mirror of
https://github.com/MariaDB/server.git
synced 2025-01-17 12:32:27 +01:00
2291f932b2
Recovery of state.records (the count of records which is stored into the header of the index file). For that, state.is_of_lsn is introduced; logic is explained in ma_recovery.c (look for "Recovery of the state"). The net gain is that in case of crash, we now recover state.records, and it is idempotent (ma_test_recovery tests it). state.checksum is not recovered yet, mail sent for discussion. - WL#3071 Maria Checkpoint: preparation for it, by protecting all modifications of the state in memory or on disk with intern_lock (with the exception of the really-often-modified state.records, which is now protected with the log's lock, see ma_recovery.c (look for "Recovery of the state"). Also, if maria_close() sees that Checkpoint is looking at this table it will not my_free() the share. - don't compute row's checksum twice in case of UPDATE (correction to a bugfix I made yesterday). storage/maria/ha_maria.cc: protect state write with intern_lock (against Checkpoint) storage/maria/ma_blockrec.c: * don't reset trn->rec_lsn in _ma_unpin_all_pages(), because it should wait until we have corrected the allocation in the bitmap (as the REDO can serve to correct the allocation during Recovery); introducing _ma_finalize_row() for that. * In a changeset yesterday I moved computation of the checksum into write_block_record(), to fix a bug in UPDATE. Now I notice that maria_update() already computes the checksum, it's just that it puts it into info->cur_row while _ma_update_block_record() uses info->new_row; so, removing the checksum computation from write_block_record(), putting it back into allocate_and_write_block_record() (which is called only by INSERT and UNDO_DELETE), and copying cur_row->checksum into new_row->checksum in _ma_update_block_record(). storage/maria/ma_check.c: new prototypes, they will take intern_lock when writing the state; also take intern_lock when changing share->kfile. In both cases this is to protect against Checkpoint reading/writing the state or reading kfile at the same time. Not updating create_rename_lsn directly at end of write_log_record_for_repair() as it wouldn't have intern_lock. storage/maria/ma_close.c: Checkpoint builds a list of shares (under THR_LOCK_maria), then it handles each such share (under intern_lock) (doing flushing etc); if maria_close() freed this share between the two, Checkpoint would see a bad pointer. To avoid this, when building the list Checkpoint marks each share, so that maria_close() knows it should not free it and Checkpoint will free it itself. Extending the zone covered by intern_lock to protect against Checkpoint reading kfile, writing state. storage/maria/ma_create.c: When we update create_rename_lsn, we also update is_of_lsn to the same value: it is logical, and allows us to test in maria_open() that the former is not bigger than the latter (the contrary is a sign of index header corruption, or severe logging bug which hinders Recovery, table needs a repair). _ma_update_create_rename_lsn_on_disk() also writes is_of_lsn; it now operates under intern_lock (protect against Checkpoint), a shortcut function is available for cases where acquiring intern_lock is not needed (table's creation or first open). storage/maria/ma_delete.c: if table is transactional, "records" is already decremented when logging UNDO_ROW_DELETE. storage/maria/ma_delete_all.c: comments storage/maria/ma_extra.c: Protect modifications of the state, in memory and/or on disk, with intern_lock, against a concurrent Checkpoint. When state goes to disk, update it's is_of_lsn (by calling the new _ma_state_info_write()). In HA_EXTRA_FORCE_REOPEN, don't set share->changed to 0 (undoing a change I made a few days ago) and ASK_MONTY storage/maria/ma_locking.c: no real code change here. storage/maria/ma_loghandler.c: Log-write-hooks for updating "state.records" under log's mutex when writing/updating/deleting a row or deleting all rows. storage/maria/ma_loghandler_lsn.h: merge (make LSN_ERROR and LSN_REPAIRED_BY_MARIA_CHK different) storage/maria/ma_open.c: When opening a table verify that is_of_lsn >= create_rename_lsn; if false the header must be corrupted. _ma_state_info_write() is split in two: _ma_state_info_write_sub() which is the old _ma_state_info_write(), and _ma_state_info_write() which additionally takes intern_lock if requested (to protect against Checkpoint) and updates is_of_lsn. _ma_open_keyfile() should change kfile.file under intern_lock to protect Checkpoint from reading a wrong kfile.file. storage/maria/ma_recovery.c: Recovery of state.records: when the REDO phase sees UNDO_ROW_INSERT which has a LSN > state.is_of_lsn it increments state.records. Same for UNDO_ROW_DELETE and UNDO_ROW_PURGE. When closing a table during Recovery, we know its state is at least as new as the current log record we are looking at, so increase is_of_lsn to the LSN of the current log record. storage/maria/ma_rename.c: update for new behaviour of _ma_update_create_rename_lsn_on_disk(). storage/maria/ma_test1.c: update to new prototype storage/maria/ma_test2.c: update to new prototype (actually prototype was changed days ago, but compiler does not complain about the extra argument??) storage/maria/ma_test_recovery.expected: new result file of ma_test_recovery. Improvements: record count read from index's header is now always correct. storage/maria/ma_test_recovery: "rm" fails if file does not exist. Redirect stderr of script. storage/maria/ma_write.c: if table is transactional, "records" is already incremented when logging UNDO_ROW_INSERT. Comments. storage/maria/maria_chk.c: update is_of_lsn too storage/maria/maria_def.h: - MARIA_STATE_INFO::is_of_lsn which is used by Recovery. It is stored into the index file's header. - Checkpoint can now mark a table as "don't free this", and maria_close() can reply "ok then you will free it". - new functions storage/maria/maria_pack.c: update for new name
156 lines
4.8 KiB
C
156 lines
4.8 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 */
|
|
|
|
/* close a isam-database */
|
|
/*
|
|
TODO:
|
|
We need to have a separate mutex on the closed file to allow other threads
|
|
to open other files during the time we flush the cache and close this file
|
|
*/
|
|
|
|
#include "maria_def.h"
|
|
|
|
int maria_close(register MARIA_HA *info)
|
|
{
|
|
int error=0,flag;
|
|
my_bool share_can_be_freed= FALSE;
|
|
MARIA_SHARE *share=info->s;
|
|
DBUG_ENTER("maria_close");
|
|
DBUG_PRINT("enter",("base: 0x%lx reopen: %u locks: %u",
|
|
(long) info, (uint) share->reopen,
|
|
(uint) share->tot_locks));
|
|
|
|
pthread_mutex_lock(&THR_LOCK_maria);
|
|
if (info->lock_type == F_EXTRA_LCK)
|
|
info->lock_type=F_UNLCK; /* HA_EXTRA_NO_USER_CHANGE */
|
|
|
|
if (share->reopen == 1 && share->kfile.file >= 0)
|
|
_ma_decrement_open_count(info);
|
|
|
|
if (info->lock_type != F_UNLCK)
|
|
{
|
|
if (maria_lock_database(info,F_UNLCK))
|
|
error=my_errno;
|
|
}
|
|
pthread_mutex_lock(&share->intern_lock);
|
|
|
|
if (share->options & HA_OPTION_READ_ONLY_DATA)
|
|
{
|
|
share->r_locks--;
|
|
share->tot_locks--;
|
|
}
|
|
if (info->opt_flag & (READ_CACHE_USED | WRITE_CACHE_USED))
|
|
{
|
|
if (end_io_cache(&info->rec_cache))
|
|
error=my_errno;
|
|
info->opt_flag&= ~(READ_CACHE_USED | WRITE_CACHE_USED);
|
|
}
|
|
flag= !--share->reopen;
|
|
maria_open_list=list_delete(maria_open_list,&info->open_list);
|
|
|
|
my_free(info->rec_buff, MYF(MY_ALLOW_ZERO_PTR));
|
|
(*share->end)(info);
|
|
|
|
if (flag)
|
|
{
|
|
/* Last close of file; Flush everything */
|
|
if (share->kfile.file >= 0)
|
|
{
|
|
if ((*share->once_end)(share))
|
|
error= my_errno;
|
|
if (flush_pagecache_blocks(share->pagecache, &share->kfile,
|
|
(share->temporary ?
|
|
FLUSH_IGNORE_CHANGED :
|
|
FLUSH_RELEASE)))
|
|
error= my_errno;
|
|
#ifdef HAVE_MMAP
|
|
if (share->file_map)
|
|
_ma_unmap_file(info);
|
|
#endif
|
|
/*
|
|
If we are crashed, we can safely flush the current state as it will
|
|
not change the crashed state.
|
|
We can NOT write the state in other cases as other threads
|
|
may be using the file at this point
|
|
IF using --external-locking, which does not apply to Maria.
|
|
*/
|
|
if ((share->changed && share->base.born_transactional) ||
|
|
(share->mode != O_RDONLY && maria_is_crashed(info)))
|
|
{
|
|
/*
|
|
State must be written to file as it was not done at table's
|
|
unlocking.
|
|
*/
|
|
if (_ma_state_info_write(share, 1))
|
|
error= my_errno;
|
|
}
|
|
/*
|
|
File must be synced as it is going out of the maria_open_list and so
|
|
becoming unknown to future Checkpoints.
|
|
*/
|
|
if (my_sync(share->kfile.file, MYF(MY_WME)))
|
|
error= my_errno;
|
|
if (my_close(share->kfile.file, MYF(0)))
|
|
error= my_errno;
|
|
}
|
|
#ifdef THREAD
|
|
thr_lock_delete(&share->lock);
|
|
{
|
|
int i,keys;
|
|
keys = share->state.header.keys;
|
|
VOID(rwlock_destroy(&share->mmap_lock));
|
|
for(i=0; i<keys; i++) {
|
|
VOID(rwlock_destroy(&share->key_root_lock[i]));
|
|
}
|
|
}
|
|
#endif
|
|
DBUG_ASSERT(share->now_transactional == share->base.born_transactional);
|
|
if (share->in_checkpoint == MARIA_CHECKPOINT_LOOKS_AT_ME)
|
|
{
|
|
share->kfile.file= -1; /* because Checkpoint does not need to flush */
|
|
/* we cannot my_free() the share, Checkpoint would see a bad pointer */
|
|
share->in_checkpoint|= MARIA_CHECKPOINT_SHOULD_FREE_ME;
|
|
}
|
|
else
|
|
share_can_be_freed= TRUE;
|
|
}
|
|
pthread_mutex_unlock(&THR_LOCK_maria);
|
|
pthread_mutex_unlock(&share->intern_lock);
|
|
if (share_can_be_freed)
|
|
{
|
|
VOID(pthread_mutex_destroy(&share->intern_lock));
|
|
my_free((uchar *)share, MYF(0));
|
|
}
|
|
if (info->ftparser_param)
|
|
{
|
|
my_free((uchar*)info->ftparser_param, MYF(0));
|
|
info->ftparser_param= 0;
|
|
}
|
|
if (info->dfile.file >= 0)
|
|
{
|
|
/*
|
|
This is outside of mutex so would confuse a concurrent
|
|
Checkpoint. Fortunately in BLOCK_RECORD we close earlier under mutex.
|
|
*/
|
|
if (my_close(info->dfile.file, MYF(0)))
|
|
error = my_errno;
|
|
}
|
|
|
|
my_free((uchar*) info,MYF(0));
|
|
|
|
if (error)
|
|
DBUG_RETURN(my_errno= error);
|
|
DBUG_RETURN(0);
|
|
} /* maria_close */
|