mirror of
https://github.com/MariaDB/server.git
synced 2025-01-16 12:02:42 +01:00
b66cdbd1ea
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)
144 lines
4.9 KiB
C++
144 lines
4.9 KiB
C++
/* Copyright (C) 2007-2013 Arjen G Lentz & Antony T Curtis for Open Query
|
|
Portions of this file copyright (C) 2000-2006 MySQL AB
|
|
|
|
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 Street, Fifth Floor, Boston, MA 02110-1335 USA */
|
|
|
|
/* ======================================================================
|
|
Open Query Graph Computation Engine, based on a concept by Arjen Lentz
|
|
v3 implementation by Antony Curtis, Arjen Lentz, Andrew McDonnell
|
|
For more information, documentation, support, enhancement engineering,
|
|
see http://openquery.com/graph or contact graph@openquery.com
|
|
======================================================================
|
|
*/
|
|
|
|
#ifdef USE_PRAGMA_INTERFACE
|
|
#pragma interface /* gcc class implementation */
|
|
#endif
|
|
|
|
#include "handler.h"
|
|
#include "table.h"
|
|
|
|
typedef struct oqgraph_info_st OQGRAPH_INFO;
|
|
typedef uchar byte;
|
|
|
|
namespace open_query
|
|
{
|
|
struct row;
|
|
class oqgraph;
|
|
class oqgraph_share;
|
|
}
|
|
|
|
/* class for the the Open Query Graph handler */
|
|
|
|
class ha_oqgraph: public handler
|
|
{
|
|
TABLE_SHARE share[1];
|
|
bool have_table_share;
|
|
TABLE edges[1];
|
|
Field *origid;
|
|
Field *destid;
|
|
Field *weight;
|
|
|
|
open_query::oqgraph_share *graph_share;
|
|
open_query::oqgraph *graph;
|
|
|
|
int fill_record(byte*, const open_query::row&);
|
|
|
|
public:
|
|
#if MYSQL_VERSION_ID >= 50100
|
|
ha_oqgraph(handlerton *hton, TABLE_SHARE *table);
|
|
ulonglong table_flags() const;
|
|
#else
|
|
ha_oqgraph(TABLE *table);
|
|
Table_flags table_flags() const;
|
|
#endif
|
|
virtual ~ha_oqgraph();
|
|
const char *index_type(uint inx)
|
|
{
|
|
return "HASH";
|
|
}
|
|
/* Rows also use a fixed-size format */
|
|
enum row_type get_row_type() const { return ROW_TYPE_FIXED; }
|
|
ulong index_flags(uint inx, uint part, bool all_parts) const;
|
|
const char **bas_ext() const;
|
|
uint max_supported_keys() const { return MAX_KEY; }
|
|
uint max_supported_key_part_length() const { return MAX_KEY_LENGTH; }
|
|
IO_AND_CPU_COST scan_time()
|
|
{ return { (double) 1000000000, (double) 1000000000 }; }
|
|
IO_AND_CPU_COST rnd_pos_time(ha_rows rows)
|
|
{ return { (double) rows, (double) rows }; }
|
|
|
|
// Doesn't make sense to change the engine on a virtual table.
|
|
virtual bool can_switch_engines() { return false; }
|
|
|
|
int open(const char *name, int mode, uint test_if_locked);
|
|
int close(void);
|
|
int write_row(const byte * buf);
|
|
int update_row(const uchar * old_data, const uchar * new_data);
|
|
int delete_row(const byte * buf);
|
|
int index_read(byte * buf, const byte * key,
|
|
uint key_len, enum ha_rkey_function find_flag);
|
|
int index_read_idx(byte * buf, uint idx, const byte * key,
|
|
uint key_len, enum ha_rkey_function find_flag);
|
|
int index_next_same(byte * buf, const byte * key, uint key_len);
|
|
int rnd_init(bool scan);
|
|
int rnd_next(byte *buf);
|
|
int rnd_pos(byte * buf, byte *pos);
|
|
void position(const byte *record);
|
|
int info(uint);
|
|
int extra(enum ha_extra_function operation);
|
|
int external_lock(THD *thd, int lock_type);
|
|
int delete_all_rows(void);
|
|
ha_rows records_in_range(uint inx, const key_range *min_key,
|
|
const key_range *max_key, page_range *pages);
|
|
int delete_table(const char *from);
|
|
int rename_table(const char * from, const char * to);
|
|
int create(const char *name, TABLE *form, HA_CREATE_INFO *create_info);
|
|
void update_create_info(HA_CREATE_INFO *create_info);
|
|
|
|
THR_LOCK_DATA **store_lock(THD *thd, THR_LOCK_DATA **to,
|
|
enum thr_lock_type lock_type);
|
|
int cmp_ref(const byte *ref1, const byte *ref2);
|
|
|
|
bool get_error_message(int error, String* buf);
|
|
|
|
void fprint_error(const char* fmt, ...);
|
|
|
|
#if MYSQL_VERSION_ID < 100000
|
|
// Allow compatibility for build with 5.5.32
|
|
virtual const char *table_type() const { return hton_name(ht)->str; }
|
|
#endif
|
|
|
|
my_bool register_query_cache_table(THD *thd, const char *table_key,
|
|
uint key_length,
|
|
qc_engine_callback
|
|
*engine_callback,
|
|
ulonglong *engine_data)
|
|
{
|
|
/*
|
|
Do not put data from OQGRAPH tables into query cache (because there
|
|
is no way to tell whether the data in the backing table has changed or
|
|
not)
|
|
*/
|
|
return FALSE;
|
|
}
|
|
|
|
private:
|
|
|
|
// Various helper functions
|
|
int oqgraph_check_table_structure (TABLE *table_arg);
|
|
bool validate_oqgraph_table_options();
|
|
void update_key_stats();
|
|
String error_message;
|
|
};
|