ORA-600(1403)和ORA-7445($cold_kslgetsl)錯誤
10.2.0.2 RAC的ASM例項,出現這兩個錯誤並導致例項的崩潰。
錯誤資訊為:
Thu Apr 12 18:55:42 2007
Starting ORACLE instance (normal)
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Interface type 1 lan901 192.168.0.0 configured from OCR for use as a cluster
interconnect
Interface type 1 lan900 198.5.1.0 configured from OCR for use as a public
interface
Picked latch-free SCN scheme 3
Using LOG_ARCHIVE_DEST_1 parameter default value as /u01/app/oracle/product/10.2.0/db_1/dbs/arch
Autotune of undo retention is turned off.
LICENSE_MAX_USERS = 0
SYS auditing is disabled
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.2.0.
System parameters with non-default values:
large_pool_size = 12582912
instance_type = asm
cluster_database = TRUE
instance_number = 2
remote_login_passwordfile= EXCLUSIVE
background_dump_dest = /u01/app/oracle/admin/+ASM/bdump
user_dump_dest = /u01/app/oracle/admin/+ASM/udump
core_dump_dest = /u01/app/oracle/admin/+ASM/cdump
asm_diskstring = /hpap/rdsk/*
asm_diskgroups = DATE, AEG2_CTL, CTL, DATA, AEG2_DATA
Cluster communication is configured to use the following interface(s) for this
instance
192.168.0.112
Thu Apr 12 18:55:43 2007
cluster interconnect IPC version:Oracle UDP/IP (generic)
IPC Vendor 1 proto 2
PMON started with pid=2, OS id=26298
DIAG started with pid=3, OS id=26300
PSP0 started with pid=4, OS id=26302
LMON started with pid=5, OS id=26304
LMD0 started with pid=6, OS id=26306
LMS0 started with pid=7, OS id=26308
MMAN started with pid=8, OS id=26310
DBW0 started with pid=9, OS id=26313
LGWR started with pid=10, OS id=26316
CKPT started with pid=11, OS id=26321
SMON started with pid=12, OS id=26324
RBAL started with pid=13, OS id=26353
GMON started with pid=14, OS id=26380
Thu Apr 12 18:55:44 2007
Errors in file /u01/app/oracle/admin/+ASM/bdump/+asm2_ckpt_26321.trc:
ORA-07445: exception encountered: core dump [$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 [$cold_kslgetsl()+1424] [SIGSEGV]
[Address not mapped to object] [0x3FFFFFFF812FA310] [] []
Thu Apr 12 18:55:45 2007
Reconfiguration started (old inc 0, new inc 6)
ASM instance
List of nodes:
0 1
Global Resource Directory frozen
Communication channels reestablished
* allocate domain 1, invalid = TRUE
* domain 1 valid = 1 according to instance 0
* allocate domain 2, invalid = TRUE
* domain 2 valid = 1 according to instance 0
* allocate domain 3, invalid = TRUE
* domain 3 valid = 1 according to instance 0
* allocate domain 4, invalid = TRUE
* domain 4 valid = 1 according to instance 0
Thu Apr 12 18:55:45 2007
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Thu Apr 12 18:55:45 2007
LMS 0: 0 GCS shadows cancelled, 0 closed
Set master node info
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Thu Apr 12 18:55:45 2007
LMS 0: 0 GCS shadows traversed, 0 replayed
Thu Apr 12 18:55:45 2007
Submitted all GCS remote-cache requests
Fix write in gcs resources
Reconfiguration complete
Thu Apr 12 18:55:45 2007
Errors in file /u01/app/oracle/admin/+ASM/udump/+asm2_ora_26212.trc:
ORA-00600: internal error code, arguments: [1403], [], [], [], [], [], [], []
Thu Apr 12 18:55:46 2007
USER: terminating instance due to error 81
Instance terminated by USER, pid = 26212
可以看到,ASM例項剛剛啟動,就由於ORA-7445[$cold_kslgetsl]錯誤和ORA-600[1403]錯誤以及ORA-81錯誤導致了例項被中止。
雖然ORA-7445對應的錯誤在MOS上幾乎沒有記載,不過ORA-600[1403]錯誤在10.2.0.2的RAC版本上有明確的bug記載:Bug 5128575 RAC install of 10.2.0.2 does not update libknlopt.a on all nodes。導致問題的原因是由於在按照10.2.0.2時,一個庫檔案libknlopt.a沒有複製到遠端站點並編譯到oracle可執行檔案中,導致遠端節點出現DUMP的情況,可能出現的錯誤包括ORA-600[1403]和ORA-81等。
解決該問題的方法是複製$ORACLE_HOME/rdbms/lib/libknlopt.a檔案到所有遠端站點,然後在遠端站點重新編輯oracle可執行檔案make -f ins_rdbms.mk ioracle。
來自 “ ITPUB部落格 ” ,連結:http://blog.itpub.net/4227/viewspace-733661/,如需轉載,請註明出處,否則將追究法律責任。
相關文章
- Oracle 不完全恢復遇到的ORA-600錯誤Oracle
- [重慶思莊每日技術分享]-建立物化檢視時出現ORA-7445錯誤
- ORA-7445[opidsa]
- 【ERROR】儲存鏈路問題造成oracle錯誤,ora-600[4193] 問題處理ErrorOracle
- Promise基礎(消化錯誤和丟擲錯誤)Promise
- C中的匯流排錯誤和段錯誤
- 錯誤和異常 (一):錯誤基礎知識
- PHP錯誤和異常PHP
- vertica ROS和WOS錯誤ROS
- Python 之 錯誤,除錯和測試Python除錯
- Flutter之異常和錯誤Flutter
- Python學習之錯誤除錯和測試Python除錯
- 前端的水平線,錯誤處理和除錯前端除錯
- Python UnboundLocalError和NameError錯誤根源解析PythonError
- ios xcode警告和錯誤彙總iOSXCode
- async和await的錯誤捕獲AI
- 【常見錯誤】--Nltk使用錯誤
- iis7.5錯誤 配置錯誤
- mongodb和python互動遇到的錯誤MongoDBPython
- C++錯誤和異常處理C++
- 六、函式、包和錯誤處理函式
- Go常見錯誤第15篇:interface使用的常見錯誤和最佳實踐Go
- nginx 錯誤除錯Nginx除錯
- PbootCMS錯誤提示:執行SQL發生錯誤!錯誤:no such column: def1bootSQL
- eclipse 並沒有 改變錯誤包名 和 改變錯誤類名 的快捷鍵!Eclipse
- Laravel 安裝後報 500 和 404 錯誤Laravel
- Python3 錯誤和異常介紹Python
- mysql慢查詢和錯誤日誌分析MySql
- 如何掃描和修復 Linux 磁碟錯誤Linux
- 物聯網學習教程—常見錯誤和程式除錯除錯
- 前端錯誤前端
- JavaFx 錯誤Java
- ORACLE 錯誤Oracle
- 記錄一次根據錯誤資訊無法定位錯誤的錯誤
- Request 驗證錯誤沒有返回錯誤資訊?
- Python之錯誤異常和檔案處理Python
- Python錯誤處理和異常處理(二)Python
- .NET----錯誤和異常處理機制
- 利用Decorator和SourceMap優化JavaScript錯誤堆疊優化JavaScript