2014-02-26 19:11:54 +01:00
|
|
|
/*****************************************************************************
|
|
|
|
|
|
2016-06-21 14:21:03 +02:00
|
|
|
Copyright (c) 1996, 2016, Oracle and/or its affiliates. All Rights Reserved.
|
2019-05-03 15:47:07 +02:00
|
|
|
Copyright (c) 2017, 2019, MariaDB Corporation.
|
2014-02-26 19:11:54 +01:00
|
|
|
|
|
|
|
|
This program is free software; you can redistribute it and/or modify it under
|
|
|
|
|
the terms of the GNU General Public License as published by the Free Software
|
|
|
|
|
Foundation; version 2 of the License.
|
|
|
|
|
|
|
|
|
|
This program is distributed in the hope that it will be useful, but WITHOUT
|
|
|
|
|
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
|
|
|
|
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
|
|
|
|
|
|
|
|
|
|
You should have received a copy of the GNU General Public License along with
|
|
|
|
|
this program; if not, write to the Free Software Foundation, Inc.,
|
2019-05-11 18:25:02 +02:00
|
|
|
51 Franklin Street, Fifth Floor, Boston, MA 02110-1335 USA
|
2014-02-26 19:11:54 +01:00
|
|
|
|
|
|
|
|
*****************************************************************************/
|
|
|
|
|
|
|
|
|
|
/**************************************************//**
|
|
|
|
|
@file include/trx0rec.h
|
|
|
|
|
Transaction undo log record
|
|
|
|
|
|
|
|
|
|
Created 3/26/1996 Heikki Tuuri
|
|
|
|
|
*******************************************************/
|
|
|
|
|
|
|
|
|
|
#ifndef trx0rec_h
|
|
|
|
|
#define trx0rec_h
|
|
|
|
|
|
|
|
|
|
#include "trx0types.h"
|
|
|
|
|
#include "row0types.h"
|
|
|
|
|
#include "mtr0mtr.h"
|
|
|
|
|
#include "rem0types.h"
|
2016-08-12 10:17:45 +02:00
|
|
|
#include "page0types.h"
|
|
|
|
|
#include "row0log.h"
|
2016-12-30 14:04:10 +01:00
|
|
|
#include "que0types.h"
|
2014-02-26 19:11:54 +01:00
|
|
|
|
|
|
|
|
/***********************************************************************//**
|
|
|
|
|
Copies the undo record to the heap.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return own: copy of undo log record */
|
2014-02-26 19:11:54 +01:00
|
|
|
UNIV_INLINE
|
|
|
|
|
trx_undo_rec_t*
|
|
|
|
|
trx_undo_rec_copy(
|
|
|
|
|
/*==============*/
|
|
|
|
|
const trx_undo_rec_t* undo_rec, /*!< in: undo log record */
|
|
|
|
|
mem_heap_t* heap); /*!< in: heap where copied */
|
|
|
|
|
/**********************************************************************//**
|
|
|
|
|
Reads the undo log record type.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return record type */
|
2014-02-26 19:11:54 +01:00
|
|
|
UNIV_INLINE
|
|
|
|
|
ulint
|
|
|
|
|
trx_undo_rec_get_type(
|
|
|
|
|
/*==================*/
|
|
|
|
|
const trx_undo_rec_t* undo_rec); /*!< in: undo log record */
|
|
|
|
|
/**********************************************************************//**
|
|
|
|
|
Reads the undo log record number.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return undo no */
|
2014-02-26 19:11:54 +01:00
|
|
|
UNIV_INLINE
|
|
|
|
|
undo_no_t
|
|
|
|
|
trx_undo_rec_get_undo_no(
|
|
|
|
|
/*=====================*/
|
|
|
|
|
const trx_undo_rec_t* undo_rec); /*!< in: undo log record */
|
|
|
|
|
|
|
|
|
|
/**********************************************************************//**
|
|
|
|
|
Returns the start of the undo record data area. */
|
|
|
|
|
#define trx_undo_rec_get_ptr(undo_rec, undo_no) \
|
|
|
|
|
((undo_rec) + trx_undo_rec_get_offset(undo_no))
|
|
|
|
|
|
|
|
|
|
/**********************************************************************//**
|
|
|
|
|
Reads from an undo log record the general parameters.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return remaining part of undo log record after reading these values */
|
2014-02-26 19:11:54 +01:00
|
|
|
byte*
|
|
|
|
|
trx_undo_rec_get_pars(
|
|
|
|
|
/*==================*/
|
|
|
|
|
trx_undo_rec_t* undo_rec, /*!< in: undo log record */
|
|
|
|
|
ulint* type, /*!< out: undo record type:
|
|
|
|
|
TRX_UNDO_INSERT_REC, ... */
|
|
|
|
|
ulint* cmpl_info, /*!< out: compiler info, relevant only
|
|
|
|
|
for update type records */
|
|
|
|
|
bool* updated_extern, /*!< out: true if we updated an
|
|
|
|
|
externally stored fild */
|
|
|
|
|
undo_no_t* undo_no, /*!< out: undo log record number */
|
|
|
|
|
table_id_t* table_id) /*!< out: table id */
|
2016-06-21 14:21:03 +02:00
|
|
|
MY_ATTRIBUTE((nonnull));
|
2014-02-26 19:11:54 +01:00
|
|
|
/*******************************************************************//**
|
|
|
|
|
Builds a row reference from an undo log record.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return pointer to remaining part of undo record */
|
2014-02-26 19:11:54 +01:00
|
|
|
byte*
|
|
|
|
|
trx_undo_rec_get_row_ref(
|
|
|
|
|
/*=====================*/
|
|
|
|
|
byte* ptr, /*!< in: remaining part of a copy of an undo log
|
|
|
|
|
record, at the start of the row reference;
|
|
|
|
|
NOTE that this copy of the undo log record must
|
|
|
|
|
be preserved as long as the row reference is
|
|
|
|
|
used, as we do NOT copy the data in the
|
|
|
|
|
record! */
|
|
|
|
|
dict_index_t* index, /*!< in: clustered index */
|
2017-09-08 12:12:01 +02:00
|
|
|
const dtuple_t**ref, /*!< out, own: row reference */
|
2014-02-26 19:11:54 +01:00
|
|
|
mem_heap_t* heap); /*!< in: memory heap from which the memory
|
|
|
|
|
needed is allocated */
|
|
|
|
|
/**********************************************************************//**
|
|
|
|
|
Reads from an undo log update record the system field values of the old
|
|
|
|
|
version.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return remaining part of undo log record after reading these values */
|
2014-02-26 19:11:54 +01:00
|
|
|
byte*
|
|
|
|
|
trx_undo_update_rec_get_sys_cols(
|
|
|
|
|
/*=============================*/
|
2016-08-12 10:17:45 +02:00
|
|
|
const byte* ptr, /*!< in: remaining part of undo
|
2014-02-26 19:11:54 +01:00
|
|
|
log record after reading
|
|
|
|
|
general parameters */
|
|
|
|
|
trx_id_t* trx_id, /*!< out: trx id */
|
|
|
|
|
roll_ptr_t* roll_ptr, /*!< out: roll ptr */
|
|
|
|
|
ulint* info_bits); /*!< out: info bits state */
|
|
|
|
|
/*******************************************************************//**
|
|
|
|
|
Builds an update vector based on a remaining part of an undo log record.
|
|
|
|
|
@return remaining part of the record, NULL if an error detected, which
|
|
|
|
|
means that the record is corrupted */
|
|
|
|
|
byte*
|
|
|
|
|
trx_undo_update_rec_get_update(
|
|
|
|
|
/*===========================*/
|
2016-08-12 10:17:45 +02:00
|
|
|
const byte* ptr, /*!< in: remaining part in update undo log
|
2014-02-26 19:11:54 +01:00
|
|
|
record, after reading the row reference
|
|
|
|
|
NOTE that this copy of the undo log record must
|
|
|
|
|
be preserved as long as the update vector is
|
|
|
|
|
used, as we do NOT copy the data in the
|
|
|
|
|
record! */
|
|
|
|
|
dict_index_t* index, /*!< in: clustered index */
|
|
|
|
|
ulint type, /*!< in: TRX_UNDO_UPD_EXIST_REC,
|
|
|
|
|
TRX_UNDO_UPD_DEL_REC, or
|
|
|
|
|
TRX_UNDO_DEL_MARK_REC; in the last case,
|
|
|
|
|
only trx id and roll ptr fields are added to
|
|
|
|
|
the update vector */
|
|
|
|
|
trx_id_t trx_id, /*!< in: transaction id from this undorecord */
|
|
|
|
|
roll_ptr_t roll_ptr,/*!< in: roll pointer from this undo record */
|
|
|
|
|
ulint info_bits,/*!< in: info bits from this undo record */
|
|
|
|
|
mem_heap_t* heap, /*!< in: memory heap from which the memory
|
|
|
|
|
needed is allocated */
|
|
|
|
|
upd_t** upd); /*!< out, own: update vector */
|
|
|
|
|
/*******************************************************************//**
|
|
|
|
|
Builds a partial row from an update undo log record, for purge.
|
|
|
|
|
It contains the columns which occur as ordering in any index of the table.
|
|
|
|
|
Any missing columns are indicated by col->mtype == DATA_MISSING.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return pointer to remaining part of undo record */
|
2014-02-26 19:11:54 +01:00
|
|
|
byte*
|
|
|
|
|
trx_undo_rec_get_partial_row(
|
|
|
|
|
/*=========================*/
|
2016-08-12 10:17:45 +02:00
|
|
|
const byte* ptr, /*!< in: remaining part in update undo log
|
2014-02-26 19:11:54 +01:00
|
|
|
record of a suitable type, at the start of
|
|
|
|
|
the stored index columns;
|
|
|
|
|
NOTE that this copy of the undo log record must
|
|
|
|
|
be preserved as long as the partial row is
|
|
|
|
|
used, as we do NOT copy the data in the
|
|
|
|
|
record! */
|
|
|
|
|
dict_index_t* index, /*!< in: clustered index */
|
2018-01-02 18:11:10 +01:00
|
|
|
const upd_t* update, /*!< in: updated columns */
|
2014-02-26 19:11:54 +01:00
|
|
|
dtuple_t** row, /*!< out, own: partial row */
|
|
|
|
|
ibool ignore_prefix, /*!< in: flag to indicate if we
|
|
|
|
|
expect blob prefixes in undo. Used
|
|
|
|
|
only in the assertion. */
|
|
|
|
|
mem_heap_t* heap) /*!< in: memory heap from which the memory
|
|
|
|
|
needed is allocated */
|
2016-06-21 14:21:03 +02:00
|
|
|
MY_ATTRIBUTE((nonnull, warn_unused_result));
|
2017-12-20 21:19:47 +01:00
|
|
|
/** Report a RENAME TABLE operation.
|
|
|
|
|
@param[in,out] trx transaction
|
|
|
|
|
@param[in] table table that is being renamed
|
|
|
|
|
@return DB_SUCCESS or error code */
|
2018-11-01 09:48:56 +01:00
|
|
|
dberr_t trx_undo_report_rename(trx_t* trx, const dict_table_t* table)
|
2017-12-20 21:19:47 +01:00
|
|
|
MY_ATTRIBUTE((nonnull, warn_unused_result));
|
2014-02-26 19:11:54 +01:00
|
|
|
/***********************************************************************//**
|
|
|
|
|
Writes information to an undo log about an insert, update, or a delete marking
|
|
|
|
|
of a clustered index record. This information is used in a rollback of the
|
|
|
|
|
transaction and in consistent reads that must look to the history of this
|
|
|
|
|
transaction.
|
2016-08-12 10:17:45 +02:00
|
|
|
@return DB_SUCCESS or error code */
|
2014-02-26 19:11:54 +01:00
|
|
|
dberr_t
|
|
|
|
|
trx_undo_report_row_operation(
|
|
|
|
|
/*==========================*/
|
|
|
|
|
que_thr_t* thr, /*!< in: query thread */
|
|
|
|
|
dict_index_t* index, /*!< in: clustered index */
|
|
|
|
|
const dtuple_t* clust_entry, /*!< in: in the case of an insert,
|
|
|
|
|
index entry to insert into the
|
2017-05-22 08:20:20 +02:00
|
|
|
clustered index; in updates,
|
|
|
|
|
may contain a clustered index
|
|
|
|
|
record tuple that also contains
|
|
|
|
|
virtual columns of the table;
|
|
|
|
|
otherwise, NULL */
|
2014-02-26 19:11:54 +01:00
|
|
|
const upd_t* update, /*!< in: in the case of an update,
|
|
|
|
|
the update vector, otherwise NULL */
|
|
|
|
|
ulint cmpl_info, /*!< in: compiler info on secondary
|
|
|
|
|
index updates */
|
|
|
|
|
const rec_t* rec, /*!< in: case of an update or delete
|
|
|
|
|
marking, the record in the clustered
|
2017-05-22 08:20:20 +02:00
|
|
|
index; NULL if insert */
|
MDEV-20950 Reduce size of record offsets
offset_t: this is a type which represents one record offset.
It's unsigned short int.
a lot of functions: replace ulint with offset_t
btr_pcur_restore_position_func(),
page_validate(),
row_ins_scan_sec_index_for_duplicate(),
row_upd_clust_rec_by_insert_inherit_func(),
row_vers_impl_x_locked_low(),
trx_undo_prev_version_build():
allocate record offsets on the stack instead of waiting for rec_get_offsets()
to allocate it from mem_heap_t. So, reducing memory allocations.
RECORD_OFFSET, INDEX_OFFSET:
now it's less convenient to store pointers in offset_t*
array. One pointer occupies now several offset_t. And those constant are start
indexes into array to places where to store pointer values
REC_OFFS_HEADER_SIZE: adjusted for the new reality
REC_OFFS_NORMAL_SIZE:
increase size from 100 to 300 which means less heap allocations.
And sizeof(offset_t[REC_OFFS_NORMAL_SIZE]) now is 600 bytes which
is smaller than previous 800 bytes.
REC_OFFS_SEC_INDEX_SIZE: adjusted for the new reality
rem0rec.h, rem0rec.ic, rem0rec.cc:
various arguments, return values and local variables types were changed to
fix numerous integer conversions issues.
enum field_type_t:
offset types concept was introduces which replaces old offset flags stuff.
Like in earlier version, 2 upper bits are used to store offset type.
And this enum represents those types.
REC_OFFS_SQL_NULL, REC_OFFS_MASK: removed
get_type(), set_type(), get_value(), combine():
these are convenience functions to work with offsets and it's types
rec_offs_base()[0]:
still uses an old scheme with flags REC_OFFS_COMPACT and REC_OFFS_EXTERNAL
rec_offs_base()[i]:
these have type offset_t now. Two upper bits contains type.
2019-11-04 20:30:12 +01:00
|
|
|
const offset_t* offsets, /*!< in: rec_get_offsets(rec) */
|
2017-12-20 08:21:08 +01:00
|
|
|
roll_ptr_t* roll_ptr) /*!< out: DB_ROLL_PTR to the
|
|
|
|
|
undo log record */
|
2017-05-17 15:14:41 +02:00
|
|
|
MY_ATTRIBUTE((nonnull(1,2,8), warn_unused_result));
|
2016-08-12 10:17:45 +02:00
|
|
|
|
|
|
|
|
/** status bit used for trx_undo_prev_version_build() */
|
|
|
|
|
|
|
|
|
|
/** TRX_UNDO_PREV_IN_PURGE tells trx_undo_prev_version_build() that it
|
|
|
|
|
is being called purge view and we would like to get the purge record
|
|
|
|
|
even it is in the purge view (in normal case, it will return without
|
|
|
|
|
fetching the purge record */
|
|
|
|
|
#define TRX_UNDO_PREV_IN_PURGE 0x1
|
|
|
|
|
|
|
|
|
|
/** This tells trx_undo_prev_version_build() to fetch the old value in
|
|
|
|
|
the undo log (which is the after image for an update) */
|
|
|
|
|
#define TRX_UNDO_GET_OLD_V_VALUE 0x2
|
|
|
|
|
|
2014-02-26 19:11:54 +01:00
|
|
|
/*******************************************************************//**
|
|
|
|
|
Build a previous version of a clustered index record. The caller must
|
|
|
|
|
hold a latch on the index page of the clustered index record.
|
|
|
|
|
@retval true if previous version was built, or if it was an insert
|
|
|
|
|
or the table has been rebuilt
|
|
|
|
|
@retval false if the previous version is earlier than purge_view,
|
|
|
|
|
which means that it may have been removed */
|
|
|
|
|
bool
|
|
|
|
|
trx_undo_prev_version_build(
|
|
|
|
|
/*========================*/
|
|
|
|
|
const rec_t* index_rec,/*!< in: clustered index record in the
|
|
|
|
|
index tree */
|
|
|
|
|
mtr_t* index_mtr,/*!< in: mtr which contains the latch to
|
|
|
|
|
index_rec page and purge_view */
|
|
|
|
|
const rec_t* rec, /*!< in: version of a clustered index record */
|
|
|
|
|
dict_index_t* index, /*!< in: clustered index */
|
MDEV-20950 Reduce size of record offsets
offset_t: this is a type which represents one record offset.
It's unsigned short int.
a lot of functions: replace ulint with offset_t
btr_pcur_restore_position_func(),
page_validate(),
row_ins_scan_sec_index_for_duplicate(),
row_upd_clust_rec_by_insert_inherit_func(),
row_vers_impl_x_locked_low(),
trx_undo_prev_version_build():
allocate record offsets on the stack instead of waiting for rec_get_offsets()
to allocate it from mem_heap_t. So, reducing memory allocations.
RECORD_OFFSET, INDEX_OFFSET:
now it's less convenient to store pointers in offset_t*
array. One pointer occupies now several offset_t. And those constant are start
indexes into array to places where to store pointer values
REC_OFFS_HEADER_SIZE: adjusted for the new reality
REC_OFFS_NORMAL_SIZE:
increase size from 100 to 300 which means less heap allocations.
And sizeof(offset_t[REC_OFFS_NORMAL_SIZE]) now is 600 bytes which
is smaller than previous 800 bytes.
REC_OFFS_SEC_INDEX_SIZE: adjusted for the new reality
rem0rec.h, rem0rec.ic, rem0rec.cc:
various arguments, return values and local variables types were changed to
fix numerous integer conversions issues.
enum field_type_t:
offset types concept was introduces which replaces old offset flags stuff.
Like in earlier version, 2 upper bits are used to store offset type.
And this enum represents those types.
REC_OFFS_SQL_NULL, REC_OFFS_MASK: removed
get_type(), set_type(), get_value(), combine():
these are convenience functions to work with offsets and it's types
rec_offs_base()[0]:
still uses an old scheme with flags REC_OFFS_COMPACT and REC_OFFS_EXTERNAL
rec_offs_base()[i]:
these have type offset_t now. Two upper bits contains type.
2019-11-04 20:30:12 +01:00
|
|
|
offset_t* offsets,/*!< in/out: rec_get_offsets(rec, index) */
|
2014-02-26 19:11:54 +01:00
|
|
|
mem_heap_t* heap, /*!< in: memory heap from which the memory
|
|
|
|
|
needed is allocated */
|
2016-08-12 10:17:45 +02:00
|
|
|
rec_t** old_vers,/*!< out, own: previous version, or NULL if
|
2014-02-26 19:11:54 +01:00
|
|
|
rec is the first inserted version, or if
|
|
|
|
|
history data has been deleted */
|
2016-08-12 10:17:45 +02:00
|
|
|
mem_heap_t* v_heap, /* !< in: memory heap used to create vrow
|
|
|
|
|
dtuple if it is not yet created. This heap
|
|
|
|
|
diffs from "heap" above in that it could be
|
|
|
|
|
prebuilt->old_vers_heap for selection */
|
2019-05-03 15:47:07 +02:00
|
|
|
dtuple_t** vrow, /*!< out: virtual column info, if any */
|
2016-08-12 10:17:45 +02:00
|
|
|
ulint v_status);
|
|
|
|
|
/*!< in: status determine if it is going
|
|
|
|
|
into this function by purge thread or not.
|
|
|
|
|
And if we read "after image" of undo log */
|
|
|
|
|
|
MDEV-15914: Restore MLOG_UNDO_INSERT
trx_undof_page_add_undo_rec_log(): Write the MLOG_UNDO_INSERT
record instead of the equivalent MLOG_2BYTES and MLOG_WRITE_STRING.
This essentially reverts commit 9ee8917dfd4b6c9d342cbc030ca71bad637fa24a.
In MariaDB 10.3, I attempted to simplify the crash recovery code
by making use of lower-level redo log records. It turns out that
we must keep the redo log parsing code in order to allow crash-upgrade
from older MariaDB versions (MDEV-14848).
Now, it further turns out that the InnoDB redo log record format is
suboptimal for logging multiple changes to a single page. This simple
change to the redo logging of undo log significantly affects the
INSERT and UPDATE performance.
Essentially, we wrote
(space_id,page_number,MLOG_2BYTES,2 bytes)
(space_id,page_number,MLOG_WRITE_STRING,N+4 bytes)
instead of the previously written
(space_id,page_number,MLOG_UNDO_INSERT,N+2 bytes)
The added redo log volume caused a single-threaded INSERT
(without innodb_adaptive_hash_index) of
1,000,000 rows to consume 11 seconds instead of 9 seconds,
and a subsequent UPDATE of 30,000,000 rows to consume 64 seconds
instead of 58 seconds. If we omitted all redo logging for the
undo log, the INSERT would consume only 4 seconds.
2018-04-25 12:05:40 +02:00
|
|
|
/** Parse MLOG_UNDO_INSERT.
|
2018-01-03 14:22:52 +01:00
|
|
|
@param[in] ptr log record
|
|
|
|
|
@param[in] end_ptr end of log record buffer
|
|
|
|
|
@param[in,out] page page or NULL
|
|
|
|
|
@return end of log record
|
|
|
|
|
@retval NULL if the log record is incomplete */
|
2019-12-09 16:13:48 +01:00
|
|
|
ATTRIBUTE_COLD /* only used when crash-upgrading */
|
2018-01-03 14:22:52 +01:00
|
|
|
byte*
|
|
|
|
|
trx_undo_parse_add_undo_rec(
|
|
|
|
|
const byte* ptr,
|
|
|
|
|
const byte* end_ptr,
|
|
|
|
|
page_t* page);
|
|
|
|
|
|
2016-08-12 10:17:45 +02:00
|
|
|
/** Read from an undo log record a non-virtual column value.
|
|
|
|
|
@param[in,out] ptr pointer to remaining part of the undo record
|
|
|
|
|
@param[in,out] field stored field
|
|
|
|
|
@param[in,out] len length of the field, or UNIV_SQL_NULL
|
|
|
|
|
@param[in,out] orig_len original length of the locally stored part
|
|
|
|
|
of an externally stored column, or 0
|
|
|
|
|
@return remaining part of undo log record after reading these values */
|
|
|
|
|
byte*
|
|
|
|
|
trx_undo_rec_get_col_val(
|
|
|
|
|
const byte* ptr,
|
|
|
|
|
const byte** field,
|
|
|
|
|
ulint* len,
|
|
|
|
|
ulint* orig_len);
|
|
|
|
|
|
|
|
|
|
/** Read virtual column value from undo log
|
|
|
|
|
@param[in] table the table
|
|
|
|
|
@param[in] ptr undo log pointer
|
|
|
|
|
@param[in,out] row the dtuple to fill
|
MDEV-13795/MDEV-14332 Corruption during online table-rebuilding ALTER when VIRTUAL columns exist
When MySQL 5.7 introduced indexed virtual columns, it introduced
several bugs into the online table-rebuilding ALTER, that is,
the row_log_table_apply() family of functions.
The online_log format that was introduced for online table-rebuilding
ALTER in MySQL 5.6 should be sufficient. Ideally, any indexed virtual
column values would be evaluated based on the log records in the temporary
file. There is no need to log virtual column values.
(For ADD INDEX, that is row_log_apply(), we always must log the values of
the keys, no matter if the columns are virtual.)
Because omitting the virtual column values removes any chance of
row_log_table_apply() working with indexed virtual columns, we
will for now refuse LOCK=NONE in table-rebuilding ALTER operations
when indexes on virtual columns exist. This restriction would be
lifted in MDEV-14341.
innobase_indexed_virtual_exist(): New predicate, to determine if
indexed virtual columns exist in a table definition.
ha_innobase::check_if_supported_inplace_alter(): Refuse online rebuild
if indexed virtual columns exist.
rec_get_converted_size_temp_v(), rec_convert_dtuple_to_temp_v(): Remove.
row_log_table_delete(), row_log_table_update(, row_log_table_insert():
Remove parameters for virtual columns.
trx_undo_read_v_rows(): Remove the col_map parameter.
row_log_table_apply(): Do not deal with virtual columns.
2017-11-09 22:01:44 +01:00
|
|
|
@param[in] in_purge whether this is called by purge */
|
2016-08-12 10:17:45 +02:00
|
|
|
void
|
|
|
|
|
trx_undo_read_v_cols(
|
|
|
|
|
const dict_table_t* table,
|
|
|
|
|
const byte* ptr,
|
2019-05-03 15:47:07 +02:00
|
|
|
dtuple_t* row,
|
MDEV-13795/MDEV-14332 Corruption during online table-rebuilding ALTER when VIRTUAL columns exist
When MySQL 5.7 introduced indexed virtual columns, it introduced
several bugs into the online table-rebuilding ALTER, that is,
the row_log_table_apply() family of functions.
The online_log format that was introduced for online table-rebuilding
ALTER in MySQL 5.6 should be sufficient. Ideally, any indexed virtual
column values would be evaluated based on the log records in the temporary
file. There is no need to log virtual column values.
(For ADD INDEX, that is row_log_apply(), we always must log the values of
the keys, no matter if the columns are virtual.)
Because omitting the virtual column values removes any chance of
row_log_table_apply() working with indexed virtual columns, we
will for now refuse LOCK=NONE in table-rebuilding ALTER operations
when indexes on virtual columns exist. This restriction would be
lifted in MDEV-14341.
innobase_indexed_virtual_exist(): New predicate, to determine if
indexed virtual columns exist in a table definition.
ha_innobase::check_if_supported_inplace_alter(): Refuse online rebuild
if indexed virtual columns exist.
rec_get_converted_size_temp_v(), rec_convert_dtuple_to_temp_v(): Remove.
row_log_table_delete(), row_log_table_update(, row_log_table_insert():
Remove parameters for virtual columns.
trx_undo_read_v_rows(): Remove the col_map parameter.
row_log_table_apply(): Do not deal with virtual columns.
2017-11-09 22:01:44 +01:00
|
|
|
bool in_purge);
|
2016-08-12 10:17:45 +02:00
|
|
|
|
|
|
|
|
/** Read virtual column index from undo log if the undo log contains such
|
|
|
|
|
info, and verify the column is still indexed, and output its position
|
|
|
|
|
@param[in] table the table
|
|
|
|
|
@param[in] ptr undo log pointer
|
|
|
|
|
@param[in] first_v_col if this is the first virtual column, which
|
|
|
|
|
has the version marker
|
2016-09-06 08:43:16 +02:00
|
|
|
@param[in,out] is_undo_log his function is used to parse both undo log,
|
|
|
|
|
and online log for virtual columns. So
|
|
|
|
|
check to see if this is undo log
|
2016-08-12 10:17:45 +02:00
|
|
|
@param[out] field_no the column number
|
|
|
|
|
@return remaining part of undo log record after reading these values */
|
|
|
|
|
const byte*
|
|
|
|
|
trx_undo_read_v_idx(
|
|
|
|
|
const dict_table_t* table,
|
|
|
|
|
const byte* ptr,
|
|
|
|
|
bool first_v_col,
|
2016-09-06 08:43:16 +02:00
|
|
|
bool* is_undo_log,
|
2016-08-12 10:17:45 +02:00
|
|
|
ulint* field_no);
|
|
|
|
|
|
2014-02-26 19:11:54 +01:00
|
|
|
/* Types of an undo log record: these have to be smaller than 16, as the
|
|
|
|
|
compilation info multiplied by 16 is ORed to this value in an undo log
|
|
|
|
|
record */
|
|
|
|
|
|
2017-12-20 21:19:47 +01:00
|
|
|
#define TRX_UNDO_RENAME_TABLE 9 /*!< RENAME TABLE */
|
2018-09-19 08:12:58 +02:00
|
|
|
#define TRX_UNDO_INSERT_METADATA 10 /*!< insert a metadata
|
MDEV-11369 Instant ADD COLUMN for InnoDB
For InnoDB tables, adding, dropping and reordering columns has
required a rebuild of the table and all its indexes. Since MySQL 5.6
(and MariaDB 10.0) this has been supported online (LOCK=NONE), allowing
concurrent modification of the tables.
This work revises the InnoDB ROW_FORMAT=REDUNDANT, ROW_FORMAT=COMPACT
and ROW_FORMAT=DYNAMIC so that columns can be appended instantaneously,
with only minor changes performed to the table structure. The counter
innodb_instant_alter_column in INFORMATION_SCHEMA.GLOBAL_STATUS
is incremented whenever a table rebuild operation is converted into
an instant ADD COLUMN operation.
ROW_FORMAT=COMPRESSED tables will not support instant ADD COLUMN.
Some usability limitations will be addressed in subsequent work:
MDEV-13134 Introduce ALTER TABLE attributes ALGORITHM=NOCOPY
and ALGORITHM=INSTANT
MDEV-14016 Allow instant ADD COLUMN, ADD INDEX, LOCK=NONE
The format of the clustered index (PRIMARY KEY) is changed as follows:
(1) The FIL_PAGE_TYPE of the root page will be FIL_PAGE_TYPE_INSTANT,
and a new field PAGE_INSTANT will contain the original number of fields
in the clustered index ('core' fields).
If instant ADD COLUMN has not been used or the table becomes empty,
or the very first instant ADD COLUMN operation is rolled back,
the fields PAGE_INSTANT and FIL_PAGE_TYPE will be reset
to 0 and FIL_PAGE_INDEX.
(2) A special 'default row' record is inserted into the leftmost leaf,
between the page infimum and the first user record. This record is
distinguished by the REC_INFO_MIN_REC_FLAG, and it is otherwise in the
same format as records that contain values for the instantly added
columns. This 'default row' always has the same number of fields as
the clustered index according to the table definition. The values of
'core' fields are to be ignored. For other fields, the 'default row'
will contain the default values as they were during the ALTER TABLE
statement. (If the column default values are changed later, those
values will only be stored in the .frm file. The 'default row' will
contain the original evaluated values, which must be the same for
every row.) The 'default row' must be completely hidden from
higher-level access routines. Assertions have been added to ensure
that no 'default row' is ever present in the adaptive hash index
or in locked records. The 'default row' is never delete-marked.
(3) In clustered index leaf page records, the number of fields must
reside between the number of 'core' fields (dict_index_t::n_core_fields
introduced in this work) and dict_index_t::n_fields. If the number
of fields is less than dict_index_t::n_fields, the missing fields
are replaced with the column value of the 'default row'.
Note: The number of fields in the record may shrink if some of the
last instantly added columns are updated to the value that is
in the 'default row'. The function btr_cur_trim() implements this
'compression' on update and rollback; dtuple::trim() implements it
on insert.
(4) In ROW_FORMAT=COMPACT and ROW_FORMAT=DYNAMIC records, the new
status value REC_STATUS_COLUMNS_ADDED will indicate the presence of
a new record header that will encode n_fields-n_core_fields-1 in
1 or 2 bytes. (In ROW_FORMAT=REDUNDANT records, the record header
always explicitly encodes the number of fields.)
We introduce the undo log record type TRX_UNDO_INSERT_DEFAULT for
covering the insert of the 'default row' record when instant ADD COLUMN
is used for the first time. Subsequent instant ADD COLUMN can use
TRX_UNDO_UPD_EXIST_REC.
This is joint work with Vin Chen (陈福荣) from Tencent. The design
that was discussed in April 2017 would not have allowed import or
export of data files, because instead of the 'default row' it would
have introduced a data dictionary table. The test
rpl.rpl_alter_instant is exactly as contributed in pull request #408.
The test innodb.instant_alter is based on a contributed test.
The redo log record format changes for ROW_FORMAT=DYNAMIC and
ROW_FORMAT=COMPACT are as contributed. (With this change present,
crash recovery from MariaDB 10.3.1 will fail in spectacular ways!)
Also the semantics of higher-level redo log records that modify the
PAGE_INSTANT field is changed. The redo log format version identifier
was already changed to LOG_HEADER_FORMAT_CURRENT=103 in MariaDB 10.3.1.
Everything else has been rewritten by me. Thanks to Elena Stepanova,
the code has been tested extensively.
When rolling back an instant ADD COLUMN operation, we must empty the
PAGE_FREE list after deleting or shortening the 'default row' record,
by calling either btr_page_empty() or btr_page_reorganize(). We must
know the size of each entry in the PAGE_FREE list. If rollback left a
freed copy of the 'default row' in the PAGE_FREE list, we would be
unable to determine its size (if it is in ROW_FORMAT=COMPACT or
ROW_FORMAT=DYNAMIC) because it would contain more fields than the
rolled-back definition of the clustered index.
UNIV_SQL_DEFAULT: A new special constant that designates an instantly
added column that is not present in the clustered index record.
len_is_stored(): Check if a length is an actual length. There are
two magic length values: UNIV_SQL_DEFAULT, UNIV_SQL_NULL.
dict_col_t::def_val: The 'default row' value of the column. If the
column is not added instantly, def_val.len will be UNIV_SQL_DEFAULT.
dict_col_t: Add the accessors is_virtual(), is_nullable(), is_instant(),
instant_value().
dict_col_t::remove_instant(): Remove the 'instant ADD' status of
a column.
dict_col_t::name(const dict_table_t& table): Replaces
dict_table_get_col_name().
dict_index_t::n_core_fields: The original number of fields.
For secondary indexes and if instant ADD COLUMN has not been used,
this will be equal to dict_index_t::n_fields.
dict_index_t::n_core_null_bytes: Number of bytes needed to
represent the null flags; usually equal to UT_BITS_IN_BYTES(n_nullable).
dict_index_t::NO_CORE_NULL_BYTES: Magic value signalling that
n_core_null_bytes was not initialized yet from the clustered index
root page.
dict_index_t: Add the accessors is_instant(), is_clust(),
get_n_nullable(), instant_field_value().
dict_index_t::instant_add_field(): Adjust clustered index metadata
for instant ADD COLUMN.
dict_index_t::remove_instant(): Remove the 'instant ADD' status
of a clustered index when the table becomes empty, or the very first
instant ADD COLUMN operation is rolled back.
dict_table_t: Add the accessors is_instant(), is_temporary(),
supports_instant().
dict_table_t::instant_add_column(): Adjust metadata for
instant ADD COLUMN.
dict_table_t::rollback_instant(): Adjust metadata on the rollback
of instant ADD COLUMN.
prepare_inplace_alter_table_dict(): First create the ctx->new_table,
and only then decide if the table really needs to be rebuilt.
We must split the creation of table or index metadata from the
creation of the dictionary table records and the creation of
the data. In this way, we can transform a table-rebuilding operation
into an instant ADD COLUMN operation. Dictionary objects will only
be added to cache when table rebuilding or index creation is needed.
The ctx->instant_table will never be added to cache.
dict_table_t::add_to_cache(): Modified and renamed from
dict_table_add_to_cache(). Do not modify the table metadata.
Let the callers invoke dict_table_add_system_columns() and if needed,
set can_be_evicted.
dict_create_sys_tables_tuple(), dict_create_table_step(): Omit the
system columns (which will now exist in the dict_table_t object
already at this point).
dict_create_table_step(): Expect the callers to invoke
dict_table_add_system_columns().
pars_create_table(): Before creating the table creation execution
graph, invoke dict_table_add_system_columns().
row_create_table_for_mysql(): Expect all callers to invoke
dict_table_add_system_columns().
create_index_dict(): Replaces row_merge_create_index_graph().
innodb_update_n_cols(): Renamed from innobase_update_n_virtual().
Call my_error() if an error occurs.
btr_cur_instant_init(), btr_cur_instant_init_low(),
btr_cur_instant_root_init():
Load additional metadata from the clustered index and set
dict_index_t::n_core_null_bytes. This is invoked
when table metadata is first loaded into the data dictionary.
dict_boot(): Initialize n_core_null_bytes for the four hard-coded
dictionary tables.
dict_create_index_step(): Initialize n_core_null_bytes. This is
executed as part of CREATE TABLE.
dict_index_build_internal_clust(): Initialize n_core_null_bytes to
NO_CORE_NULL_BYTES if table->supports_instant().
row_create_index_for_mysql(): Initialize n_core_null_bytes for
CREATE TEMPORARY TABLE.
commit_cache_norebuild(): Call the code to rename or enlarge columns
in the cache only if instant ADD COLUMN is not being used.
(Instant ADD COLUMN would copy all column metadata from
instant_table to old_table, including the names and lengths.)
PAGE_INSTANT: A new 13-bit field for storing dict_index_t::n_core_fields.
This is repurposing the 16-bit field PAGE_DIRECTION, of which only the
least significant 3 bits were used. The original byte containing
PAGE_DIRECTION will be accessible via the new constant PAGE_DIRECTION_B.
page_get_instant(), page_set_instant(): Accessors for the PAGE_INSTANT.
page_ptr_get_direction(), page_get_direction(),
page_ptr_set_direction(): Accessors for PAGE_DIRECTION.
page_direction_reset(): Reset PAGE_DIRECTION, PAGE_N_DIRECTION.
page_direction_increment(): Increment PAGE_N_DIRECTION
and set PAGE_DIRECTION.
rec_get_offsets(): Use the 'leaf' parameter for non-debug purposes,
and assume that heap_no is always set.
Initialize all dict_index_t::n_fields for ROW_FORMAT=REDUNDANT records,
even if the record contains fewer fields.
rec_offs_make_valid(): Add the parameter 'leaf'.
rec_copy_prefix_to_dtuple(): Assert that the tuple is only built
on the core fields. Instant ADD COLUMN only applies to the
clustered index, and we should never build a search key that has
more than the PRIMARY KEY and possibly DB_TRX_ID,DB_ROLL_PTR.
All these columns are always present.
dict_index_build_data_tuple(): Remove assertions that would be
duplicated in rec_copy_prefix_to_dtuple().
rec_init_offsets(): Support ROW_FORMAT=REDUNDANT records whose
number of fields is between n_core_fields and n_fields.
cmp_rec_rec_with_match(): Implement the comparison between two
MIN_REC_FLAG records.
trx_t::in_rollback: Make the field available in non-debug builds.
trx_start_for_ddl_low(): Remove dangerous error-tolerance.
A dictionary transaction must be flagged as such before it has generated
any undo log records. This is because trx_undo_assign_undo() will mark
the transaction as a dictionary transaction in the undo log header
right before the very first undo log record is being written.
btr_index_rec_validate(): Account for instant ADD COLUMN
row_undo_ins_remove_clust_rec(): On the rollback of an insert into
SYS_COLUMNS, revert instant ADD COLUMN in the cache by removing the
last column from the table and the clustered index.
row_search_on_row_ref(), row_undo_mod_parse_undo_rec(), row_undo_mod(),
trx_undo_update_rec_get_update(): Handle the 'default row'
as a special case.
dtuple_t::trim(index): Omit a redundant suffix of an index tuple right
before insert or update. After instant ADD COLUMN, if the last fields
of a clustered index tuple match the 'default row', there is no
need to store them. While trimming the entry, we must hold a page latch,
so that the table cannot be emptied and the 'default row' be deleted.
btr_cur_optimistic_update(), btr_cur_pessimistic_update(),
row_upd_clust_rec_by_insert(), row_ins_clust_index_entry_low():
Invoke dtuple_t::trim() if needed.
row_ins_clust_index_entry(): Restore dtuple_t::n_fields after calling
row_ins_clust_index_entry_low().
rec_get_converted_size(), rec_get_converted_size_comp(): Allow the number
of fields to be between n_core_fields and n_fields. Do not support
infimum,supremum. They are never supposed to be stored in dtuple_t,
because page creation nowadays uses a lower-level method for initializing
them.
rec_convert_dtuple_to_rec_comp(): Assign the status bits based on the
number of fields.
btr_cur_trim(): In an update, trim the index entry as needed. For the
'default row', handle rollback specially. For user records, omit
fields that match the 'default row'.
btr_cur_optimistic_delete_func(), btr_cur_pessimistic_delete():
Skip locking and adaptive hash index for the 'default row'.
row_log_table_apply_convert_mrec(): Replace 'default row' values if needed.
In the temporary file that is applied by row_log_table_apply(),
we must identify whether the records contain the extra header for
instantly added columns. For now, we will allocate an additional byte
for this for ROW_T_INSERT and ROW_T_UPDATE records when the source table
has been subject to instant ADD COLUMN. The ROW_T_DELETE records are
fine, as they will be converted and will only contain 'core' columns
(PRIMARY KEY and some system columns) that are converted from dtuple_t.
rec_get_converted_size_temp(), rec_init_offsets_temp(),
rec_convert_dtuple_to_temp(): Add the parameter 'status'.
REC_INFO_DEFAULT_ROW = REC_INFO_MIN_REC_FLAG | REC_STATUS_COLUMNS_ADDED:
An info_bits constant for distinguishing the 'default row' record.
rec_comp_status_t: An enum of the status bit values.
rec_leaf_format: An enum that replaces the bool parameter of
rec_init_offsets_comp_ordinary().
2017-10-06 06:00:05 +02:00
|
|
|
pseudo-record for instant ALTER */
|
2014-02-26 19:11:54 +01:00
|
|
|
#define TRX_UNDO_INSERT_REC 11 /* fresh insert into clustered index */
|
|
|
|
|
#define TRX_UNDO_UPD_EXIST_REC 12 /* update of a non-delete-marked
|
|
|
|
|
record */
|
|
|
|
|
#define TRX_UNDO_UPD_DEL_REC 13 /* update of a delete marked record to
|
|
|
|
|
a not delete marked record; also the
|
|
|
|
|
fields of the record can change */
|
|
|
|
|
#define TRX_UNDO_DEL_MARK_REC 14 /* delete marking of a record; fields
|
|
|
|
|
do not change */
|
2017-03-01 07:27:39 +01:00
|
|
|
#define TRX_UNDO_CMPL_INFO_MULT 16U /* compilation info is multiplied by
|
2014-02-26 19:11:54 +01:00
|
|
|
this and ORed to the type above */
|
2017-03-01 07:27:39 +01:00
|
|
|
#define TRX_UNDO_UPD_EXTERN 128U /* This bit can be ORed to type_cmpl
|
2014-02-26 19:11:54 +01:00
|
|
|
to denote that we updated external
|
|
|
|
|
storage fields: used by purge to
|
|
|
|
|
free the external storage */
|
|
|
|
|
|
2018-09-19 08:12:58 +02:00
|
|
|
/** The search tuple corresponding to TRX_UNDO_INSERT_METADATA */
|
|
|
|
|
extern const dtuple_t trx_undo_metadata;
|
MDEV-11369 Instant ADD COLUMN for InnoDB
For InnoDB tables, adding, dropping and reordering columns has
required a rebuild of the table and all its indexes. Since MySQL 5.6
(and MariaDB 10.0) this has been supported online (LOCK=NONE), allowing
concurrent modification of the tables.
This work revises the InnoDB ROW_FORMAT=REDUNDANT, ROW_FORMAT=COMPACT
and ROW_FORMAT=DYNAMIC so that columns can be appended instantaneously,
with only minor changes performed to the table structure. The counter
innodb_instant_alter_column in INFORMATION_SCHEMA.GLOBAL_STATUS
is incremented whenever a table rebuild operation is converted into
an instant ADD COLUMN operation.
ROW_FORMAT=COMPRESSED tables will not support instant ADD COLUMN.
Some usability limitations will be addressed in subsequent work:
MDEV-13134 Introduce ALTER TABLE attributes ALGORITHM=NOCOPY
and ALGORITHM=INSTANT
MDEV-14016 Allow instant ADD COLUMN, ADD INDEX, LOCK=NONE
The format of the clustered index (PRIMARY KEY) is changed as follows:
(1) The FIL_PAGE_TYPE of the root page will be FIL_PAGE_TYPE_INSTANT,
and a new field PAGE_INSTANT will contain the original number of fields
in the clustered index ('core' fields).
If instant ADD COLUMN has not been used or the table becomes empty,
or the very first instant ADD COLUMN operation is rolled back,
the fields PAGE_INSTANT and FIL_PAGE_TYPE will be reset
to 0 and FIL_PAGE_INDEX.
(2) A special 'default row' record is inserted into the leftmost leaf,
between the page infimum and the first user record. This record is
distinguished by the REC_INFO_MIN_REC_FLAG, and it is otherwise in the
same format as records that contain values for the instantly added
columns. This 'default row' always has the same number of fields as
the clustered index according to the table definition. The values of
'core' fields are to be ignored. For other fields, the 'default row'
will contain the default values as they were during the ALTER TABLE
statement. (If the column default values are changed later, those
values will only be stored in the .frm file. The 'default row' will
contain the original evaluated values, which must be the same for
every row.) The 'default row' must be completely hidden from
higher-level access routines. Assertions have been added to ensure
that no 'default row' is ever present in the adaptive hash index
or in locked records. The 'default row' is never delete-marked.
(3) In clustered index leaf page records, the number of fields must
reside between the number of 'core' fields (dict_index_t::n_core_fields
introduced in this work) and dict_index_t::n_fields. If the number
of fields is less than dict_index_t::n_fields, the missing fields
are replaced with the column value of the 'default row'.
Note: The number of fields in the record may shrink if some of the
last instantly added columns are updated to the value that is
in the 'default row'. The function btr_cur_trim() implements this
'compression' on update and rollback; dtuple::trim() implements it
on insert.
(4) In ROW_FORMAT=COMPACT and ROW_FORMAT=DYNAMIC records, the new
status value REC_STATUS_COLUMNS_ADDED will indicate the presence of
a new record header that will encode n_fields-n_core_fields-1 in
1 or 2 bytes. (In ROW_FORMAT=REDUNDANT records, the record header
always explicitly encodes the number of fields.)
We introduce the undo log record type TRX_UNDO_INSERT_DEFAULT for
covering the insert of the 'default row' record when instant ADD COLUMN
is used for the first time. Subsequent instant ADD COLUMN can use
TRX_UNDO_UPD_EXIST_REC.
This is joint work with Vin Chen (陈福荣) from Tencent. The design
that was discussed in April 2017 would not have allowed import or
export of data files, because instead of the 'default row' it would
have introduced a data dictionary table. The test
rpl.rpl_alter_instant is exactly as contributed in pull request #408.
The test innodb.instant_alter is based on a contributed test.
The redo log record format changes for ROW_FORMAT=DYNAMIC and
ROW_FORMAT=COMPACT are as contributed. (With this change present,
crash recovery from MariaDB 10.3.1 will fail in spectacular ways!)
Also the semantics of higher-level redo log records that modify the
PAGE_INSTANT field is changed. The redo log format version identifier
was already changed to LOG_HEADER_FORMAT_CURRENT=103 in MariaDB 10.3.1.
Everything else has been rewritten by me. Thanks to Elena Stepanova,
the code has been tested extensively.
When rolling back an instant ADD COLUMN operation, we must empty the
PAGE_FREE list after deleting or shortening the 'default row' record,
by calling either btr_page_empty() or btr_page_reorganize(). We must
know the size of each entry in the PAGE_FREE list. If rollback left a
freed copy of the 'default row' in the PAGE_FREE list, we would be
unable to determine its size (if it is in ROW_FORMAT=COMPACT or
ROW_FORMAT=DYNAMIC) because it would contain more fields than the
rolled-back definition of the clustered index.
UNIV_SQL_DEFAULT: A new special constant that designates an instantly
added column that is not present in the clustered index record.
len_is_stored(): Check if a length is an actual length. There are
two magic length values: UNIV_SQL_DEFAULT, UNIV_SQL_NULL.
dict_col_t::def_val: The 'default row' value of the column. If the
column is not added instantly, def_val.len will be UNIV_SQL_DEFAULT.
dict_col_t: Add the accessors is_virtual(), is_nullable(), is_instant(),
instant_value().
dict_col_t::remove_instant(): Remove the 'instant ADD' status of
a column.
dict_col_t::name(const dict_table_t& table): Replaces
dict_table_get_col_name().
dict_index_t::n_core_fields: The original number of fields.
For secondary indexes and if instant ADD COLUMN has not been used,
this will be equal to dict_index_t::n_fields.
dict_index_t::n_core_null_bytes: Number of bytes needed to
represent the null flags; usually equal to UT_BITS_IN_BYTES(n_nullable).
dict_index_t::NO_CORE_NULL_BYTES: Magic value signalling that
n_core_null_bytes was not initialized yet from the clustered index
root page.
dict_index_t: Add the accessors is_instant(), is_clust(),
get_n_nullable(), instant_field_value().
dict_index_t::instant_add_field(): Adjust clustered index metadata
for instant ADD COLUMN.
dict_index_t::remove_instant(): Remove the 'instant ADD' status
of a clustered index when the table becomes empty, or the very first
instant ADD COLUMN operation is rolled back.
dict_table_t: Add the accessors is_instant(), is_temporary(),
supports_instant().
dict_table_t::instant_add_column(): Adjust metadata for
instant ADD COLUMN.
dict_table_t::rollback_instant(): Adjust metadata on the rollback
of instant ADD COLUMN.
prepare_inplace_alter_table_dict(): First create the ctx->new_table,
and only then decide if the table really needs to be rebuilt.
We must split the creation of table or index metadata from the
creation of the dictionary table records and the creation of
the data. In this way, we can transform a table-rebuilding operation
into an instant ADD COLUMN operation. Dictionary objects will only
be added to cache when table rebuilding or index creation is needed.
The ctx->instant_table will never be added to cache.
dict_table_t::add_to_cache(): Modified and renamed from
dict_table_add_to_cache(). Do not modify the table metadata.
Let the callers invoke dict_table_add_system_columns() and if needed,
set can_be_evicted.
dict_create_sys_tables_tuple(), dict_create_table_step(): Omit the
system columns (which will now exist in the dict_table_t object
already at this point).
dict_create_table_step(): Expect the callers to invoke
dict_table_add_system_columns().
pars_create_table(): Before creating the table creation execution
graph, invoke dict_table_add_system_columns().
row_create_table_for_mysql(): Expect all callers to invoke
dict_table_add_system_columns().
create_index_dict(): Replaces row_merge_create_index_graph().
innodb_update_n_cols(): Renamed from innobase_update_n_virtual().
Call my_error() if an error occurs.
btr_cur_instant_init(), btr_cur_instant_init_low(),
btr_cur_instant_root_init():
Load additional metadata from the clustered index and set
dict_index_t::n_core_null_bytes. This is invoked
when table metadata is first loaded into the data dictionary.
dict_boot(): Initialize n_core_null_bytes for the four hard-coded
dictionary tables.
dict_create_index_step(): Initialize n_core_null_bytes. This is
executed as part of CREATE TABLE.
dict_index_build_internal_clust(): Initialize n_core_null_bytes to
NO_CORE_NULL_BYTES if table->supports_instant().
row_create_index_for_mysql(): Initialize n_core_null_bytes for
CREATE TEMPORARY TABLE.
commit_cache_norebuild(): Call the code to rename or enlarge columns
in the cache only if instant ADD COLUMN is not being used.
(Instant ADD COLUMN would copy all column metadata from
instant_table to old_table, including the names and lengths.)
PAGE_INSTANT: A new 13-bit field for storing dict_index_t::n_core_fields.
This is repurposing the 16-bit field PAGE_DIRECTION, of which only the
least significant 3 bits were used. The original byte containing
PAGE_DIRECTION will be accessible via the new constant PAGE_DIRECTION_B.
page_get_instant(), page_set_instant(): Accessors for the PAGE_INSTANT.
page_ptr_get_direction(), page_get_direction(),
page_ptr_set_direction(): Accessors for PAGE_DIRECTION.
page_direction_reset(): Reset PAGE_DIRECTION, PAGE_N_DIRECTION.
page_direction_increment(): Increment PAGE_N_DIRECTION
and set PAGE_DIRECTION.
rec_get_offsets(): Use the 'leaf' parameter for non-debug purposes,
and assume that heap_no is always set.
Initialize all dict_index_t::n_fields for ROW_FORMAT=REDUNDANT records,
even if the record contains fewer fields.
rec_offs_make_valid(): Add the parameter 'leaf'.
rec_copy_prefix_to_dtuple(): Assert that the tuple is only built
on the core fields. Instant ADD COLUMN only applies to the
clustered index, and we should never build a search key that has
more than the PRIMARY KEY and possibly DB_TRX_ID,DB_ROLL_PTR.
All these columns are always present.
dict_index_build_data_tuple(): Remove assertions that would be
duplicated in rec_copy_prefix_to_dtuple().
rec_init_offsets(): Support ROW_FORMAT=REDUNDANT records whose
number of fields is between n_core_fields and n_fields.
cmp_rec_rec_with_match(): Implement the comparison between two
MIN_REC_FLAG records.
trx_t::in_rollback: Make the field available in non-debug builds.
trx_start_for_ddl_low(): Remove dangerous error-tolerance.
A dictionary transaction must be flagged as such before it has generated
any undo log records. This is because trx_undo_assign_undo() will mark
the transaction as a dictionary transaction in the undo log header
right before the very first undo log record is being written.
btr_index_rec_validate(): Account for instant ADD COLUMN
row_undo_ins_remove_clust_rec(): On the rollback of an insert into
SYS_COLUMNS, revert instant ADD COLUMN in the cache by removing the
last column from the table and the clustered index.
row_search_on_row_ref(), row_undo_mod_parse_undo_rec(), row_undo_mod(),
trx_undo_update_rec_get_update(): Handle the 'default row'
as a special case.
dtuple_t::trim(index): Omit a redundant suffix of an index tuple right
before insert or update. After instant ADD COLUMN, if the last fields
of a clustered index tuple match the 'default row', there is no
need to store them. While trimming the entry, we must hold a page latch,
so that the table cannot be emptied and the 'default row' be deleted.
btr_cur_optimistic_update(), btr_cur_pessimistic_update(),
row_upd_clust_rec_by_insert(), row_ins_clust_index_entry_low():
Invoke dtuple_t::trim() if needed.
row_ins_clust_index_entry(): Restore dtuple_t::n_fields after calling
row_ins_clust_index_entry_low().
rec_get_converted_size(), rec_get_converted_size_comp(): Allow the number
of fields to be between n_core_fields and n_fields. Do not support
infimum,supremum. They are never supposed to be stored in dtuple_t,
because page creation nowadays uses a lower-level method for initializing
them.
rec_convert_dtuple_to_rec_comp(): Assign the status bits based on the
number of fields.
btr_cur_trim(): In an update, trim the index entry as needed. For the
'default row', handle rollback specially. For user records, omit
fields that match the 'default row'.
btr_cur_optimistic_delete_func(), btr_cur_pessimistic_delete():
Skip locking and adaptive hash index for the 'default row'.
row_log_table_apply_convert_mrec(): Replace 'default row' values if needed.
In the temporary file that is applied by row_log_table_apply(),
we must identify whether the records contain the extra header for
instantly added columns. For now, we will allocate an additional byte
for this for ROW_T_INSERT and ROW_T_UPDATE records when the source table
has been subject to instant ADD COLUMN. The ROW_T_DELETE records are
fine, as they will be converted and will only contain 'core' columns
(PRIMARY KEY and some system columns) that are converted from dtuple_t.
rec_get_converted_size_temp(), rec_init_offsets_temp(),
rec_convert_dtuple_to_temp(): Add the parameter 'status'.
REC_INFO_DEFAULT_ROW = REC_INFO_MIN_REC_FLAG | REC_STATUS_COLUMNS_ADDED:
An info_bits constant for distinguishing the 'default row' record.
rec_comp_status_t: An enum of the status bit values.
rec_leaf_format: An enum that replaces the bool parameter of
rec_init_offsets_comp_ordinary().
2017-10-06 06:00:05 +02:00
|
|
|
|
MDEV-16678 Prefer MDL to dict_sys.latch for innodb background tasks
This is joint work with Thirunarayanan Balathandayuthapani.
The MDL interface between InnoDB and the rest of the server
(in storage/innobase/dict/dict0dict.cc and in include/)
is my work, while most everything else is Thiru's.
The collection of InnoDB persistent statistics and the
defragmentation were not refactored to use MDL. They will
keep relying on lower-level interlocking with
fil_check_pending_operations().
The purge of transaction history and the background operations on
fulltext indexes will use MDL. We will revert
commit 2c4844c9e76427525e8c39a2d72686085efe89c3
(MDEV-17813) because thanks to MDL, purge cannot conflict
with DDL operations anymore. For a similar reason, we will remove
the MDEV-16222 test case from gcol.innodb_virtual_debug_purge.
Purge is essentially replacing all use of the global dict_sys.latch
with MDL. Purge will skip the undo log records for tables whose names
start with #sql-ib or #sql2. Theoretically, such tables might
be renamed back to visible table names if TRUNCATE fails to
create a new table, or the final rename in ALTER TABLE...ALGORITHM=COPY
fails. In that case, purge could permanently leave some garbage
in the table. Such garbage will be tolerated; the table would not
be considered corrupted.
To avoid repeated MDL releases and acquisitions,
trx_purge_attach_undo_recs() will sort undo log records by table_id,
and purge_node_t will keep the MDL and table handle open for multiple
successive undo log records.
get_purge_table(): A new accessor, used during the purge of
history for indexed virtual columns. This interface should ideally
not exist at all.
thd_mdl_context(): Accessor of THD::mdl_context.
Wrapped in a new thd_mdl_service.
dict_get_db_name_len(): Define inline.
dict_acquire_mdl_shared(): Acquire explicit shared MDL on a table name
if needed.
dict_table_open_on_id(): Return MDL_ticket, if requested.
dict_table_close(): Release MDL ticket, if requested.
dict_fts_index_syncing(), dict_index_t::index_fts_syncing: Remove.
row_drop_table_for_mysql() no longer needs to check these, because
MDL guarantees that a fulltext index sync will not be in progress
while MDL_EXCLUSIVE is protecting a DDL operation.
dict_table_t::parse_name(): Parse the table name for acquiring MDL.
purge_node_t::undo_recs: Change the type to std::list<trx_purge_rec_t*>
(different container, and storing also roll_ptr).
purge_node_t: Add mdl_ticket, last_table_id, purge_thd, mdl_hold_recs
for acquiring MDL and for keeping the table open across multiple
undo log records.
purge_vcol_info_t, row_purge_store_vsec_cur(), row_purge_restore_vsec_cur():
Remove. We will acquire the MDL earlier.
purge_sys_t::heap: Added, for reading undo log records.
fts_sync_during_ddl(): Invoked during ALGORITHM=INPLACE operations
to ensure that fts_sync_table() will not conflict with MDL_EXCLUSIVE.
Uses fts_t::sync_message for bookkeeping.
2019-12-10 14:42:50 +01:00
|
|
|
/** Read the table id from an undo log record.
|
|
|
|
|
@param[in] rec Undo log record
|
|
|
|
|
@return table id stored as a part of undo log record */
|
|
|
|
|
inline table_id_t trx_undo_rec_get_table_id(const trx_undo_rec_t *rec)
|
|
|
|
|
{
|
|
|
|
|
rec+= 3;
|
|
|
|
|
mach_read_next_much_compressed(&rec);
|
|
|
|
|
return mach_read_next_much_compressed(&rec);
|
|
|
|
|
}
|
|
|
|
|
|
2014-02-26 19:11:54 +01:00
|
|
|
#include "trx0rec.ic"
|
|
|
|
|
|
|
|
|
|
#endif /* trx0rec_h */
|