mariadb/storage/sphinx/ha_sphinx.h

184 lines
5.7 KiB
C
Raw Normal View History

//
2014-11-18 18:10:29 +01:00
// $Id: ha_sphinx.h 4818 2014-09-24 08:53:38Z tomat $
//
#ifdef USE_PRAGMA_INTERFACE
#pragma interface // gcc class implementation
#endif
#if MYSQL_VERSION_ID>=50515
2011-04-25 17:22:25 +02:00
#define TABLE_ARG TABLE_SHARE
#elif MYSQL_VERSION_ID>50100
#define TABLE_ARG st_table_share
#else
#define TABLE_ARG st_table
#endif
#if MYSQL_VERSION_ID>=50120
typedef uchar byte;
#endif
/// forward decls
class THD;
struct CSphReqQuery;
struct CSphSEShare;
struct CSphSEAttr;
struct CSphSEStats;
2014-11-18 18:10:29 +01:00
struct CSphSEThreadTable;
/// Sphinx SE handler class
class ha_sphinx final : public handler
{
protected:
THR_LOCK_DATA m_tLock; ///< MySQL lock
CSphSEShare * m_pShare; ///< shared lock info
uint m_iMatchesTotal;
uint m_iCurrentPos;
const byte * m_pCurrentKey;
uint m_iCurrentKeyLen;
char * m_pResponse; ///< searchd response storage
char * m_pResponseEnd; ///< searchd response storage end (points to wilderness!)
char * m_pCur; ///< current position into response
bool m_bUnpackError; ///< any errors while unpacking response
public:
#if MYSQL_VERSION_ID<50100
ha_sphinx ( TABLE_ARG * table_arg ); // NOLINT
#else
ha_sphinx ( handlerton * hton, TABLE_ARG * table_arg );
#endif
~ha_sphinx ();
2024-06-24 13:09:47 +03:00
const char * table_type () const override { return "SPHINX"; } ///< SE name for display purposes
const char * index_type ( uint ) override { return "HASH"; } ///< index type name for display purposes
#if MYSQL_VERSION_ID>50100
ulonglong table_flags () const override { return HA_CAN_INDEX_BLOBS |
HA_CAN_TABLE_CONDITION_PUSHDOWN; } ///< bitmap of implemented flags (see handler.h for more info)
#else
ulong table_flags () const { return HA_CAN_INDEX_BLOBS; } ///< bitmap of implemented flags (see handler.h for more info)
#endif
ulong index_flags ( uint, uint, bool ) const override { return 0; } ///< bitmap of flags that says how SE implements indexes
uint max_supported_record_length () const override { return HA_MAX_REC_LENGTH; }
uint max_supported_keys () const override { return 1; }
uint max_supported_key_parts () const override { return 1; }
uint max_supported_key_length () const override { return MAX_KEY_LENGTH; }
uint max_supported_key_part_length () const override { return MAX_KEY_LENGTH; }
2024-07-05 12:45:07 +02:00
IO_AND_CPU_COST scan_time () override
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)
2022-08-11 13:05:23 +03:00
{
IO_AND_CPU_COST cost;
cost.io= 0;
Add limits for how many IO operations a table access will do This solves the current problem in the optimizer - SELECT FROM big_table - SELECT from small_table where small_table.eq_ref_key=big_table.id The old code assumed that each eq_ref access will cause an IO. As the cost of IO is high, this dominated the cost for the later table which caused the optimizer to prefer table scans + join cache over index reads. This patch fixes this issue by limit the number of expected IO calls, for rows and index separately, to the size of the table or index or the number of accesses that we except in a range for the index. The major changes are: - Adding a new structure ALL_READ_COST that is mainly used in best_access_path() to hold the costs parts of the cost we are calculating. This allows us to limit the number of IO when multiplying the cost with the previous row combinations. - All storage engine cost functions are changed to return IO_AND_CPU_COST. The virtual cost functions should now return in IO_AND_CPU_COST.io the number of disk blocks that will be accessed instead of the cost of the access. - We are not limiting the io_blocks for table or index scans as we assume that engines may not store these in the 'hot' part of the cache. Table and index scan also uses much less IO blocks than key accesses, so the original issue is not as critical with scans. Other things: OPT_RANGE now holds a 'Cost_estimate cost' instead a lot of different costs. All the old costs, like index_only_read, can be extracted from 'cost'. - Added to the start of some functions 'handler *file= table->file' to shorten the code that is using the handler. - handler->cost() is used to change a ALL_READ_COST or IO_AND_CPU_COST to 'cost in milliseconds' - New functions: handler::index_blocks() and handler::row_blocks() which are used to limit the IO. - Added index_cost and row_cost to Cost_estimate and removed all not needed members. - Removed cost coefficients from Cost_estimate as these don't make sense when costs (except IO_BLOCKS) are in milliseconds. - Removed handler::avg_io_cost() and replaced it with DISK_READ_COST. - Renamed best_range_rowid_filter_for_partial_join() to best_range_rowid_filter() as using the old name made rows too long. - Changed all SJ_MATERIALIZATION_INFO 'Cost_estimate' variables to 'double' as Cost_estimate power was not used for these and thus just caused storage and performance overhead. - Changed cost_for_index_read() to use 'worst_seeks' to only limit IO, not number of table accesses. With this patch worst_seeks is probably not needed anymore, but I kept it around just in case. - Applying cost for filter got to be much shorter and easier thanks to the API changes. - Adjusted cost for fulltext keys in collaboration with Sergei Golubchik. - Most test changes caused by this patch is that table scans are changed to use indexes. - Added ha_seq::keyread_time() and ha_seq::key_scan_time() to get make checking number of potential IO blocks easier during debugging.
2022-09-30 17:10:37 +03:00
cost.cpu= (double) (stats.records+stats.deleted) * DISK_READ_COST;
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)
2022-08-11 13:05:23 +03:00
return cost;
}
IO_AND_CPU_COST keyread_time(uint index, ulong ranges, ha_rows rows,
2024-07-05 12:45:07 +02:00
ulonglong blocks) override
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)
2022-08-11 13:05:23 +03:00
{
IO_AND_CPU_COST cost;
cost.io= ranges;
cost.cpu= 0;
return cost;
}
2024-07-05 12:45:07 +02:00
IO_AND_CPU_COST rnd_pos_time(ha_rows rows) override
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)
2022-08-11 13:05:23 +03:00
{
IO_AND_CPU_COST cost;
cost.io= 0;
cost.cpu= 0;
return cost;
}
public:
int open ( const char * name, int mode, uint test_if_locked ) override;
int close () override;
int write_row ( const byte * buf ) override;
int update_row ( const byte * old_data, const byte * new_data ) override;
int delete_row ( const byte * buf ) override;
int extra ( enum ha_extra_function op ) override;
int index_init ( uint keynr, bool sorted ) override; // 5.1.x
int index_init ( uint keynr ) { return index_init ( keynr, false ); } // 5.0.x
int index_end () override;
int index_read ( byte * buf, const byte * key, uint key_len, enum ha_rkey_function find_flag ) override;
int index_read_idx ( byte * buf, uint idx, const byte * key, uint key_len, enum ha_rkey_function find_flag );
int index_next ( byte * buf ) override;
int index_next_same ( byte * buf, const byte * key, uint keylen ) override;
int index_prev ( byte * buf ) override;
int index_first ( byte * buf ) override;
int index_last ( byte * buf ) override;
int get_rec ( byte * buf, const byte * key, uint keylen );
int rnd_init ( bool scan ) override;
int rnd_end () override;
int rnd_next ( byte * buf ) override;
int rnd_pos ( byte * buf, byte * pos ) override;
void position ( const byte * record ) override;
#if MYSQL_VERSION_ID>=50030
int info ( uint ) override;
#else
void info ( uint );
#endif
int reset() override;
int external_lock ( THD * thd, int lock_type ) override;
int delete_all_rows () override;
ha_rows records_in_range ( uint inx, const key_range * min_key, const key_range * max_key, page_range *pages) override;
int delete_table ( const char * from ) override;
int rename_table ( const char * from, const char * to ) override;
int create ( const char * name, TABLE * form, HA_CREATE_INFO * create_info ) override;
THR_LOCK_DATA ** store_lock ( THD * thd, THR_LOCK_DATA ** to, enum thr_lock_type lock_type ) override;
public:
2014-02-01 10:56:56 +01:00
#if MYSQL_VERSION_ID<50610
virtual const COND * cond_push ( const COND *cond );
2014-02-01 10:56:56 +01:00
#else
const Item * cond_push ( const Item *cond ) override;
2014-02-01 10:56:56 +01:00
#endif
void cond_pop () override;
private:
uint32 m_iFields;
char ** m_dFields;
uint32 m_iAttrs;
CSphSEAttr * m_dAttrs;
int m_bId64;
int * m_dUnboundFields;
private:
int Connect ( const char * sQueryHost, ushort uPort );
int ConnectAPI ( const char * sQueryHost, int iQueryPort );
int HandleMysqlError ( struct st_mysql * pConn, int iErrCode );
uint32 UnpackDword ();
char * UnpackString ();
bool UnpackSchema ();
bool UnpackStats ( CSphSEStats * pStats );
bool CheckResponcePtr ( int iLen );
2014-11-18 18:10:29 +01:00
CSphSEThreadTable * GetTls ();
};
#if MYSQL_VERSION_ID < 50100
bool sphinx_show_status ( THD * thd );
#endif
//
2014-11-18 18:10:29 +01:00
// $Id: ha_sphinx.h 4818 2014-09-24 08:53:38Z tomat $
//