Application v/s RAC database

Hi Team,
Please clear me these doubts
As of now my application connects to the single instance oracle10g database
with IP, port and service
ex: 192.168.2.79:1521:orcl
Fine,
now we have a newly set 2 node RAC setup on RHEL4
how can i connect application to the RAC Database?
i have following scenarios
1. if i connect my application to node1's public ip:port:service
if node1 fails how failover happens2. Is there anything required for the application to explicitly specify for connecting RAC database 2 nodes
if you are not clear with above
my application identifies any single instance oracle database with IP:port:service
how can i make this to work for RAC databaseCan anyone please lighten me on this.
Thanks in Advance
AJ

You didn't post a version and 10g RAC is a different animal from 9i RAC.
A client will always be connected to 1 instance only.
Other than that I recommend you read up on Transparent Application Failover (in a standard install your tnsnames.ora already has been configured for TAF) and on FCF for Oracle 10g. Both are in the Net administrators manual.
Sybrand Bakker
Senior Oracle DBA

Similar Messages

Can I put ALL my applications into one RAC database

Dear all,
Is it possible to share all of my workloads between a single RAC database or would it be better to run more than one RAC database on the the same cluster if they have very different characteristics (e.g. OLTP vs DSS or sensitive vs non-sensitive data). Oracle seem to imply that they have cut down their number of physical databases drastically but have they been able to do that because the workload is very homongenous, i.e all ERP stuff? Should it be possible to accommodate all workloads by having different instance parameters or does that defeat the object of being able to fail over a service from one instance to another?
Views/experiences please.

Hi, generally it is possible to put everything into one RAC database, especially if they share the same data. So you do not have to transport data from one database into the other.
Furthermore the resource allocation can perfectly be addressed with the resource manager of the database together with services. The workload has not to be homogenous.
However it might make sense to connect the DSS users to different nodes in the cluster than the OLTP users (via. services).
On the other hand there might be non technical issues which would make seperate databases more attractive. Like Patching could mean downtime of all applications. Like certifications of software, which would not allow you to upgrade your database, like ERP needs 10.2.0.2 while DSS would be better off with 11g) and so on.
There is really no right or wrong.
Still to get the most of the benefits out of a cluster the fewer databases you have.

How to I find a RAC database in oracle SR support

Hi Friends,
I could not find a product name for oracle RAC /database in product box when I try to make a SR.
But I need to selecte a name from dripdown list. however I can not find a name that is for oracle RAC or real application cluster or RAC database
any suggestion?
thanks
Jim

Oracle Server - Enterprise Edition
Oracle Server - Personal Edition
Oracle Server - Standarad Edition
It's there. Look harder!
RAC is selected in the Problem drop-down.

Oracle RAC 10g - Application connect directly to database IP address

Hi,
I am a developer and does not have much knowledge about oracle admin. Sorry, if I don't use the term correctly.
We have a vendor application using Oracle RAC on two node (node1/vip1,node2/vip2). Our application was configured to use JDBC connection string (not TNS, someone told me it's a bad practice - but it's how our consultant vendor set it up). The connection string is configured to point to VIP1 hostname and VIP2 hostname.
When I look at the list of connections using netstat, I am seeing the connection was established to vip1's ip address as well as node2's ip address (no vip2 or node1 ip).
1) Should the application just only connect to VIP ip address and not to server ip address?
2) Because our JDBC entry only contains VIP1 and VIP2 hostname, does it normal that the application can resolve the NODE2 ipaddress? ( we look on all application's configuration files, we are sure that application does not have knowledge of node1/node2 ip address or hostname)
3) Is this a normal VIP hostname to be resolved to database ip address and not VIP ip address?
4) I read about VIP address that it will be mapped to the other node's MAC when the node fail, could this happen because VIP misconfiguration?
Edited by: user644523 on Aug 19, 2010 1:34 PM

Hi buddy,
When I look at the list of connections using netstat, I am seeing the connection was established to vip1's ip address as well as node2's ip address (no vip2 or node1 ip). pls show us what You are seing.
1) Should the application just only connect to VIP ip address and not to server ip address? Yes
2) Because our JDBC entry only contains VIP1 and VIP2 hostname, does it normal that the application can resolve the NODE2 ipaddress? ( we look on all application's configuration files, we are sure that application does not have knowledge of node1/node2 ip address or hostname)No it's not. It should use the vip until release 11.1 and on release 11.2 the scan
3) Is this a normal VIP hostname to be resolved to database ip address and not VIP ip address?no, it's not it should be resolved to the ip address configured to the VIP
4) I read about VIP address that it will be mapped to the other node's MAC when the node fail, could this happen because VIP misconfiguration?We have to check that. Get the nodeapps config (ask trhe dba the output off "srvctl config nodeapps -n <nodename> -a" ) for all nodes and check if the client machine is resolving the name to the right IP address. (good start I guess).
Regards,
Cerreia

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.

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.

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.

Another RMAN duplicate problem - RAC database to single instance

Hi,
I have a problem with the RMAN duplicate procedure and was hoping someone can help.
I would like to create a duplicate of our production RAC database on a separate, stand-alone, database server on another site. This duplicate will be used for intensive querying by another business unit who I don't want to have access to our production database.
My procedure goes like this:
1. Create a disk (not ASM) based backup of the datafiles and any archived redo logs:
"run {
allocate channel d1 type disk;
backup format '/u02/stage/df_t%t_s%s_p%p' database plus archivelog delete input;
release channel d1;
2. Tar and scp these files to the same location on the stand-alone database server.
3. In the meantime, work has been happening on the production database and further archived redo logs have been generated. I don't really care about these logs for the purposes of the duplicate however, I just want to duplicate to the point of the recent backup. To do this, I run the following SQL to determine the sequence number that I should be duplicating up to:
"select max(sequence#), thread# from v$archived_log where deleted='YES' group by thread#;"
4. Duplicate the production database to the stand-alone database (all the SQL Net stuff is working).
"run {
set until sequence (value returned by above SQL statement);
duplicate target database to XXX;
However, my problem arises because I don't know how to handle the fact that there are two threads. I understand that each thread relates to one of the RAC instances, I just don't know which one to specify for the duplicate. We have a database service which the client application connects through, and that service runs on on or other of the instances. Should I just care about the logs from the instance where the service is currently running?
Am I even approaching this is the correct way?
I look forward to any help that people may be able to offer.
Regards,
Phil

Hi Werner,
Thanks again for your help, there is still something wrong though. "list backup of archivelog all;" shows:
BS Key Size Device Type Elapsed Time Completion Time
3784 202.34M DISK 00:00:08 28-OCT-09
BP Key: 3784 Status: AVAILABLE Compressed: NO Tag: TAG20091028T111718
Piece Name: /u02/stage/df_t701435838_s3820_p1
List of Archived Logs in backup set 3784
Thrd Seq Low SCN Low Time Next SCN Next Time
1 9746 569095777 28-OCT-09 569150229 28-OCT-09
1 9747 569150229 28-OCT-09 569187892 28-OCT-09
1 9748 569187892 28-OCT-09 569231956 28-OCT-09
1 9749 569231956 28-OCT-09 569259816 28-OCT-09
2 7931 569095774 28-OCT-09 569187902 28-OCT-09
2 7932 569187902 28-OCT-09 569259814 28-OCT-09
BS Key Size Device Type Elapsed Time Completion Time
3787 1.04M DISK 00:00:02 28-OCT-09
BP Key: 3787 Status: AVAILABLE Compressed: NO Tag: TAG20091028T112222
Piece Name: /u02/stage/df_t701436142_s3823_p1
List of Archived Logs in backup set 3787
Thrd Seq Low SCN Low Time Next SCN Next Time
1 9750 569259816 28-OCT-09 569261110 28-OCT-09
2 7933 569259814 28-OCT-09 569261108 28-OCT-09
You can see that the highest sequence number is 9750 of thread 1, and that the Low and Next SCNs are 569259816 and 56926111. However, when I look at the output of the RMAN duplicate command:
contents of Memory Script:
set until scn 569505448;
recover
clone database
delete archivelog
executing Memory Script
executing command: SET until clause
Starting recover at 28-OCT-09
allocated channel: ORA_AUX_DISK_1
channel ORA_AUX_DISK_1: sid=39 devtype=DISK
starting media recovery
Oracle Error:
ORA-01547: warning: RECOVER succeeded but OPEN RESETLOGS would get error below
ORA-01194: file 4 needs more recovery to be consistent
ORA-01110: data file 4: '/u02/sca-standby/data/users.260.623418479'
RMAN-03002: failure of Duplicate Db command at 10/28/2009 16:12:55
RMAN-03015: error occurred in stored script Memory Script
RMAN-06053: unable to perform media recovery because of missing log
RMAN-06025: no backup of log thread 2 seq 7936 lowscn 569411744 found to restore
RMAN-06025: no backup of log thread 2 seq 7935 lowscn 569321987 found to restore
RMAN-06025: no backup of log thread 2 seq 7934 lowscn 569261108 found to restore
RMAN-06025: no backup of log thread 1 seq 9758 lowscn 569471890 found to restore
RMAN-06025: no backup of log thread 1 seq 9757 lowscn 569440076 found to restore
RMAN-06025: no backup of log thread 1 seq 9756 lowscn 569411439 found to restore
RMAN-06025: no backup of log thread 1 seq 9755 lowscn 569378529 found to restore
RMAN-06025: no backup of log thread 1 seq 9754 lowscn 569358970 found to restore
RMAN-06025: no backup of log thread 1 seq 9753 lowscn 569321882 found to restore
RMAN-06025: no backup of log thread 1 seq 9752 lowscn 569284238 found to restore
RMAN-06025: no backup of log thread 1 seq 9751 lowscn 569261110 found to restore
you can see that something is setting the recovery SCN to 569505448 which higher even then any of the archived logs mentioned above. If I select current_scn from the production database, this gives me 569528258 which is closer to the value which RMAN is expecting to recover to than any of the archived redo logs.
Can you think what might be causing RMAN to try to recover to this value? and why does it appear to be ignoring the SET UNTIL SEQUENCE command?
Cheers,
Phil

Use Oracle RAC Database 10g on SunOS nova 5.9

Hello!
We use Oracle RAC Database 10g Enterprise Edition Release 10.1.0.5.0 - 64bit that consist of two nodes on SunOS nova 5.9 Generic_117171-17 sun4u sparc SUNW,Sun-Fire-V440.
Connection string as follows:
jdbc:oracle:thin:@(DESCRIPTION=(LOAD_BALANCE=ON)(ADDRESS=(PROTOCOL=TCP)(HOST=host1)(PORT=1521))(ADDRESS=
(PROTOCOL=TCP)(HOST=host2)(PORT=1521))(CONNECT_DATA=(SERVER=DEDICATED)(SERVICE_NAME=proddb))).
Clustered Java application performs direct JDBC INSERT of record into database throw oracle.jdbc.pool.OracleDataSource.
Table got the following fields:
FIELD1 VARCHAR2(100 BYTE) NOT NULL,
FIELD2 VARCHAR2(100 BYTE) NOT NULL,
FIELD3 VARCHAR2(100 BYTE) NOT NULL,
FIELD4 VARCHAR2(100 BYTE),
FIELD5 VARCHAR2(100 BYTE),
FIELD6 VARCHAR2(100 BYTE),
FIELD7 INTEGER,
FIELD8 BLOB,
FIELD9 BLOB
Approx in 60 milliseconds another application node performs SELECT of that record, which return void result. However next SELECT returns needed result.
Defect is occurs with 50% probability.
Whether problem is connected with defect in Oracle RAC/JDBC Driver?
Thanks in advance!

RAC propogates commit messages using a method which piggy-backs on the next available inter-instance message. I think it's called the Lampart Method, but anyways .... it means you have an uncontrollable delay between committed data in your two instances.
Look at the init.ora parameter max_commit_propagation_delay, and consider setting it to 0. The parameter is briefly described in the Oracle Reference Guide.
cheers,
-Mark
www.remidata.com/book_nuts2soup.htm

How to use RAC database connection details in oc4j.xcfg files

Hi all,
we are using oc4j.xcfg files for the application module configuration for an ADF application. and one of the database has been configured on RAC. Any input on how to specify the RAC database details in the oc4j.xcfg file specially for the host name parameter.
The example entry like in oc4j.xcfg is like
?xml version = '1.0' encoding = 'UTF-8'?>
<BC4JConfig>
<AppModuleConfigBag>
<AppModuleConfig name="AppModuleLocal">
<AppModuleJndiName>dbta.model.AppModule</AppModuleJndiName>
<DeployPlatform>LOCAL</DeployPlatform>
<JDBCName>connectDB</JDBCName>
<ApplicationName>dbta.model.AppModule</ApplicationName>
<jbo.project>Model</jbo.project>
</AppModuleConfig>
</AppModuleConfigBag>
<ConnectionDefinition name="connectDB">
<ENTRY name="ConnectionName" value="connectDB"/>
<ENTRY name="URL" value="jdbc:oracle:thin:<user>/<pass>@<server>:<Port>:<SID>"/>
<ENTRY name="HOSTNAME" value="<server>"/>
<ENTRY name="JDBC_PORT" value="<port>"/>
<ENTRY name="SID" value="<SID>"/>
<ENTRY name="ConnectionType" value="JDBC"/>
<ENTRY name="JdbcDriver" value="oracle.jdbc.driver.OracleDriver"/>
<ENTRY name="ORACLE_JDBC_TYPE" value="thin"/>
<ENTRY name="DeployPassword" value="true"/>
</ConnectionDefinition>
how to specify the failover nodes details in the above entry for host name etc.
Thanks
Navin

Here you are; all you want at
http://www.oracle.com/technology/sample_code/tech/java/sqlj_jdbc/files/9i_jdbc/OCIdriverTAFSample/OCIdriverTAFSample.java.html

Whats the BEST Deployment Practice for appsTier (2 Node) with RAC Database

Hi All,
Whats the BEST Deployment Practice for appsTier on Shared APPL_TOP between two application tier Nodes and a RAC Database.
Regards
Satish

Satish,
Could you elaborate; are you looking for how to distribute the tiers(forms, web, conc., etc.); are you asking about PCP (parallelt concurrent processing)..
Regards,

What steps to follow to make RAC Database down.

hi all,
I need to know the order which we have to follow in making RAC database Down Completely,
Information reg database:
OS::IBM AIX,
ASM Storage,
2 node RAC,
2 databases.
order in the sence to shutdown the RAC database first what we have to shutdown like ,
database,asm,cluster, etc.and also give respective commands for reference.
Regards,
vamsi.

844795 wrote:
hi all,
I need to know the order which we have to follow in making RAC database Down Completely,
Information reg database:
OS::IBM AIX,
ASM Storage,
2 node RAC,
2 databases.
order in the sence to shutdown the RAC database first what we have to shutdown like ,
database,asm,cluster, etc.and also give respective commands for reference.
Regards,
vamsi.Stopping the Oracle RAC 10g Environment
The first step is to stop the Oracle instance. When the instance (and related services) is down, then bring down the ASM instance. Finally, shut down the node applications (Virtual IP, GSD, TNS Listener, and ONS).
$ export ORACLE_SID=orcl1
$ emctl stop dbconsole
$ srvctl stop instance -d orcl -i orcl1
$ srvctl stop asm -n linux1
$ srvctl stop nodeapps -n linux1
Starting the Oracle RAC 10g Environment
The first step is to start the node applications (Virtual IP, GSD, TNS Listener, and ONS). When the node applications are successfully started, then bring up the ASM instance. Finally, bring up the Oracle instance (and related services) and the Enterprise Manager Database console.
$ export ORACLE_SID=orcl1
$ srvctl start nodeapps -n linux1
$ srvctl start asm -n linux1
$ srvctl start instance -d orcl -i orcl1
$ emctl start dbconsole
Start/Stop All Instances with SRVCTL
Start/stop all the instances and their enabled services. I have included this step just for fun as a way to bring down all instances!
$ srvctl start database -d orcl
$ srvctl stop database -d orcl
reference:http://www.rampant-books.com/art_hunter_rac_start_stop_cluster.htm
refer the links for more informations:
Starting and Stopping Instances and Oracle Real Application Clusters Databases
http://download.oracle.com/docs/cd/B19306_01/rac.102/b14197/dbinstmgt.htm#BCEBGHHC
Server Control Utility Reference
http://download.oracle.com/docs/cd/B19306_01/rac.102/b14197/srvctladmin.htm
answered by ssolbach
Just a minor comment on the stop nodeapps.
While it is fine to stop the nodeapps on the server, the drawback to this is, that the VIP will not failover if you stop the nodeapps, but will be stopped.
Hence if you only shutdown one server, then you are causing clients to fail to connect to the VIP and having to wait for the TCP/Timeout.
So if you are not going to shut down all the server, but just want to shutdown one node, you should failover the VIP the the other node.
See: Note 749160.1 Vip Does Not Failover When Nodeapps Stopped
So it is sometimes better instead of stopping the nodeapps, to simply shutdown the cluster with crsctl stop crs (which will failover the VIP).
Sebastian
reference:-
Re: RAC Questions

Will Nodeapps register the listener service of RAC database?

Hi Friends,
In 10g RAC will Nodeapps register the listener service of RAC database?
because if i bring down nodeapps the listenener is also going down
ora....C1.lsnr application OFFLINE OFFLINE
ora.rac1.gsd application OFFLINE OFFLINE
ora.rac1.ons application OFFLINE OFFLINE
ora.rac1.vip application OFFLINE OFFLINE
Regards,
DB

Hi,
This is expected behavior. The default listener (listener_nodename) could be starte and stopped with nodeapps.
srvctl listener is mainly for specific listeners that are other than default.
http://docs.oracle.com/cd/B19306_01/rac.102/b14197/whatsnew.htm#sthref6
If you create additional Listeners with non-default names, in other words, with names other than the name listener_nodename where nodename is the name of the node on which the Listener resides, then you must start and stop these Listeners with SRVCTL commands.
http://docs.oracle.com/cd/B19306_01/rac.102/b14197/srvctladmin.htm#i1009606
http://docs.oracle.com/cd/B19306_01/rac.102/b14197/srvctladmin.htm#CDCEIDFH

Using Oracle 11gR1 OID to control access to 11gR2 RAC database ?

I have a two 11gR2 RAC Node database that I would like to implement Oracle 11gR1 OID to manage all access to the RAC database.
Should I install and configure Oracle 11gR1 OID into the same RAC database to control access to the RAC database? Is this the appropriate approach?
Please share your ideas... I couldn't make it to Openword to ask this type of question.

Hi,
I think there is some confusion here. OID doesnt protect your database. All OID is doing is taking the authentication of the user and authorization (privileges) of the user to OID and out of the database. This way you can centralize the management of all user accounts in one place and not worry about it in the database. This is helpful only if you have many databases. If you have a very small number of databases and small number of user accounts, then OID is not really buying you anything. The best practices is published in the oracle docs. Just that you have to read a lot to figure it all out. Here are some info from our installation.
1. weblogic and oid application is installed on a application server
2. Repository database is a independant database (not shared with other apps) in a shared RAC cluster.
3. Replication (OID application replication) setup between a primary oid server and a secondary oid server in the DR site
4. Load balancer configured to point to the primary server and if primary server is not available, point the connection to secondary server
5. DIP configured to pull all users and groups from active directory
6. Password filter installed on all DC's to capture passwords and ship it to oid.
7. Users creation, modification,deletion, expiry, etc., is all controlled on active directory.
8. Database registered with OID for user authentication and authorization
For protecting you data, you will need to use additional security methods/products like :
1. Database vault (to prevent privileged users from operating on the data)
2. Database auditing
3. Fine-grained access control
4. table level policies
5. Fine-grained auditing (column level)
6. Audit vault (to consolidate all audit records to a central place for auditors to classify and research each audit event)
7. operational/process to enforce security.
Good luck :-).
Regards,
Shaji.

Application v/s RAC database

Similar Messages

Maybe you are looking for