mariadb/storage/maria/ma_update.c
Michael Widenius 6db663d614 Fixes for Aria storage engine:
- Fixed bug lp:624099 ma_close.c:75: maria_close: Assertion `share->in_trans == 0' failed on UNLOCK TABLES
- Fixed bug that caused table to be marked as not closed (crashed) during recovery testing.
- Use maria_delete_table_files() instead of maria_delete_table() to delete tempoary tables (faster and safer)
- Added checks to ensure that bitmap and internal mutex are always taken in right order.
- For transactional tables, only mark the table as changed before page for table is to be written to disk (and thus the log is flushed).
  This speeds up things a bit and fixes a problem where open_count was incremented on disk but there was no log entry to fix it during recovery -> table was crashed.
- Fixed a bug in repair() where table was not automaticly repaired.
- Ensure that state->global_changed, share->changed and share->state.open_count are set and reset properly.
- Added option --ignore-control-file to maria_chk to be able to run maria_chk even if the control file is locked.


mysql-test/suite/maria/r/maria-recover.result:
  Test result changed as we now force checkpoint before copying table, which results in pagecache getting flushed and we have more rows to recover.
mysql-test/suite/maria/r/maria.result:
  Added new tests
mysql-test/suite/maria/t/maria-recover.test:
  Force checkpoint before copying table.
  This is needed as now the open-count is increased first when first page is flushed.
mysql-test/suite/maria/t/maria.test:
  Added tests to verify fix for lp:624099
storage/maria/ha_maria.cc:
  Use table->in_use instead of current_thd (trivial optimization)
  Use maria_delete_table_files() instead of maria_delete_table() to delete tempoary tables (faster and safer)
  More DBUG_ASSERT()
  Reset locked tables count after locked tables have been moved to new transaction. This fixed lp:624099
storage/maria/ma_bitmap.c:
  Temporarly unlock bitmap mutex when calling _ma_mark_file_changed() and pagecache_delete_pages() to ensure right mutex lock order.
  Call _ma_bitmap_unpin_all() when bitmap->non_flusable is set to 0. This fixed a case when bitmap was not proparly unpinned.
  More comments
  Added DBUG_ASSERT() for detecting wrong share->bitmap usage
storage/maria/ma_blockrec.c:
  More DBUG_ASSERT()
  Moved code around in _ma_apply_redo_insert_row_head_or_tail() to make things safer on error conditions.
storage/maria/ma_check.c:
  Changed parameter for _ma_set_uuid()
  Corrected test for detecting if we lost many rows. This fixed some cases where auto-recovery failed.
  share->changed need to be set if state.open_count is changed.
  Removed setting of share->changed= 0 as called function sets it.
storage/maria/ma_close.c:
  - Added code to properly decrement open_count and have it written by _ma_state_info_write() for transactional tables.
    (This is more correct and also saves us one extra write by _ma_decrement_open_count() at close.
  - Added DBUG_ASSERT() to detect if open_count is wrong at maria_close().
storage/maria/ma_delete.c:
  Updated argument to _ma_mark_file_changed()
storage/maria/ma_delete_all.c:
  Updated argument to _ma_mark_file_changed()
  For transactional tables, call _ma_mark_file_changed() after log entry has been written (to allow recover to fix open_count)
  Reset more needed variables in _ma_reset_status()
storage/maria/ma_delete_table.c:
  Moved deletion of Aria files to maria_delete_table_files().
  Remove RAID usage (old not working code)
storage/maria/ma_extra.c:
  Set share->changed=1 when state needs to be updated on disk.
  Don't reset share->changed after call to _ma_state_info_write() as this calls sets share->changed.
  Set share->state.open_count to 1 to force table to be auto repaired if drop fails.
  Set share->global_changed before call to _ma_flush_table_files() to ensure that we don't try to mark the table changed during flush.
  Added DBUG_ENTER
storage/maria/ma_locking.c:
  Split _ma_mark_file_changed() into two functions to delay marking transactional tables as changed on disk until first disk write.
  Added argument to _ma_decrement_open_count() to tell if we should call ma_lock_database() or not.
  Don't decrement open count for transactional tables during _ma_decrement_open_count(). This will be done during close.
  Changed parameter for _ma_set_uuid()
storage/maria/ma_open.c:
  Set share->open_count_not_zero_on_open if state.open_count is not zero.
  This is needed for DBUG_ASSERT() in maria_close() that is there to enforce that open_count is always 0 at close.
  This test doesn't however work for tables that had open_count != 0 already on disk (ie, crashed tables).
  Enforce right mutex order for share->intern_lock and share->bitmap.bitmap_lock
  Don't set share->changed to 0 if share->state.open_count != 0, as state needs to be be written at close
storage/maria/ma_pagecache.c:
  Moved a bit of code in find_block() to avoid one if.
  More DBUG_ASSERT()
  (I left a comment in the code for Sanja to look at;  The code probably works but we need to check if it's optimal)
storage/maria/ma_pagecrc.c:
  For transactional tables, just before first write to disk, but after log is flushed, mark the file changed.
  This fixes some cases where recovery() did not detect that table was marked as changed and could thus not recover the marker.
storage/maria/ma_recovery.c:
  Set share->changed when share->global_changed is set.
storage/maria/ma_update.c:
  Updated parameter for _ma_mark_file_changed()
storage/maria/ma_write.c:
  Updated parameter for _ma_mark_file_changed()
storage/maria/maria_chk.c:
  Added option --ignore-control-file to be able to run maria_chk even if the control file is locked.
storage/maria/maria_def.h:
  Updated function prototypes.
  Added open_count_not_zero_on_open to MARIA_SHARE.
storage/myisam/ha_myisam.cc:
  current_thd -> table->in_use
2011-02-10 20:33:51 +02:00

255 lines
8 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 */
#include "ma_fulltext.h"
#include "ma_rt_index.h"
#include "trnman.h"
/**
Update an old row in a MARIA table
*/
int maria_update(register MARIA_HA *info, const uchar *oldrec, uchar *newrec)
{
int flag,key_changed,save_errno;
reg3 my_off_t pos;
uint i;
uchar old_key_buff[MARIA_MAX_KEY_BUFF],*new_key_buff;
my_bool auto_key_changed= 0;
ulonglong changed;
MARIA_SHARE *share= info->s;
MARIA_KEYDEF *keyinfo;
DBUG_ENTER("maria_update");
LINT_INIT(new_key_buff);
LINT_INIT(changed);
DBUG_EXECUTE_IF("maria_pretend_crashed_table_on_usage",
maria_print_error(info->s, HA_ERR_CRASHED);
DBUG_RETURN(my_errno= HA_ERR_CRASHED););
if (!(info->update & HA_STATE_AKTIV))
{
DBUG_RETURN(my_errno=HA_ERR_KEY_NOT_FOUND);
}
if (share->options & HA_OPTION_READ_ONLY_DATA)
{
DBUG_RETURN(my_errno=EACCES);
}
if (share->state.state.key_file_length >= share->base.margin_key_file_length)
{
DBUG_RETURN(my_errno=HA_ERR_INDEX_FILE_FULL);
}
pos= info->cur_row.lastpos;
if (_ma_readinfo(info,F_WRLCK,1))
DBUG_RETURN(my_errno);
if ((*share->compare_record)(info,oldrec))
{
save_errno= my_errno;
DBUG_PRINT("warning", ("Got error from compare record"));
goto err_end; /* Record has changed */
}
/* Calculate and check all unique constraints */
key_changed=0;
for (i=0 ; i < share->state.header.uniques ; i++)
{
MARIA_UNIQUEDEF *def=share->uniqueinfo+i;
if (_ma_unique_comp(def, newrec, oldrec,1) &&
_ma_check_unique(info, def, newrec, _ma_unique_hash(def, newrec),
pos))
{
save_errno=my_errno;
goto err_end;
}
}
if (_ma_mark_file_changed(share))
{
save_errno=my_errno;
goto err_end;
}
/* Ensure we don't try to restore auto_increment if it doesn't change */
info->last_auto_increment= ~(ulonglong) 0;
/* Check which keys changed from the original row */
new_key_buff= info->lastkey_buff2;
changed=0;
for (i=0, keyinfo= share->keyinfo ; i < share->base.keys ; i++, keyinfo++)
{
if (maria_is_key_active(share->state.key_map, i))
{
if (keyinfo->flag & HA_FULLTEXT )
{
if (_ma_ft_cmp(info,i,oldrec, newrec))
{
if ((int) i == info->lastinx)
{
/*
We are changeing the index we are reading on. Mark that
the index data has changed and we need to do a full search
when doing read-next
*/
key_changed|=HA_STATE_WRITTEN;
}
changed|=((ulonglong) 1 << i);
if (_ma_ft_update(info,i,old_key_buff,oldrec,newrec,pos))
goto err;
}
}
else
{
MARIA_KEY new_key, old_key;
(*keyinfo->make_key)(info,&new_key, i, new_key_buff, newrec,
pos, info->trn->trid);
(*keyinfo->make_key)(info,&old_key, i, old_key_buff,
oldrec, pos, info->cur_row.trid);
/* The above changed info->lastkey2. Inform maria_rnext_same(). */
info->update&= ~HA_STATE_RNEXT_SAME;
if (new_key.data_length != old_key.data_length ||
memcmp(old_key.data, new_key.data, new_key.data_length))
{
if ((int) i == info->lastinx)
key_changed|=HA_STATE_WRITTEN; /* Mark that keyfile changed */
changed|=((ulonglong) 1 << i);
keyinfo->version++;
if (keyinfo->ck_delete(info,&old_key))
goto err;
if (keyinfo->ck_insert(info,&new_key))
goto err;
if (share->base.auto_key == i+1)
auto_key_changed=1;
}
}
}
}
if (share->calc_checksum)
{
/*
We can't use the row based checksum as this doesn't have enough
precision (one byte, while the table's is more bytes).
At least _ma_check_unique() modifies the 'newrec' record, so checksum
has to be computed _after_ it. Nobody apparently modifies 'oldrec'.
We need to pass the old row's checksum down to (*update_record)(), we do
this via info->new_row.checksum (not intuitive but existing code
mandated that cur_row is the new row).
If (*update_record)() fails, table will be marked corrupted so no need
to revert the live checksum change.
*/
info->cur_row.checksum= (*share->calc_checksum)(info, newrec);
info->new_row.checksum= (*share->calc_checksum)(info, oldrec);
info->state->checksum+= info->cur_row.checksum - info->new_row.checksum;
}
if ((*share->update_record)(info, pos, oldrec, newrec))
goto err;
if (auto_key_changed & !share->now_transactional)
{
const HA_KEYSEG *keyseg= share->keyinfo[share->base.auto_key-1].seg;
const uchar *key= newrec + keyseg->start;
set_if_bigger(share->state.auto_increment,
ma_retrieve_auto_increment(key, keyseg->type));
}
/*
We can't yet have HA_STATE_AKTIV here, as block_record dosn't support it
*/
info->update= (HA_STATE_CHANGED | HA_STATE_ROW_CHANGED | key_changed);
share->state.changed|= STATE_NOT_MOVABLE | STATE_NOT_ZEROFILLED;
info->state->changed= 1;
/*
Every Maria function that updates Maria table must end with
call to _ma_writeinfo(). If operation (second param of
_ma_writeinfo()) is not 0 it sets share->changed to 1, that is
flags that data has changed. If operation is 0, this function
equals to no-op in this case.
ma_update() must always pass !0 value as operation, since even if
there is no index change there could be data change.
*/
VOID(_ma_writeinfo(info, WRITEINFO_UPDATE_KEYFILE));
allow_break(); /* Allow SIGHUP & SIGINT */
if (info->invalidator != 0)
{
DBUG_PRINT("info", ("invalidator... '%s' (update)",
share->open_file_name.str));
(*info->invalidator)(share->open_file_name.str);
info->invalidator=0;
}
DBUG_RETURN(0);
err:
DBUG_PRINT("error",("key: %d errno: %d",i,my_errno));
save_errno= my_errno;
DBUG_ASSERT(save_errno);
if (!save_errno)
save_errno= HA_ERR_INTERNAL_ERROR; /* Should never happen */
if (my_errno == HA_ERR_FOUND_DUPP_KEY || my_errno == HA_ERR_OUT_OF_MEM ||
my_errno == HA_ERR_RECORD_FILE_FULL)
{
info->errkey= (int) i;
flag=0;
do
{
if (((ulonglong) 1 << i) & changed)
{
if (share->keyinfo[i].flag & HA_FULLTEXT)
{
if ((flag++ && _ma_ft_del(info,i,new_key_buff,newrec,pos)) ||
_ma_ft_add(info,i,old_key_buff,oldrec,pos))
{
_ma_set_fatal_error(share, my_errno);
break;
}
}
else
{
MARIA_KEY new_key, old_key;
(*share->keyinfo[i].make_key)(info, &new_key, i, new_key_buff,
newrec, pos,
info->trn->trid);
(*share->keyinfo[i].make_key)(info, &old_key, i, old_key_buff,
oldrec, pos, info->cur_row.trid);
if ((flag++ && _ma_ck_delete(info, &new_key)) ||
_ma_ck_write(info, &old_key))
{
_ma_set_fatal_error(share, my_errno);
break;
}
}
}
} while (i-- != 0);
}
else
_ma_set_fatal_error(share, save_errno);
info->update= (HA_STATE_CHANGED | HA_STATE_AKTIV | HA_STATE_ROW_CHANGED |
key_changed);
err_end:
VOID(_ma_writeinfo(info,WRITEINFO_UPDATE_KEYFILE));
allow_break(); /* Allow SIGHUP & SIGINT */
if (save_errno == HA_ERR_KEY_NOT_FOUND)
_ma_set_fatal_error(share, HA_ERR_CRASHED);
DBUG_RETURN(my_errno=save_errno);
} /* maria_update */