mariadb/sql/ha_ndbcluster.h
unknown f631b361b6 Table definition cache, part 2
The table opening process now works the following way:
- Create common TABLE_SHARE object
- Read the .frm file and unpack it into the TABLE_SHARE object
- Create a TABLE object based on the information in the TABLE_SHARE
  object and open a handler to the table object

Other noteworthy changes:
- In TABLE_SHARE the most common strings are now LEX_STRING's
- Better error message when table is not found
- Variable table_cache is now renamed 'table_open_cache'
- New variable 'table_definition_cache' that is the number of table defintions that will be cached
- strxnmov() calls are now fixed to avoid overflows
- strxnmov() will now always add one end \0 to result
- engine objects are now created with a TABLE_SHARE object instead of a TABLE object.
- After creating a field object one must call field->init(table) before using it

- For a busy system this change will give you:
 - Less memory usage for table object
 - Faster opening of tables (if it's has been in use or is in table definition cache)
 - Allow you to cache many table definitions objects
 - Faster drop of table


mysql-test/mysql-test-run.sh:
  Fixed some problems with --gdb option
  Test both with socket and tcp/ip port that all old servers are killed
mysql-test/r/flush_table.result:
  More tests with lock table with 2 threads + flush table
mysql-test/r/information_schema.result:
  Removed old (now wrong) result
mysql-test/r/innodb.result:
  Better error messages (thanks to TDC patch)
mysql-test/r/merge.result:
  Extra flush table test
mysql-test/r/ndb_bitfield.result:
  Better error messages (thanks to TDC patch)
mysql-test/r/ndb_partition_error.result:
  Better error messages (thanks to TDC patch)
mysql-test/r/query_cache.result:
  Remove tables left from old tests
mysql-test/r/temp_table.result:
  Test truncate with temporary tables
mysql-test/r/variables.result:
  Table_cache -> Table_open_cache
mysql-test/t/flush_table.test:
  More tests with lock table with 2 threads + flush table
mysql-test/t/merge.test:
  Extra flush table test
mysql-test/t/multi_update.test:
  Added 'sleep' to make test predictable
mysql-test/t/query_cache.test:
  Remove tables left from old tests
mysql-test/t/temp_table.test:
  Test truncate with temporary tables
mysql-test/t/variables.test:
  Table_cache -> Table_open_cache
mysql-test/valgrind.supp:
  Remove warning that may happens becasue threads dies in different order
mysys/hash.c:
  Fixed wrong DBUG_PRINT
mysys/mf_dirname.c:
  More DBUG
mysys/mf_pack.c:
  Better comment
mysys/mf_tempdir.c:
  More DBUG
  Ensure that we call cleanup_dirname() on all temporary directory paths.
  
  If we don't do this, we will get a failure when comparing temporary table
  names as in some cases the temporary table name is run through convert_dirname())
mysys/my_alloc.c:
  Indentation fix
sql/examples/ha_example.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/examples/ha_example.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/examples/ha_tina.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/examples/ha_tina.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/field.cc:
  Update for table definition cache:
  - Field creation now takes TABLE_SHARE instead of TABLE as argument
    (This is becasue field definitions are now cached in TABLE_SHARE)
    When a field is created, one now must call field->init(TABLE) before using it
  - Use s->db instead of s->table_cache_key
  - Added Field::clone() to create a field in TABLE from a field in TABLE_SHARE
  - make_field() takes TABLE_SHARE as argument instead of TABLE
  - move_field() -> move_field_offset()
sql/field.h:
  Update for table definition cache:
  - Field creation now takes TABLE_SHARE instead of TABLE as argument
    (This is becasue field definitions are now cached in TABLE_SHARE)
    When a field is created, one now must call field->init(TABLE) before using it
  - Added Field::clone() to create a field in TABLE from a field in TABLE_SHARE
  - make_field() takes TABLE_SHARE as argument instead of TABLE
  - move_field() -> move_field_offset()
sql/ha_archive.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_archive.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_berkeley.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Changed name of argument create() to not hide internal 'table' variable.
  table->s  -> table_share
sql/ha_berkeley.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_blackhole.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_blackhole.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_federated.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Fixed comments
  Remove index variable and replace with pointers (simple optimization)
  move_field() -> move_field_offset()
  Removed some strlen() calls
sql/ha_federated.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_heap.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Simplify delete_table() and create() as the given file names are now without extension
sql/ha_heap.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_innodb.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_innodb.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_myisam.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Remove not needed fn_format()
  Fixed for new table->s structure
sql/ha_myisam.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_myisammrg.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Don't set 'is_view' for MERGE tables
  Use new interface to find_temporary_table()
sql/ha_myisammrg.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Added flag HA_NO_COPY_ON_ALTER
sql/ha_ndbcluster.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Fixed wrong calls to strxnmov()
  Give error HA_ERR_TABLE_DEF_CHANGED if table definition has changed
  drop_table -> intern_drop_table()
  table->s -> table_share
  Move part_info to TABLE
  Fixed comments & DBUG print's
  New arguments to print_error()
sql/ha_ndbcluster.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
sql/ha_partition.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  We can't set up or use part_info when creating handler as there is not yet any table object
  New ha_intialise() to work with TDC (Done by Mikael)
sql/ha_partition.h:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  Got set_part_info() from Mikael
sql/handler.cc:
  We new use TABLE_SHARE instead of TABLE when creating engine handlers
  ha_delete_table() now also takes database as an argument
  handler::ha_open() now takes TABLE as argument
  ha_open() now calls ha_allocate_read_write_set()
  Simplify ha_allocate_read_write_set()
  Remove ha_deallocate_read_write_set()
  Use table_share (Cached by table definition cache)
sql/handler.h:
  New table flag: HA_NO_COPY_ON_ALTER (used by merge tables)
  Remove ha_deallocate_read_write_set()
  get_new_handler() now takes TABLE_SHARE as argument
  ha_delete_table() now gets database as argument
sql/item.cc:
  table_name and db are now LEX_STRING objects
  When creating fields, we have now have to call field->init(table)
  move_field -> move_field_offset()
sql/item.h:
  tmp_table_field_from_field_type() now takes an extra paramenter 'fixed_length' to allow one to force usage of CHAR
   instead of BLOB
sql/item_cmpfunc.cc:
  Fixed call to tmp_table_field_from_field_type()
sql/item_create.cc:
  Assert if new not handled cast type
sql/item_func.cc:
  When creating fields, we have now have to call field->init(table)
  dummy_table used by 'sp' now needs a TABLE_SHARE object
sql/item_subselect.cc:
  Trivial code cleanups
sql/item_sum.cc:
  When creating fields, we have now have to call field->init(table)
sql/item_timefunc.cc:
  Item_func_str_to_date::tmp_table_field() now replaced by call to
   tmp_table_field_from_field_type() (see item_timefunc.h)
sql/item_timefunc.h:
  Simply tmp_table_field()
sql/item_uniq.cc:
  When creating fields, we have now have to call field->init(table)
sql/key.cc:
  Added 'KEY' argument to 'find_ref_key' to simplify code
sql/lock.cc:
  More debugging
  Use create_table_def_key() to create key for table cache
  Allocate TABLE_SHARE properly when creating name lock
  Fix that locked_table_name doesn't test same table twice
sql/mysql_priv.h:
  New functions for table definition cache
  New interfaces to a lot of functions.
  New faster interface to find_temporary_table() and close_temporary_table()
sql/mysqld.cc:
  Added support for table definition cache of size 'table_def_size'
  Fixed som calls to strnmov()
  Changed name of 'table_cache' to 'table_open_cache'
sql/opt_range.cc:
  Use new interfaces
  Fixed warnings from valgrind
sql/parse_file.cc:
  Safer calls to strxnmov()
  Fixed typo
sql/set_var.cc:
  Added variable 'table_definition_cache'
  Variable table_cache renamed to 'table_open_cache'
sql/slave.cc:
  Use new interface
sql/sp.cc:
  Proper use of TABLE_SHARE
sql/sp_head.cc:
  Remove compiler warnings
  We have now to call field->init(table)
sql/sp_head.h:
  Pointers to parsed strings are now const
sql/sql_acl.cc:
  table_name is now a LEX_STRING
sql/sql_base.cc:
  Main implementation of table definition cache
  (The #ifdef's are there for the future when table definition cache will replace open table cache)
  Now table definitions are cached indepndent of open tables, which will speed up things when a table is in use at once from several places
  Views are not yet cached; For the moment we only cache if a table is a view or not.
  
  Faster implementation of find_temorary_table()
  Replace 'wait_for_refresh()' with the more general function 'wait_for_condition()'
  Drop table is slightly faster as we can use the table definition cache to know the type of the table
sql/sql_cache.cc:
  table_cache_key and table_name are now LEX_STRING
  'sDBUG print fixes
sql/sql_class.cc:
  table_cache_key is now a LEX_STRING
  safer strxnmov()
sql/sql_class.h:
  Added number of open table shares (table definitions)
sql/sql_db.cc:
  safer strxnmov()
sql/sql_delete.cc:
  Use new interface to find_temporary_table()
sql/sql_derived.cc:
  table_name is now a LEX_STRING
sql/sql_handler.cc:
  TABLE_SHARE->db and TABLE_SHARE->table_name are now LEX_STRING's
sql/sql_insert.cc:
  TABLE_SHARE->db and TABLE_SHARE->table_name are now LEX_STRING's
sql/sql_lex.cc:
  Make parsed string a const (to quickly find out if anything is trying to change the query string)
sql/sql_lex.h:
  Make parsed string a const (to quickly find out if anything is trying to change the query string)
sql/sql_load.cc:
  Safer strxnmov()
sql/sql_parse.cc:
  Better error if wrong DB name
sql/sql_partition.cc:
  part_info moved to TABLE from TABLE_SHARE
  Indentation changes
sql/sql_select.cc:
  Indentation fixes
  Call field->init(TABLE) for new created fields
  Update create_tmp_table() to use TABLE_SHARE properly
sql/sql_select.h:
  Call field->init(TABLE) for new created fields
sql/sql_show.cc:
  table_name is now a LEX_STRING
  part_info moved to TABLE
sql/sql_table.cc:
  Use table definition cache to speed up delete of tables
  Fixed calls to functions with new interfaces
  Don't use 'share_not_to_be_used'
  Instead of doing openfrm() when doing repair, we now have to call
  get_table_share() followed by open_table_from_share().
  Replace some fn_format() with faster unpack_filename().
  Safer strxnmov()
  part_info is now in TABLE
  Added Mikaels patch for partition and ALTER TABLE
  Instead of using 'TABLE_SHARE->is_view' use 'table_flags() & HA_NO_COPY_ON_ALTER
sql/sql_test.cc:
  table_name and table_cache_key are now LEX_STRING's
sql/sql_trigger.cc:
  TABLE_SHARE->db and TABLE_SHARE->table_name are now LEX_STRING's
  safer strxnmov()
  Removed compiler warnings
sql/sql_update.cc:
  Call field->init(TABLE) after field is created
sql/sql_view.cc:
  safer strxnmov()
  Create common TABLE_SHARE object for views to allow us to cache if table is a view
sql/structs.h:
  Added SHOW_TABLE_DEFINITIONS
sql/table.cc:
  Creation and destruct of TABLE_SHARE objects that are common for many TABLE objects
  
  The table opening process now works the following way:
  - Create common TABLE_SHARE object
  - Read the .frm file and unpack it into the TABLE_SHARE object
  - Create a TABLE object based on the information in the TABLE_SHARE
    object and open a handler to the table object
  
  open_table_def() is written in such a way that it should be trival to add parsing of the .frm files in new formats
sql/table.h:
  TABLE objects for the same database table now share a common TABLE_SHARE object
  In TABLE_SHARE the most common strings are now LEX_STRING's
sql/unireg.cc:
  Changed arguments to rea_create_table() to have same order as other functions
  Call field->init(table) for new created fields
sql/unireg.h:
  Added OPEN_VIEW
strings/strxnmov.c:
  Change strxnmov() to always add end \0
  This makes usage of strxnmov() safer as most of MySQL code assumes that strxnmov() will create a null terminated string
2005-11-23 22:45:02 +02:00

787 lines
24 KiB
C++

/* Copyright (C) 2000-2003 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; either version 2 of the License, or
(at your option) any later version.
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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
/*
This file defines the NDB Cluster handler: the interface between MySQL and
NDB Cluster
*/
/* The class defining a handle to an NDB Cluster table */
#ifdef USE_PRAGMA_INTERFACE
#pragma interface /* gcc class implementation */
#endif
#include <NdbApi.hpp>
#include <ndbapi_limits.h>
class Ndb; // Forward declaration
class NdbOperation; // Forward declaration
class NdbTransaction; // Forward declaration
class NdbRecAttr; // Forward declaration
class NdbScanOperation;
class NdbScanFilter;
class NdbIndexScanOperation;
class NdbBlob;
class NdbIndexStat;
class NdbEventOperation;
// connectstring to cluster if given by mysqld
extern const char *ndbcluster_connectstring;
extern ulong ndb_cache_check_time;
extern ulong ndb_report_thresh_binlog_epoch_slip;
extern ulong ndb_report_thresh_binlog_mem_usage;
typedef enum ndb_index_type {
UNDEFINED_INDEX = 0,
PRIMARY_KEY_INDEX = 1,
PRIMARY_KEY_ORDERED_INDEX = 2,
UNIQUE_INDEX = 3,
UNIQUE_ORDERED_INDEX = 4,
ORDERED_INDEX = 5
} NDB_INDEX_TYPE;
typedef struct ndb_index_data {
NDB_INDEX_TYPE type;
void *index;
void *unique_index;
unsigned char *unique_index_attrid_map;
// In this version stats are not shared between threads
NdbIndexStat* index_stat;
uint index_stat_cache_entries;
// Simple counter mechanism to decide when to connect to db
uint index_stat_update_freq;
uint index_stat_query_count;
} NDB_INDEX_DATA;
typedef union { const NdbRecAttr *rec; NdbBlob *blob; void *ptr; } NdbValue;
typedef enum {
NSS_INITIAL= 0,
NSS_DROPPED
} NDB_SHARE_STATE;
typedef struct st_ndbcluster_share {
MEM_ROOT mem_root;
THR_LOCK lock;
pthread_mutex_t mutex;
char *key;
uint key_length;
THD *util_lock;
uint use_count;
uint commit_count_lock;
ulonglong commit_count;
char *db;
char *table_name;
} NDB_SHARE;
typedef enum ndb_item_type {
NDB_VALUE = 0, // Qualified more with Item::Type
NDB_FIELD = 1, // Qualified from table definition
NDB_FUNCTION = 2,// Qualified from Item_func::Functype
NDB_END_COND = 3 // End marker for condition group
} NDB_ITEM_TYPE;
typedef enum ndb_func_type {
NDB_EQ_FUNC = 0,
NDB_NE_FUNC = 1,
NDB_LT_FUNC = 2,
NDB_LE_FUNC = 3,
NDB_GT_FUNC = 4,
NDB_GE_FUNC = 5,
NDB_ISNULL_FUNC = 6,
NDB_ISNOTNULL_FUNC = 7,
NDB_LIKE_FUNC = 8,
NDB_NOTLIKE_FUNC = 9,
NDB_NOT_FUNC = 10,
NDB_UNKNOWN_FUNC = 11,
NDB_COND_AND_FUNC = 12,
NDB_COND_OR_FUNC = 13,
NDB_UNSUPPORTED_FUNC = 14
} NDB_FUNC_TYPE;
typedef union ndb_item_qualification {
Item::Type value_type;
enum_field_types field_type; // Instead of Item::FIELD_ITEM
NDB_FUNC_TYPE function_type; // Instead of Item::FUNC_ITEM
} NDB_ITEM_QUALIFICATION;
typedef struct ndb_item_field_value {
Field* field;
int column_no;
} NDB_ITEM_FIELD_VALUE;
typedef union ndb_item_value {
const Item *item;
NDB_ITEM_FIELD_VALUE *field_value;
uint arg_count;
} NDB_ITEM_VALUE;
struct negated_function_mapping
{
NDB_FUNC_TYPE pos_fun;
NDB_FUNC_TYPE neg_fun;
};
/*
Define what functions can be negated in condition pushdown.
Note, these HAVE to be in the same order as in definition enum
*/
static const negated_function_mapping neg_map[]=
{
{NDB_EQ_FUNC, NDB_NE_FUNC},
{NDB_NE_FUNC, NDB_EQ_FUNC},
{NDB_LT_FUNC, NDB_GE_FUNC},
{NDB_LE_FUNC, NDB_GT_FUNC},
{NDB_GT_FUNC, NDB_LE_FUNC},
{NDB_GE_FUNC, NDB_LT_FUNC},
{NDB_ISNULL_FUNC, NDB_ISNOTNULL_FUNC},
{NDB_ISNOTNULL_FUNC, NDB_ISNULL_FUNC},
{NDB_LIKE_FUNC, NDB_NOTLIKE_FUNC},
{NDB_NOTLIKE_FUNC, NDB_LIKE_FUNC},
{NDB_NOT_FUNC, NDB_UNSUPPORTED_FUNC},
{NDB_UNKNOWN_FUNC, NDB_UNSUPPORTED_FUNC},
{NDB_COND_AND_FUNC, NDB_UNSUPPORTED_FUNC},
{NDB_COND_OR_FUNC, NDB_UNSUPPORTED_FUNC},
{NDB_UNSUPPORTED_FUNC, NDB_UNSUPPORTED_FUNC}
};
/*
This class is the construction element for serialization of Item tree
in condition pushdown.
An instance of Ndb_Item represents a constant, table field reference,
unary or binary comparison predicate, and start/end of AND/OR.
Instances of Ndb_Item are stored in a linked list implemented by Ndb_cond
class.
The order of elements produced by Ndb_cond::next corresponds to
breadth-first traversal of the Item (i.e. expression) tree in prefix order.
AND and OR have arbitrary arity, so the end of AND/OR group is marked with
Ndb_item with type == NDB_END_COND.
NOT items represent negated conditions and generate NAND/NOR groups.
*/
class Ndb_item {
public:
Ndb_item(NDB_ITEM_TYPE item_type) : type(item_type) {};
Ndb_item(NDB_ITEM_TYPE item_type,
NDB_ITEM_QUALIFICATION item_qualification,
const Item *item_value)
: type(item_type), qualification(item_qualification)
{
switch(item_type) {
case(NDB_VALUE):
value.item= item_value;
break;
case(NDB_FIELD): {
NDB_ITEM_FIELD_VALUE *field_value= new NDB_ITEM_FIELD_VALUE();
Item_field *field_item= (Item_field *) item_value;
field_value->field= field_item->field;
field_value->column_no= -1; // Will be fetched at scan filter generation
value.field_value= field_value;
break;
}
case(NDB_FUNCTION):
value.item= item_value;
value.arg_count= ((Item_func *) item_value)->argument_count();
break;
case(NDB_END_COND):
break;
}
};
Ndb_item(Field *field, int column_no) : type(NDB_FIELD)
{
NDB_ITEM_FIELD_VALUE *field_value= new NDB_ITEM_FIELD_VALUE();
qualification.field_type= field->type();
field_value->field= field;
field_value->column_no= column_no;
value.field_value= field_value;
};
Ndb_item(Item_func::Functype func_type, const Item *item_value)
: type(NDB_FUNCTION)
{
qualification.function_type= item_func_to_ndb_func(func_type);
value.item= item_value;
value.arg_count= ((Item_func *) item_value)->argument_count();
};
Ndb_item(Item_func::Functype func_type, uint no_args)
: type(NDB_FUNCTION)
{
qualification.function_type= item_func_to_ndb_func(func_type);
value.arg_count= no_args;
};
~Ndb_item()
{
if (type == NDB_FIELD)
{
delete value.field_value;
value.field_value= NULL;
}
};
uint32 pack_length()
{
switch(type) {
case(NDB_VALUE):
if(qualification.value_type == Item::STRING_ITEM)
return value.item->str_value.length();
break;
case(NDB_FIELD):
return value.field_value->field->pack_length();
default:
break;
}
return 0;
};
Field * get_field() { return value.field_value->field; };
int get_field_no() { return value.field_value->column_no; };
int argument_count()
{
return value.arg_count;
};
const char* get_val()
{
switch(type) {
case(NDB_VALUE):
if(qualification.value_type == Item::STRING_ITEM)
return value.item->str_value.ptr();
break;
case(NDB_FIELD):
return value.field_value->field->ptr;
default:
break;
}
return NULL;
};
void save_in_field(Ndb_item *field_item)
{
Field *field = field_item->value.field_value->field;
const Item *item= value.item;
if (item && field)
((Item *)item)->save_in_field(field, false);
};
static NDB_FUNC_TYPE item_func_to_ndb_func(Item_func::Functype fun)
{
switch (fun) {
case (Item_func::EQ_FUNC): { return NDB_EQ_FUNC; }
case (Item_func::NE_FUNC): { return NDB_NE_FUNC; }
case (Item_func::LT_FUNC): { return NDB_LT_FUNC; }
case (Item_func::LE_FUNC): { return NDB_LE_FUNC; }
case (Item_func::GT_FUNC): { return NDB_GT_FUNC; }
case (Item_func::GE_FUNC): { return NDB_GE_FUNC; }
case (Item_func::ISNULL_FUNC): { return NDB_ISNULL_FUNC; }
case (Item_func::ISNOTNULL_FUNC): { return NDB_ISNOTNULL_FUNC; }
case (Item_func::LIKE_FUNC): { return NDB_LIKE_FUNC; }
case (Item_func::NOT_FUNC): { return NDB_NOT_FUNC; }
case (Item_func::UNKNOWN_FUNC): { return NDB_UNKNOWN_FUNC; }
case (Item_func::COND_AND_FUNC): { return NDB_COND_AND_FUNC; }
case (Item_func::COND_OR_FUNC): { return NDB_COND_OR_FUNC; }
default: { return NDB_UNSUPPORTED_FUNC; }
}
};
static NDB_FUNC_TYPE negate(NDB_FUNC_TYPE fun)
{
uint i= (uint) fun;
DBUG_ASSERT(fun == neg_map[i].pos_fun);
return neg_map[i].neg_fun;
};
NDB_ITEM_TYPE type;
NDB_ITEM_QUALIFICATION qualification;
private:
NDB_ITEM_VALUE value;
};
/*
This class implements a linked list used for storing a
serialization of the Item tree for condition pushdown.
*/
class Ndb_cond
{
public:
Ndb_cond() : ndb_item(NULL), next(NULL), prev(NULL) {};
~Ndb_cond()
{
if (ndb_item) delete ndb_item;
ndb_item= NULL;
if (next) delete next;
next= prev= NULL;
};
Ndb_item *ndb_item;
Ndb_cond *next;
Ndb_cond *prev;
};
/*
This class implements a stack for storing several conditions
for pushdown (represented as serialized Item trees using Ndb_cond).
The current implementation only pushes one condition, but is
prepared for handling several (C1 AND C2 ...) if the logic for
pushing conditions is extended in sql_select.
*/
class Ndb_cond_stack
{
public:
Ndb_cond_stack() : ndb_cond(NULL), next(NULL) {};
~Ndb_cond_stack()
{
if (ndb_cond) delete ndb_cond;
ndb_cond= NULL;
if (next) delete next;
next= NULL;
};
Ndb_cond *ndb_cond;
Ndb_cond_stack *next;
};
class Ndb_rewrite_context
{
public:
Ndb_rewrite_context(Item_func *func)
: func_item(func), left_hand_item(NULL), count(0) {};
~Ndb_rewrite_context()
{
if (next) delete next;
}
const Item_func *func_item;
const Item *left_hand_item;
uint count;
Ndb_rewrite_context *next;
};
/*
This class is used for storing the context when traversing
the Item tree. It stores a reference to the table the condition
is defined on, the serialized representation being generated,
if the condition found is supported, and information what is
expected next in the tree inorder for the condition to be supported.
*/
class Ndb_cond_traverse_context
{
public:
Ndb_cond_traverse_context(TABLE *tab, void* ndb_tab, Ndb_cond_stack* stack)
: table(tab), ndb_table(ndb_tab),
supported(TRUE), stack_ptr(stack), cond_ptr(NULL),
expect_mask(0), expect_field_result_mask(0), skip(0), collation(NULL),
rewrite_stack(NULL)
{
if (stack)
cond_ptr= stack->ndb_cond;
};
~Ndb_cond_traverse_context()
{
if (rewrite_stack) delete rewrite_stack;
}
void expect(Item::Type type)
{
expect_mask|= (1 << type);
};
void dont_expect(Item::Type type)
{
expect_mask&= ~(1 << type);
};
bool expecting(Item::Type type)
{
return (expect_mask & (1 << type));
};
void expect_nothing()
{
expect_mask= 0;
};
void expect_only(Item::Type type)
{
expect_mask= 0;
expect(type);
};
void expect_field_result(Item_result result)
{
expect_field_result_mask|= (1 << result);
};
bool expecting_field_result(Item_result result)
{
return (expect_field_result_mask & (1 << result));
};
void expect_no_field_result()
{
expect_field_result_mask= 0;
};
void expect_only_field_result(Item_result result)
{
expect_field_result_mask= 0;
expect_field_result(result);
};
void expect_collation(CHARSET_INFO* col)
{
collation= col;
};
bool expecting_collation(CHARSET_INFO* col)
{
bool matching= (!collation) ? true : (collation == col);
collation= NULL;
return matching;
};
TABLE* table;
void* ndb_table;
bool supported;
Ndb_cond_stack* stack_ptr;
Ndb_cond* cond_ptr;
uint expect_mask;
uint expect_field_result_mask;
uint skip;
CHARSET_INFO* collation;
Ndb_rewrite_context *rewrite_stack;
};
/*
Place holder for ha_ndbcluster thread specific data
*/
class Thd_ndb
{
public:
Thd_ndb();
~Thd_ndb();
Ndb *ndb;
ulong count;
uint lock_count;
NdbTransaction *all;
NdbTransaction *stmt;
int error;
List<NDB_SHARE> changed_tables;
};
class ha_ndbcluster: public handler
{
public:
ha_ndbcluster(TABLE_SHARE *table);
~ha_ndbcluster();
int open(const char *name, int mode, uint test_if_locked);
int close(void);
int write_row(byte *buf);
int update_row(const byte *old_data, byte *new_data);
int delete_row(const byte *buf);
int index_init(uint index, bool sorted);
int index_end();
int index_read(byte *buf, const byte *key, uint key_len,
enum ha_rkey_function find_flag);
int index_read_idx(byte *buf, uint index, const byte *key, uint key_len,
enum ha_rkey_function find_flag);
int index_next(byte *buf);
int index_prev(byte *buf);
int index_first(byte *buf);
int index_last(byte *buf);
int index_read_last(byte * buf, const byte * key, uint key_len);
int rnd_init(bool scan);
int rnd_end();
int rnd_next(byte *buf);
int rnd_pos(byte *buf, byte *pos);
void position(const byte *record);
int read_range_first(const key_range *start_key,
const key_range *end_key,
bool eq_range, bool sorted);
int read_range_first_to_buf(const key_range *start_key,
const key_range *end_key,
bool eq_range, bool sorted,
byte* buf);
int read_range_next();
/**
* Multi range stuff
*/
int read_multi_range_first(KEY_MULTI_RANGE **found_range_p,
KEY_MULTI_RANGE*ranges, uint range_count,
bool sorted, HANDLER_BUFFER *buffer);
int read_multi_range_next(KEY_MULTI_RANGE **found_range_p);
bool get_error_message(int error, String *buf);
void info(uint);
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);
int start_stmt(THD *thd, thr_lock_type lock_type);
const char * table_type() const;
const char ** bas_ext() const;
ulong table_flags(void) const;
ulong partition_flags(void) const
{
return (HA_CAN_PARTITION | HA_CAN_UPDATE_PARTITION_KEY |
HA_CAN_PARTITION_UNIQUE);
}
ulong index_flags(uint idx, uint part, bool all_parts) const;
uint max_supported_record_length() const;
uint max_supported_keys() const;
uint max_supported_key_parts() const;
uint max_supported_key_length() const;
int rename_table(const char *from, const char *to);
int delete_table(const char *name);
int create(const char *name, TABLE *form, HA_CREATE_INFO *info);
int get_default_no_partitions(ulonglong max_rows);
THR_LOCK_DATA **store_lock(THD *thd,
THR_LOCK_DATA **to,
enum thr_lock_type lock_type);
bool low_byte_first() const;
bool has_transactions();
const char* index_type(uint key_number);
double scan_time();
ha_rows records_in_range(uint inx, key_range *min_key, key_range *max_key);
void start_bulk_insert(ha_rows rows);
int end_bulk_insert();
static Thd_ndb* seize_thd_ndb();
static void release_thd_ndb(Thd_ndb* thd_ndb);
static void set_dbname(const char *pathname, char *dbname);
static void set_tabname(const char *pathname, char *tabname);
/*
Condition pushdown
*/
/*
Push condition down to the table handler.
SYNOPSIS
cond_push()
cond Condition to be pushed. The condition tree must not be
modified by the by the caller.
RETURN
The 'remainder' condition that caller must use to filter out records.
NULL means the handler will not return rows that do not match the
passed condition.
NOTES
The pushed conditions form a stack (from which one can remove the
last pushed condition using cond_pop).
The table handler filters out rows using (pushed_cond1 AND pushed_cond2
AND ... AND pushed_condN)
or less restrictive condition, depending on handler's capabilities.
handler->extra(HA_EXTRA_RESET) call empties the condition stack.
Calls to rnd_init/rnd_end, index_init/index_end etc do not affect the
condition stack.
The current implementation supports arbitrary AND/OR nested conditions
with comparisons between columns and constants (including constant
expressions and function calls) and the following comparison operators:
=, !=, >, >=, <, <=, like, "not like", "is null", and "is not null".
Negated conditions are supported by NOT which generate NAND/NOR groups.
*/
const COND *cond_push(const COND *cond);
/*
Pop the top condition from the condition stack of the handler instance.
SYNOPSIS
cond_pop()
Pops the top if condition stack, if stack is not empty
*/
void cond_pop();
uint8 table_cache_type();
my_bool register_query_cache_table(THD *thd, char *table_key,
uint key_length,
qc_engine_callback *engine_callback,
ulonglong *engine_data);
bool check_if_incompatible_data(HA_CREATE_INFO *info,
uint table_changes);
static void invalidate_dictionary_cache(TABLE *table, Ndb *ndb,
const char *tabname, bool global);
private:
friend int ndbcluster_drop_database_impl(const char *path);
int alter_table_name(const char *to);
static int delete_table(ha_ndbcluster *h, Ndb *ndb,
const char *path,
const char *db,
const char *table_name);
int intern_drop_table();
int create_index(const char *name, KEY *key_info, bool unique);
int create_ordered_index(const char *name, KEY *key_info);
int create_unique_index(const char *name, KEY *key_info);
int initialize_autoincrement(const void *table);
enum ILBP {ILBP_CREATE = 0, ILBP_OPEN = 1}; // Index List Build Phase
int build_index_list(Ndb *ndb, TABLE *tab, enum ILBP phase);
int get_metadata(const char* path);
void release_metadata();
NDB_INDEX_TYPE get_index_type(uint idx_no) const;
NDB_INDEX_TYPE get_index_type_from_table(uint index_no) const;
int check_index_fields_not_null(uint index_no);
uint set_up_partition_info(partition_info *part_info,
TABLE *table,
void *tab);
int complemented_pk_read(const byte *old_data, byte *new_data,
uint32 old_part_id);
int pk_read(const byte *key, uint key_len, byte *buf, uint32 part_id);
int ordered_index_scan(const key_range *start_key,
const key_range *end_key,
bool sorted, bool descending, byte* buf,
part_id_range *part_spec);
int full_table_scan(byte * buf);
int peek_row(const byte *record);
int unique_index_read(const byte *key, uint key_len,
byte *buf);
int fetch_next(NdbScanOperation* op);
int next_result(byte *buf);
int define_read_attrs(byte* buf, NdbOperation* op);
int filtered_scan(const byte *key, uint key_len,
byte *buf,
enum ha_rkey_function find_flag);
int close_scan();
void unpack_record(byte *buf);
int get_ndb_lock_type(enum thr_lock_type type);
void set_dbname(const char *pathname);
void set_tabname(const char *pathname);
bool set_hidden_key(NdbOperation*,
uint fieldnr, const byte* field_ptr);
int set_ndb_key(NdbOperation*, Field *field,
uint fieldnr, const byte* field_ptr);
int set_ndb_value(NdbOperation*, Field *field, uint fieldnr,
int row_offset= 0, bool *set_blob_value= 0);
int get_ndb_value(NdbOperation*, Field *field, uint fieldnr, byte*);
friend int g_get_ndb_blobs_value(NdbBlob *ndb_blob, void *arg);
int get_ndb_blobs_value(NdbBlob *last_ndb_blob);
int set_primary_key(NdbOperation *op, const byte *key);
int set_primary_key_from_record(NdbOperation *op, const byte *record);
int set_bounds(NdbIndexScanOperation*, uint inx, bool rir,
const key_range *keys[2], uint= 0);
int key_cmp(uint keynr, const byte * old_row, const byte * new_row);
int set_index_key(NdbOperation *, const KEY *key_info, const byte *key_ptr);
void print_results();
ulonglong get_auto_increment();
void invalidate_dictionary_cache(bool global);
int ndb_err(NdbTransaction*);
bool uses_blob_value();
char *update_table_comment(const char * comment);
int write_ndb_file();
int check_ndb_connection(THD* thd= current_thd);
void set_rec_per_key();
void records_update();
void no_uncommitted_rows_execute_failure();
void no_uncommitted_rows_update(int);
void no_uncommitted_rows_init(THD *);
void no_uncommitted_rows_reset(THD *);
/*
Condition pushdown
*/
void cond_clear();
bool serialize_cond(const COND *cond, Ndb_cond_stack *ndb_cond);
int build_scan_filter_predicate(Ndb_cond* &cond,
NdbScanFilter* filter,
bool negated= false);
int build_scan_filter_group(Ndb_cond* &cond,
NdbScanFilter* filter);
int build_scan_filter(Ndb_cond* &cond, NdbScanFilter* filter);
int generate_scan_filter(Ndb_cond_stack* cond_stack,
NdbScanOperation* op);
friend int execute_commit(ha_ndbcluster*, NdbTransaction*);
friend int execute_no_commit_ignore_no_key(ha_ndbcluster*, NdbTransaction*);
friend int execute_no_commit(ha_ndbcluster*, NdbTransaction*);
friend int execute_no_commit_ie(ha_ndbcluster*, NdbTransaction*);
NdbTransaction *m_active_trans;
NdbScanOperation *m_active_cursor;
void *m_table;
int m_table_version;
void *m_table_info;
char m_dbname[FN_HEADLEN];
//char m_schemaname[FN_HEADLEN];
char m_tabname[FN_HEADLEN];
ulong m_table_flags;
THR_LOCK_DATA m_lock;
NDB_SHARE *m_share;
NDB_INDEX_DATA m_index[MAX_KEY];
// NdbRecAttr has no reference to blob
NdbValue m_value[NDB_MAX_ATTRIBUTES_IN_TABLE];
partition_info *m_part_info;
byte *m_rec0;
Field **m_part_field_array;
bool m_use_partition_function;
bool m_sorted;
bool m_use_write;
bool m_ignore_dup_key;
bool m_primary_key_update;
bool m_write_op;
bool m_ignore_no_key;
ha_rows m_rows_to_insert;
ha_rows m_rows_inserted;
ha_rows m_bulk_insert_rows;
ha_rows m_rows_changed;
bool m_bulk_insert_not_flushed;
ha_rows m_ops_pending;
bool m_skip_auto_increment;
bool m_blobs_pending;
// memory for blobs in one tuple
char *m_blobs_buffer;
uint32 m_blobs_buffer_size;
uint m_dupkey;
// set from thread variables at external lock
bool m_ha_not_exact_count;
bool m_force_send;
ha_rows m_autoincrement_prefetch;
bool m_transaction_on;
Ndb_cond_stack *m_cond_stack;
bool m_disable_multi_read;
byte *m_multi_range_result_ptr;
KEY_MULTI_RANGE *m_multi_ranges;
KEY_MULTI_RANGE *m_multi_range_defined;
const NdbOperation *m_current_multi_operation;
NdbIndexScanOperation *m_multi_cursor;
byte *m_multi_range_cursor_result_ptr;
int setup_recattr(const NdbRecAttr*);
Ndb *get_ndb();
};
extern struct show_var_st ndb_status_variables[];
bool ndbcluster_init(void);
int ndbcluster_end(ha_panic_function flag);
int ndbcluster_discover(THD* thd, const char* dbname, const char* name,
const void** frmblob, uint* frmlen);
int ndbcluster_find_files(THD *thd,const char *db,const char *path,
const char *wild, bool dir, List<char> *files);
int ndbcluster_table_exists_in_engine(THD* thd,
const char *db, const char *name);
void ndbcluster_drop_database(char* path);
void ndbcluster_print_error(int error, const NdbOperation *error_op);
bool ndbcluster_show_status(THD*,stat_print_fn *,enum ha_stat_type);