Undo Tablespace - Huge file growth.
Hi,
My undo tablespace increases in size rapidly. We have to perform huge number of update operations in this database. How can I reduce the size of the undo tablespace on a regular basis?
Regards,
Santhosh
There is known bug in prior 9.2.0.5 releses . Undo tablespace does not use expired extents properly if it can allocate new segment. Upgrade to 9.2.0.5 is regular solution. Workaround is seting undotablespace autoextend off.
ciaos
Srdjan Rasulic
Similar Messages
-
XE11: sysaux & undo tablespaces and files
Hello,
does anyone recognized the mixed names of sysaux and undo tablespaces?
If i use:
SQL> SELECT file_name, tablespace_name, ROUND(bytes/1024000) MB
SQL> FROM dba_data_files
SQL> ORDER BY 1;
then i will get:
FILE_NAME TABLESPACE MB
C:\ORACLEXE\APP\ORACLE\ORADATA\XE\SYSAUX.DBF UNDOTBS1 26
C:\ORACLEXE\APP\ORACLE\ORADATA\XE\SYSTEM.DBF SYSTEM 369
C:\ORACLEXE\APP\ORACLE\ORADATA\XE\UNDOTBS1.DBF SYSAUX 666
C:\ORACLEXE\APP\ORACLE\ORADATA\XE\USERS.DBF USERS 102
The file SYSAUX.DBF points to tablespace UNDOTBS1 and
the file UNDOTBS1.DBF points to tablespace SYSAUX
Could this cause a Problem ?
Can this be solved?
This is only in the windows-version, not in the linux-version.
Best reagrds
AKHello,
i did the following:
SQLPLUS:
SHUTDOWN IMMEDIATE;
AS ADMINISTRATOR:
COPY C:\oraclexe\app\oracle\oradata\XE\SYSAUX.DBF C:\oraclexe\app\oracle\oradata\XE\UNDOTBS2.DBF
COPY C:\oraclexe\app\oracle\oradata\XE\UNDOTBS1.DBF C:\oraclexe\app\oracle\oradata\XE\SYSAUX2.DBF
SQLPLUS:
STARTUP MOUNT:
ALTER DATABASE RENAME FILE 'C:\oraclexe\app\oracle\oradata\XE\SYSAUX.DBF' TO 'C:\oraclexe\app\oracle\oradata\XE\UNDOTBS2.DBF';
ALTER DATABASE RENAME FILE 'C:\oraclexe\app\oracle\oradata\XE\UNDOTBS1.DBF' TO 'C:\oraclexe\app\oracle\oradata\XE\SYSAUX2.DBF';
ALTER DATABASE OPEN;
SHUTDOWN IMMEDIATE;
AS ADMINISTRATOR:
COPY C:\oraclexe\app\oracle\oradata\XE\SYSAUX2.DBF C:\oraclexe\app\oracle\oradata\XE\SYSAUX.DBF (overwrite y)
COPY C:\oraclexe\app\oracle\oradata\XE\UNDOTBS2.DBF C:\oraclexe\app\oracle\oradata\XE\UNDOTBS1.DBF (overwrite y)
SQLPLUS:
STARTUP MOUNT:
ALTER DATABASE RENAME FILE 'C:\oraclexe\app\oracle\oradata\XE\SYSAUX2.DBF' TO 'C:\oraclexe\app\oracle\oradata\XE\SYSAUX.DBF';
ALTER DATABASE RENAME FILE 'C:\oraclexe\app\oracle\oradata\XE\UNDOTBS2.DBF' TO 'C:\oraclexe\app\oracle\oradata\XE\UNDOTBS1.DBF';
ALTER DATABASE OPEN;
SHUTDOWN IMMEDIATE;
AS ADMINISTRATOR:
DEL C:\oraclexe\app\oracle\oradata\XE\SYSAUX2.DBF
DEL C:\oraclexe\app\oracle\oradata\XE\UNDOTBS2.DBF
SQLPLUS:
STARTUP
RMAN:
REPORT SCHEMA;
Spooling started in log file: switch.txt
Recovery Manager11.2.0.2.0
RMAN>
Report of database schema for database with db_unique_name XE
List of Permanent Datafiles
===========================
File Size(MB) Tablespace RB segs Datafile Name
1 360 SYSTEM *** C:\ORACLEXE\APP\ORACLE\ORADATA\XE\SYSTEM.DBF
2 650 SYSAUX *** C:\ORACLEXE\APP\ORACLE\ORADATA\XE\SYSAUX.DBF
3 25 UNDOTBS1 *** C:\ORACLEXE\APP\ORACLE\ORADATA\XE\UNDOTBS1.DBF
4 100 USERS *** C:\ORACLEXE\APP\ORACLE\ORADATA\XE\USERS.DBF
List of Temporary Files
=======================
File Size(MB) Tablespace Maxsize(MB) Tempfile Name
1 20 TEMP 32767 C:\ORACLEXE\APP\ORACLE\ORADATA\XE\TEMP.DBF
RMAN>
Recovery Manager complete.
It's not looking elegant but it's working.
Is there a other way?
Best regards. -
Hello, I was processing a batch job that commits every 5,000 records. I have the UNDO_RETENTION set to 10,800. UNDO_MANAGEMENT is set to AUTO. at some point the database shut down
with the following errors in the alert log:
ORA-1654: unable to extend index CRM.XIF35CUSTOMER by 16 in tablespace RCRMCUSTIX01
ORA-1654: unable to extend index CRM.XIF35CUSTOMER by 16 in tablespace RCRMCUSTIX01
ORA-1654: unable to extend index CRM.XIF35CUSTOMER by 16 in tablespace RCRMCUSTIX01
ORA-1654: unable to extend index CRM.XIF35CUSTOMER by 16 in tablespace RCRMCUSTIX01
Fri Jun 09 02:19:48 2006
KCF: write/open error block=0x1faa4f online=1
file=2 C:\ORACLE\ORADATA\CRMMGG\UNDOTBS01.DBF
error=27069 txt: 'OSD-04026: Invalid parameter passed. (OS 2075215)'
Fri Jun 09 02:19:48 2006
Errors in file c:\oracle\admin\crmmgg\bdump\crmmgg_dbw0_20680.trc:
ORA-01242: data file suffered media failure: database in NOARCHIVELOG mode
ORA-01114: IO error writing block to file 2 (block # 2075215)
ORA-01110: data file 2: 'C:\ORACLE\ORADATA\CRMMGG\UNDOTBS01.DBF'
ORA-27069: skgfdisp: attempt to do I/O beyond the range of the file
OSD-04026: Invalid parameter passed. (OS 2075215)
I noticed the the undo datafile is over 16GB. I reset the UNDO_RETENTION to 5 seconds. The undo tablespace data file is staying at 16GB. Is there any way to shring this file. It is a test DB so I can rebuild if necessary. What is the best way to recover from this? Thak you,
DavidYou are facing a generic problem on Windows platforms, when datafiles configured as AUTOEXTEND ON reach a 4GB boundary (4GB,8GB,...). The best way to avoid the problem is switch AUTOEXTEND to OFF and define the appropriate number of single datafiles for the tablespace. From metalink:
ALERT: Problems with Datafile AUTOEXTEND/RESIZE on NT/2000 Platforms
Doc ID:148894.1
Werner -
Hey Folks,
I really need some help here.
I'm trying to drop/recreate the undo tablespace (currently 25gig) Oracle 9i
When I try to drop the undo tablespace 'UNDOTBS1' I get the following error:
âORA-01548: active rollback segment '_SYSSMU1$' found, terminate dropping tablespaceâ
Here's what I have tried so far:
- Bounced the DB several times hoping to get rid of the reference to the active rollback segment. No luck.
- Created a new undo table space
- Tried 'Alter system set undo_tablespace=new_one' (noticed that 10 new rollback segs were created '_SYSMU11$..SYSMU20$' pointing to the new undo tablespace)
- I then performed an offline drop of the undo tablespace data file. After the offline drop, the system rollback segs SYSMU01$..SYSMU10$ went offline as would be expected.
- Even with the new undo tablespace, all other application tablespaces still use the old undo which due to the offline drop, no inserts, deletes, etc. will work.
After all the above, I still get the same error when trying to drop the undo tablespace.
Any ideas? Ideally I would like to be able to drop the undo tablespace and recreate it, but at this point I'd be happy to bring back the undo tablespace datafile so we can at least use the database again.
Thanks in advance!!
ColinSQL> show parameters undo
undo_retention integer
10800
undo_suppress_errors boolean
FALSE
undo_tablespace string
UNDOTBS03
r.- The undo tablespace which the database is looking for is this one ( UNDOTBS03 )
What is strange about the lines above is that I have
all those params above commented out in my
\pfile\init.ora file (and have bounced the db).
Iâm not sure why they are still showing up.
r.- Perhaps your instance is started with the spfile instead of the init file
Here's what we did after the UNDOTBS1 tablespace
caused the disk to run out of space during a large
import (from now on we are going to use commit = y):
1. Created a new undo tablespace UNDOTBS03 - got
errors so instead we to created it as a temp
tablespace UNDOTBS03 which worked. r.- Yes, but that tablespace was created as a UNDO TABLESPACE ?
2. Tried to drop UNDOTBS1 got the following error
msg:
ORA-01548: active rollback segment '_SYSSMU1$' found,
terminate dropping tablespacer.- Of course, the database did not allow to drop it beacause there were pending transactions
3. SQL> alter system set undo_tablespace =
'UNDOTBS03' scope = both. Tried dropping UNDOTBS1.
Same error as in #2 above.r.- There were still pending transactions with the older undo tablespace
4. We then offline dropped the datafile associated
with UNDOTBS1 hoping that would then allow us to drop
UNDOTBS1. Same error as #2.r.- That was the worst you did. You can not drop a tablespace so...
5. Then tried creating a undo tablespace again:
Create UNDO tablespace undo_temp
datafile 'D:\oracle\oradata\usbperf\undo_temp.DBF'
size 25m autoextend on;
Error on line 0
Create UNDO Tablespace undo_temp
datafile 'D:\oracle\oradata\usbperf\undo_temp.
ORA-00604: error occurred at recursive SQL level 1
ORA-00376: file 2 cannot be read at this time
ORA-01110: data file 2:
'D:\ORACLE\ORADATA\USBPERF\UNDOTBS01.DBF'
So thatâs where we are. I'm guessing that the
original undo tablespace corrupted when it tried to
extend and ran of disk space?
Thanks again for the help.
Colin ok I can guide to solve this but you have to do what I am going to tell you step by step. Is this a production database ?
Joel Pérez
http://www.oracle.com/technology/experts -
Hello Friends
I am confuse about a snario, please clear it:
What if we loss undo tablespace(data files), and all files remain safe(database in archive log 9i) and the tablespace have some active transactions at the time of failure. My question is that how oracle will recover ? and where the undo data for uncommited transaction will come from at the time of recovery.
Sunil KumarYou can create new undo tablespace , though, is that there cannot be any active transactions in the Undo segments of the tablespace when it is time to actually drop it. In the case of data file corruption, uncommitted transactions in the database that have data in Undo segments can be extremely troublesome because the existence of any uncommitted transactions will lock the Undo segments holding the data so that they cannot be dropped. This will be evidenced by an "ORA-01548" error if this is attempted. This error, in turn, prevents the drop and recreation of the Undo tablespace, and thus prevents the successful recovery of the database.
To overcome this problem, the transaction tables of the Undo segments can be traced to provide details on transactions that Oracle is trying to recover via rollback and these traces will also identify the objects that Oracle is trying to apply the undo to. Oracle Doc ID: 94114.1 may be referenced to set up a trace on the database startup so that the actual transactions that are locking the Undo segments can be identified and dropped. Dropping objects that contain uncommitted transactions that are holding locks on Undo segments does entail data loss, and the amount of loss depends on how much uncommitted data was in the Undo segments at the point of failure.
Hope this hepls... -
UNDO tablespace file size is huge
Have noticed that UNDO tablespace is eating the disk space of our server. Now, the size is 40GB. Can I recreate a new one with smaller size and drop the existing one? If yes, how?
I have another problem
SQL> startup
ORACLE instance started.
Total System Global Area 1367343104 bytes
Fixed Size 1292468 bytes
Variable Size 838862668 bytes
Database Buffers 520093696 bytes
Redo Buffers 7094272 bytes
Database mounted.
ORA-01092: ORACLE instance terminated. Disconnection forced
As I checked the alert log:
Mon Oct 04 13:47:18 2010
Error 30012 happened during db open, shutting down database
USER: terminating instance due to error 30012
Mon Oct 04 13:47:19 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_pmon_7572.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:19 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_reco_2168.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:19 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_smon_6552.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:19 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_lgwr_9108.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:20 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_ckpt_7152.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:20 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_psp0_3612.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:20 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_mman_6528.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Mon Oct 04 13:47:20 2010
Errors in file d:\oracle\product\10.2.0\admin\axphq01\bdump\axphq01_dbw0_7120.trc:
ORA-30012: undo tablespace '' does not exist or of wrong type
Instance terminated by USER, pid = 9204
ORA-1092 signalled during: ALTER DATABASE OPEN... -
What is the difference between undo tablespace and online redo log files.
what is the difference between undo tablespace and online redo log files. I am confused
as per my knowledge undo tablespace is used to store the undo information when a table is being updated so that, just incase we need to rollback a transaction we know what was present in the table earlier.
when a transaction fails the SMON performs the rollback of the data.
This undo data is stored in the undo tablespace and read consistency if any is enforced.
is my understanding till here correct?
Now, can this undo data/before image not be stored in the redo log buffer and online redolog files?
can redo-log files not store this information?
in fact, is it that when undo tablespaces exist in a database, the undo data/before image is stored in both the undo tablespace and also the redo log files?
kindly clarify my doubt.
thank you.This question has been asked many times before. The answer is always the same.
Yes, redo contains the before image of data (and the after-image). Therefore, it **COULD** be used to roll back a transaction.
BUT... Redo is written sequentially. Using it to rollback your transaction would involve reading through all the redo written by maybe thousands of other people. It would be painfully slow.
Your transaction is, however, directly linked to just the UNDO that it generates (which is JUST the before image of the data). So, your undo is your undo and doesn't share space with anyone else's undo. Therefore, using it to roll back YOUR transaction is fast.
The fact that undo is only the before image of the data also makes it faster than wading through a sea of before and AFTER images as you'd find in redo. About twice as fast, in fact, since there's half the data. Roughly.
Redo also gets written and flushed to disk whenever there's a commit, 3 seconds are up or too much (1MB, actually) redo gets generated between flushes caused by other factors. Your redo gets flushed when those things happen, even if you haven't actually committed your transaction. And redo logs recycle themselves, meaning that your redo -even if your transaction hasn't been committed yet- can be over-written by later transactions. Try rolling back when that's happened, if redo was the source of your rollback data!
Undo, however, cannot be over-written if the transaction has not been committed. Ever. If you don't commit for three years, there will be three years' undo stored in your database (assuming you had the space, of course!).
I could go on, but that will do. Redo is there fore RECOVERY, after catastrophe. Undo is there for read-consistency (and the occasional change of mind). Two different functions. Two different mechanisms. Each one highly tuned to doing what it does, why it does it, most efficiently and effectively. -
RedoLog File 과 Undo Tablespace의 명확한 차이를 알고 싶습니다.
Redo Log File - DML에 의한 모든 변경된 DATA를 저장
Undo Tablespace (Rollback Segments) - 변경전의 data 저장
둘을 구분짓는 명확한 차이를 알고 싶습니다.....
항상 둘이 햇갈리네요...
감사합니다.혼동되시지요 ?
해답은 이름에 있습니다.
redo log 즉 다시 되 돌리기 위함
undo 즉 실행을 취소 하기 위함 입니다.
간단히 설명을 덧 붙이지면 ..
undo는 트랜잭션단위로 발생하는 DML에 대하여 유저가 rollback문을 수행 하거나 다른 세션에서 이전 이미지 값을 요청 할 경우를 대비 하여 DML이전의 원본 이미지를 저장해 놓는 것입니다.
redo 데이터 베이스 단위로 트랜잭션 정보를 저장해 놓습니다.
이는 후에 데이터 베이스가 깨지거나 백업본을 가지고 현재 시점까지 복구를 해야 하는경우에 사용하기 위함입니다.
redolog 파일에는 각각의 세션에서 일으켰던 트랜잭션 정보가 모두 저장이 되어 있습니다. 그래서 복구 시에 redo로그 파일을 읽어서 해당 트랜잭션을 자동으로 수행해서 현재 시점까지 데이터를 복구 하는 것입니다.
구분에 도움이 되었으면 하네요 ... 수고하세요 ~ -
Hi ..
My undo tablespace is Growing rapidly from 1gb to 10 gb with an Hour.
Is there any ways to find out which operation Generates More Undo ..
Can i able to restrict it...hi,
there is parameter that control the aging out of undo blocks that leverages size of UNDO tbs:
UNDO_RETENTION
You can guarantee that unexpired undo data is not overwritten even if it means that future operations that need to generate undo data will fail. This is done by specifying the RETENTION GUARANTEE clause for the undo tablespace when it is created by either the CREATE DATABASE or CREATE UNDO TABLESPACE statement. Alternatively, you can later specify this clause in an ALTER TABLESPACE statement.
more: UNDO RETENTION GUARANTEE -
While dropping the old undo tablespace we get an error
Hello friends ,
i Cannot drop old undo tablespace. While dropping the old undo tablespace we get an error
ERROR at line 1:
ORA-01548: active rollback segment '_SYSSMU77$' found, terminate dropping
tablespace
SQL> select tablespace_name, status, segment_name from dba_rollback_segs where status != 'OFFLINE';
TABLESPACE_NAME STATUS SEGMENT_NAME
SYSTEM ONLINE SYSTEM
APPS_UNDO NEEDS RECOVERY _SYSSMU77$
Please help
Thanks
Edited by: Vicky C on Dec 23, 2012 9:23 AMHi peter
We not using rman backup only cold backup.. i tried using cold backup in ramn block media recovery but that recovery needs archive log
RMAN> BLOCKRECOVER DATAFILE 158 BLOCK 48829;
Starting blockrecover at 18-DEC-12
allocated channel: ORA_DISK_1
channel ORA_DISK_1: sid=437 devtype=DISK
channel ORA_DISK_1: restoring block(s) from datafile copy /var/undo/undo02.dbf
starting media recovery
media recovery failed
RMAN-00571: ===========================================================
RMAN-00569: =============== ERROR MESSAGE STACK FOLLOWS ===============
RMAN-00571: ===========================================================
RMAN-03002: failure of blockrecover command at 12/18/2012 16:45:11
ORA-00604: error occurred at recursive SQL level 1
ORA-01422: exact fetch returns more than requested number of rows
ORA-00279: change 5975281035000 generated at 12/08/2012 06:00:58 needed for thread 1
ORA-00289: suggestion : /prod/archlogs/1_465484_683651989.dbf
ORA-00280: change 5975281035000 for thread 1 is in sequence #465484
ORA-00278: log file '/prod/archlogs/1_465484_683651989.dbf' no longer needed for this re covery
we did not have block media recovery needed archivelog
Regards
Vignesh C -
Regarding Maxsize of Undo Tablespace
Dear expetrs
While executing a procedure i got error.
Error In Insertion..ORA-30036: unable to extend segment by 16384 in undo tablesp
ace 'UNDOTBS1'
then i increase the size of the Undo Tablespace
then again i got error.
ORA-01144: File size (7680000 blocks) exceeds maximum of 4194303 blocks
plz give me answer as soon as possible.
thnaks.1) resize your datafile to 4194303 * db_block_size
alter database datafile < path/filename > resize <4194303 * db_block_size> ;
you find db_block_size by:
sqlplus /nolog
SQL> connect / as sysdba
SQL> show parameter db_block_size
or by simply have a look in the pfile (init<SID>.ora) in $ORACLE_HOME/dbs
2) add another file to the undo tablespace:
SQL>alter tablespace undotbs1 add datafile <path/filename> size <n> M;
a tablespace may have up to 1022 datafiles.
hope this helps
roman -
Undo tablespace recovery from RMAN backup
Hi,
Lets's assume we have RMAN backup and archivelog backups, and now
my undo tablespace's disk crashed ,how can i recover?
Can i recover while database is up?
Thanks,
Kumar.to recover UNDO tablespace from RMAN backup you must shutdown the database and start it in the MOUNT state to recover the missing files as follows
rman target /
RUN
STARTUP MOUNT;
ALLOCATE CHANNEL ch3 TYPE Disk;
RESTORE datafile 'c:\u01\prod3\undo01.dbf';
RECOVER datafile 'c:\u01\prod3\undo01.dbf';
ALTER DATABASE OPEN;
RELEASE CHANNEL ch3;
hope this will help you -
ORA-30012: undo tablespace 'UNDOTBS' does not exist or of wrong type
OS Version : AIX 6.1
DB Version : 11.2.0.1
I am duplicating database and got below error:
contents of Memory Script:
Alter clone database open resetlogs;
executing Memory Script
RMAN-00571: ===========================================================
RMAN-00569: =============== ERROR MESSAGE STACK FOLLOWS ===============
RMAN-00571: ===========================================================
RMAN-00601: fatal error in recovery manager
RMAN-03004: fatal error during execution of command
RMAN-10041: Could not re-create polling channel context following failure.
RMAN-10024: error setting up for rpc polling
RMAN-10005: error opening cursor
RMAN-10002: ORACLE error: ORA-03114: not connected to ORACLE
RMAN-03002: failure of Duplicate Db command at 02/16/2013 17:20:02
RMAN-03015: error occurred in stored script Memory Script
RMAN-06136: ORACLE error from auxiliary database: ORA-01092: ORACLE instance terminated. Disconnection forced
ORA-30012: undo tablespace 'UNDOTBS' does not exist or of wrong type
Process ID: 44040326
Session ID: 65 Serial number: 3
Error is because in target database undo tablespace is UNDOTBS_NEW and in auxiliary database undo tablespace name in init file is UNDOTBS. I followed the meatlink doc 433992.1 which suggest following steps to recover from above error:
1) edit the parameter UNDO_MANAGEMENT to "MANUAL"
2) start database again
3) drop the UNDO tablespace
4) recreate UNDO tablespace which matches to name in init file.
5) shutdown & start DB again.
Now, i edited init file and tried to start DB and got following error:
oracore@cph-core-db01-s $ sqlplus /nolog
SQL*Plus: Release 11.2.0.1.0 Production on Sat Feb 16 17:22:11 2013
Copyright (c) 1982, 2009, Oracle. All rights reserved.
SQL> conn sys as sysdba
Enter password:
Connected to an idle instance.
SQL> startup
ORACLE instance started.
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 822085888 bytes
Database Buffers 3439329280 bytes
Redo Buffers 12152832 bytes
Database mounted.
ORA-01113: file 1 needs media recovery
ORA-01110: data file 1: '/u04/oradata/CORE/CORE_DUP/system01.dbf'I don't want to run duplicate command with correct UNDO tablespace name. Any other work around for this ?STARTUP MOUNT
RECOVER DATABASE USING BACKUP CONTROLFILE UNTIL CANCEL
CANCEL
ALTER DATABASE OPEN RESETLOGS
Above option is not working for CORE_DUP, i am getting very strange error, while trying to recover i am getting very strange error as below:
oracore@cph-core-db01-s $ export ORACLE_SID=CORE_DUP
SQL*Plus: Release 11.2.0.1.0 Production on Mon Feb 18 11:17:25 2013
Copyright (c) 1982, 2009, Oracle. All rights reserved.
SQL> conn sys as sysdba
Enter password:
Connected to an idle instance.
SQL> startup mount
ORACLE instance started.
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 822085888 bytes
Database Buffers 3439329280 bytes
Redo Buffers 12152832 bytes
Database mounted.
SQL> alter database open resetlogs;
alter database open resetlogs
ERROR at line 1:
ORA-01139: RESETLOGS option only valid after an incomplete database recovery
SQL> recover database using backup controlfile until cancel;
ORA-00283: recovery session canceled due to errors
ORA-16433: The database must be opened in read/write mode.Primary database initfile:
event="10298 trace name context forever, level 32"
db_block_size=8192
db_file_multiblock_read_count=16
open_cursors=300
db_name=CORE
cursor_sharing='SIMILAR'
global_names=FALSE
diagnostic_dest=/u01/app/oracore/diag/CORE
#background_dump_dest=/u01/app/oracore/diag/rdbms/bdump
#core_dump_dest=/u01/app/oracore/diag/rdbms/cdump
#user_dump_dest=/u01/app/oracore/diag/rdbms/udump
control_files=("/u01/oradata/CORE/control01.ctl", "/u02/oradata/CORE/control02.ctl", "/u03/oradata/CORE/control03.ctl")
log_archive_dest_1='LOCATION=/u05/oradata/CORE/'
log_archive_format='CORE_%s%t%r.ARC'
job_queue_processes=10
compatible=11.2.0.1
processes=150
fast_start_mttr_target=300
filesystemio_options='SETALL'
pga_aggregate_target=500M
recyclebin='OFF'
remote_login_passwordfile='EXCLUSIVE'
session_cached_cursors=100
sga_target=4G
undo_management='AUTO'
undo_tablespace='UNDOTBS_NEW'
nls_date_format='DD-MON-RRRR'
nls_length_semantics='CHAR'initfile for CORE_DUP
event="10298 trace name context forever, level 32"
db_block_size=8192
db_file_multiblock_read_count=16
open_cursors=300
db_name=CORE_DUP
cursor_sharing='SIMILAR'
global_names=FALSE
diagnostic_dest=/u01/app/oracore/diag/CORE/CORE_DUP
control_files=("/u01/oradata/CORE/CORE_DUP/control01.ctl", "/u02/oradata/CORE/CORE_DUP/control02.ctl", "/u03/oradata/CORE/CORE_DUP/control03.ctl")
log_archive_dest_1='LOCATION=/u05/oradata/CORE/CORE_DUP/'
log_archive_format='CORE_DUP%s%t%r.ARC'
job_queue_processes=10
compatible=11.2.0.1
_compression_compatibility="11.2.0"
processes=150
fast_start_mttr_target=300
filesystemio_options='SETALL'
pga_aggregate_target=500M
recyclebin='OFF'
remote_login_passwordfile='EXCLUSIVE'
session_cached_cursors=100
sga_target=4G
undo_management='AUTO'
undo_tablespace='UNDOTBS'
nls_date_format='DD-MON-RRRR'
nls_length_semantics='CHAR'
log_file_name_convert='/CORE','/CORE/CORE_DUP'
db_file_name_convert='/CORE','/CORE/CORE_DUP'Duplicate steps are as:
oracore@cph-core-db01-s $ rman target sys/zzzz@core catalog rmantst10/zzzzz@catdb auxiliary /
Recovery Manager: Release 11.2.0.1.0 - Production on Mon Feb 18 15:50:00 2013
Copyright (c) 1982, 2009, Oracle and/or its affiliates. All rights reserved.
connected to target database: CORE (DBID=913972022)
connected to recovery catalog database
connected to auxiliary database: CORE_DUP (not mounted)
RMAN> duplicate target database to CORE_DUP;
Starting Duplicate Db at 18-FEB-13
allocated channel: ORA_AUX_DISK_1
channel ORA_AUX_DISK_1: SID=96 device type=DISK
allocated channel: ORA_AUX_DISK_2
channel ORA_AUX_DISK_2: SID=127 device type=DISK
contents of Memory Script:
sql clone "create spfile from memory";
executing Memory Script
sql statement: create spfile from memory
contents of Memory Script:
shutdown clone immediate;
startup clone nomount;
executing Memory Script
Oracle instance shut down
connected to auxiliary database (not started)
Oracle instance started
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 838863104 bytes
Database Buffers 3422552064 bytes
Redo Buffers 12152832 bytes
contents of Memory Script:
sql clone "alter system set db_name =
''CORE'' comment=
''Modified by RMAN duplicate'' scope=spfile";
sql clone "alter system set db_unique_name =
''CORE_DUP'' comment=
''Modified by RMAN duplicate'' scope=spfile";
shutdown clone immediate;
startup clone force nomount
restore clone primary controlfile;
alter clone database mount;
executing Memory Script
sql statement: alter system set db_name = ''CORE'' comment= ''Modified by RMAN duplicate'' scope=spfile
sql statement: alter system set db_unique_name = ''CORE_DUP'' comment= ''Modified by RMAN duplicate'' scope=spfile
Oracle instance shut down
Oracle instance started
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 838863104 bytes
Database Buffers 3422552064 bytes
Redo Buffers 12152832 bytes
Starting restore at 18-FEB-13
allocated channel: ORA_AUX_DISK_1
channel ORA_AUX_DISK_1: SID=96 device type=DISK
allocated channel: ORA_AUX_DISK_2
channel ORA_AUX_DISK_2: SID=127 device type=DISK
channel ORA_AUX_DISK_1: starting datafile backup set restore
channel ORA_AUX_DISK_1: restoring control file
channel ORA_AUX_DISK_1: reading from backup piece /oraclebackup/CORE/DF_L1_CORE_16022013_5fo246k3_175_1
channel ORA_AUX_DISK_1: piece handle=/oraclebackup/CORE/DF_L1_CORE_16022013_5fo246k3_175_1 tag=LEVEL1
channel ORA_AUX_DISK_1: restored backup piece 1
channel ORA_AUX_DISK_1: restore complete, elapsed time: 00:00:03
output file name=/u01/oradata/CORE/CORE_DUP/control01.ctl
output file name=/u02/oradata/CORE/CORE_DUP/control02.ctl
output file name=/u03/oradata/CORE/CORE_DUP/control03.ctl
Finished restore at 18-FEB-13
database mounted
contents of Memory Script:
set until scn 1217601;
set newname for datafile 1 to
"/u04/oradata/CORE/CORE_DUP/system01.dbf";
set newname for datafile 2 to
"/u04/oradata/CORE/CORE_DUP/sysaux01.dbf";
set newname for datafile 4 to
"/u04/oradata/CORE/CORE_DUP/users01.dbf";
set newname for datafile 5 to
"/u04/oradata/CORE/CORE_DUP/users02.dbf";
set newname for datafile 6 to
"/u04/oradata/CORE/CORE_DUP/users03.dbf";
set newname for datafile 9 to
"/u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf";
restore
clone database
executing Memory Script
executing command: SET until clause
executing command: SET NEWNAME
executing command: SET NEWNAME
executing command: SET NEWNAME
executing command: SET NEWNAME
executing command: SET NEWNAME
executing command: SET NEWNAME
Starting restore at 18-FEB-13
using channel ORA_AUX_DISK_1
using channel ORA_AUX_DISK_2
channel ORA_AUX_DISK_1: starting datafile backup set restore
channel ORA_AUX_DISK_1: specifying datafile(s) to restore from backup set
channel ORA_AUX_DISK_1: restoring datafile 00004 to /u04/oradata/CORE/CORE_DUP/users01.dbf
channel ORA_AUX_DISK_1: restoring datafile 00005 to /u04/oradata/CORE/CORE_DUP/users02.dbf
channel ORA_AUX_DISK_1: restoring datafile 00006 to /u04/oradata/CORE/CORE_DUP/users03.dbf
channel ORA_AUX_DISK_1: reading from backup piece /oraclebackup/CORE/DF_L0_CORE_16022013_55o246fe_165_1
channel ORA_AUX_DISK_2: starting datafile backup set restore
channel ORA_AUX_DISK_2: specifying datafile(s) to restore from backup set
channel ORA_AUX_DISK_2: restoring datafile 00001 to /u04/oradata/CORE/CORE_DUP/system01.dbf
channel ORA_AUX_DISK_2: restoring datafile 00002 to /u04/oradata/CORE/CORE_DUP/sysaux01.dbf
channel ORA_AUX_DISK_2: restoring datafile 00009 to /u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf
channel ORA_AUX_DISK_2: reading from backup piece /oraclebackup/CORE/DF_L0_CORE_16022013_56o246fe_166_1
channel ORA_AUX_DISK_2: piece handle=/oraclebackup/CORE/DF_L0_CORE_16022013_56o246fe_166_1 tag=LEVEL0
channel ORA_AUX_DISK_2: restored backup piece 1
channel ORA_AUX_DISK_2: restore complete, elapsed time: 00:01:15
channel ORA_AUX_DISK_1: piece handle=/oraclebackup/CORE/DF_L0_CORE_16022013_55o246fe_165_1 tag=LEVEL0
channel ORA_AUX_DISK_1: restored backup piece 1
channel ORA_AUX_DISK_1: restore complete, elapsed time: 00:01:35
Finished restore at 18-FEB-13
contents of Memory Script:
switch clone datafile all;
executing Memory Script
datafile 1 switched to datafile copy
input datafile copy RECID=24 STAMP=807724355 file name=/u04/oradata/CORE/CORE_DUP/system01.dbf
datafile 2 switched to datafile copy
input datafile copy RECID=25 STAMP=807724355 file name=/u04/oradata/CORE/CORE_DUP/sysaux01.dbf
datafile 4 switched to datafile copy
input datafile copy RECID=26 STAMP=807724356 file name=/u04/oradata/CORE/CORE_DUP/users01.dbf
datafile 5 switched to datafile copy
input datafile copy RECID=27 STAMP=807724356 file name=/u04/oradata/CORE/CORE_DUP/users02.dbf
datafile 6 switched to datafile copy
input datafile copy RECID=28 STAMP=807724356 file name=/u04/oradata/CORE/CORE_DUP/users03.dbf
datafile 9 switched to datafile copy
input datafile copy RECID=29 STAMP=807724356 file name=/u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf
contents of Memory Script:
set until scn 1217601;
recover
clone database
delete archivelog
executing Memory Script
executing command: SET until clause
Starting recover at 18-FEB-13
using channel ORA_AUX_DISK_1
using channel ORA_AUX_DISK_2
channel ORA_AUX_DISK_1: starting incremental datafile backup set restore
channel ORA_AUX_DISK_1: specifying datafile(s) to restore from backup set
destination for restore of datafile 00001: /u04/oradata/CORE/CORE_DUP/system01.dbf
destination for restore of datafile 00002: /u04/oradata/CORE/CORE_DUP/sysaux01.dbf
destination for restore of datafile 00009: /u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf
channel ORA_AUX_DISK_1: reading from backup piece /oraclebackup/CORE/DF_L1_CORE_16022013_5eo246k2_174_1
channel ORA_AUX_DISK_2: starting incremental datafile backup set restore
channel ORA_AUX_DISK_2: specifying datafile(s) to restore from backup set
destination for restore of datafile 00004: /u04/oradata/CORE/CORE_DUP/users01.dbf
destination for restore of datafile 00005: /u04/oradata/CORE/CORE_DUP/users02.dbf
destination for restore of datafile 00006: /u04/oradata/CORE/CORE_DUP/users03.dbf
channel ORA_AUX_DISK_2: reading from backup piece /oraclebackup/CORE/DF_L1_CORE_16022013_5do246k2_173_1
channel ORA_AUX_DISK_1: piece handle=/oraclebackup/CORE/DF_L1_CORE_16022013_5eo246k2_174_1 tag=LEVEL1
channel ORA_AUX_DISK_1: restored backup piece 1
channel ORA_AUX_DISK_1: restore complete, elapsed time: 00:00:01
channel ORA_AUX_DISK_2: piece handle=/oraclebackup/CORE/DF_L1_CORE_16022013_5do246k2_173_1 tag=LEVEL1
channel ORA_AUX_DISK_2: restored backup piece 1
channel ORA_AUX_DISK_2: restore complete, elapsed time: 00:00:01
starting media recovery
archived log for thread 1 with sequence 1718 is already on disk as file /u05/oradata/CORE/CORE_17181807276264.ARC
archived log for thread 1 with sequence 1719 is already on disk as file /u05/oradata/CORE/CORE_17191807276264.ARC
archived log for thread 1 with sequence 1720 is already on disk as file /u05/oradata/CORE/CORE_17201807276264.ARC
archived log for thread 1 with sequence 1721 is already on disk as file /u05/oradata/CORE/CORE_17211807276264.ARC
archived log for thread 1 with sequence 1722 is already on disk as file /u05/oradata/CORE/CORE_17221807276264.ARC
archived log for thread 1 with sequence 1723 is already on disk as file /u05/oradata/CORE/CORE_17231807276264.ARC
archived log for thread 1 with sequence 1724 is already on disk as file /u05/oradata/CORE/CORE_17241807276264.ARC
archived log for thread 1 with sequence 1725 is already on disk as file /u05/oradata/CORE/CORE_17251807276264.ARC
archived log for thread 1 with sequence 1726 is already on disk as file /u05/oradata/CORE/CORE_17261807276264.ARC
archived log for thread 1 with sequence 1727 is already on disk as file /u05/oradata/CORE/CORE_17271807276264.ARC
archived log for thread 1 with sequence 1728 is already on disk as file /u05/oradata/CORE/CORE_17281807276264.ARC
archived log for thread 1 with sequence 1729 is already on disk as file /u05/oradata/CORE/CORE_17291807276264.ARC
archived log for thread 1 with sequence 1730 is already on disk as file /u05/oradata/CORE/CORE_17301807276264.ARC
archived log for thread 1 with sequence 1731 is already on disk as file /u05/oradata/CORE/CORE_17311807276264.ARC
archived log for thread 1 with sequence 1732 is already on disk as file /u05/oradata/CORE/CORE_17321807276264.ARC
archived log for thread 1 with sequence 1733 is already on disk as file /u05/oradata/CORE/CORE_17331807276264.ARC
archived log for thread 1 with sequence 1734 is already on disk as file /u05/oradata/CORE/CORE_17341807276264.ARC
archived log for thread 1 with sequence 1735 is already on disk as file /u05/oradata/CORE/CORE_17351807276264.ARC
archived log for thread 1 with sequence 1736 is already on disk as file /u05/oradata/CORE/CORE_17361807276264.ARC
archived log for thread 1 with sequence 1737 is already on disk as file /u05/oradata/CORE/CORE_17371807276264.ARC
archived log for thread 1 with sequence 1738 is already on disk as file /u05/oradata/CORE/CORE_17381807276264.ARC
archived log for thread 1 with sequence 1739 is already on disk as file /u05/oradata/CORE/CORE_17391807276264.ARC
archived log for thread 1 with sequence 1740 is already on disk as file /u05/oradata/CORE/CORE_17401807276264.ARC
archived log for thread 1 with sequence 1741 is already on disk as file /u05/oradata/CORE/CORE_17411807276264.ARC
archived log for thread 1 with sequence 1742 is already on disk as file /u05/oradata/CORE/CORE_17421807276264.ARC
archived log for thread 1 with sequence 1743 is already on disk as file /u05/oradata/CORE/CORE_17431807276264.ARC
archived log for thread 1 with sequence 1744 is already on disk as file /u05/oradata/CORE/CORE_17441807276264.ARC
channel ORA_AUX_DISK_1: starting archived log restore to default destination
channel ORA_AUX_DISK_1: restoring archived log
archived log thread=1 sequence=1710
channel ORA_AUX_DISK_1: reading from backup piece /oraclebackup/CORE/ARC_1HR_CORE_16022013_5jo24jp8_179_1
channel ORA_AUX_DISK_2: starting archived log restore to default destination
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1711
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1712
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1713
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1714
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1715
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1716
channel ORA_AUX_DISK_2: restoring archived log
archived log thread=1 sequence=1717
channel ORA_AUX_DISK_2: reading from backup piece /oraclebackup/CORE/ARC_1HR_CORE_18022013_5ko296uf_180_1
channel ORA_AUX_DISK_1: piece handle=/oraclebackup/CORE/ARC_1HR_CORE_16022013_5jo24jp8_179_1 tag=ARC_1HR
channel ORA_AUX_DISK_1: restored backup piece 1
channel ORA_AUX_DISK_1: restore complete, elapsed time: 00:00:01
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17101807276264.ARC thread=1 sequence=1710
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17101807276264.ARC RECID=3041 STAMP=807724360
channel ORA_AUX_DISK_2: piece handle=/oraclebackup/CORE/ARC_1HR_CORE_18022013_5ko296uf_180_1 tag=ARC_1HR
channel ORA_AUX_DISK_2: restored backup piece 1
channel ORA_AUX_DISK_2: restore complete, elapsed time: 00:00:08
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17111807276264.ARC thread=1 sequence=1711
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17111807276264.ARC RECID=3042 STAMP=807724362
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17121807276264.ARC thread=1 sequence=1712
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17121807276264.ARC RECID=3043 STAMP=807724363
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17131807276264.ARC thread=1 sequence=1713
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17131807276264.ARC RECID=3044 STAMP=807724367
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17141807276264.ARC thread=1 sequence=1714
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17141807276264.ARC RECID=3048 STAMP=807724367
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17151807276264.ARC thread=1 sequence=1715
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17151807276264.ARC RECID=3046 STAMP=807724367
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17161807276264.ARC thread=1 sequence=1716
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17161807276264.ARC RECID=3045 STAMP=807724367
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17171807276264.ARC thread=1 sequence=1717
channel clone_default: deleting archived log(s)
archived log file name=/u05/oradata/CORE/CORE_DUP/CORE_DUP17171807276264.ARC RECID=3047 STAMP=807724367
archived log file name=/u05/oradata/CORE/CORE_17181807276264.ARC thread=1 sequence=1718
archived log file name=/u05/oradata/CORE/CORE_17191807276264.ARC thread=1 sequence=1719
archived log file name=/u05/oradata/CORE/CORE_17201807276264.ARC thread=1 sequence=1720
archived log file name=/u05/oradata/CORE/CORE_17211807276264.ARC thread=1 sequence=1721
archived log file name=/u05/oradata/CORE/CORE_17221807276264.ARC thread=1 sequence=1722
archived log file name=/u05/oradata/CORE/CORE_17231807276264.ARC thread=1 sequence=1723
archived log file name=/u05/oradata/CORE/CORE_17241807276264.ARC thread=1 sequence=1724
archived log file name=/u05/oradata/CORE/CORE_17251807276264.ARC thread=1 sequence=1725
archived log file name=/u05/oradata/CORE/CORE_17261807276264.ARC thread=1 sequence=1726
archived log file name=/u05/oradata/CORE/CORE_17271807276264.ARC thread=1 sequence=1727
archived log file name=/u05/oradata/CORE/CORE_17281807276264.ARC thread=1 sequence=1728
archived log file name=/u05/oradata/CORE/CORE_17291807276264.ARC thread=1 sequence=1729
archived log file name=/u05/oradata/CORE/CORE_17301807276264.ARC thread=1 sequence=1730
archived log file name=/u05/oradata/CORE/CORE_17311807276264.ARC thread=1 sequence=1731
archived log file name=/u05/oradata/CORE/CORE_17321807276264.ARC thread=1 sequence=1732
archived log file name=/u05/oradata/CORE/CORE_17331807276264.ARC thread=1 sequence=1733
archived log file name=/u05/oradata/CORE/CORE_17341807276264.ARC thread=1 sequence=1734
archived log file name=/u05/oradata/CORE/CORE_17351807276264.ARC thread=1 sequence=1735
archived log file name=/u05/oradata/CORE/CORE_17361807276264.ARC thread=1 sequence=1736
archived log file name=/u05/oradata/CORE/CORE_17371807276264.ARC thread=1 sequence=1737
archived log file name=/u05/oradata/CORE/CORE_17381807276264.ARC thread=1 sequence=1738
archived log file name=/u05/oradata/CORE/CORE_17391807276264.ARC thread=1 sequence=1739
archived log file name=/u05/oradata/CORE/CORE_17401807276264.ARC thread=1 sequence=1740
archived log file name=/u05/oradata/CORE/CORE_17411807276264.ARC thread=1 sequence=1741
archived log file name=/u05/oradata/CORE/CORE_17421807276264.ARC thread=1 sequence=1742
archived log file name=/u05/oradata/CORE/CORE_17431807276264.ARC thread=1 sequence=1743
archived log file name=/u05/oradata/CORE/CORE_17441807276264.ARC thread=1 sequence=1744
media recovery complete, elapsed time: 00:00:33
Finished recover at 18-FEB-13
contents of Memory Script:
shutdown clone immediate;
startup clone nomount;
sql clone "alter system set db_name =
''CORE_DUP'' comment=
''Reset to original value by RMAN'' scope=spfile";
sql clone "alter system reset db_unique_name scope=spfile";
shutdown clone immediate;
startup clone nomount;
executing Memory Script
database dismounted
Oracle instance shut down
connected to auxiliary database (not started)
Oracle instance started
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 838863104 bytes
Database Buffers 3422552064 bytes
Redo Buffers 12152832 bytes
sql statement: alter system set db_name = ''CORE_DUP'' comment= ''Reset to original value by RMAN'' scope=spfile
sql statement: alter system reset db_unique_name scope=spfile
Oracle instance shut down
connected to auxiliary database (not started)
Oracle instance started
Total System Global Area 4275781632 bytes
Fixed Size 2213632 bytes
Variable Size 838863104 bytes
Database Buffers 3422552064 bytes
Redo Buffers 12152832 bytes
sql statement: CREATE CONTROLFILE REUSE SET DATABASE "CORE_DUP" RESETLOGS ARCHIVELOG
MAXLOGFILES 32
MAXLOGMEMBERS 4
MAXDATAFILES 500
MAXINSTANCES 1
MAXLOGHISTORY 2298
LOGFILE
GROUP 1 ( '/u02/oradata/CORE/CORE_DUP/redo01a.log', '/u03/oradata/CORE/CORE_DUP/redo01b.log' ) SIZE 10 M REUSE,
GROUP 2 ( '/u02/oradata/CORE/CORE_DUP/redo02a.log', '/u03/oradata/CORE/CORE_DUP/redo02b.log' ) SIZE 10 M REUSE,
GROUP 3 ( '/u02/oradata/CORE/CORE_DUP/redo03a.log', '/u03/oradata/CORE/CORE_DUP/redo03b.log' ) SIZE 10 M REUSE
DATAFILE
'/u04/oradata/CORE/CORE_DUP/system01.dbf'
CHARACTER SET AL32UTF8
contents of Memory Script:
set newname for tempfile 1 to
"/u04/oradata/CORE/CORE_DUP/temp01.dbf";
switch clone tempfile all;
catalog clone datafilecopy "/u04/oradata/CORE/CORE_DUP/sysaux01.dbf",
"/u04/oradata/CORE/CORE_DUP/users01.dbf",
"/u04/oradata/CORE/CORE_DUP/users02.dbf",
"/u04/oradata/CORE/CORE_DUP/users03.dbf",
"/u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf";
switch clone datafile all;
executing Memory Script
executing command: SET NEWNAME
renamed tempfile 1 to /u04/oradata/CORE/CORE_DUP/temp01.dbf in control file
cataloged datafile copy
datafile copy file name=/u04/oradata/CORE/CORE_DUP/sysaux01.dbf RECID=1 STAMP=807724423
cataloged datafile copy
datafile copy file name=/u04/oradata/CORE/CORE_DUP/users01.dbf RECID=2 STAMP=807724423
cataloged datafile copy
datafile copy file name=/u04/oradata/CORE/CORE_DUP/users02.dbf RECID=3 STAMP=807724423
cataloged datafile copy
datafile copy file name=/u04/oradata/CORE/CORE_DUP/users03.dbf RECID=4 STAMP=807724423
cataloged datafile copy
datafile copy file name=/u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf RECID=5 STAMP=807724423
datafile 2 switched to datafile copy
input datafile copy RECID=1 STAMP=807724423 file name=/u04/oradata/CORE/CORE_DUP/sysaux01.dbf
datafile 4 switched to datafile copy
input datafile copy RECID=2 STAMP=807724423 file name=/u04/oradata/CORE/CORE_DUP/users01.dbf
datafile 5 switched to datafile copy
input datafile copy RECID=3 STAMP=807724423 file name=/u04/oradata/CORE/CORE_DUP/users02.dbf
datafile 6 switched to datafile copy
input datafile copy RECID=4 STAMP=807724423 file name=/u04/oradata/CORE/CORE_DUP/users03.dbf
datafile 9 switched to datafile copy
input datafile copy RECID=5 STAMP=807724423 file name=/u04/oradata/CORE/CORE_DUP/undotbs_new01.dbf
contents of Memory Script:
Alter clone database open resetlogs;
executing Memory Script
RMAN-00571: ===========================================================
RMAN-00569: =============== ERROR MESSAGE STACK FOLLOWS ===============
RMAN-00571: ===========================================================
RMAN-00601: fatal error in recovery manager
RMAN-03004: fatal error during execution of command
RMAN-10041: Could not re-create polling channel context following failure.
RMAN-10024: error setting up for rpc polling
RMAN-10005: error opening cursor
RMAN-10002: ORACLE error: ORA-03114: not connected to ORACLE
RMAN-03002: failure of Duplicate Db command at 02/18/2013 15:53:50
RMAN-03015: error occurred in stored script Memory Script
RMAN-06136: ORACLE error from auxiliary database: ORA-01092: ORACLE instance terminated. Disconnection forced
ORA-30012: undo tablespace 'UNDOTBS' does not exist or of wrong type
Process ID: 3670170
Session ID: 33 Serial number: 7
oracore@cph-core-db01-s $ -
Cannot drop old undo tablespace. Cause: active rollback segment
dear all.
db: oracle 10.2.0.1
os: rhel as version 5 64 bits.
This is a testing database. And my database is online and open. But i can free the external usb disk that contains my ols undotbs.
I want to drop old undo tablespace but this is not possible.
1.- In order to open my database i had my datafile( '/mnt/hdext/back_plelds/undotbs02.dbf') offline drop, and then i can to open my database.
2.- When i try to delete my old undo tablespace im getting this error:
SQL> drop tablespace undotbs1 including contents and datafiles;
drop tablespace undotbs1 including contents and datafiles
ERROR at line 1:
ORA-01548: active rollback segment '_SYSSMU1$' found, terminate dropping
tablespace
3.- My default undo_tablespace is another that i was created before step 1.
SQL> sho parameter undo_ta
NAME TYPE VALUE
undo_tablespace string UNDOTMP
SQL>
Well i search in metalink ORA-01548 code error and in 18947.1 doc whows me that the solution is:
Action: Shut down instances that use the active rollback segments in the
tablespace and then drop the tablespace.
4.- I try to shutdown but im getting:
SQL> shutdown immediate;
ORA-00376: file 10 cannot be read at this time
ORA-01110: data file 10: '/mnt/hdext/back_plelds/undotbs02.dbf'
SQL>
This /mnt/hdext is an external USB disk and i have all permissions. I exported tables without any problem and i can read all files.
i search un metalink again ora codes (ORA-00376 ORA-01110) and the doc id: 427801.1 shows in the solution:
Drop the old undo tablespace instead of making it offline.
but when i try to drop the tablespace it shows the error describe in the step 2.
Facts:
- my tablespace UNDOTBS1 is ONLINE. I put in offline and this is not the solution.
- This is the status of my rollback segments:
SQL> select segment_name, status from dba_rollback_segs where
2 tablespace_name='UNDOTBS1';
SEGMENT_NAME STATUS
_SYSSMU1$ NEEDS RECOVERY
_SYSSMU2$ NEEDS RECOVERY
_SYSSMU3$ NEEDS RECOVERY
_SYSSMU4$ NEEDS RECOVERY
_SYSSMU5$ NEEDS RECOVERY
_SYSSMU6$ NEEDS RECOVERY
_SYSSMU7$ NEEDS RECOVERY
_SYSSMU8$ NEEDS RECOVERY
_SYSSMU9$ NEEDS RECOVERY
_SYSSMU10$ NEEDS RECOVERY
_SYSSMU11$ OFFLINE
SEGMENT_NAME STATUS
_SYSSMU12$ OFFLINE
12 rows selected.
SQL>
- I have the note (Unable to drop und tablespace In this article describe the problem but this is not the same. The difference is that i cannot drop the rollback segment that describe in step 2.
SQL> drop rollback segment "_SYSSMU1$";
drop rollback segment "_SYSSMU1$"
ERROR at line 1:
ORA-30025: DROP segment '_SYSSMU1$' (in undo tablespace) not allowed
in metalink the doc id: 173696.1 shows the solution:
Action: Check the undo segment name and reissue statement if necessary.
i cannot drop the rollback_segment
What can i do ???
thanks a lot.in step 4 did you try with shutdown abort?
If its still does not work then create another new table space with new file and then swtich to that tablespace http://download.oracle.com/docs/cd/B19306_01/server.102/b14231/undo.htm#sthref1504Khurram -
Hello:
I've created a new undo tablespace undotbs2. I've set it to the default undo tablespace. When I've tried to drop the old one, I get the following error:
SQL> conn / as sysdba
Connected.
SQL> DROP TABLESPACE undotbs1 INCLUDING CONTENTS AND DATAFILES;
DROP TABLESPACE undotbs1 INCLUDING CONTENTS AND DATAFILES
ERROR at line 1: ORA-01548: active rollback segment '_SYSSMU7$' found, terminate dropping tablespace
This is a production database. The service is down because the partition with the Oracle tablespaces: system, undo, temp, etc is full.
After shutting down the database the problem persist: I cannot drop the old undo tablespace because of the same error.
I've followed the note 1321093.1. Here the query results:
Select segment_name, status, tablespace_name, rs.segment_id
from dba_rollback_segs rs
where status not in ('ONLINE','OFFLINE');
_SYSSMU7$ PARTLY AVAILABLE UNDOTBS1 7
SELECT KTUXEUSN, KTUXESLT, KTUXESQN, /* Transaction ID */ KTUXESTA Status, KTUXECFL Flags
FROM x$ktuxe
WHERE ktuxesta !='INACTIVE' AND ktuxeusn =7;
7 47 382687 ACTIVE DEAD
SELECT LOCAL_TRAN_ID,GLOBAL_TRAN_ID,STATE,MIXED,COMMIT# FROM DBA_2PC_PENDING;
No rows
SELECT LOCAL_TRAN_ID,IN_OUT,DATABASE,INTERFACE FROM dba_2pc_neighbors;
No rows
As you can see, there is no pending transactions. No application is connected to the database (service is down), however the database is appling rollbacks since 2 days.
A lot of archivelogs are being created at rolling back (30 GB archivelogs per hour). Here a tail of the alertlog file:
Wed Apr 17 06:19:53 2013
Thread 1 advanced to log sequence 7382
Current log# 5 seq# 7382 mem# 0: /ora2/origlogs/webfrbr/redo05_m1.log
Current log# 5 seq# 7382 mem# 1: /ora3/mirrorlogs/webfrbr/redo05_m2.log
Wed Apr 17 06:21:16 2013
Thread 1 advanced to log sequence 7383
Current log# 6 seq# 7383 mem# 0: /ora2/origlogs/webfrbr/redo06_m1.log
Current log# 6 seq# 7383 mem# 1: /ora3/mirrorlogs/webfrbr/redo06_m2.log
Wed Apr 17 06:22:41 2013
Thread 1 advanced to log sequence 7384
Current log# 4 seq# 7384 mem# 0: /ora2/origlogs/webfrbr/redo04_m1.log
Current log# 4 seq# 7384 mem# 1: /ora3/mirrorlogs/webfrbr/redo04_m2.log
Wed Apr 17 06:24:02 2013
Thread 1 advanced to log sequence 7385
Current log# 5 seq# 7385 mem# 0: /ora2/origlogs/webfrbr/redo05_m1.log
Current log# 5 seq# 7385 mem# 1: /ora3/mirrorlogs/webfrbr/redo05_m2.log
Wed Apr 17 06:25:24 2013
Thread 1 advanced to log sequence 7386
Current log# 6 seq# 7386 mem# 0: /ora2/origlogs/webfrbr/redo06_m1.log
Current log# 6 seq# 7386 mem# 1: /ora3/mirrorlogs/webfrbr/redo06_m2.log
Wed Apr 17 06:26:46 2013
Thread 1 advanced to log sequence 7387
Current log# 4 seq# 7387 mem# 0: /ora2/origlogs/webfrbr/redo04_m1.log
Current log# 4 seq# 7387 mem# 1: /ora3/mirrorlogs/webfrbr/redo04_m2.log
Oracle Database - Enterprise Edition 10.2.0.3
Linux x86-64 Oracle Linux 5
Please, consider the output of the following queries too:
select * from V$FAST_START_TRANSACTIONS
USN 7 -- Undo segment number of the transaction
SLT 47 -- Slot within the rollback segment
SEQ 382687 -- Incarnation number of the slot
STATE RECOVERING --
UNDOBLOCKSDONE 0 -- Number of undo blocks completed on the transaction
UNDOBLOCKSTOTAL 2079151 -- Total number of undo blocks that need recovery
PID 15 -- ID of the current server it has been assigned to
CPUTIME 1153 -- Time for which recovery has progressed (in seconds)
PARENTUSN 0 -- Undo segment number of the parent transaction in PDML
PARENTSLT 0 -- Slot of the parent transaction in PDML
PARENTSEQ 0 -- Sequence number of the parent transaction in PDML
XID 07002F00DFD60500 -- Transaction ID
PXID 0000000000000000 -- Parent transaction ID
RCVSERVERS 1 -- Number of servers used in the last recovery
select * from x$ktuxe where ktuxecfl = 'DEAD';
ADDR 00002B3E808B9BD8
INDX 145
INST_ID 1
KTUXEUSN 7
KTUXESLT 47
KTUXESQN 382687
KTUXERDBF 2
KTUXERDBB 2080076
KTUXESCNB 424110769
KTUXESCNW 0
KTUXESTA ACTIVE
KTUXECFL DEAD
KTUXEUEL 3739
KTUXEDDBF 0
KTUXEDDBB 0
KTUXEPUSN 0
KTUXEPSLT 0
KTUXEPSQN 0
KTUXESIZ 2079151
select * from v$fast_start_servers;
RECOVERING 0 15 07002F00DFD60500
IDLE 0 16 0000000000000000
IDLE 0 17 0000000000000000
IDLE 0 18 0000000000000000
IDLE 0 19 0000000000000000
IDLE 0 20 0000000000000000
IDLE 0 21 0000000000000000
IDLE 0 22 0000000000000000
IDLE 0 25 0000000000000000
IDLE 0 26 0000000000000000
IDLE 0 27 0000000000000000
IDLE 0 28 0000000000000000
IDLE 0 29 0000000000000000
IDLE 0 30 0000000000000000
IDLE 0 31 0000000000000000
IDLE 0 32 0000000000000000
Any ideas to solve this issue?
Thank you in advance
Edited by: albrotar on Apr 17, 2013 1:48 AM
Edited by: albrotar on Apr 17, 2013 1:49 AM
Edited by: albrotar on Apr 17, 2013 1:51 AM
Edited by: albrotar on Apr 17, 2013 1:52 AM
Edited by: albrotar on Apr 17, 2013 1:54 AMI've found some errors in alert log file occurred at shutting down the database:
+...+
Control autobackup written to DISK device
handle '/orabck/rman/webfrbr/ora_cfc-3587726327-20130414-00'
Completed: CREATE UNDO TABLESPACE undotbs2 DATAFILE '/orabck/undo/undotbs02.dbf'
SIZE 500M reuse autoextend ON NEXT 5M maxsize 32767M
Sun Apr 14 15:46:43 2013
Successfully onlined Undo Tablespace 5.
Undo Tablespace 1 moved to Pending Switch-Out state.
*** active transactions found in undo tablespace 1 during switch-out.
Sun Apr 14 15:46:44 2013
ALTER SYSTEM SET undo_tablespace='UNDOTBS2' SCOPE=BOTH;
Sun Apr 14 16:11:42 2013
ALTER ROLLBACK SEGMENT "_SYSSMU7$" offLINE
Sun Apr 14 16:11:42 2013
Completed: ALTER ROLLBACK SEGMENT "_SYSSMU7$" offLINE
Sun Apr 14 16:12:36 2013
DROP TABLESPACE undotbs1 INCLUDING CONTENTS AND DATAFILES
Sun Apr 14 16:12:36 2013
+...+
Thread 1 advanced to log sequence 5107
Current log# 4 seq# 5107 mem# 0: /ora2/origlogs/webfrbr/redo04_m1.log
Current log# 4 seq# 5107 mem# 1: /ora3/mirrorlogs/webfrbr/redo04_m2.log
Sun Apr 14 19:00:28 2013
Stopping background process CJQ0
Sun Apr 14 19:00:29 2013
Stopping background process QMNC
Sun Apr 14 19:00:31 2013
Stopping background process MMNL
Sun Apr 14 19:00:32 2013
Stopping background process MMON
Sun Apr 14 19:00:34 2013
Shutting down instance (immediate)
License high water mark = 31
Sun Apr 14 19:00:34 2013
Stopping Job queue slave processes
Sun Apr 14 19:00:34 2013
Job queue slave processes stopped
All dispatchers and shared servers shutdown
Sun Apr 14 19:00:42 2013
ALTER DATABASE CLOSE NORMAL
Sun Apr 14 19:04:28 2013
+...+
Thread 1 advanced to log sequence 5118
Current log# 6 seq# 5118 mem# 0: /ora2/origlogs/webfrbr/redo06_m1.log
Current log# 6 seq# 5118 mem# 1: /ora3/mirrorlogs/webfrbr/redo06_m2.log
Sun Apr 14 20:11:21 2013
Errors in file /ora1/admin/webfrbr/bdump/webfrbr_smon_4629.trc:
+ORA-07445: exception encountered: core dump [_intel_fast_memcpy.A()+10] [SIGSEGV] [Invalid permissions for mapped object] [0x2B6B66003000] [] []+*
Sun Apr 14 20:11:21 2013
Errors in file /ora1/admin/webfrbr/bdump/webfrbr_smon_4629.trc:
ORA-00600: internal error code, arguments: [999], [0x107C14015], [], [], [], [], [], []*
+ORA-07445: exception encountered: core dump [_intel_fast_memcpy.A()+10] [SIGSEGV] [Invalid permissions for mapped object] [0x2B6B66003000] [] []+*
Sun Apr 14 20:11:22 2013
+...+
Sun Apr 14 20:11:48 2013
Errors in file /ora1/admin/webfrbr/bdump/webfrbr_pmon_4617.trc:
ORA-00474: SMON process terminated with error
Sun Apr 14 20:11:48 2013
+...+
The instance could start up, but after this, it is recovering undo and generating redo since 2 days
Maybe you are looking for
-
Time Machine can not be mounted - external drive
I have an external Maxtor USB drive that's been my time machine since forever. Yesterday I noticed that it's not mounting. I KNOW it was mounting the day before because I had to use it. But now the drive is not mounting, and I don't know why. The dri
-
F4IF_INT_TABLE_VALUE_REQUEST in me53n
Hi all, in customer tab data of me53n, i added field zzafnam. when i added AT SELECTION-SCREEN ON VALUE-REQUEST FOR eban-zzafnam. in the module input, error occurs indicating that the POV should be done after endmodule..how can i fix this? shall i de
-
Problem connecting as instructor and student. Admin is ok though.
I am trying to set up instructor & student access and I can not log in. The admin account works fine. What am I doing wrong? Thanks in advance. Here is the debug info: Received Destination blah.edu Identity "Mark lastname" <[email protected]> (me) Cr
-
Parsing a string in powershell
I've looked around a bit and can't quite find an answer to this. I've got a script going that looks at a configuration file, and I need to find the values that is inside of quotes. config file: Version = "3.2" currently in my script I simply ha
-
Hi, I am setting ViewObject's where clause by using setWhereClause(strWhereClause). strWhereClause is of sort ATTRIBUTE_ID IN (42912850, 42302602, 43326003, 43582985, 43582465, 43474749......) But number of elements in IN clause are greater than 10