ORA-600(1403)和ORA-7445($cold_kslgetsl)错误

10.2.0.2 RAC的ASM实例,出现这两个错误并导致实例的崩溃。
错误信息为:

Thu Apr 12 18:55:42 2007
Starting ORACLE instance (normal)
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Interface TYPE 1 lan901 192.168.0.0 configured FROM OCR FOR USE AS a cluster interconnect
Interface TYPE 1 lan900 198.5.1.0 configured FROM OCR FOR USE AS a public interface
Picked latch-free SCN scheme 3
USING LOG_ARCHIVE_DEST_1 parameter DEFAULT VALUE AS /u01/app/oracle/product/10.2.0/db_1/dbs/arch
Autotune OF undo retention IS turned off. 
LICENSE_MAX_USERS = 0
SYS auditing IS disabled
ksdpec: called FOR event 13740 prior TO event GROUP initialization
Starting up ORACLE RDBMS Version: 10.2.0.2.0.
System parameters WITH non-DEFAULT VALUES:
large_pool_size = 12582912
instance_type = asm
cluster_database = TRUE
instance_number = 2
remote_login_passwordfile= EXCLUSIVE
background_dump_dest = /u01/app/oracle/admin/+ASM/bdump
user_dump_dest = /u01/app/oracle/admin/+ASM/udump
core_dump_dest = /u01/app/oracle/admin/+ASM/cdump
asm_diskstring = /hpap/rdsk/*
asm_diskgroups = DATE, AEG2_CTL, CTL, DATA, AEG2_DATA
Cluster communication is configured to use the following interface(s) for this instance
192.168.0.112
Thu Apr 12 18:55:43 2007
cluster interconnect IPC version:Oracle UDP/IP (generic)
IPC Vendor 1 proto 2
PMON started with pid=2, OS id=26298
DIAG started with pid=3, OS id=26300
PSP0 started with pid=4, OS id=26302
LMON started with pid=5, OS id=26304
LMD0 started with pid=6, OS id=26306
LMS0 started with pid=7, OS id=26308
MMAN started with pid=8, OS id=26310
DBW0 started with pid=9, OS id=26313
LGWR started with pid=10, OS id=26316
CKPT started with pid=11, OS id=26321
SMON started with pid=12, OS id=26324
RBAL started with pid=13, OS id=26353
GMON started with pid=14, OS id=26380
Thu Apr 12 18:55:44 2007
Errors in file /u01/app/oracle/admin/+ASM/bdump/+asm2_ckpt_26321.trc:
ORA-07445: exception encountered: core dump [$cold_kslgetsl()+1424] [SIGSEGV] [Address not mapped to object] [0x3FFFFFFF812FA310] [] []
Thu Apr 12 18:55:44 2007
lmon registered with NM - instance id 2 (internal mem no 1)
Thu Apr 12 18:55:44 2007
Errors in file /u01/app/oracle/admin/+ASM/bdump/+asm2_ckpt_26321.trc:
ORA-00081: address range [0x60000000000A7D70, 0x60000000000A7D74) is not readable
ORA-07445: exception encountered: core dump [$cold_kslgetsl()+1424] [SIGSEGV] [Address not mapped to object] [0x3FFFFFFF812FA310] [] []
Thu Apr 12 18:55:45 2007
Reconfiguration started (old inc 0, new inc 6)
ASM instance 
List of nodes:
0 1
Global Resource Directory frozen
Communication channels reestablished
* allocate domain 1, invalid = TRUE 
* domain 1 valid = 1 according to instance 0 
* allocate domain 2, invalid = TRUE 
* domain 2 valid = 1 according to instance 0 
* allocate domain 3, invalid = TRUE 
* domain 3 valid = 1 according to instance 0 
* allocate domain 4, invalid = TRUE 
* domain 4 valid = 1 according to instance 0 
Thu Apr 12 18:55:45 2007
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Thu Apr 12 18:55:45 2007
LMS 0: 0 GCS shadows cancelled, 0 closed
Set master node info 
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Thu Apr 12 18:55:45 2007
LMS 0: 0 GCS shadows traversed, 0 replayed
Thu Apr 12 18:55:45 2007
Submitted all GCS remote-cache requests
Fix write in gcs resources
Reconfiguration complete
Thu Apr 12 18:55:45 2007
Errors in file /u01/app/oracle/admin/+ASM/udump/+asm2_ora_26212.trc:
ORA-00600: internal error code, arguments: [1403], [], [], [], [], [], [], []
Thu Apr 12 18:55:46 2007
USER: terminating instance due to error 81
Instance terminated by USER, pid = 26212

可以看到,ASM实例刚刚启动,就由于ORA-7445[$cold_kslgetsl]错误和ORA-600[1403]错误以及ORA-81错误导致了实例被中止。
虽然ORA-7445对应的错误在MOS上几乎没有记载,不过ORA-600[1403]错误在10.2.0.2的RAC版本上有明确的bug记载:Bug 5128575 RAC install of 10.2.0.2 does not update libknlopt.a on all nodes。导致问题的原因是由于在按照10.2.0.2时,一个库文件libknlopt.a没有拷贝到远端站点并编译到oracle可执行文件中,导致远端节点出现DUMP的情况,可能出现的错误包括ORA-600[1403]和ORA-81等。
解决该问题的方法是拷贝$ORACLE_HOME/rdbms/lib/libknlopt.a文件到所有远端站点,然后在远端站点重新编辑oracle可执行文件make -f ins_rdbms.mk ioracle。

This entry was posted in BUG and tagged , , , , , , , , , , , . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *