RAC Database

Hello,
While installing RAC database binaries , Following error was reported into installation logs and installation hang.
INFO: ORACLE_HOME = /u01/oracle/app/oracle/product/11.2.0
INFO: PATH = /usr/bin:/usr/ccs/bin:/usr/kerberos/bin:/usr/local/bin:/usr/bin:/bin:/usr/X11R6/bin:/home/oracle/bin:=/usr/kerberos/bin:/usr/local/bin:/usr/bin:/bin:/usr/X11R6/bin:/home/oracle/bin:/home/oracle/bin:/u01/oracle/app/oracle/product/11.2.0/bin:/u01/oracle/app/oracle/product/11.2.0/OPatch:/usr/java/jdk1.6.0_18:/grid/oracle/app/oracle/product/11.2.0/bin:/home/oracle/Desktop/database/install
INFO: CLASSPATH =
INFO: Username:oracle
INFO: Oracle Universal Installer version is 11.2.0.1.0
INFO: Initializing the OiicInstallAPISession
INFO: Shutting down OUISetupDriver.JobExecutorThread
*SEVERE: [FATAL] [INS-00001] Unknown irrecoverable error*
CAUSE: No additional information available.
ACTION: Refer to the logs or contact Oracle Support Services
SUMMARY:
- java.lang.NullPointerException.
Refer associated stacktrace #oracle.install.commons.util.exception.DefaultErrorAdvisor:2094
RAC setup detail :
Host OS: Windows 7
Guest os : OEL5
-> GI installation & root.sh went successfully on both nodes.
Thank you.

Whenever you come across this kind of problems, Just raise an SR. Oracle will respond very quickly and could solve your issue in a cleaner way...
Regards,
CSM

Similar Messages

Unable to startup 12c RAC database, can't open spfile in ASM

hello,
I'm testing 12cRAC database on RHEL5 and need your help to troubleshoot and fix the following issue -
DBCA fails at the end of the configuration to create and startup new RAC database with the following errors
ORA-01078: failure in processing system parameters
ORA-01565: error in identifying file '+DATA/TDB1/spfileTDB1.ora'
ORA-17503: ksfdopn:2 Failed to open file +DATA/TDB1/spfileTDB1.ora
ORA-15056: additional error message
ORA-17503: ksfdopn:2 Failed to open file +DATA/TDB1/spfiletdb1.ora
ORA-01017: invalid username/password; logon denied
I also tried executing script (which was created by DBCA) to create the new DB manually and got the same results - it happens during first attempt to start it up using SPFILE after new DB was successfully created (it was started up using pfile)
Clusterware with ASM install was successful, binaries were also installed without issues,
cluster seems healthy, I see correct files within ASM using asmcmd etc ..
got stuck here and need some directions ... very confused by ORA-01017 password error
wonder if anyone had same or similar issues ?
Thank you !

Fixed.
Thank you everyone for suggestions and recommendations -
ASM is accessible using asmcmd and I can see all the DB files incuding spfile, they were created by DBCA, alert log showed same information I posted
After extensive troubleshooting and testing the issue was idedntified and fixed - 'dba' group needs to be the primary group for 'oracle' user, not the secondary one. I suspected that something was not right with 'oracle' user access to asm based on that strange password error. There is more I need to check as the issue and fix with swapping groups seems strange. Secondary group is not enough ti have proper rights ??? my first reaction was - seriously ? wtf ?
Anyway - I need to move one now ...
Thank you again !

How can I have a collective AWR report for RAC database in 10gR2 and 11gR1?

Plz correct me here
awrrpt.sql takes the snapshot at the instance level and incase we have 5 instances we have to take 5 awr reports for a particular period.correct???
If above is true ,any wayout to collect a single collective AWR report for RAC database which includes information on all the instances in Oracle 10g R2 or 11gR1 ?
Thanks in advance
Gagan

I have never come across a way for this. though I can n't say it is not there.
But I guess it may not be feasible too becuase as we know the current AWR report contains data which is specific for one instance.
Various hit ratios, top events, instance effeciency reports.... what not ..
It would be really nice to see something is a new format where it lists values from each instance in a single report.. I guess such a thing Does not exiist as of now.

Question about DBCA generate script o create RAC database 2 node cluster

Question about creating two node RAC database 11g after installing and configuration 11g clusterware. I've used DBCA to generate script to create a rac database. I've set
environment variable ORACLE_SID=RAC and the creating script creates instance of RAC1 and RAC2. My understanding is that each node will represent a node, however there should only be one database with a name of 'RAC'. Please advise

You are getting your terminology mixed up.
You only have one database. Take a look, there are one set of datafiles on shared storage.
You have 2 instances which are accessing one database.
Database name is RAC. Instance names are RAC1, RAC2, etc, etc.
Also, if you look at the listener configuration and if your tnsnames is setup properly then connecting to RAC will connect you to either one of the instances wheras connecting to RAC1 will connect you to that instance.

ORA-20600 error while trying to add RAC database

I'm receiving the following error while trying to add the RAC database in grid control. Any idea?.
ORA-20600: The specified target is in the process of being deleted
This database doesn't exists in targets. But, I'm still unable to add.

Check the metalink Note: Unable To Add Rac Database To Grid Control Getting Error Ora-20600 [ID 1218797.1]
You need to wait for a while and check the status.

Anybody using 11g RAC Database with OIM 9.1.0.2?

Hi,
We have poor performance problems with 11g RAC Database with OIM 9.1.0.2.
It looks like the issue could be because of RAC Ccluster.
Anybody using 11g RAC Database with OIM 9.1.0.2?
If so, What is the JDBC Driver r u using? Also what App Server (Weblogic or OAS etc) ?
Appreciate your input.
Regards
Vijay Chinnasamy

We are using weblogic 10.3. And I am sorry to tell you that we are yet to move to production.
We are planning to have Database in RAC, so i just thought of taking inputs from you.
can you tell me under what operations you face the poor performance issue?
For us the max no. of users in production is around 6k. So I am wondering how this RAC availability will affect the performance.
Thanks for sharing your inputs.

Can not start Rac database

Hi,
Oracle RAC database 10.2.0.3/RedHat4 with 2 nodes.
In the begining we had an error ORA-600[12803] so only sys can connect to database I find the note 1026653.6 this note said that we need to create AUDSES$ sequence but befor that we have to restart the database.
When we stop the datanbase we had another ORA-600 and it's impossible to start it!!
Here is a coppy of our alert file:
Picked latch-free SCN scheme 2
Autotune of undo retention is turned on.
LICENSE_MAX_USERS = 0
SYS auditing is disabled
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.3.0.
System parameters with non-default values:
processes = 300
sessions = 335
sga_max_size = 524288000
__shared_pool_size = 310378496
__large_pool_size = 4194304
__java_pool_size = 8388608
__streams_pool_size = 8388608
spfile = +DATA/osista/spfileosista.ora
nls_language = FRENCH
nls_territory = FRANCE
nls_length_semantics = CHAR
sga_target = 524288000
control_files = DATA/osista/controlfile/control01.ctl, DATA/osista/controlfile/control02.ctl
db_block_size = 8192
__db_cache_size = 184549376
compatible = 10.2.0.3.0
log_archive_dest_1 = LOCATION=USE_DB_RECOVERY_FILE_DEST
db_file_multiblock_read_count= 16
cluster_database = TRUE
cluster_database_instances= 2
db_create_file_dest = +DATA
db_recovery_file_dest = +FLASH
db_recovery_file_dest_size= 68543315968
thread = 2
instance_number = 2
undo_management = AUTO
undo_tablespace = UNDOTBS2
undo_retention = 29880
remote_login_passwordfile= EXCLUSIVE
db_domain =
dispatchers = (PROTOCOL=TCP) (SERVICE=OSISTAXDB)
local_listener = (address=(protocol=tcp)(port=1521)(host=132.147.160.243))
remote_listener = LISTENERS_OSISTA
job_queue_processes = 10
background_dump_dest = /oracle/product/admin/OSISTA/bdump
user_dump_dest = /oracle/product/admin/OSISTA/udump
core_dump_dest = /oracle/product/admin/OSISTA/cdump
audit_file_dest = /oracle/product/admin/OSISTA/adump
db_name = OSISTA
open_cursors = 300
pga_aggregate_target = 104857600
aq_tm_processes = 1
Cluster communication is configured to use the following interface(s) for this instance
172.16.0.2
Wed Jun 13 11:04:30 2012
cluster interconnect IPC version:Oracle UDP/IP (generic)
IPC Vendor 1 proto 2
PMON started with pid=2, OS id=8560
DIAG started with pid=3, OS id=8562
PSP0 started with pid=4, OS id=8566
LMON started with pid=5, OS id=8570
LMD0 started with pid=6, OS id=8574
LMS0 started with pid=7, OS id=8576
LMS1 started with pid=8, OS id=8580
MMAN started with pid=9, OS id=8584
DBW0 started with pid=10, OS id=8586
LGWR started with pid=11, OS id=8588
CKPT started with pid=12, OS id=8590
SMON started with pid=13, OS id=8592
RECO started with pid=14, OS id=8594
CJQ0 started with pid=15, OS id=8596
MMON started with pid=16, OS id=8598
Wed Jun 13 11:04:31 2012
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
MMNL started with pid=17, OS id=8600
Wed Jun 13 11:04:31 2012
starting up 1 shared server(s) ...
Wed Jun 13 11:04:31 2012
lmon registered with NM - instance id 2 (internal mem no 1)
Wed Jun 13 11:04:31 2012
Reconfiguration started (old inc 0, new inc 2)
List of nodes:
1
Global Resource Directory frozen
* allocate domain 0, invalid = TRUE
Communication channels reestablished
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Wed Jun 13 11:04:31 2012
LMS 0: 0 GCS shadows cancelled, 0 closed
Wed Jun 13 11:04:31 2012
LMS 1: 0 GCS shadows cancelled, 0 closed
Set master node info
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Post SMON to start 1st pass IR
Wed Jun 13 11:04:31 2012
LMS 0: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:04:31 2012
LMS 1: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:04:31 2012
Submitted all GCS remote-cache requests
Fix write in gcs resources
Reconfiguration complete
LCK0 started with pid=20, OS id=8877
Wed Jun 13 11:04:43 2012
alter database mount
Wed Jun 13 11:04:43 2012
This instance was first to mount
Wed Jun 13 11:04:43 2012
Starting background process ASMB
ASMB started with pid=25, OS id=10068
Starting background process RBAL
RBAL started with pid=26, OS id=10072
Wed Jun 13 11:04:47 2012
SUCCESS: diskgroup DATA was mounted
Wed Jun 13 11:04:51 2012
Setting recovery target incarnation to 1
Wed Jun 13 11:04:52 2012
Successful mount of redo thread 2, with mount id 3005749259
Wed Jun 13 11:04:52 2012
Database mounted in Shared Mode (CLUSTER_DATABASE=TRUE)
Completed: alter database mount
Wed Jun 13 11:05:06 2012
alter database open
Wed Jun 13 11:05:06 2012
This instance was first to open
Wed Jun 13 11:05:06 2012
Beginning crash recovery of 1 threads
parallel recovery started with 2 processes
Wed Jun 13 11:05:07 2012
Started redo scan
Wed Jun 13 11:05:07 2012
Completed redo scan
61 redo blocks read, 4 data blocks need recovery
Wed Jun 13 11:05:07 2012
Started redo application at
Thread 1: logseq 7924, block 3, scn 506098125
Wed Jun 13 11:05:07 2012
Recovery of Online Redo Log: Thread 1 Group 2 Seq 7924 Reading mem 0
Mem# 0: +DATA/osista/onlinelog/group_2.372.742132543
Wed Jun 13 11:05:07 2012
Completed redo application
Wed Jun 13 11:05:07 2012
Completed crash recovery at
Thread 1: logseq 7924, block 64, scn 506118186
4 data blocks read, 4 data blocks written, 61 redo blocks read
Switch log for thread 1 to sequence 7925
Picked broadcast on commit scheme to generate SCNs
db_recovery_file_dest_size of 65368 MB is 0.61% used. This is a
user-specified limit on the amount of space that will be used by this
database for recovery-related files, and does not reflect the amount of
space available in the underlying filesystem or ASM diskgroup.
SUCCESS: diskgroup FLASH was mounted
SUCCESS: diskgroup FLASH was dismounted
Thread 1 advanced to log sequence 7926
SUCCESS: diskgroup FLASH was mounted
SUCCESS: diskgroup FLASH was dismounted
Thread 1 advanced to log sequence 7927
Wed Jun 13 11:05:11 2012
LGWR: STARTING ARCH PROCESSES
ARC0 started with pid=31, OS id=12747
Wed Jun 13 11:05:11 2012
ARC0: Archival started
ARC1: Archival started
LGWR: STARTING ARCH PROCESSES COMPLETE
ARC1 started with pid=32, OS id=12749
Wed Jun 13 11:05:12 2012
Thread 2 opened at log sequence 7176
Current log# 4 seq# 7176 mem# 0: +DATA/osista/onlinelog/group_4.289.742134597
Wed Jun 13 11:05:12 2012
ARC1: Becoming the 'no FAL' ARCH
ARC1: Becoming the 'no SRL' ARCH
Wed Jun 13 11:05:12 2012
Successful open of redo thread 2
Wed Jun 13 11:05:12 2012
MTTR advisory is disabled because FAST_START_MTTR_TARGET is not set
Wed Jun 13 11:05:12 2012
ARC0: Becoming the heartbeat ARCH
Wed Jun 13 11:05:12 2012
SMON: enabling cache recovery
Wed Jun 13 11:05:15 2012
Successfully onlined Undo Tablespace 20.
Wed Jun 13 11:05:15 2012
SMON: enabling tx recovery
Wed Jun 13 11:05:15 2012
Database Characterset is AL32UTF8
Wed Jun 13 11:05:16 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_9174.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Wed Jun 13 11:05:16 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_9174.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Error 600 happened during db open, shutting down database
USER: terminating instance due to error 600
Instance terminated by USER, pid = 9174
ORA-1092 signalled during: alter database open...
Wed Jun 13 11:06:16 2012
Starting ORACLE instance (normal)
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Interface type 1 eth0 172.16.0.0 configured from OCR for use as a cluster interconnect
Interface type 1 bond0 132.147.160.0 configured from OCR for use as a public interface
Picked latch-free SCN scheme 2
Autotune of undo retention is turned on.
LICENSE_MAX_USERS = 0
SYS auditing is disabled
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.3.0.
System parameters with non-default values:
processes = 300
sessions = 335
sga_max_size = 524288000
__shared_pool_size = 314572800
__large_pool_size = 4194304
__java_pool_size = 8388608
__streams_pool_size = 8388608
spfile = +DATA/osista/spfileosista.ora
nls_language = FRENCH
nls_territory = FRANCE
nls_length_semantics = CHAR
sga_target = 524288000
control_files = DATA/osista/controlfile/control01.ctl, DATA/osista/controlfile/control02.ctl
db_block_size = 8192
__db_cache_size = 180355072
compatible = 10.2.0.3.0
log_archive_dest_1 = LOCATION=USE_DB_RECOVERY_FILE_DEST
db_file_multiblock_read_count= 16
cluster_database = TRUE
cluster_database_instances= 2
db_create_file_dest = +DATA
db_recovery_file_dest = +FLASH
db_recovery_file_dest_size= 68543315968
thread = 2
instance_number = 2
undo_management = AUTO
undo_tablespace = UNDOTBS2
undo_retention = 29880
remote_login_passwordfile= EXCLUSIVE
db_domain =
dispatchers = (PROTOCOL=TCP) (SERVICE=OSISTAXDB)
local_listener = (address=(protocol=tcp)(port=1521)(host=132.147.160.243))
remote_listener = LISTENERS_OSISTA
job_queue_processes = 10
background_dump_dest = /oracle/product/admin/OSISTA/bdump
user_dump_dest = /oracle/product/admin/OSISTA/udump
core_dump_dest = /oracle/product/admin/OSISTA/cdump
audit_file_dest = /oracle/product/admin/OSISTA/adump
db_name = OSISTA
open_cursors = 300
pga_aggregate_target = 104857600
aq_tm_processes = 1
Cluster communication is configured to use the following interface(s) for this instance
172.16.0.2
Wed Jun 13 11:06:16 2012
cluster interconnect IPC version:Oracle UDP/IP (generic)
IPC Vendor 1 proto 2
PMON started with pid=2, OS id=18682
DIAG started with pid=3, OS id=18684
PSP0 started with pid=4, OS id=18695
LMON started with pid=5, OS id=18704
LMD0 started with pid=6, OS id=18721
LMS0 started with pid=7, OS id=18735
LMS1 started with pid=8, OS id=18753
MMAN started with pid=9, OS id=18767
DBW0 started with pid=10, OS id=18788
LGWR started with pid=11, OS id=18796
CKPT started with pid=12, OS id=18799
SMON started with pid=13, OS id=18801
RECO started with pid=14, OS id=18803
CJQ0 started with pid=15, OS id=18805
MMON started with pid=16, OS id=18807
Wed Jun 13 11:06:17 2012
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
MMNL started with pid=17, OS id=18809
Wed Jun 13 11:06:17 2012
starting up 1 shared server(s) ...
Wed Jun 13 11:06:17 2012
lmon registered with NM - instance id 2 (internal mem no 1)
Wed Jun 13 11:06:17 2012
Reconfiguration started (old inc 0, new inc 2)
List of nodes:
1
Global Resource Directory frozen
* allocate domain 0, invalid = TRUE
Communication channels reestablished
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Wed Jun 13 11:06:18 2012
LMS 0: 0 GCS shadows cancelled, 0 closed
Wed Jun 13 11:06:18 2012
LMS 1: 0 GCS shadows cancelled, 0 closed
Set master node info
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Post SMON to start 1st pass IR
Wed Jun 13 11:06:18 2012
LMS 0: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:06:18 2012
LMS 1: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:06:18 2012
Submitted all GCS remote-cache requests
Fix write in gcs resources
Reconfiguration complete
LCK0 started with pid=20, OS id=18816
Wed Jun 13 11:06:18 2012
ALTER DATABASE MOUNT
Wed Jun 13 11:06:18 2012
This instance was first to mount
Wed Jun 13 11:06:18 2012
Reconfiguration started (old inc 2, new inc 4)
List of nodes:
0 1
Wed Jun 13 11:06:18 2012
Starting background process ASMB
Wed Jun 13 11:06:18 2012
Global Resource Directory frozen
Communication channels reestablished
ASMB started with pid=22, OS id=18913
Starting background process RBAL
* domain 0 valid = 0 according to instance 0
Wed Jun 13 11:06:18 2012
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Wed Jun 13 11:06:18 2012
LMS 0: 0 GCS shadows cancelled, 0 closed
Wed Jun 13 11:06:18 2012
LMS 1: 0 GCS shadows cancelled, 0 closed
Set master node info
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Wed Jun 13 11:06:18 2012
LMS 0: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:06:18 2012
LMS 1: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:06:18 2012
Submitted all GCS remote-cache requests
Fix write in gcs resources
RBAL started with pid=23, OS id=18917
Reconfiguration complete
Wed Jun 13 11:06:22 2012
SUCCESS: diskgroup DATA was mounted
Wed Jun 13 11:06:26 2012
Setting recovery target incarnation to 1
Wed Jun 13 11:06:26 2012
Successful mount of redo thread 2, with mount id 3005703530
Wed Jun 13 11:06:26 2012
Database mounted in Shared Mode (CLUSTER_DATABASE=TRUE)
Completed: ALTER DATABASE MOUNT
Wed Jun 13 11:06:27 2012
ALTER DATABASE OPEN
This instance was first to open
Wed Jun 13 11:06:27 2012
Beginning crash recovery of 1 threads
parallel recovery started with 2 processes
Wed Jun 13 11:06:27 2012
Started redo scan
Wed Jun 13 11:06:27 2012
Completed redo scan
61 redo blocks read, 4 data blocks need recovery
Wed Jun 13 11:06:28 2012
Started redo application at
Thread 2: logseq 7176, block 3
Wed Jun 13 11:06:28 2012
Recovery of Online Redo Log: Thread 2 Group 4 Seq 7176 Reading mem 0
Mem# 0: +DATA/osista/onlinelog/group_4.289.742134597
Wed Jun 13 11:06:28 2012
Completed redo application
Wed Jun 13 11:06:28 2012
Completed crash recovery at
Thread 2: logseq 7176, block 64, scn 506138248
4 data blocks read, 4 data blocks written, 61 redo blocks read
Picked broadcast on commit scheme to generate SCNs
Wed Jun 13 11:06:28 2012
LGWR: STARTING ARCH PROCESSES
ARC0 started with pid=28, OS id=19692
Wed Jun 13 11:06:28 2012
ARC0: Archival started
ARC1: Archival started
LGWR: STARTING ARCH PROCESSES COMPLETE
ARC1 started with pid=29, OS id=19695
Wed Jun 13 11:06:28 2012
Thread 2 advanced to log sequence 7177
Thread 2 opened at log sequence 7177
Current log# 3 seq# 7177 mem# 0: +DATA/osista/onlinelog/group_3.291.742134597
Successful open of redo thread 2
Wed Jun 13 11:06:28 2012
MTTR advisory is disabled because FAST_START_MTTR_TARGET is not set
Wed Jun 13 11:06:28 2012
ARC0: Becoming the 'no FAL' ARCH
ARC0: Becoming the 'no SRL' ARCH
Wed Jun 13 11:06:28 2012
ARC1: Becoming the heartbeat ARCH
Wed Jun 13 11:06:28 2012
SMON: enabling cache recovery
Wed Jun 13 11:06:28 2012
db_recovery_file_dest_size of 65368 MB is 0.61% used. This is a
user-specified limit on the amount of space that will be used by this
database for recovery-related files, and does not reflect the amount of
space available in the underlying filesystem or ASM diskgroup.
SUCCESS: diskgroup FLASH was mounted
SUCCESS: diskgroup FLASH was dismounted
Wed Jun 13 11:06:31 2012
Successfully onlined Undo Tablespace 20.
Wed Jun 13 11:06:31 2012
SMON: enabling tx recovery
Wed Jun 13 11:06:31 2012
Database Characterset is AL32UTF8
Wed Jun 13 11:06:31 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_19596.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Wed Jun 13 11:06:32 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_19596.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Error 600 happened during db open, shutting down database
USER: terminating instance due to error 600
Instance terminated by USER, pid = 19596
ORA-1092 signalled during: ALTER DATABASE OPEN...
Wed Jun 13 11:11:35 2012
Starting ORACLE instance (normal)
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Interface type 1 eth0 172.16.0.0 configured from OCR for use as a cluster interconnect
Interface type 1 bond0 132.147.160.0 configured from OCR for use as a public interface
Picked latch-free SCN scheme 2
Autotune of undo retention is turned on.
LICENSE_MAX_USERS = 0
SYS auditing is disabled
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.3.0.
System parameters with non-default values:
processes = 300
sessions = 335
sga_max_size = 524288000
__shared_pool_size = 318767104
__large_pool_size = 4194304
__java_pool_size = 8388608
__streams_pool_size = 8388608
spfile = +DATA/osista/spfileosista.ora
nls_language = FRENCH
nls_territory = FRANCE
nls_length_semantics = CHAR
sga_target = 524288000
control_files = DATA/osista/controlfile/control01.ctl, DATA/osista/controlfile/control02.ctl
db_block_size = 8192
__db_cache_size = 176160768
compatible = 10.2.0.3.0
log_archive_dest_1 = LOCATION=USE_DB_RECOVERY_FILE_DEST
db_file_multiblock_read_count= 16
cluster_database = TRUE
cluster_database_instances= 2
db_create_file_dest = +DATA
db_recovery_file_dest = +FLASH
db_recovery_file_dest_size= 68543315968
thread = 2
instance_number = 2
undo_management = AUTO
undo_tablespace = UNDOTBS2
undo_retention = 29880
remote_login_passwordfile= EXCLUSIVE
db_domain =
dispatchers = (PROTOCOL=TCP) (SERVICE=OSISTAXDB)
local_listener = (address=(protocol=tcp)(port=1521)(host=132.147.160.243))
remote_listener = LISTENERS_OSISTA
job_queue_processes = 10
background_dump_dest = /oracle/product/admin/OSISTA/bdump
user_dump_dest = /oracle/product/admin/OSISTA/udump
core_dump_dest = /oracle/product/admin/OSISTA/cdump
audit_file_dest = /oracle/product/admin/OSISTA/adump
db_name = OSISTA
open_cursors = 300
pga_aggregate_target = 104857600
aq_tm_processes = 1
Cluster communication is configured to use the following interface(s) for this instance
172.16.0.2
Wed Jun 13 11:11:35 2012
cluster interconnect IPC version:Oracle UDP/IP (generic)
IPC Vendor 1 proto 2
PMON started with pid=2, OS id=16101
DIAG started with pid=3, OS id=16103
PSP0 started with pid=4, OS id=16105
LMON started with pid=5, OS id=16107
LMD0 started with pid=6, OS id=16110
LMS0 started with pid=7, OS id=16112
LMS1 started with pid=8, OS id=16116
MMAN started with pid=9, OS id=16120
DBW0 started with pid=10, OS id=16132
LGWR started with pid=11, OS id=16148
CKPT started with pid=12, OS id=16169
SMON started with pid=13, OS id=16185
RECO started with pid=14, OS id=16203
CJQ0 started with pid=15, OS id=16219
MMON started with pid=16, OS id=16227
Wed Jun 13 11:11:36 2012
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
MMNL started with pid=17, OS id=16229
Wed Jun 13 11:11:36 2012
starting up 1 shared server(s) ...
Wed Jun 13 11:11:36 2012
lmon registered with NM - instance id 2 (internal mem no 1)
Wed Jun 13 11:11:36 2012
Reconfiguration started (old inc 0, new inc 2)
List of nodes:
1
Global Resource Directory frozen
* allocate domain 0, invalid = TRUE
Communication channels reestablished
Master broadcasted resource hash value bitmaps
Non-local Process blocks cleaned out
Wed Jun 13 11:11:36 2012
LMS 0: 0 GCS shadows cancelled, 0 closed
Wed Jun 13 11:11:36 2012
LMS 1: 0 GCS shadows cancelled, 0 closed
Set master node info
Submitted all remote-enqueue requests
Dwn-cvts replayed, VALBLKs dubious
All grantable enqueues granted
Post SMON to start 1st pass IR
Wed Jun 13 11:11:36 2012
LMS 1: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:11:36 2012
LMS 0: 0 GCS shadows traversed, 0 replayed
Wed Jun 13 11:11:36 2012
Submitted all GCS remote-cache requests
Fix write in gcs resources
Reconfiguration complete
LCK0 started with pid=20, OS id=16235
Wed Jun 13 11:11:37 2012
ALTER DATABASE MOUNT
Wed Jun 13 11:11:37 2012
This instance was first to mount
Wed Jun 13 11:11:37 2012
Starting background process ASMB
ASMB started with pid=22, OS id=16343
Starting background process RBAL
RBAL started with pid=23, OS id=16347
Wed Jun 13 11:11:44 2012
SUCCESS: diskgroup DATA was mounted
Wed Jun 13 11:11:49 2012
Setting recovery target incarnation to 1
Wed Jun 13 11:11:49 2012
Successful mount of redo thread 2, with mount id 3005745065
Wed Jun 13 11:11:49 2012
Database mounted in Shared Mode (CLUSTER_DATABASE=TRUE)
Completed: ALTER DATABASE MOUNT
Wed Jun 13 11:22:25 2012
alter database open
This instance was first to open
Wed Jun 13 11:22:26 2012
Beginning crash recovery of 1 threads
parallel recovery started with 2 processes
Wed Jun 13 11:22:26 2012
Started redo scan
Wed Jun 13 11:22:26 2012
Completed redo scan
61 redo blocks read, 4 data blocks need recovery
Wed Jun 13 11:22:26 2012
Started redo application at
Thread 1: logseq 7927, block 3
Wed Jun 13 11:22:26 2012
Recovery of Online Redo Log: Thread 1 Group 1 Seq 7927 Reading mem 0
Mem# 0: +DATA/osista/onlinelog/group_1.283.742132543
Wed Jun 13 11:22:26 2012
Completed redo application
Wed Jun 13 11:22:26 2012
Completed crash recovery at
Thread 1: logseq 7927, block 64, scn 506178382
4 data blocks read, 4 data blocks written, 61 redo blocks read
Switch log for thread 1 to sequence 7928
Picked broadcast on commit scheme to generate SCNs
Wed Jun 13 11:22:27 2012
LGWR: STARTING ARCH PROCESSES
ARC0 started with pid=31, OS id=13010
Wed Jun 13 11:22:27 2012
ARC0: Archival started
ARC1: Archival started
LGWR: STARTING ARCH PROCESSES COMPLETE
ARC1 started with pid=32, OS id=13033
Wed Jun 13 11:22:27 2012
Thread 2 opened at log sequence 7178
Current log# 4 seq# 7178 mem# 0: +DATA/osista/onlinelog/group_4.289.742134597
Successful open of redo thread 2
Wed Jun 13 11:22:27 2012
MTTR advisory is disabled because FAST_START_MTTR_TARGET is not set
Wed Jun 13 11:22:27 2012
ARC0: Becoming the 'no FAL' ARCH
ARC0: Becoming the 'no SRL' ARCH
Wed Jun 13 11:22:27 2012
ARC1: Becoming the heartbeat ARCH
Wed Jun 13 11:22:27 2012
SMON: enabling cache recovery
Wed Jun 13 11:22:30 2012
db_recovery_file_dest_size of 65368 MB is 0.61% used. This is a
user-specified limit on the amount of space that will be used by this
database for recovery-related files, and does not reflect the amount of
space available in the underlying filesystem or ASM diskgroup.
SUCCESS: diskgroup FLASH was mounted
SUCCESS: diskgroup FLASH was dismounted
Wed Jun 13 11:22:31 2012
Successfully onlined Undo Tablespace 20.
Wed Jun 13 11:22:31 2012
SMON: enabling tx recovery
Wed Jun 13 11:22:32 2012
Database Characterset is AL32UTF8
Wed Jun 13 11:22:32 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_11751.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Wed Jun 13 11:22:33 2012
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_11751.trc:
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []
Error 600 happened during db open, shutting down database
USER: terminating instance due to error 600
Instance terminated by USER, pid = 11751
ORA-1092 signalled during: alter database open...
regards,

Hi;
Errors in file /oracle/product/admin/OSISTA/udump/osista2_ora_9174.trc:Did you check trc file?
ORA-00600: code d'erreur interne, arguments : [kokiasg1], [], [], [], [], [], [], []You are getting oracle internal error(ORA 600) which mean you could need to work wiht oracle support team. Please see below note, if its not help than i suggest log a sr:
Troubleshoot an ORA-600 or ORA-7445 Error Using the Error Lookup Tool [ID 153788.1]
for your future rac issue please use Forum Home » High Availability » RAC, ASM & Clusterware Installation which is RAC dedicated forum site.
Regard
Helios

Multiple RAC databases on same GI using different subnets for Public i/face

Hello. We are configuring a 2 node cluster. That cluster will host several RAC databases. For security reasons our networking team want to create separate subnets for the application traffic to each specific RAC database on the cluster.
E.g. application 1 has 2 application servers that will connect to RAC database PROD1 via one subnet, application 2 has 3 application servers that will connect to RAC database PROD2 via a different subnet, etc.
In addition the networking team want to configure a separate management subnet that DBAs etc. will use to administer all RAC databases and infrastructure in the cluster.
Grid Infrastructure version 11.2.0.2. Database versions will vary from 10.2.0.x to 11.2.0.2. All databases will utilise RAC.
We want to take advantage of SCAN listener functionality to support connectivity to all databases on the cluster. Forum thread 2199620 [https://cn.forums.oracle.com/forums/thread.jspa?threadID=2199620] suggests that 11gR2 supports multiple subnets, which looks to be exactly the feature we need. Please can you confirm how this works and point us to any documentation (standard docs, white papers, MOS, etc.) that might help us configure this.
Document referenced in thread 2199620 was not exactly what we were looking for, and didn't translate too well in Google Translate.
Any guidance much appreciated. Thanks, Rich.
Similar threads:
https://cn.forums.oracle.com/forums/thread.jspa?messageID=9846298? (Dual SCAN on multi homed cluster)
https://cn.forums.oracle.com/forums/thread.jspa?threadID=2199620 (scan listener in OAM VLAN)
Edited by: 887449 on 26-Sep-2011 01:41

Thanks Levi. Your advice is very much appreciated.
Your statement that we can only have one SCAN listener listening on one public network is actually the clarification I was looking for.
For anyone else reading this thread I believe this gives us 3 options:
1) Configure a SCAN listener and have all applications, and all management/administration, connecting to the corresponding database on the same cluster via that SCAN listener, all on the same subnet.
2) Configure a SCAN listener for use by all applications connecting to the corresponding database on the same cluster, and use TNSNAMES/VIP for management/administration traffic, both on separate subnets (by configuring the LISTENER_NETWORKS parameter)
3) Configure a SCAN listener for use by applications connecting to one of the databases on the cluster via one subnet, use TNSNAMES/VIP for all other applications connecting to other databases, each using their own subnet. Plus, the management/administration could be via another subnet utilising TNSNAMES/VIP.
From our perspective we will work out the best one for us and implement accordingly.
Thanks again for your timely and comprehensive response.

Help needed in deleting nodes from RAC database

Our DB is 10g RAC database and the servers are Window 2003 server. Initially the database was configured to have 4 nodes. For some reason we stopped the instances in the first two nodes and the current database is running on node3 and node4. I queried the v$thread view and it shows 3 records. Thread 2 is closed and disabled. Thread 3 is open and public and thread 4 is open and private. Now we need to disconnect nodes 1 and 2 from RAC db and cluster ware (We use Oracle cluster ware) and plan to use those two servers for other purposes. Although I read through the Oracle doc regarding deleting node from RAC “11 Adding and Deleting Nodes and Instances on Windows-Based Systems” and wrote down the steps we need to take but I am still not comfortable in doing it since it is production env and we don’t have any dev env to practice those steps. So I would like to borrow your experiences and your lessons learned while you were doing those. Please share your thoughts and insights with us.
Thank you so much for your help,
Shirley

what's your full version? I can warn about specific issues in 10.1.0.3 and 10.2.0.1 - for example, in some cases (depending on how the listener was configured), it will be impossible to delete the listener for the deleted node. Known bug.
To avoid many many known bugs, you may want to upgrade to at least 10.2.0.2 before removing a node (from my experience, this is the first stable RAC version).
In any case, deleting a node is a rather delicate process. I really really recommend practicing. Take any pc/laptop, install VMWARE, define two virtual machines, install RAC and remove one node. It will take you an extra day or two, and could save your production.

How to install Oracle 11.2.0.4.0 Rac Database on Grid Infrastructure 12.1.0.2.0 (Windows 2012 R2)

Hi all.
This is the scenario:
I have a 2 node cluster Microsoft Windows 2012 R2 x86_64, the nodes are part of domain.
Installed Oracle 12cR1 (12.1.0.2.0) as follows:
Installation done using domain administrator named "installoracle" that has been EXPLICIT promoted to local administrator in both nodes.
One domain user named "oracle12c" with no administrator privileges neither in the domain or nodes.
Installation, after a lot of customization in the OS of the nodes, has gone ok, perfect indeed, not even a warning during runinstaller execution.
All services and resources are up & running, I have rebooted nodes and all comes back ok in place. In windows services I can see some services started with "oracle12c" user, and all windows groups: DBA, SYSKM, etc, has been created.
Now I have to install Oracle RAC database in 11gR2 version (11.2.0.4.0) to accomplish with application requirements.
So, I execute runInstaller (setup.exe) logged as administrator via domain administrator "installoracle" (the one that was able to do the smooth 12c GI installation) and the gui comes with out problems, but at 4th screen the one in which you have to choose what kind of installation you want to do (Single, RAC or RoN) I select RAC option, the gui returns error: crs is not running in the local node...
Finally, in order to deliver some database 11.2.0.4.0 for my customer, I try to do installation of SW for Single Node, I did using "installoracle". The sw has been installed in one of the nodes. Then I have created a database and I have stored datafiles in ASM (this ASM is part of 12c clusterware) and also register the 11gR2 single instance database in the Grid Infrastructure listener
So, whats next??? Why is this behavior??? I did similar installations in Linux/Solaris with no issue (well as everyone can imagine, always there are some issues, but when solved you got GI in 12c and databases in the release that you want 12c, 11g, 10g...)
Any clue?
Thanks in advance!!
Best Regards!!

To go back to old version (without changing compatible parameter), you can perform downgrade.
Instructions are available at
How to Downgrade from Database 11.2 to Previous Release (Includes 11.2.0.4 - 11.2.0.1) (Doc ID 883335.1)
In this case you will having all the data file including the new one.
But remember database may not be in the same status as before (Before upgrade). it may have invalid objects of higher version after downgrade.
Downgrade is applicable only to successfully upgraded databases. In case upgrade faced some issue, do not try downgrade there.
Your second approach it not correct. Note that each datafile header will have db version. We can not open database in normal mode when header version and binary versions are different.

Data Guard configuration for RAC database disappeared from Grid control

Primary Database Environment - Three node cluster
RAC Database 10.2.0.1.0
Linux Red Hat 4.0 2.6.9-22 64bit
ASM 10.2.0.1.0
Management Agent 10.2.0.2.0
Standby Database Environment - one Node database
Oracle Enterprise Edition 10.2.0.1.0 Single standby
Linux Red Hat 4.0 2.6.9-22 64bit
ASM 10.2.0.1.0
Management Agent 10.2.0.2.0
Grid Control 10.2.0.1.0 - Node separate from standby and cluster environments
Oracle 10.1.0.1.0
Grid Control 10.2.0.1.0
Red Hat 4.0 2.6.9-22 32bit
After adding a logical standby database through Grid Control for a RAC database, I noticed sometime later the Data Guard configuration disappeared from Grid Control. Not sure why but it is gone. I did notice that something went wrong with the standby creation but i did not get much feedback from Grid Control. The last thing I did was to view the configuration, see output below.
Initializing
Connected to instance qdcls0427:ELCDV3
Starting alert log monitor...
Updating Data Guard link on database homepage...
Data Protection Settings:
Protection mode : Maximum Performance
Log Transport Mode settings:
ELCDV.qdx.com: ARCH
ELXDV: ARCH
Checking standby redo log files.....OK
Checking Data Guard status
ELCDV.qdx.com : ORA-16809: multiple warnings detected for the database
ELXDV : Creation status unknown
Checking Inconsistent Properties
Checking agent status
ELCDV.qdx.com
qdcls0387.qdx.com ... OK
qdcls0388.qdx.com ... OK
qdcls0427.qdx.com ... OK
ELXDV ... WARNING: No credentials available for target ELXDV
Attempting agent ping ... OK
Switching log file 672.Done
WARNING: Skipping check for applied log on ELXDV : disabled
Processing completed.
Here are the steps followed to add the standby database in Grid Control
Maintenance tab
Setup and Manage Data Guard
Logged in as sys
Add standby database
Create a new logical standby database
Perform a live backup of the primary database
Specify backup directory for staging area
Specify standby database name and Oracle home location
Specify file location staging area on standby node
At the end am presented with a review of the selected options and then the standby database is created
Has any body come across a similar issue?
Thanks,

Any resolution on this?
I just created a Logical Standby database and I'm getting the same warning (WARNING: No credentials available for target ...) when I do a 'Verify Configuration' from the Data Guard page.
Everything else seems to be working fine. Logs are being applied, etc.
I can't figure out what credentials its looking for.

Configured TNS in oracle client to RAC database

Hi Experts,
I have a 4 nodes oracle RAC in radhat 5.0
both oracle database and client as 10.2.0.4.
I created a TNS that works in our office but it does not work in our remote brance office.
Based on experts instruction, I set up sqlnet trace at client side. but not any file that be gererated.
In linux RAC database, I saw listener.log file as
28-AUG-2009 11:00:01 * (CONNECT_DATA=(SERVER=DEDICATED)(SERVICE_NAME=sale)(INSTANCE_NAME=sale1)(CID=(PR OGRAM=D:\oracle\product\10.2.0\client_1\BIN\sqlplusw.exe)(HOST=TRAC3)(USER=JIM))) * (ADDRESS=(PROTOCOL=tcp)( HOST=xxx.18.10.xx)(PORT=3289)) * establish * sale * 0
in client pc sqlnet.ora my setting as
SQLNET.AUTHENTICATION_SERVICES= (NTS)
TRACE_LEVEL_CLIENT = 16
TRACE_FILE_CLIENT = client
TRACE_DIRECTORY_CLIENT = C:\TEMPODBC
TRACE_TIMESTAMP_CLIENT = ON
SQLNET.EXPIRE_TIME =10
SQLNET.INBOUND_CONNECT_TIMEOUT = 500
SQLNET.SEND_TIMEOUT = 500
SQLNET.RECV_TIMEOUT = 500
I got a error as
ERROR:
ORA-03135: connection lost contact
which wrong is in my case?
I can connect to all other window database from thsi PC.But I can not connect to RAC database from this PC.
However, I can ping RAC node's IP and VIP from this PC
I also can connect to RAC database with TNS from other window PC.
What do I need to do?
ThanKs for any help.
JIM

Hi Sb92075,
Thanks for your help.
I got same error after comment #SQLNET.AUTHENTICATION_SERVICES= (NTS) in client sqlnet.ora in client.
the server side does not have sqlnet file in linux platform.
I also check listener services that all instance status is ready.
I just saw sqlnet.log file in server side that error as
Fatal NI connect error 12170.
VERSION INFORMATION:
TNS for Linux: Version 10.2.0.4.0 - Production
Oracle Bequeath NT Protocol Adapter for Linux: Version 10.2.0.4.0 - Production
TCP/IP NT Protocol Adapter for Linux: Version 10.2.0.4.0 - Production
Time: 28-AUG-2009 13:21:06
Tracing not turned on.
Tns error struct:
ns main err code: 12535
TNS-12535: TNS:operation timed out
ns secondary err code: 12606
nt main err code: 0
nt secondary err code: 0
nt OS err code: 0
Client address: (ADDRESS=(PROTOCOL=tcp)(HOST=xxx.18.xx.xx)(PORT=3513))
what do i need to do?
Thanks
JiM
Edited by: user589812 on Aug 28, 2009 10:22 AM

Get the table's rowid of the session that is locking in RAC database

I am a developer and not a DBA and I need to find th correct query to find the exact rowid of the record locked on a table. This is for a RAC database and locked record can be from the web form in oracle application server. When I try to get the correct row id, I get the following error:
ORA-01410 - Invalid row id
For the criteria, the output is Dbms_Rowid.rowid_create(1, -1, 36, 7845, 0), why I get a -1 for the ROW_WAIT_OBJ#?
Additional Information: The lock type is DML and the lock mode is: Row Exclusive, the table is locked and the program is web oracle forms executiong.
I am executing the query in Oracle Database 11g Enterprise Edition Release 11.1.0.7.0
How to accomplish gettting the correct rowid? Below is the selection criteria I have:
select vs.inst_id,
vs.audsid audsid,
locks.sid sid,
locks.type,
locks.id1 id1,
locks.id2 id2,
locks.lmode lmode,
locks.request request,
locks.ctime ctime,
locks.block block,
vs.serial# serial#,
vs.username oracle_user,
vs.osuser os_user,
vs.program program,
vs.module module,
vs.action action,
vs.process process,
decode(locks.lmode,
0, '0 None',
1, '1 NULL',
2, '2 Row Share',
3, '3 Row Exclusive',
4, '4 Share',
5, '5 Share Row Exclusive',
6, '6 Exclusive', '?') lock_mode_held,
decode(locks.request,
0, '0 None',
1, '1 NULL',
2, '2 Row Share',
3, '3 Row Exclusive',
4, '4 Share',
5, '5 Share Row Exclusive',
6, '6 Exclusive', '?') lock_mode_requested,
decode(locks.type,
'MR', 'Media Recovery',
'RT', 'Redo Thread',
'UN', 'User Name',
'TX', 'Transaction',
'TM', 'DML',
'UL', 'PL/SQL User Lock',
'DX', 'Distributed Xaction',
'CF', 'Control File',
'IS', 'Instance State',
'FS', 'File Set',
'IR', 'Instance Recovery',
'ST', 'Disk Space Transaction',
'TS', 'Temp Segment',
'IV', 'Library Cache Invalidation',
'LS', 'Log Start or Log Switch',
'RW', 'Row Wait',
'SQ', 'Sequence Number',
'TE', 'Extend Table',
'TT', 'Temp Table',
locks.type) lock_type,
vs.row_wait_obj# row_wait_obj#,
vs.row_wait_file# row_wait_file,
vs.row_wait_block# row_wait_block#,
vs.row_wait_row# row_wait_row#,
dbms_rowid.rowid_create ( 1, vs.ROW_WAIT_OBJ#, vs.ROW_WAIT_FILE#, vs.ROW_WAIT_BLOCK#, vs.ROW_WAIT_ROW# ) rowid_created,
objs.owner object_owner,
objs.object_name object_name,
objs.object_type object_type,
round( locks.ctime/60, 2 ) lock_time_in_minutes,
from gv$session vs,
gv$lock locks,
dba_objects objs,
dba_tables tbls
where locks.id1 = objs.object_id
and vs.sid = locks.sid
and objs.owner = tbls.owner
and objs.object_name = tbls.table_name
and objs.owner != 'SYS'
-- and locks.type in ('TM', 'TX')
order by lock_time_in_minutes;
Edited by: user3564713 on Jun 10, 2012 10:56 PM

Firstly, read this thread
Identifying locked rows
And the last bit from Randolf
>
It is a common misconception that you can locate a locked row in Oracle via a query. The point is that the information that you're querying only gets populated in case of a blocking lock, and even then not in every case, since you might have blocking locks that do not refer to a particular row.
Oracle stores the lock information within the block, so if you identified in which block the row is located that you've attempted to lock, you could get detailed information about the row locks of that block by performing a block dump.
Other than that Oracle doesn't maintain this information anywhere else and it is only externalized for blocking situations - it is a matter of design that there is no central lock manager in Oracle that would inherently limit scalability, hence the downside of that approach is that there is no central information pool where you could obtain detailed information about row level locks.
>
However, if you see support note "Sample Code to Select from a Table EXCLUDING Locked Rows [ID 186531.1]"
You can take the same code from the script in that note to identify rowid of the locked rows.

"Alter system set command" in a RAC database!!

Hi, all.
The database is (10.2.0.2.0) 2- node RAC database on 32-bit windows 2003
EE SP1.
I issued the following command on Node 1 database.
--> Alter system set db_block_buffers= xxx sid='rac1';
I was able to see "PE enqueue" in top 5 wait event section from an AWR report.
In addition, I was able to find "PZ99","PZ98" process dump file in BDUMP.
Soon later, I could find CKPT and DBWR hung.
Is there anyone who experienced this issue?
Thanks and Regards.
Message was edited by:
user507290

10.2.0.2 has some bug which is fixed 10.2.0.3
You check sequence cache. If it has less value, increase it to 10000.
select CACHE_SIZE from dba_sequences where SEQUENCE_OWNER='SYS' and SEQUENCE_NAME='AUDSES$';
SQL> alter sequence sys.audses$ cache 10000;
Ashok

DBA panel not working correctly for RAC databases

I hope this is the correct forum for this stuff... I learned that there is a DBA panel in SQL Developer - which is a great idea. But then, trying it on a RAC database, the output is quite confusing. For example, the init parameters are desplayed twice, or better: once for every instance. But a display column to identify the instance is missing. I assume that the query goes to gv$parameter but doesn't make use of the INST_ID column. Or am I lacking some configuration trick...?

This probably has nothing to do with your problem but something is screwed up in the way CSCC handles Configurator panels.
Converted a panel made for CS6 using Configurator4. Got it loaded into CC. It was not quite right so I made some minor changes. The changes never showed up in CC. Deleted the original folder under Panels, changed the name of the panel and reinstalled. Whoa! The original deleted panel was the only one that showed up under Extensions not the new one. This in spite of the fact that that folder no longer existied.
I have tried all sorts of maneauvers but the fact is that the original panel is the only one that PS recognizes even though it does not exist on the drive. It is locked into PS and nothing I have done will change it.
Larry

NIC ROUTER requirement for 10g RAC database

I need to know what hardware to order in setting up an 10g RAC database without a single-point-of-failure. My question centers on the networks. If each server has one NIC for the public interface and one NIC for the private interconnect, aren't the routers these NICs are attached to a single point of failure? If each server has two NICs bonded together for the public interface and two NICs bonded together for the private interconnect, does each NIC attach to a different router?

sayantan chakraborty wrote:
is RDMA and infiband ar same??Infiniband is a switched fabric layer for high speed communication. RDMA is a protocol for "+remote direct memory access+".
Infiniband supports the Internet Protocol suite over Infiniband, or IPoIB. It also supports RDMA over Infiniband.
so do we need only infiband SDR / QDR switch to set infiband OR what else??You need an Infiniband switch - Cisco and Voltaire are two companies that supply this type of hardware. The latter is used by Oracle in its Exadata database machines. Unsure about Cisco's commitment to Infiniband switches as they have discontinued their Infiniband switches with integrated fibre channel gateways. A sore point with us after we bought into this technology about 2 years ago, in part on their very own recommendations - and now own very expensive, somewhat buggy and totally unsupported hardware. Seems like the new Cisco California servers are GigE and not Infiniband, which perhaps explain this (flawed) decision of theirs...
For each cluster node, you need an Infiniband PCI card (typically has 2 ports). If you are going to use bonding, you will need a pair of Infiniband cables per server. Also remember to get spares - both PCI cards and cables.
If you want redundancy at the switch, you need to get yourself 2 Infiniband switches.
But if you're planning to invest this into a RAC cluster, then surely you should also invest money in RAC licensing and support - and with that gain access to very useful documentation like the RAC Starter Kit and so on.

RAC Database

Similar Messages

Maybe you are looking for