mirror of
https://github.com/MariaDB/server.git
synced 2025-01-16 20:12:31 +01:00
2fcff8988a
command-line" and BUG#34062 "Maria table corruption on master". Use 5 bytes (instead of 4) to store page's number in the checkpoint record, to allow bigger table (1PB with maria-block-size=1kB). Help pushbuild not run out of memory by moving the portion of maria-recovery.test which generates lots of data into a -big.test. mysql-test/r/maria-recovery.result: result moved mysql-test/t/maria-recovery.test: piece which generates much data moved to maria-recovery-big.test mysys/my_pread.c: To fix BUG#34062, where a 1.1TB file was generated due to a wrong pwrite offset, it was useful to not lose precision on 'offset' in DBUG_PRINT, so that the crazy value is visible. mysys/my_read.c: To fix BUG#34062, where a 1.1TB file was generated due to a wrong pwrite offset, it was useful to not lose precision on 'offset' in DBUG_PRINT, so that the crazy value is visible. mysys/my_write.c: To fix BUG#34062, where a 1.1TB file was generated due to a wrong pwrite offset, it was useful to not lose precision on 'offset' in DBUG_PRINT, so that the crazy value is visible. storage/maria/ha_maria.cc: When starting a bulk insert, we throw away dirty index pages from the cache. Unique (non disabled) key insertions thus read out-of-date pages from the disk leading to BUG#34062 "Maria table corruption on master": a DELETE in procedure viewer_sp() had deleted all rows of viewer_tbl2 one by one, putting index page 1 into key_del; that page was thrown away at start of INSERT SELECT, then the INSERT SELECT needed a page to insert keys, looked at key_del, found 1, read page 1 from disk, and its out-of-date content was used to set the new value of key_del (crazy value of 1TB), then a later insertion needed another index page, tried to read page at this crazy offset and failed, leading to corruption mark. The fix is to destroy out-of-date pages and make the state consistent with that, i.e. call maria_delete_all_rows(). storage/maria/ma_blockrec.c: Special hook for UNDO_BULK_INSERT storage/maria/ma_blockrec.h: special hook for UNDO_BULK_INSERT storage/maria/ma_check.c: Fix for BUG#34114 "maria_chk reports false error when several tables on command-line": if the Nth (on the command line) table was BLOCK_RECORD it would start checks by using the param->record_checksum computed by checks of table N-1. storage/maria/ma_delete_all.c: comment storage/maria/ma_loghandler.c: special hook for UNDO_BULK_INSERT storage/maria/ma_page.c: comment storage/maria/ma_pagecache.c: page number is 5 bytes in checkpoint record now (allows bigger tables) storage/maria/ma_recovery.c: page number is 5 bytes in checkpoint record now storage/maria/ma_recovery_util.c: page number is 5 bytes now storage/maria/ma_write.c: typo mysql-test/r/maria-recovery-big.result: result is correct mysql-test/t/maria-recovery-big-master.opt: usual options for recovery tests mysql-test/t/maria-recovery-big.test: Moving out the big blob test to a -big test (it exhausts memory when using /dev/shm on certain machines)
173 lines
5.4 KiB
C
173 lines
5.4 KiB
C
/* Copyright (C) 2006 MySQL AB & MySQL Finland AB & TCX DataKonsult AB
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; version 2 of the License.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program; if not, write to the Free Software
|
|
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
|
|
|
|
/* Remove all rows from a MARIA table */
|
|
/* This clears the status information and truncates files */
|
|
|
|
#include "maria_def.h"
|
|
#include "trnman.h"
|
|
|
|
/**
|
|
@brief deletes all rows from a table
|
|
|
|
@param info Maria handler
|
|
|
|
@note It is important that this function does not rely on the state
|
|
information, as it may be called by ma_apply_undo_bulk_insert() on an
|
|
inconsistent table left by a crash.
|
|
|
|
@return Operation status
|
|
@retval 0 ok
|
|
@retval 1 error
|
|
*/
|
|
|
|
int maria_delete_all_rows(MARIA_HA *info)
|
|
{
|
|
MARIA_SHARE *share= info->s;
|
|
my_bool log_record;
|
|
LSN lsn;
|
|
DBUG_ENTER("maria_delete_all_rows");
|
|
|
|
if (share->options & HA_OPTION_READ_ONLY_DATA)
|
|
{
|
|
DBUG_RETURN(my_errno=EACCES);
|
|
}
|
|
/**
|
|
@todo LOCK take X-lock on table here.
|
|
When we have versioning, if some other thread is looking at this table,
|
|
we cannot shrink the file like this.
|
|
*/
|
|
if (_ma_readinfo(info,F_WRLCK,1))
|
|
DBUG_RETURN(my_errno);
|
|
log_record= share->now_transactional && !share->temporary;
|
|
if (_ma_mark_file_changed(info))
|
|
goto err;
|
|
|
|
if (log_record)
|
|
{
|
|
/*
|
|
This record will be used by Recovery to finish the deletion if it
|
|
crashed. We force it to have a complete history in the log.
|
|
*/
|
|
LEX_STRING log_array[TRANSLOG_INTERNAL_PARTS + 1];
|
|
uchar log_data[FILEID_STORE_SIZE];
|
|
log_array[TRANSLOG_INTERNAL_PARTS + 0].str= (char*) log_data;
|
|
log_array[TRANSLOG_INTERNAL_PARTS + 0].length= sizeof(log_data);
|
|
if (unlikely(translog_write_record(&lsn, LOGREC_REDO_DELETE_ALL,
|
|
info->trn, info, 0,
|
|
sizeof(log_array)/sizeof(log_array[0]),
|
|
log_array, log_data, NULL) ||
|
|
translog_flush(lsn)))
|
|
goto err;
|
|
/*
|
|
If we fail in this function after this point, log and table will be
|
|
inconsistent.
|
|
*/
|
|
}
|
|
else
|
|
{
|
|
/* Other branch called function below when writing log record, in hook */
|
|
_ma_reset_status(info);
|
|
}
|
|
|
|
/*
|
|
If we are using delayed keys or if the user has done changes to the tables
|
|
since it was locked then there may be key blocks in the page cache. Or
|
|
there may be data blocks there. We need to throw them away or they may
|
|
re-enter the emptied table or another table later.
|
|
*/
|
|
if (_ma_flush_table_files(info, MARIA_FLUSH_DATA|MARIA_FLUSH_INDEX,
|
|
FLUSH_IGNORE_CHANGED, FLUSH_IGNORE_CHANGED) ||
|
|
my_chsize(info->dfile.file, 0, 0, MYF(MY_WME)) ||
|
|
my_chsize(share->kfile.file, share->base.keystart, 0, MYF(MY_WME)) )
|
|
goto err;
|
|
|
|
if (_ma_initialize_data_file(share, info->dfile.file))
|
|
goto err;
|
|
|
|
|
|
if (log_record)
|
|
{
|
|
/*
|
|
Because LOGREC_REDO_DELETE_ALL does not operate on pages, it has the
|
|
following problem:
|
|
delete_all; inserts (redo_insert); all pages get flushed; checkpoint:
|
|
the dirty pages list will be empty. In recovery, delete_all is executed,
|
|
but redo_insert are skipped (dirty pages list is empty).
|
|
To avoid this, we need to set skip_redo_lsn now, and thus need to sync
|
|
files.
|
|
*/
|
|
my_bool error= _ma_state_info_write(share, 1|4) ||
|
|
_ma_update_state_lsns(share, lsn, FALSE, FALSE) ||
|
|
_ma_sync_table_files(info);
|
|
info->trn->rec_lsn= LSN_IMPOSSIBLE;
|
|
if (error)
|
|
goto err;
|
|
}
|
|
|
|
VOID(_ma_writeinfo(info,WRITEINFO_UPDATE_KEYFILE));
|
|
#ifdef HAVE_MMAP
|
|
/* Resize mmaped area */
|
|
rw_wrlock(&info->s->mmap_lock);
|
|
_ma_remap_file(info, (my_off_t)0);
|
|
rw_unlock(&info->s->mmap_lock);
|
|
#endif
|
|
allow_break(); /* Allow SIGHUP & SIGINT */
|
|
DBUG_RETURN(0);
|
|
|
|
err:
|
|
{
|
|
int save_errno=my_errno;
|
|
VOID(_ma_writeinfo(info,WRITEINFO_UPDATE_KEYFILE));
|
|
info->update|=HA_STATE_WRITTEN; /* Buffer changed */
|
|
allow_break(); /* Allow SIGHUP & SIGINT */
|
|
DBUG_RETURN(my_errno=save_errno);
|
|
}
|
|
} /* maria_delete_all_rows */
|
|
|
|
|
|
/*
|
|
Reset status information
|
|
|
|
SYNOPSIS
|
|
_ma_reset_status()
|
|
maria Maria handler
|
|
|
|
DESCRIPTION
|
|
Resets data and index file information as if the file would be empty
|
|
Files are not touched.
|
|
*/
|
|
|
|
void _ma_reset_status(MARIA_HA *info)
|
|
{
|
|
MARIA_SHARE *share= info->s;
|
|
MARIA_STATE_INFO *state= &share->state;
|
|
uint i;
|
|
|
|
info->state->records= info->state->del= state->split= 0;
|
|
state->changed= 0; /* File is optimized */
|
|
state->dellink= HA_OFFSET_ERROR;
|
|
state->sortkey= (ushort) ~0;
|
|
info->state->key_file_length= share->base.keystart;
|
|
info->state->data_file_length= 0;
|
|
info->state->empty= info->state->key_empty= 0;
|
|
info->state->checksum= 0;
|
|
|
|
/* Drop the delete key chain. */
|
|
state->key_del= HA_OFFSET_ERROR;
|
|
/* Clear all keys */
|
|
for (i=0 ; i < share->base.keys ; i++)
|
|
state->key_root[i]= HA_OFFSET_ERROR;
|
|
}
|