms.
- Changed DISK_READ_COST (was DISK_SEEK_BASE_COST) from a hard disk cost
  (9 ms) to common SSD cost (400MB/sec).
- Removed cost calculations for hard disks (rotation etc).
- Changed the following handler functions to return IO_AND_CPU_COST.
  This makes it easy to apply different cost modifiers in ha_..time()
  functions for io and cpu costs.
  - scan_time()
  - rnd_pos_time() & rnd_pos_call_time()
  - keyread_time()
- Enhanched keyread_time() to calculate the full cost of reading of a set
  of keys with a given number of ranges and optional number of blocks that
  need to be accessed.
- Removed read_time() as keyread_time() + rnd_pos_time() can do the same
  thing and more.
- Tuned cost for: heap, myisam, Aria, InnoDB, archive and MyRocks.
  Used heap table costs for json_table. The rest are using default engine
  costs.
- Added the following new optimizer variables:
  - optimizer_disk_read_ratio
  - optimizer_disk_read_cost
  - optimizer_key_lookup_cost
  - optimizer_row_lookup_cost
  - optimizer_row_next_find_cost
  - optimizer_scan_cost
- Moved all engine specific cost to OPTIMIZER_COSTS structure.
- Changed costs to use 'records_out' instead of 'records_read' when
  recalculating costs.
- Split optimizer_costs.h to optimizer_costs.h and optimizer_defaults.h.
  This allows one to change costs without having to compile a lot of
  files.
- Updated costs for filter lookup.
- Use a better cost estimate in best_extension_by_limited_search()
  for the sorting cost.
- Fixed previous issues with 'filtered' explain column as we are now
  using 'records_out' (min rows seen for table) to calculate filtering.
  This greatly simplifies the filtering code in
  JOIN_TAB::save_explain_data().

This change caused a lot of queries to be optimized differently than
before, which exposed different issues in the optimizer that needs to
be fixed.  These fixes are in the following commits.  To not have to
change the same test case over and over again, the changes in the test
cases are done in a single commit after all the critical change sets
are done.

InnoDB changes:
- Updated InnoDB to not divide big range cost with 2.
- Added cost for InnoDB (innobase_update_optimizer_costs()).
- Don't mark clustered primary key with HA_KEYREAD_ONLY. This will
  prevent that the optimizer is trying to use index-only scans on
  the clustered key.
- Disabled ha_innobase::scan_time() and ha_innobase::read_time() and
  ha_innobase::rnd_pos_time() as the default engine cost functions now
  works good for InnoDB.

Other things:
- Added  --show-query-costs (\Q) option to mysql.cc to show the query
  cost after each query (good when working with query costs).
- Extended my_getopt with GET_ADJUSTED_VALUE which allows one to adjust
  the value that user is given. This is used to change cost from
  microseconds (user input) to milliseconds (what the server is
  internally using).
- Added include/my_tracker.h  ; Useful include file to quickly test
  costs of a function.
- Use handler::set_table() in all places instead of 'table= arg'.
- Added SHOW_OPTIMIZER_COSTS to sys variables. These are input and
  shown in microseconds for the user but stored as milliseconds.
  This is to make the numbers easier to read for the user (less
  pre-zeros).  Implemented in 'Sys_var_optimizer_cost' class.
- In test_quick_select() do not use index scans if 'no_keyread' is set
  for the table. This is what we do in other places of the server.
- Added THD parameter to Unique::get_use_cost() and
  check_index_intersect_extension() and similar functions to be able
  to provide costs to called functions.
- Changed 'records' to 'rows' in optimizer_trace.
- Write more information to optimizer_trace.
- Added INDEX_BLOCK_FILL_FACTOR_MUL (4) and INDEX_BLOCK_FILL_FACTOR_DIV (3)
  to calculate usage space of keys in b-trees. (Before we used numeric
  constants).
- Removed code that assumed that b-trees has similar costs as binary
  trees. Replaced with engine calls that returns the cost.
- Added Bitmap::find_first_bit()
- Added timings to join_cache for ANALYZE table (patch by Sergei Petrunia).
- Added records_init and records_after_filter to POSITION to remember
  more of what best_access_patch() calculates.
- table_after_join_selectivity() changed to recalculate 'records_out'
  based on the new fields from best_access_patch()

Bug fixes:
- Some queries did not update last_query_cost (was 0). Fixed by moving
  setting thd->...last_query_cost in JOIN::optimize().
- Write '0' as number of rows for const tables with a matching row.

Some internals:
- Engine cost are stored in OPTIMIZER_COSTS structure.  When a
  handlerton is created, we also created a new cost variable for the
  handlerton. We also create a new variable if the user changes a
  optimizer cost for a not yet loaded handlerton either with command
  line arguments or with SET
  @@global.engine.optimizer_cost_variable=xx.
- There are 3 global OPTIMIZER_COSTS variables:
  default_optimizer_costs   The default costs + changes from the
                            command line without an engine specifier.
  heap_optimizer_costs      Heap table costs, used for temporary tables
  tmp_table_optimizer_costs The cost for the default on disk internal
                            temporary table (MyISAM or Aria)
- The engine cost for a table is stored in table_share. To speed up
  accesses the handler has a pointer to this. The cost is copied
  to the table on first access. If one wants to change the cost one
  must first update the global engine cost and then do a FLUSH TABLES.
  This was done to be able to access the costs for an open table
  without any locks.
- When a handlerton is created, the cost are updated the following way:
  See sql/keycaches.cc for details:
  - Use 'default_optimizer_costs' as a base
  - Call hton->update_optimizer_costs() to override with the engines
    default costs.
  - Override the costs that the user has specified for the engine.
  - One handler open, copy the engine cost from handlerton to TABLE_SHARE.
  - Call handler::update_optimizer_costs() to allow the engine to update
    cost for this particular table.
  - There are two costs stored in THD. These are copied to the handler
    when the table is used in a query:
    - optimizer_where_cost
    - optimizer_scan_setup_cost
- Simply code in best_access_path() by storing all cost result in a
  structure. (Idea/Suggestion by Igor)
2023-02-02 23:54:45 +03:00

170 lines
6.4 KiB
C++

/*
Copyright (c) 2000, 2011, Oracle and/or its affiliates
This program 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; version 2 of the License.
This program 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 St, Fifth Floor, Boston, MA 02110-1335 USA */
#ifdef USE_PRAGMA_INTERFACE
#pragma interface /* gcc class implementation */
#endif
/* class for the the myisam merge handler */
#include <myisammrg.h>
/**
Represents one name of a MERGE child.
@todo: Add MYRG_SHARE and store chlidren names in the
share.
*/
class Mrg_child_def: public Sql_alloc
{
/* Remembered MERGE child def version. See top comment in ha_myisammrg.cc */
enum_table_ref_type m_child_table_ref_type;
ulong m_child_def_version;
public:
LEX_STRING db;
LEX_STRING name;
/* Access MERGE child def version. See top comment in ha_myisammrg.cc */
inline enum_table_ref_type get_child_table_ref_type()
{
return m_child_table_ref_type;
}
inline ulong get_child_def_version()
{
return m_child_def_version;
}
inline void set_child_def_version(enum_table_ref_type child_table_ref_type,
ulong version)
{
m_child_table_ref_type= child_table_ref_type;
m_child_def_version= version;
}
Mrg_child_def(char *db_arg, size_t db_len_arg,
char *table_name_arg, size_t table_name_len_arg)
{
db.str= db_arg;
db.length= db_len_arg;
name.str= table_name_arg;
name.length= table_name_len_arg;
m_child_def_version= ~0UL;
m_child_table_ref_type= TABLE_REF_NULL;
}
};
class ha_myisammrg final : public handler
{
MYRG_INFO *file;
my_bool is_cloned; /* This instance has been cloned */
public:
MEM_ROOT children_mem_root; /* mem root for children list */
List<Mrg_child_def> child_def_list;
TABLE_LIST *children_l; /* children list */
TABLE_LIST **children_last_l; /* children list end */
uint test_if_locked; /* flags from ::open() */
ha_myisammrg(handlerton *hton, TABLE_SHARE *table_arg);
~ha_myisammrg();
const char *index_type(uint key_number);
ulonglong table_flags() const
{
return (HA_REC_NOT_IN_SEQ | HA_AUTO_PART_KEY | HA_NO_TRANSACTIONS |
HA_BINLOG_ROW_CAPABLE | HA_BINLOG_STMT_CAPABLE |
HA_NULL_IN_KEY | HA_CAN_INDEX_BLOBS | HA_FILE_BASED |
HA_ANY_INDEX_MAY_BE_UNIQUE | HA_CAN_BIT_FIELD |
HA_HAS_RECORDS | HA_CAN_EXPORT |
HA_NO_COPY_ON_ALTER |
HA_DUPLICATE_POS | HA_CAN_MULTISTEP_MERGE);
}
ulong index_flags(uint inx, uint part, bool all_parts) const
{
return ((table_share->key_info[inx].algorithm == HA_KEY_ALG_FULLTEXT) ?
0 : HA_READ_NEXT | HA_READ_PREV | HA_READ_RANGE |
HA_READ_ORDER | HA_KEYREAD_ONLY);
}
uint max_supported_keys() const { return MI_MAX_KEY; }
uint max_supported_key_length() const { return HA_MAX_KEY_LENGTH; }
uint max_supported_key_part_length() const { return HA_MAX_KEY_LENGTH; }
IO_AND_CPU_COST scan_time() override
{
IO_AND_CPU_COST cost;
cost.io= (ulonglong2double(stats.data_file_length) / IO_SIZE +
file->tables) * avg_io_cost();
cost.cpu= records() * ROW_NEXT_FIND_COST;
return cost;
}
IO_AND_CPU_COST rnd_pos_time(ha_rows rows) override;
IO_AND_CPU_COST keyread_time(uint index, ulong ranges, ha_rows rows,
ulonglong blocks) override;
int open(const char *name, int mode, uint test_if_locked);
int add_children_list(void);
int attach_children(void);
int detach_children(void);
virtual handler *clone(const char *name, MEM_ROOT *mem_root);
int close(void);
int write_row(const uchar * buf);
int update_row(const uchar * old_data, const uchar * new_data);
int delete_row(const uchar * buf);
int index_read_map(uchar *buf, const uchar *key, key_part_map keypart_map,
enum ha_rkey_function find_flag);
int index_read_idx_map(uchar *buf, uint index, const uchar *key,
key_part_map keypart_map,
enum ha_rkey_function find_flag);
int index_read_last_map(uchar *buf, const uchar *key, key_part_map keypart_map);
int index_next(uchar * buf);
int index_prev(uchar * buf);
int index_first(uchar * buf);
int index_last(uchar * buf);
int index_next_same(uchar *buf, const uchar *key, uint keylen);
int rnd_init(bool scan);
int rnd_next(uchar *buf);
int rnd_pos(uchar * buf, uchar *pos);
void position(const uchar *record);
ha_rows records_in_range(uint inx, const key_range *start_key,
const key_range *end_key, page_range *pages);
int delete_all_rows();
int info(uint);
int reset(void);
int extra(enum ha_extra_function operation);
int extra_opt(enum ha_extra_function operation, ulong cache_size);
int external_lock(THD *thd, int lock_type);
uint lock_count(void) const;
int create_mrg(const char *name, HA_CREATE_INFO *create_info);
int create(const char *name, TABLE *form, HA_CREATE_INFO *create_info);
THR_LOCK_DATA **store_lock(THD *thd, THR_LOCK_DATA **to,
enum thr_lock_type lock_type);
void update_create_info(HA_CREATE_INFO *create_info);
void append_create_info(String *packet);
MYRG_INFO *myrg_info() { return file; }
TABLE *table_ptr() { return table; }
enum_alter_inplace_result check_if_supported_inplace_alter(TABLE *,
Alter_inplace_info *);
bool inplace_alter_table(TABLE *altered_table,
Alter_inplace_info *ha_alter_info);
int check(THD* thd, HA_CHECK_OPT* check_opt);
ha_rows records();
virtual uint count_query_cache_dependant_tables(uint8 *tables_type);
virtual my_bool
register_query_cache_dependant_tables(THD *thd,
Query_cache *cache,
Query_cache_block_table **block,
uint *n);
virtual void set_lock_type(enum thr_lock_type lock);
};