mirror of
https://github.com/MariaDB/server.git
synced 2025-01-19 13:32:33 +01:00
780f80be16
* Fix BUG#15650: "DELETE with LEFT JOIN crashes server with innodb_locks_unsafe_for binlog"
* Fix BUG#17134: "Partitions: uncommitted changes are visible"
* Fix BUG#17992: "Partitions: InnoDB, somehow rotten table after UPDATE"
row0ins.c: MySQL's partitioned table code does not set preduilt->sql_stat_start right
if it does an insert in the same statement after doing a search first in the same
partition table. We now write trx id always to the buffer, not just when flag
sql_stat_start is on. This will waste CPU time very sightly.
* Fix BUG#18077: "InnoDB uses full explicit table locks in stored FUNCTION"
* Fix BUG#18238: "When locks exhaust the buffer pool, InnoDB does not roll back the trx"
* Fix BUG#18252" "Disk space leak in updates of InnoDB BLOB rows in 5.0 and 5.1"
* Fix BUG#18283: "When InnoDB returns error 'lock table full', MySQL can write to binlog too much"
* Fix BUG#18350: "Use consistent read in CREATE ... SELECT ... if innodb_locks_unsafe_for_binlog"
* Fix BUG#18384: "InnoDB memory leak on duplicate key errors in 5.0 if row has many columns"
* Fix BUG#18934: "InnoDB crashes when table uses column names like DB_ROW_ID"
Refuse tables that use reserved column names.
* InnoDB's SQL parser:
- Add support for UNSIGNED types, EXIT keyword, quoted identifiers, user-function callbacks
for processing results of FETCH statements, bound literals, DATA_VARCHAR for bound literals.
- Allow bound literals of type non-INTEGER to be of length 0.
- Add make_flex.sh and update lexer/parser generation documentation.
- Add comment clarifying the difference between 'alias' and 'indirection' fields in sym_node_t.
- Remove never reached duplicate code in pars_set_dfield_type().
- Rewrite pars_info datatypes and APIs, add a few helper functions.
- Since the functions definitions in pars_info_t are accessed after pars_sql() returns
in the query graph execution stage, we can't free pars_info_t in pars_sql(). Instead,
make pars_sql() transfer ownership of pars_info_t to the created query graph, and
make que_graph_free() free it if needed.
- Allow access to system columns like DB_ROW_ID.
* Use bound literals in row_truncate_table_for_mysql, row_drop_table_for_mysql,
row_discard_tablespace_for_mysql, and row_rename_table_for_mysql.
* Setting an isolation level of the transaction to read committed weakens the locks for
this session similarly like the option innodb_locks_unsafe_for binlog. This patch removes
alnost all gap locking (used in next-key locking) and makes MySQL to release the row locks
on the rows which does not belong to result set. Additionally, nonlocking selects on
INSERT INTO SELECT, UPDATE ... (SELECT ...), and CREATE ... SELECT ... use a nonlocking
consistent read. If a binlog is used, then binlog format should be set to row based
binloging to make the execution of the complex SQL statements.
* Disable the statistic variables btr_search_n_hash_fail and n_hash_succ, n_hash_fail,
n_patt_succ, and n_searches of btr_search_t in builds without #ifdef UNIV_SEARCH_PERF_STAT.
* Make innodb.test faster. Group all consistent read test cases to a one test case and
wait their lock timeout after all have been send to the server. Decrease amount of rows
inserted in a certain test - this has no effect on the effectiveness of the test and
reduces the running time by ~10 sec. Remove temporary work-arounds from innodb.result
now that ALTER TABLE DROP FOREIGN KEY works once again.
* Make innodb_unsafe_binlog.test faster. Grout all consistent read test cases to a one
test case amd wait their lock timeout after all have been sent to the server. Remove
unnecessary option --loose_innodb_lock_wait_timeout.
* Print dictionary memory size in SHOW INNODB STATUS.
* Fix memory leaks in row_create_table_for_mysql() in rare corner cases.
* Remove code related to clustered tables. They were never implemented, and the
implementation would be challenging with ROW_FORMAT=COMPACT. Remove the table types
DICT_TABLE_CLUSTER_MEMBER and DICT_TABLE_CLUSTER and all related tests and functions.
dict_table_t: Remove mix_id, mix_len, mix_id_len, mix_id_buf, and cluster_name.
plan_t: Remove mixed_index.
dict_create_sys_tables_tuple(): Set MIX_ID=0, MIX_LEN=0, CLUSTER_NAME=NULL when
inserting into SYS_TABLES.
dict_tree_check_search_tuple(): Enclose in #ifdef UNIV_DEBUG.
* Move calling of thr_local_free() from trx_free_for_mysql() to
innobase_close_connection().
432 lines
16 KiB
C
432 lines
16 KiB
C
/******************************************************
|
|
Update of a row
|
|
|
|
(c) 1996 Innobase Oy
|
|
|
|
Created 12/27/1996 Heikki Tuuri
|
|
*******************************************************/
|
|
|
|
#ifndef row0upd_h
|
|
#define row0upd_h
|
|
|
|
#include "univ.i"
|
|
#include "data0data.h"
|
|
#include "btr0types.h"
|
|
#include "btr0pcur.h"
|
|
#include "dict0types.h"
|
|
#include "trx0types.h"
|
|
#include "que0types.h"
|
|
#include "row0types.h"
|
|
#include "pars0types.h"
|
|
|
|
/*************************************************************************
|
|
Creates an update vector object. */
|
|
UNIV_INLINE
|
|
upd_t*
|
|
upd_create(
|
|
/*=======*/
|
|
/* out, own: update vector object */
|
|
ulint n, /* in: number of fields */
|
|
mem_heap_t* heap); /* in: heap from which memory allocated */
|
|
/*************************************************************************
|
|
Returns the number of fields in the update vector == number of columns
|
|
to be updated by an update vector. */
|
|
UNIV_INLINE
|
|
ulint
|
|
upd_get_n_fields(
|
|
/*=============*/
|
|
/* out: number of fields */
|
|
upd_t* update); /* in: update vector */
|
|
/*************************************************************************
|
|
Returns the nth field of an update vector. */
|
|
UNIV_INLINE
|
|
upd_field_t*
|
|
upd_get_nth_field(
|
|
/*==============*/
|
|
/* out: update vector field */
|
|
upd_t* update, /* in: update vector */
|
|
ulint n); /* in: field position in update vector */
|
|
/*************************************************************************
|
|
Sets an index field number to be updated by an update vector field. */
|
|
UNIV_INLINE
|
|
void
|
|
upd_field_set_field_no(
|
|
/*===================*/
|
|
upd_field_t* upd_field, /* in: update vector field */
|
|
ulint field_no, /* in: field number in a clustered
|
|
index */
|
|
dict_index_t* index, /* in: index */
|
|
trx_t* trx); /* in: transaction */
|
|
/*************************************************************************
|
|
Writes into the redo log the values of trx id and roll ptr and enough info
|
|
to determine their positions within a clustered index record. */
|
|
|
|
byte*
|
|
row_upd_write_sys_vals_to_log(
|
|
/*==========================*/
|
|
/* out: new pointer to mlog */
|
|
dict_index_t* index, /* in: clustered index */
|
|
trx_t* trx, /* in: transaction */
|
|
dulint roll_ptr,/* in: roll ptr of the undo log record */
|
|
byte* log_ptr,/* pointer to a buffer of size > 20 opened
|
|
in mlog */
|
|
mtr_t* mtr); /* in: mtr */
|
|
/*************************************************************************
|
|
Updates the trx id and roll ptr field in a clustered index record when
|
|
a row is updated or marked deleted. */
|
|
UNIV_INLINE
|
|
void
|
|
row_upd_rec_sys_fields(
|
|
/*===================*/
|
|
rec_t* rec, /* in: record */
|
|
dict_index_t* index, /* in: clustered index */
|
|
const ulint* offsets,/* in: rec_get_offsets(rec, index) */
|
|
trx_t* trx, /* in: transaction */
|
|
dulint roll_ptr);/* in: roll ptr of the undo log record */
|
|
/*************************************************************************
|
|
Sets the trx id or roll ptr field of a clustered index entry. */
|
|
|
|
void
|
|
row_upd_index_entry_sys_field(
|
|
/*==========================*/
|
|
dtuple_t* entry, /* in: index entry, where the memory buffers
|
|
for sys fields are already allocated:
|
|
the function just copies the new values to
|
|
them */
|
|
dict_index_t* index, /* in: clustered index */
|
|
ulint type, /* in: DATA_TRX_ID or DATA_ROLL_PTR */
|
|
dulint val); /* in: value to write */
|
|
/*************************************************************************
|
|
Creates an update node for a query graph. */
|
|
|
|
upd_node_t*
|
|
upd_node_create(
|
|
/*============*/
|
|
/* out, own: update node */
|
|
mem_heap_t* heap); /* in: mem heap where created */
|
|
/***************************************************************
|
|
Writes to the redo log the new values of the fields occurring in the index. */
|
|
|
|
void
|
|
row_upd_index_write_log(
|
|
/*====================*/
|
|
upd_t* update, /* in: update vector */
|
|
byte* log_ptr,/* in: pointer to mlog buffer: must contain at least
|
|
MLOG_BUF_MARGIN bytes of free space; the buffer is
|
|
closed within this function */
|
|
mtr_t* mtr); /* in: mtr into whose log to write */
|
|
/***************************************************************
|
|
Returns TRUE if row update changes size of some field in index or if some
|
|
field to be updated is stored externally in rec or update. */
|
|
|
|
ibool
|
|
row_upd_changes_field_size_or_external(
|
|
/*===================================*/
|
|
/* out: TRUE if the update changes the size of
|
|
some field in index or the field is external
|
|
in rec or update */
|
|
dict_index_t* index, /* in: index */
|
|
const ulint* offsets,/* in: rec_get_offsets(rec, index) */
|
|
upd_t* update);/* in: update vector */
|
|
/***************************************************************
|
|
Replaces the new column values stored in the update vector to the record
|
|
given. No field size changes are allowed. This function is used only for
|
|
a clustered index */
|
|
|
|
void
|
|
row_upd_rec_in_place(
|
|
/*=================*/
|
|
rec_t* rec, /* in/out: record where replaced */
|
|
const ulint* offsets,/* in: array returned by rec_get_offsets() */
|
|
upd_t* update);/* in: update vector */
|
|
/*******************************************************************
|
|
Builds an update vector from those fields which in a secondary index entry
|
|
differ from a record that has the equal ordering fields. NOTE: we compare
|
|
the fields as binary strings! */
|
|
|
|
upd_t*
|
|
row_upd_build_sec_rec_difference_binary(
|
|
/*====================================*/
|
|
/* out, own: update vector of differing
|
|
fields */
|
|
dict_index_t* index, /* in: index */
|
|
dtuple_t* entry, /* in: entry to insert */
|
|
rec_t* rec, /* in: secondary index record */
|
|
trx_t* trx, /* in: transaction */
|
|
mem_heap_t* heap); /* in: memory heap from which allocated */
|
|
/*******************************************************************
|
|
Builds an update vector from those fields, excluding the roll ptr and
|
|
trx id fields, which in an index entry differ from a record that has
|
|
the equal ordering fields. NOTE: we compare the fields as binary strings! */
|
|
|
|
upd_t*
|
|
row_upd_build_difference_binary(
|
|
/*============================*/
|
|
/* out, own: update vector of differing
|
|
fields, excluding roll ptr and trx id */
|
|
dict_index_t* index, /* in: clustered index */
|
|
dtuple_t* entry, /* in: entry to insert */
|
|
ulint* ext_vec,/* in: array containing field numbers of
|
|
externally stored fields in entry, or NULL */
|
|
ulint n_ext_vec,/* in: number of fields in ext_vec */
|
|
rec_t* rec, /* in: clustered index record */
|
|
trx_t* trx, /* in: transaction */
|
|
mem_heap_t* heap); /* in: memory heap from which allocated */
|
|
/***************************************************************
|
|
Replaces the new column values stored in the update vector to the index entry
|
|
given. */
|
|
|
|
void
|
|
row_upd_index_replace_new_col_vals_index_pos(
|
|
/*=========================================*/
|
|
dtuple_t* entry, /* in/out: index entry where replaced */
|
|
dict_index_t* index, /* in: index; NOTE that this may also be a
|
|
non-clustered index */
|
|
upd_t* update, /* in: an update vector built for the index so
|
|
that the field number in an upd_field is the
|
|
index position */
|
|
ibool order_only,
|
|
/* in: if TRUE, limit the replacement to
|
|
ordering fields of index; note that this
|
|
does not work for non-clustered indexes. */
|
|
mem_heap_t* heap); /* in: memory heap to which we allocate and
|
|
copy the new values, set this as NULL if you
|
|
do not want allocation */
|
|
/***************************************************************
|
|
Replaces the new column values stored in the update vector to the index entry
|
|
given. */
|
|
|
|
void
|
|
row_upd_index_replace_new_col_vals(
|
|
/*===============================*/
|
|
dtuple_t* entry, /* in/out: index entry where replaced */
|
|
dict_index_t* index, /* in: index; NOTE that this may also be a
|
|
non-clustered index */
|
|
upd_t* update, /* in: an update vector built for the
|
|
CLUSTERED index so that the field number in
|
|
an upd_field is the clustered index position */
|
|
mem_heap_t* heap); /* in: memory heap to which we allocate and
|
|
copy the new values, set this as NULL if you
|
|
do not want allocation */
|
|
/***************************************************************
|
|
Checks if an update vector changes an ordering field of an index record.
|
|
This function is fast if the update vector is short or the number of ordering
|
|
fields in the index is small. Otherwise, this can be quadratic.
|
|
NOTE: we compare the fields as binary strings! */
|
|
|
|
ibool
|
|
row_upd_changes_ord_field_binary(
|
|
/*=============================*/
|
|
/* out: TRUE if update vector changes
|
|
an ordering field in the index record;
|
|
NOTE: the fields are compared as binary
|
|
strings */
|
|
dtuple_t* row, /* in: old value of row, or NULL if the
|
|
row and the data values in update are not
|
|
known when this function is called, e.g., at
|
|
compile time */
|
|
dict_index_t* index, /* in: index of the record */
|
|
upd_t* update);/* in: update vector for the row; NOTE: the
|
|
field numbers in this MUST be clustered index
|
|
positions! */
|
|
/***************************************************************
|
|
Checks if an update vector changes an ordering field of an index record.
|
|
This function is fast if the update vector is short or the number of ordering
|
|
fields in the index is small. Otherwise, this can be quadratic.
|
|
NOTE: we compare the fields as binary strings! */
|
|
|
|
ibool
|
|
row_upd_changes_some_index_ord_field_binary(
|
|
/*========================================*/
|
|
/* out: TRUE if update vector may change
|
|
an ordering field in an index record */
|
|
dict_table_t* table, /* in: table */
|
|
upd_t* update);/* in: update vector for the row */
|
|
/***************************************************************
|
|
Updates a row in a table. This is a high-level function used
|
|
in SQL execution graphs. */
|
|
|
|
que_thr_t*
|
|
row_upd_step(
|
|
/*=========*/
|
|
/* out: query thread to run next or NULL */
|
|
que_thr_t* thr); /* in: query thread */
|
|
/*************************************************************************
|
|
Performs an in-place update for the current clustered index record in
|
|
select. */
|
|
|
|
void
|
|
row_upd_in_place_in_select(
|
|
/*=======================*/
|
|
sel_node_t* sel_node, /* in: select node */
|
|
que_thr_t* thr, /* in: query thread */
|
|
mtr_t* mtr); /* in: mtr */
|
|
/*************************************************************************
|
|
Parses the log data of system field values. */
|
|
|
|
byte*
|
|
row_upd_parse_sys_vals(
|
|
/*===================*/
|
|
/* out: log data end or NULL */
|
|
byte* ptr, /* in: buffer */
|
|
byte* end_ptr,/* in: buffer end */
|
|
ulint* pos, /* out: TRX_ID position in record */
|
|
dulint* trx_id, /* out: trx id */
|
|
dulint* roll_ptr);/* out: roll ptr */
|
|
/*************************************************************************
|
|
Updates the trx id and roll ptr field in a clustered index record in database
|
|
recovery. */
|
|
|
|
void
|
|
row_upd_rec_sys_fields_in_recovery(
|
|
/*===============================*/
|
|
rec_t* rec, /* in: record */
|
|
const ulint* offsets,/* in: array returned by rec_get_offsets() */
|
|
ulint pos, /* in: TRX_ID position in rec */
|
|
dulint trx_id, /* in: transaction id */
|
|
dulint roll_ptr);/* in: roll ptr of the undo log record */
|
|
/*************************************************************************
|
|
Parses the log data written by row_upd_index_write_log. */
|
|
|
|
byte*
|
|
row_upd_index_parse(
|
|
/*================*/
|
|
/* out: log data end or NULL */
|
|
byte* ptr, /* in: buffer */
|
|
byte* end_ptr,/* in: buffer end */
|
|
mem_heap_t* heap, /* in: memory heap where update vector is
|
|
built */
|
|
upd_t** update_out);/* out: update vector */
|
|
|
|
|
|
/* Update vector field */
|
|
struct upd_field_struct{
|
|
ulint field_no; /* field number in an index, usually
|
|
the clustered index, but in updating
|
|
a secondary index record in btr0cur.c
|
|
this is the position in the secondary
|
|
index */
|
|
que_node_t* exp; /* expression for calculating a new
|
|
value: it refers to column values and
|
|
constants in the symbol table of the
|
|
query graph */
|
|
dfield_t new_val; /* new value for the column */
|
|
ibool extern_storage; /* this is set to TRUE if dfield
|
|
actually contains a reference to
|
|
an externally stored field */
|
|
};
|
|
|
|
/* Update vector structure */
|
|
struct upd_struct{
|
|
ulint info_bits; /* new value of info bits to record;
|
|
default is 0 */
|
|
ulint n_fields; /* number of update fields */
|
|
upd_field_t* fields; /* array of update fields */
|
|
};
|
|
|
|
/* Update node structure which also implements the delete operation
|
|
of a row */
|
|
|
|
struct upd_node_struct{
|
|
que_common_t common; /* node type: QUE_NODE_UPDATE */
|
|
ibool is_delete;/* TRUE if delete, FALSE if update */
|
|
ibool searched_update;
|
|
/* TRUE if searched update, FALSE if
|
|
positioned */
|
|
ibool select_will_do_update;
|
|
/* TRUE if a searched update where ordering
|
|
fields will not be updated, and the size of
|
|
the fields will not change: in this case the
|
|
select node will take care of the update */
|
|
ibool in_mysql_interface;
|
|
/* TRUE if the update node was created
|
|
for the MySQL interface */
|
|
dict_foreign_t* foreign;/* NULL or pointer to a foreign key
|
|
constraint if this update node is used in
|
|
doing an ON DELETE or ON UPDATE operation */
|
|
upd_node_t* cascade_node;/* NULL or an update node template which
|
|
is used to implement ON DELETE/UPDATE CASCADE
|
|
or ... SET NULL for foreign keys */
|
|
mem_heap_t* cascade_heap;/* NULL or a mem heap where the cascade
|
|
node is created */
|
|
sel_node_t* select; /* query graph subtree implementing a base
|
|
table cursor: the rows returned will be
|
|
updated */
|
|
btr_pcur_t* pcur; /* persistent cursor placed on the clustered
|
|
index record which should be updated or
|
|
deleted; the cursor is stored in the graph
|
|
of 'select' field above, except in the case
|
|
of the MySQL interface */
|
|
dict_table_t* table; /* table where updated */
|
|
upd_t* update; /* update vector for the row */
|
|
ulint update_n_fields;
|
|
/* when this struct is used to implement
|
|
a cascade operation for foreign keys, we store
|
|
here the size of the buffer allocated for use
|
|
as the update vector */
|
|
sym_node_list_t columns;/* symbol table nodes for the columns
|
|
to retrieve from the table */
|
|
ibool has_clust_rec_x_lock;
|
|
/* TRUE if the select which retrieves the
|
|
records to update already sets an x-lock on
|
|
the clustered record; note that it must always
|
|
set at least an s-lock */
|
|
ulint cmpl_info;/* information extracted during query
|
|
compilation; speeds up execution:
|
|
UPD_NODE_NO_ORD_CHANGE and
|
|
UPD_NODE_NO_SIZE_CHANGE, ORed */
|
|
/*----------------------*/
|
|
/* Local storage for this graph node */
|
|
ulint state; /* node execution state */
|
|
dict_index_t* index; /* NULL, or the next index whose record should
|
|
be updated */
|
|
dtuple_t* row; /* NULL, or a copy (also fields copied to
|
|
heap) of the row to update; this must be reset
|
|
to NULL after a successful update */
|
|
ulint* ext_vec;/* array describing which fields are stored
|
|
externally in the clustered index record of
|
|
row */
|
|
ulint n_ext_vec;/* number of fields in ext_vec */
|
|
mem_heap_t* heap; /* memory heap used as auxiliary storage;
|
|
this must be emptied after a successful
|
|
update */
|
|
/*----------------------*/
|
|
sym_node_t* table_sym;/* table node in symbol table */
|
|
que_node_t* col_assign_list;
|
|
/* column assignment list */
|
|
ulint magic_n;
|
|
};
|
|
|
|
#define UPD_NODE_MAGIC_N 1579975
|
|
|
|
/* Node execution states */
|
|
#define UPD_NODE_SET_IX_LOCK 1 /* execution came to the node from
|
|
a node above and if the field
|
|
has_clust_rec_x_lock is FALSE, we
|
|
should set an intention x-lock on
|
|
the table */
|
|
#define UPD_NODE_UPDATE_CLUSTERED 2 /* clustered index record should be
|
|
updated */
|
|
#define UPD_NODE_INSERT_CLUSTERED 3 /* clustered index record should be
|
|
inserted, old record is already delete
|
|
marked */
|
|
#define UPD_NODE_UPDATE_ALL_SEC 4 /* an ordering field of the clustered
|
|
index record was changed, or this is
|
|
a delete operation: should update
|
|
all the secondary index records */
|
|
#define UPD_NODE_UPDATE_SOME_SEC 5 /* secondary index entries should be
|
|
looked at and updated if an ordering
|
|
field changed */
|
|
|
|
/* Compilation info flags: these must fit within 3 bits; see trx0rec.h */
|
|
#define UPD_NODE_NO_ORD_CHANGE 1 /* no secondary index record will be
|
|
changed in the update and no ordering
|
|
field of the clustered index */
|
|
#define UPD_NODE_NO_SIZE_CHANGE 2 /* no record field size will be
|
|
changed in the update */
|
|
|
|
#ifndef UNIV_NONINL
|
|
#include "row0upd.ic"
|
|
#endif
|
|
|
|
#endif
|