使用_allow_resetlogs_corruption导致ORA-00704/ORA-01555故障

联系:手机/微信(+86 17813235971) QQ(107644445)

标题:使用_allow_resetlogs_corruption导致ORA-00704/ORA-01555故障

作者:惜分飞©版权所有[未经本人同意,不得以任何形式转载,否则有进一步追究法律责任的权利.]

以前写过一篇乱用_allow_resetlogs_corruption参数导致悲剧的文章,昨天晚上又遇到一个朋友不谨慎使用_allow_resetlogs_corruption导致ORA-00704/ORA-01555故障
环境描述
系统环境:solaris
数据库版本:10.2.0.5.7
数据存储方式:ASM
数据量:15T以上
补充事宜:数据库SCN距离headroom只有54天

报ORA-00020错误,实例crash
数据库因为超过了系统的进程数,出现dbwn进程写数据文件异常

Sun Aug 25 16:00:41 CST 2013
Errors in file /opt/oracle/admin/orcl/bdump/orcl_dbw0_7490.trc:
ORA-01148: 无法刷新数据文件 22 的文件大小
ORA-01110: 数据文件 22: '+DATA/orcl/datafile/index_jh.dbf'
ORA-00020: 超出最大进程数 ()
Sun Aug 25 16:00:41 CST 2013
Errors in file /opt/oracle/admin/orcl/bdump/orcl_dbw0_7490.trc:
ORA-01242: 数据文件出现介质故障: 数据库处于 NOARCHIVELOG 模式
ORA-01110: 数据文件 22: '+DATA/orcl/datafile/index_jh.dbf'
Sun Aug 25 16:00:41 CST 2013
DBW0: terminating instance due to error 1242
Termination issued to instance processes. Waiting for the processes to exit
Sun Aug 25 16:00:51 CST 2013
Instance termination failed to kill one or more processes
Instance terminated by DBW0, pid = 7490

ORA-00600[kcbtema_10]
实例恢复出现ORA-00600: 内部错误代码, 参数: [kcbtema_10], [1], [], [], [], [], [], []

Sun Aug 25 19:19:23 CST 2013
ALTER DATABASE OPEN
Sun Aug 25 19:19:38 CST 2013
Beginning crash recovery of 1 threads
 parallel recovery started with 16 processes
Sun Aug 25 19:19:40 CST 2013
Started redo scan
Sun Aug 25 19:20:07 CST 2013
Completed redo scan
 12016413 redo blocks read, 93405 data blocks need recovery
Sun Aug 25 19:20:19 CST 2013
Started redo application at
 Thread 1: logseq 53681, block 1091966
Sun Aug 25 19:20:19 CST 2013
Recovery of Online Redo Log: Thread 1 Group 1 Seq 53681 Reading mem 0
  Mem# 0: +DATA/orcl/onlinelog/redo_1_1.log
  Mem# 1: +DATA/orcl/onlinelog/redo_1_2.log
Sun Aug 25 19:20:21 CST 2013
Errors in file /opt/oracle/admin/orcl/bdump/orcl_p011_16944.trc:
ORA-00600: 内部错误代码, 参数: [kcbtema_10], [1], [], [], [], [], [], []
Sun Aug 25 19:20:23 CST 2013
Errors in file /opt/oracle/admin/orcl/bdump/orcl_p011_16944.trc:
ORA-00600: 内部错误代码, 参数: [kcbtema_10], [1], [], [], [], [], [], []
Sun Aug 25 19:20:23 CST 2013
Aborting crash recovery due to slave death, attempting serial crash recovery
Sun Aug 25 19:20:23 CST 2013
Beginning crash recovery of 1 threads
Sun Aug 25 19:20:23 CST 2013
Started redo scan
Sun Aug 25 19:20:47 CST 2013
Completed redo scan
 12016413 redo blocks read, 93405 data blocks need recovery
Sun Aug 25 19:20:54 CST 2013
Started redo application at
 Thread 1: logseq 53681, block 1091966
Sun Aug 25 19:20:54 CST 2013
Recovery of Online Redo Log: Thread 1 Group 1 Seq 53681 Reading mem 0
  Mem# 0: +DATA/orcl/onlinelog/redo_1_1.log
  Mem# 1: +DATA/orcl/onlinelog/redo_1_2.log
Sun Aug 25 19:20:54 CST 2013
Errors in file /opt/oracle/admin/orcl/udump/orcl_ora_16751.trc:
ORA-00600: 内部错误代码, 参数: [kcbtema_10], [1], [], [], [], [], [], []
Sun Aug 25 19:20:56 CST 2013
Aborting crash recovery due to error 600
Sun Aug 25 19:20:56 CST 2013
Errors in file /opt/oracle/admin/orcl/udump/orcl_ora_16751.trc:
ORA-00600: 内部错误代码, 参数: [kcbtema_10], [1], [], [], [], [], [], []
ORA-600 signalled during: ALTER DATABASE OPEN...

使用隐含参数

ALTER SYSTEM SET _allow_resetlogs_corruption=TRUE SCOPE=SPFILE;

报ORA-00704/ORA-01555
因为在前面的恢复中进行了不完全恢复,因此这里加入隐含参数,然后尝试resetlogs,然后报如下错误

Sun Aug 25 20:11:54 CST 2013
alter database open resetlogs
Sun Aug 25 20:12:10 CST 2013
RESETLOGS is being done without consistancy checks. This may result
in a corrupted database. The database should be recreated.
RESETLOGS after incomplete recovery UNTIL CHANGE 13429649847189
Resetting resetlogs activation ID 1312390734 (0x4e397e4e)
Sun Aug 25 20:16:25 CST 2013
Setting recovery target incarnation to 2
Sun Aug 25 20:16:42 CST 2013
************************************************************
Warning: The SCN headroom for this database is only 54 days!
************************************************************
Sun Aug 25 20:16:43 CST 2013
Assigning activation ID 1352200163 (0x5098efe3)
Thread 1 opened at log sequence 1
  Current log# 1 seq# 1 mem# 0: +DATA/orcl/onlinelog/redo_1_1.log
  Current log# 1 seq# 1 mem# 1: +DATA/orcl/onlinelog/redo_1_2.log
Successful open of redo thread 1
Sun Aug 25 20:16:43 CST 2013
MTTR advisory is disabled because FAST_START_MTTR_TARGET is not set
Sun Aug 25 20:16:52 CST 2013
SMON: enabling cache recovery
Sun Aug 25 20:16:52 CST 2013
ORA-01555 caused by SQL statement below (SQL ID: 4krwuz0ctqxdt, SCN: 0x0c36.d582339b):
Sun Aug 25 20:16:52 CST 2013
select ctime, mtime, stime from obj$ where obj# = :1
Sun Aug 25 20:16:52 CST 2013
Errors in file /opt/oracle/admin/orcl/udump/orcl_ora_2859.trc:
ORA-00704: 引导程序进程失败
ORA-00704: 引导程序进程失败
ORA-00604: 递归 SQL 级别 1 出现错误
ORA-01555: 快照过旧: 回退段号 143 (名称为 "_SYSSMU143$") 过小
Error 704 happened during db open, shutting down database
USER: terminating instance due to error 704
Termination issued to instance processes. Waiting for the processes to exit
Sun Aug 25 20:17:02 CST 2013
Instance termination failed to kill one or more processes
Instance terminated by USER, pid = 2859
ORA-1092 signalled during: alter database open resetlogs...

数据库当前SCN

SQL > select CHECKPOINT_CHANGE# from v$database;
CHECKPOINT_CHANGE#
------------------
    13429649947222
SQL > select distinct CHECKPOINT_CHANGE# from v$datafile_header;
CHECKPOINT_CHANGE#
------------------
    13429649947222

解决方法
因为该数据库版本为10.2.0.5.7,已经包含了scn patch,因此不能使用event或者隐含参数来修改scn,而且该库容量15T以上(asm),因此也无法使用bbed修改数据文件头,最后决定使用ordebug来解决该问题
使用oradebug DUMPvar SGA kcsgscn_
使用oradebug poke

sqlplus / as sysdba
startup mount
oradebug setmypid
oradebug DUMPvar SGA kcsgscn_
oradebug poke
recover database;
alter database open;

事后总结
查询MOS,发现ORA-00600[kcbtema_10] Raised During Recovery Operations (Doc ID 472282.1)

--故障原因
The cause of this problem has been identified and verified in unpublished Bug 5184359 ORA-600 [KCBTEMA_10].
Due to this bug, during recovery, the class designation of a data block has changed.
--处理方法
SQL>startup mount
SQL>recover database;
SQL>alter database open;

因为MOS上给的解决思路在该数据库中已经无法尝试,不能确定该方法一定可行,但是对于本次的恢复过程中,没有任何直接recover database操作(只有一次不完全恢复)确实让人有无限的遗憾和可惜。对于本次应该先查询MOS,尝试该种方法,慎重使用_allow_resetlogs_corruption参数

发表评论

邮箱地址不会被公开。 必填项已用*标注

4 × 4 =