Limit parralel in rac

HEllo,
   we have an RAC with 4 nodes, Some queries overload database with a hight degree of parallel : 192 degree of parallel, paralle on 4 instances and i found 384 actives sessions for 1 query!!
I need your help to limit parallel and avoid to overload database.
I configure the degree of every (used) table to parallel 8 (Alter table XXX parallel 8) but it's notre used.
Some parameters of instance : cpu_count      24 show parameter parallel
fast_start_parallel_rollback         string     LOW
parallel_adaptive_multi_user         boolean     TRUE
parallel_automatic_tuning         boolean     FALSE
parallel_degree_limit             string     32
parallel_degree_policy             string     LIMITED
parallel_execution_message_size      integer     16384
parallel_force_local             boolean     FALSE
parallel_instance_group          string
parallel_io_cap_enabled          boolean     FALSE
parallel_max_servers             integer     960
parallel_min_percent             integer     0
parallel_min_servers             integer     0
parallel_min_time_threshold         string     AUTO
parallel_server              boolean     TRUE
parallel_server_instances         integer     4
parallel_servers_target          integer     64
parallel_threads_per_cpu         integer     2
recovery_parallelism             integer     0
Any help will be appreciated :-)
Regardrs
Djm

PARALLEL_MAX_SERVERS
http://docs.oracle.com/database/121/REFRN/refrn10158.htm#REFRN10158
Mustafa DOGANAY
http://doganay.wordpress.com

Similar Messages

Question: what is node limit on RAC?

Any body know what is the max number of node the RAC can has?
Thanks,

Why do you ask?
Practically, the limit is far, far more likely to be dictated by your application(s) than by Oracle. As with any scale out solution, there is a declining marginal benefit as you add nodes. Beyond that, individual applications are generally not built in such a way that they scale nearly as well as RAC itself does. So you are almost always limited by the scalability of your application long before you are limited by the scalability of RAC.
Justin

Limit on number of instances in RAC

Hi,
Is there any limit on number of Oracle Instances (other than hardware resources) in RAC environment.
Thanks
Manmohan

In theory, no. Certainly not one that you're going to hit unless you're planning on hitting a triple digit number of nodes.
In practice, as you add nodes, the scaling factor decreases, so adding nodes gets less and less bang for the buck as you add additional nodes. Most applications (particularly those not designed with massive scale-out in mind) have various bottlenecks that tend to get more and more apparent as additional nodes are added which require more and more tuning efforts to identify and remove. So your application(s) most likely impose much lower practical caps on the number of nodes than Oracle does.
Justin

Oracle RAC Interconnect, PowerVM VLANs, and the Limit of 20

Hello,
Our company has a requirement to build a multitude of Oracle RAC clusters on AIX using Power VM on 770s and 795 hardware.
We presently have 802.1q trunking configured on our Virtual I/O Servers, and have currently consumed 12 of 20 allowed VLANs for a virtual ethernet adapter. We have read the Oracle RAC FAQ on Oracle Metalink and it seems to otherwise discourage the use of sharing these interconnect VLANs between different clusters. This puts us in a scalability bind; IBM limits VLANs to 20 and Oracle says there is a one-to-one relationship between VLANs and subnets and RAC clusters. We must assume we have a fixed number of network interfaces available and that we absolutely have to leverage virtualized network hardware in order to build these environments. "add more network adapters to VIO" isn't an acceptable solution for us.
Does anyone know if Oracle can afford any flexibility which would allow us to host multiple Oracle RAC interconnects on the same 802.1q trunk VLAN? We will independently guarantee the bandwidth, latency, and redundancy requirements are met for proper Oracle RAC performance, however we don't want a design "flaw" to cause us supportability issues in the future.
We'd like it very much if we could have a bunch of two-node clusters all sharing the same private interconnect. For example:
Cluster 1, node 1: 192.168.16.2 / 255.255.255.0 / VLAN 16
Cluster 1, node 2: 192.168.16.3 / 255.255.255.0 / VLAN 16
Cluster 2, node 1: 192.168.16.4 / 255.255.255.0 / VLAN 16
Cluster 2, node 2: 192.168.16.5 / 255.255.255.0 / VLAN 16
Cluster 3, node 1: 192.168.16.6 / 255.255.255.0 / VLAN 16
Cluster 3, node 2: 192.168.16.7 / 255.255.255.0 / VLAN 16
Cluster 4, node 1: 192.168.16.8 / 255.255.255.0 / VLAN 16
Cluster 4, node 2: 192.168.16.9 / 255.255.255.0 / VLAN 16
etc.
Whereas the concern is that Oracle Corp will only support us if we do this:
Cluster 1, node 1: 192.168.16.2 / 255.255.255.0 / VLAN 16
Cluster 1, node 2: 192.168.16.3 / 255.255.255.0 / VLAN 16
Cluster 2, node 1: 192.168.17.2 / 255.255.255.0 / VLAN 17
Cluster 2, node 2: 192.168.17.3 / 255.255.255.0 / VLAN 17
Cluster 3, node 1: 192.168.18.2 / 255.255.255.0 / VLAN 18
Cluster 3, node 2: 192.168.18.3 / 255.255.255.0 / VLAN 18
Cluster 4, node 1: 192.168.19.2 / 255.255.255.0 / VLAN 19
Cluster 4, node 2: 192.168.19.3 / 255.255.255.0 / VLAN 19
Which eats one VLAN per RAC cluster.

Thank you for your answer!!
I think I roughly understand the argument behind a 2-node RAC and a 3-node or greater RAC. We, unfortunately, were provided with two physical pieces of hardware to virtualize to support production (and two more to support non-production) and as a result we really have no place to host a third RAC node without placing it within the same "failure domain" (I hate that term) as one of the other nodes.
My role is primarily as a system engineer, and, generally speaking, our main goals are eliminating single points of failure. We may be misusing 2-node RACs to eliminate single points of failure since it seems to violate the real intentions behind RAC, which is used more appropriately to scale wide to many nodes. Unfortunately, we've scaled out to only two nodes, and opted to scale these two nodes up, making them huge with many CPUs and lots of memory.
Other options, notably the active-passive failover cluster we have in HACMP or PowerHA on the AIX / IBM Power platform is unattractive as the standby node drives no resources yet must consume CPU and memory resources so that it is prepared for a failover of the primary node. We use HACMP / PowerHA with Oracle and it works nice, however Oracle RAC, even in a two-node configuration, drives load on both nodes unlike with an active-passive clustering technology.
All that aside, I am posing the question to both IBM, our Oracle DBAs (whom will ask Oracle Support). Typically the answers we get vary widely depending on the experience and skill level of the support personnel we get on both the Oracle and IBM sides... so on a suggestion from a colleague (Hi Kevin!) I posted here. I'm concerned that the answer from Oracle Support will unthinkingly be "you can't do that, my script says to tell you the absolute most rigid interpretation of the support document" while all the time the same document talks of the use of NFS and/or iSCSI storage eye roll
We have a massive deployment of Oracle EBS and honestly the interconnect doesn't even touch 100mbit speeds even though the configuration has been checked multiple times by Oracle and IBM and with the knowledge that Oracle EBS is supposed to heavily leverage RAC. I haven't met a single person who doesn't look at our environment and suggest jumbo frames. It's a joke at this point... comments like "OMG YOU DON'T HAVE JUMBO FRAMES" and/or "OMG YOU'RE NOT USING INFINIBAND WHATTA NOOB" are commonplace when new DBAs are hired. I maintain that the utilization numbers don't support this.
I can tell you that we have 8Gb fiber channel storage and 10Gb network connectivity. I would probably assume that there were a bottleneck in the storage infrastructure first. But alas, I digress.
Mainly I'm looking for a real-world answer to this question. Aside from violating every last recommendation and making oracle support folk gently weep at the suggestion, are there any issues with sharing interconnects between RAC environments that will prevent it's functionality and/or reduce it's stability?
We have rapid spanning tree configured, as far as I know, and our network folks have tuned the timers razor thin. We have Nexus 5k and Nexus 7k network infrastructure. The typical issues you'd fine with standard spanning tree really don't affect us because our network people are just that damn good.

Distance limit between nodes on RAC

Hi all,
Can anyone give idea that what's the maximum distance allowed between nodes in RAC.We're planning to install 10g RAC on Solaris and we've two sites.Distance between these sites is 12 KM's.
Any feedback will be appreciated.
Regards.

See the following two papers on OTN
http://www.oracle.com/technology/products/database/clustering/index.html
Using standard NFS to support a third voting disk on an Extended Distance cluster configuration on Linux,AIX, or Solaris (PDF) January 2007
Oracle Real Application Clusters on Extended Distance Clusters(PDF) November 2006
12km is fine as far as distance goes, but there are other requirements.
-Erik

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

Oracle RAC implementation scenario

Hello DB Experts,
I have got a very specific business scenario to be implemented.
Basically we need to implement 2 Node RAC infrastructure.
But in this on each node we have 2 oracle instances running.
Now is it possible to have one Instance running on Active / Active mode and another instance in Active / Passive mode.
First of all i want to know it is possible to implement RAC in this manner.
If yes, then for Active / Passive instance if Active instance goes down how to switch the traffic to the passive node? Or basically i want to know how do i make that passive node active?
Would really appreciate some quick response.
Thanks,
Darshan

Lets assume some better names for this discussion...
RAC Database MYDB (instance on node1 = MYDB1, instance on node2=MYDB2)
SI Database URDB (instance on node1 = URDB with active/passive on node2)
Can this be done? Yes. But why? You can use SERVICES to limit on which node your application is accessing.

Question on RAC

Hi friends,
I have got this question from customer regarding Oracle 11G R2 RAC.
The customer have stated a preference for configuring the Oracle RAC nodes so that, in a two node system, the first node bears all the update load, whereas the second RAC node would have connections that are read-only. The two nodes would still operate as failovers for one another. The reason for this , they stated was to reduce network traffic between the nodes to coordinate transactions and locking. They have asked for this configuration as 'one update node and one read-only node' / a primary update node and a secondary read-only node .
We have thought about implementing this configuration for our two applications as follows
Application features
Application 1 - which performs regular updates,heavy transactions,long running reports et - schema 1
Application 2 - performs smalled updates and small reads. - schema 2
Application 1 can point to node 1 of this RAC and application 2 to node 2 ( using node affinity ).When any of the node fails , the client connections will fail over to surviving node.
I would like to get some recommendations on this approach from experts.
1) Do you think the above approach using node affinity is a good approach , ie pinning one schema in one node with one database for a two instance(node) RAC ?
2) Any documents / reference to configure this approach in RAC ?
3) Is there any other way to achieve the requirement put by the customer ?
4) If the above said nodes are in two data centres, Will it be a recommended approach ? I think these two nodes should be in same data centre.
5) If we configure Load balancing ( in normal RAC or in the setup mentioned above) then that would take considerable network b/w ?
OS is RHEL 5.4 on 64 bit.
Please share your view on this.
Thanks ,
SSN

1) Do you think the above approach using node affinity is a good approach , ie pinning one schema in one node with one database for a two instance(node) RAC ?In RAC , database remains same. So all schemas can be accessed from all nodes.
You can configure RAC services and then you can use one service for the updates and the other one can be used for read only application.
http://download.oracle.com/docs/cd/E11882_01/rac.112/e16795/hafeats.htm#BABJJJAG
4) If the above said nodes are in two data centres, Will it be a recommended approach ? I think these two nodes should be in same data centre.Why do you want to put RAC nodes in different data centers ?
You can use Oracle extended RAC in that case.
http://blogs.oracle.com/AlejandroVargas/2008/03/extended_rac_on_pure_oracle_st.html
http://www.databasejournal.com/features/oracle/article.php/3675096/Oracle-Extended-RAC-Stretching-your-RAC-to-the-limit.htm
Regards
Rajesh

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.

Installing 10g rac on Solaris 64-bit Sparc

I ran my preinstallation cluvufy
using ./cluvfy stage -pre crsinst -n racnode3,racnode4 -verbose -r 10gR2
I get failed errors at
1) Node connectivity failed
2) SUNWi15cs and SUNWi1cs- missing
3) Clock synchronization check using Network Time Protocol(NTP) failed
I am so lost as to figure out whats happening. have beenn working on it for two weeks now. Here is the log
Any help would be greatly appreciated
Thanks
Performing pre-checks for cluster services setup
Checking node reachability...
Check: Node reachability from node "racnode3"
Destination Node Reachable?
racnode3 yes
racnode4 yes
Result: Node reachability check passed from node "racnode3"
Checking user equivalence...
Check: User equivalence for user "oracle"
Node Name Comment
racnode4 passed
racnode3 passed
Result: User equivalence check passed for user "oracle"
Version of exectask could not be retrieved from node "racnode3"
Checking node connectivity...
Checking hosts config file...
Node Name Status Comment
racnode4 passed
Verification of the hosts config file successful
Interface information for node "racnode4"
Name IP Address Subnet Gateway Def. Gateway HW Address MTU
vnet0 10.23.11.127 10.23.11.0 10.23.11.127 10.23.11.1 00:14:4F:FB:A4:A5 1500
vnet1 192.168.2.127 192.168.0.0 192.168.2.127 10.23.11.1 00:14:4F:F8:5A:A3 9216
Check: Node connectivity of subnet "10.23.11.0"
Result: Node connectivity passed for subnet "10.23.11.0" with node(s) racnode4
Check: TCP connectivity of subnet "10.23.11.0"
Source Destination Connected?
racnode3:10.23.11.126 racnode4:10.23.11.127 failed
ERROR:
PRVF-7617 : Node connectivity between "racnode3 : 10.23.11.126" and "racnode4 : 10.23.11.127" failed
Result: TCP connectivity check failed for subnet "10.23.11.0"
Check: Node connectivity of subnet "192.168.0.0"
Result: Node connectivity passed for subnet "192.168.0.0" with node(s) racnode4
Check: TCP connectivity of subnet "192.168.0.0"
Source Destination Connected?
racnode3:10.23.11.126 racnode4:192.168.2.127 failed
ERROR:
PRVF-7617 : Node connectivity between "racnode3 : 10.23.11.126" and "racnode4 : 192.168.2.127" failed
Result: TCP connectivity check failed for subnet "192.168.0.0"
Interfaces found on subnet "10.23.11.0" that are likely candidates for VIP are:
racnode4 vnet0:10.23.11.127
WARNING:
Could not find a suitable set of interfaces for the private interconnect
Result: Node connectivity check failed
Check: Total memory
Node Name Available Required Comment
racnode4 5.75GB (6029312.0KB) 1GB (1048576.0KB) passed
Result: Total memory check passed
Check: Swap space
Node Name Available Required Comment
racnode4 8GB (8388600.0KB) 5.75GB (6029312.0KB) passed
Result: Swap space check passed
Check: Free disk space for "racnode4:/var/tmp/"
Path Node Name Mount point Available Required Comment
/var/tmp/ racnode4 / 11.8299GB 400MB passed
Result: Free disk space check passed for "racnode4:/var/tmp/"
Check: User existence for "oracle"
Node Name Status Comment
racnode4 exists(200) passed
Checking for multiple users with UID value 200
Result: Check for multiple users with UID value 200 passed
Result: User existence check passed for "oracle"
Check: User existence for "nobody"
Node Name Status Comment
racnode4 exists(60001) passed
Checking for multiple users with UID value 60001
Result: Check for multiple users with UID value 60001 passed
Result: User existence check passed for "nobody"
Check: Group existence for "oinstall"
Node Name Status Comment
racnode4 exists passed
Result: Group existence check passed for "oinstall"
Check: Group existence for "dba"
Node Name Status Comment
racnode4 exists passed
Result: Group existence check passed for "dba"
Check: Membership of user "oracle" in group "oinstall" [as Primary]
Node Name User Exists Group Exists User in Group Primary Comment
racnode4 yes yes yes yes passed
Result: Membership check for user "oracle" in group "oinstall" [as Primary] passed
Check: Membership of user "oracle" in group "dba"
Node Name User Exists Group Exists User in Group Comment
racnode4 yes yes yes passed
Result: Membership check for user "oracle" in group "dba" passed
Check: Run level
Node Name run level Required Comment
racnode4 3 3 passed
Result: Run level check passed
Check: Hard limits for "maximum open file descriptors"
Node Name Type Available Required Comment
racnode4 hard 65536 65536 passed
Result: Hard limits check passed for "maximum open file descriptors"
Check: Soft limits for "maximum open file descriptors"
Node Name Type Available Required Comment
racnode4 soft 1024 1024 passed
Result: Soft limits check passed for "maximum open file descriptors"
Check: Hard limits for "maximum user processes"
Node Name Type Available Required Comment
racnode4 hard 16384 16384 passed
Result: Hard limits check passed for "maximum user processes"
Check: Soft limits for "maximum user processes"
Node Name Type Available Required Comment
racnode4 soft 16384 2047 passed
Result: Soft limits check passed for "maximum user processes"
Check: System architecture
Node Name Available Required Comment
racnode4 64-bit sparcv9 kernel modules 64-bit sparcv9 kernel modules passed
Result: System architecture check passed
Check: Kernel version
Node Name Available Required Comment
racnode4 5.10-2011.08.23.15.26 5.10-2005.01 passed
Result: Kernel version check passed
Check: Kernel parameter for "project.max-sem-ids"
Node Name Configured Required Comment
racnode4 128 100 passed
Result: Kernel parameter check passed for "project.max-sem-ids"
Check: Kernel parameter for "process.max-sem-nsems"
Node Name Configured Required Comment
racnode4 512 256 passed
Result: Kernel parameter check passed for "process.max-sem-nsems"
Check: Kernel parameter for "project.max-shm-memory"
Node Name Configured Required Comment
racnode4 4294967296 4294967295 passed
Result: Kernel parameter check passed for "project.max-shm-memory"
Check: Kernel parameter for "project.max-shm-ids"
Node Name Configured Required Comment
racnode4 128 100 passed
Result: Kernel parameter check passed for "project.max-shm-ids"
Check: Package existence for "SUNWarc-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWarc-11.10.0-2005.01.21.15.53 SUNWarc-...( sparc) passed
Result: Package existence check passed for "SUNWarc-...( sparc)"
Check: Package existence for "SUNWbtool-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWbtool-11.10.0-2005.01.21.15.53 SUNWbtool-...( sparc) passed
Result: Package existence check passed for "SUNWbtool-...( sparc)"
Check: Package existence for "SUNWhea-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWhea-11.10.0-2005.01.21.15.53 SUNWhea-...( sparc) passed
Result: Package existence check passed for "SUNWhea-...( sparc)"
Check: Package existence for "SUNWlibC-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWlibC-5.10-2004.12.22 SUNWlibC-...( sparc) passed
Result: Package existence check passed for "SUNWlibC-...( sparc)"
Check: Package existence for "SUNWlibm-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWlibm-5.10-2004.12.18 SUNWlibm-...( sparc) passed
Result: Package existence check passed for "SUNWlibm-...( sparc)"
Check: Package existence for "SUNWlibms-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWlibms-5.10-2004.11.23 SUNWlibms-...( sparc) passed
Result: Package existence check passed for "SUNWlibms-...( sparc)"
Check: Package existence for "SUNWsprot-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWsprot-5.10-2004.11.23 SUNWsprot-...( sparc) passed
Result: Package existence check passed for "SUNWsprot-...( sparc)"
Check: Package existence for "SUNWtoo-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWtoo-11.10.0-2005.01.21.15.53 SUNWtoo-...( sparc) passed
Result: Package existence check passed for "SUNWtoo-...( sparc)"
Check: Package existence for "SUNWi1of-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWi1of-6.6.2.7400-0.2004.12.15 SUNWi1of-...( sparc) passed
Result: Package existence check passed for "SUNWi1of-...( sparc)"
Check: Package existence for "SUNWi1cs-...( sparc)"
Node Name Available Required Comment
racnode4 missing SUNWi1cs-...( sparc) failed
Result: Package existence check failed for "SUNWi1cs-...( sparc)"
Check: Package existence for "SUNWi15cs-...( sparc)"
Node Name Available Required Comment
racnode4 missing SUNWi15cs-...( sparc) failed
Result: Package existence check failed for "SUNWi15cs-...( sparc)"
Check: Package existence for "SUNWxwfnt-...( sparc)"
Node Name Available Required Comment
racnode4 SUNWxwfnt-6.6.2.7400-0.2004.12.15 SUNWxwfnt-...( sparc) passed
Result: Package existence check passed for "SUNWxwfnt-...( sparc)"
Checking for multiple users with UID value 0
Result: Check for multiple users with UID value 0 passed
Check: Current group ID
ERROR:
PRVF-5502 : Current group ID check cannot be performed
Result: Current group ID check failed
Starting Clock synchronization checks using Network Time Protocol(NTP)...
NTP Configuration file check started...
The NTP configuration file "/etc/inet/ntp.conf" is available on all nodes
NTP Configuration file check passed
Checking daemon liveness...
Check: Liveness for "xntpd"
Node Name Running?
racnode4 yes
Result: Liveness check passed for "xntpd"
Check for NTP daemon or service alive passed on all nodes
Checking NTP daemon command line for slewing option "'slewalways yes' & 'disable pll'"
Check: NTP daemon command line
Node Name Slewing Option Set?
racnode4 no
Result:
NTP daemon slewing option check failed on some nodes
PRVF-5436 : The NTP daemon running on one or more nodes lacks the slewing option "'slewalways yes' & 'disable pll'"
Result: Clock synchronization check using Network Time Protocol(NTP) failed
Checking Core file name pattern consistency...
Core file name pattern consistency check passed.
Checking to make sure user "oracle" is not in "root" group
Node Name Status Comment
racnode4 does not exist passed
Result: User "oracle" is not part of "root" group. Check passed
Check default user file creation mask
Node Name Available Required Comment
racnode4 0022 0022 passed
Result: Default user file creation mask check passed
Checking consistency of file "/etc/resolv.conf" across nodes
Checking the file "/etc/resolv.conf" to make sure only one of domain and search entries is defined
File "/etc/resolv.conf" does not have both domain and search entries defined
Checking if domain entry in file "/etc/resolv.conf" is consistent across the nodes...
domain entry in file "/etc/resolv.conf" is consistent across nodes
Checking if search entry in file "/etc/resolv.conf" is consistent across the nodes...
search entry in file "/etc/resolv.conf" is consistent across nodes
Checking file "/etc/resolv.conf" to make sure that only one search entry is defined
All nodes have one search entry defined in file "/etc/resolv.conf"
Checking DNS response time for an unreachable node
Node Name Status
racnode4 passed
The DNS response time for an unreachable node is within acceptable limit on all nodes
File "/etc/resolv.conf" is consistent across nodes
Check: Time zone consistency
Result: Time zone consistency check passed
Pre-check for cluster services setup was unsuccessful on all the nodes.
Edited by: Aj05 on Feb 2, 2012 8:26 AM

Daniel,
Again ... my initial response was that I was insulted by the implications: Still am.
Perhaps you are hoping someone else will steal that copywrited material and send it to you? Is that what you are asking?I think your initial response is little bit excessive (IMO). OP didn't say that "Somebody steal the content from metalink and send it to me please". He might requesting specific note id for appropriate document which describes installation in "instant" form.
But do you really think, for even one minute, that anyone who has invested many hundreds of hours into creating a training class is going to send you their materials for free?Somebody called "Linus" and many others invested many hundreds of hours to create OS which you are using for free (and you are recommending it in your posts)... ;-)
What if there is some altruist which could provide the such complex paper for RAC?
Your third post is correct and I absolutely agree with you (except last sentence).
Salman,
you can look to get inspired at "DBA" articles on OTN website (http://www.oracle.com/technology/pub/articles/tech_dba.html#linux) or RAC SIG site and compare it with official documentation or metalink notes. Only documentation and metalink notes are 100% assurance that your installation/configuration will be supported. And in case of doubts you still can contact Oracle support and consult planned steps/implementation.
Message was edited by:
Ivan Kartik
s/second post/third post/

ORA-19566: exceeded limit of 999 corrupt blocks for file

Hi All,
I am new to Oracle RMAN & RAC Administration. Looking for your support to solve the below issue.
We have 2 disk groups - +ETDATA & +ETFLASH in our 3 node RAC environments in which RMAN is configured in node-2 to take backup. We do not have RMAN catalog and the RMAN is fetching information from control file.
Recently, the backup failed with the error ORA-19566: exceeded limit of 999 corrupt blocks for file +ETFLASH/datafile/users.6187.802328091.
We found that the datafiles are present in both disk groups and from the control file info, we got to know that the datafiles in +ETDATA are currently in use and +ETFLASH is having old datafiles.
RMAN> show all;
RMAN configuration parameters for database with db_unique_name LABWRKT are:
CONFIGURE RETENTION POLICY TO RECOVERY WINDOW OF 3 DAYS;
CONFIGURE BACKUP OPTIMIZATION ON;
CONFIGURE DEFAULT DEVICE TYPE TO DISK; # default
CONFIGURE CONTROLFILE AUTOBACKUP ON;
CONFIGURE CONTROLFILE AUTOBACKUP FORMAT FOR DEVICE TYPE DISK TO '%F'; # default
CONFIGURE DEVICE TYPE DISK PARALLELISM 4 BACKUP TYPE TO BACKUPSET;
CONFIGURE DATAFILE BACKUP COPIES FOR DEVICE TYPE DISK TO 1; # default
CONFIGURE ARCHIVELOG BACKUP COPIES FOR DEVICE TYPE DISK TO 1; # default
CONFIGURE MAXSETSIZE TO UNLIMITED; # default
CONFIGURE ENCRYPTION FOR DATABASE OFF; # default
CONFIGURE ENCRYPTION ALGORITHM 'AES128'; # default
CONFIGURE COMPRESSION ALGORITHM 'BASIC' AS OF RELEASE 'DEFAULT' OPTIMIZE FOR LOAD TRUE ; # default
CONFIGURE ARCHIVELOG DELETION POLICY TO NONE; # default
CONFIGURE SNAPSHOT CONTROLFILE NAME TO '+ETFLASH/CONTROLFILE/snapcf_LABWRKT.f';
CONFIGURE SNAPSHOT CONTROLFILE NAME TO '+ETFLASH/controlfile/snapcf_labwrkt.f';
Above configuration shows that SNAPSHOT CONTROLFILE is pointing to +ETFLASH. So I changed the configuration with the SNAPSHOT CONTROLFILE points to '+ETDATA/controlfile/snapcf_labwrkt.f'. At the end of backup, SNAPSHOT file was created in +ETDATA and I was expecting it to be the copy of control file being used which has dbf located in +ETDATA. But still the backup was pointing to old datafiles in +ETFLASH. Since we dont have RMAN catalog, resync also is not possible.
When I ran it manually, it was successfull without any error and was pointing to the exisiting datafiles.
RMAN> backup database plus archivelog all;
I hope the issue will get resolved if the RMAN points only to the datafiles present in +ETDATA. If I am correct, please let me know how can i make it possible? Also please explain me why the newly created snapshot file does not reflect the existing control file info?

Hi,
I am getting an error from the DBA Planning Calendar every time the job ...
So when was your last successfull backup of this datafile. Check if still available.
If this is some time ago, and may be you are currently without any backup, try to backup without rman at once,
to have at least something to work with in case you get additional errors right now.
Then you need to find out what object is affected. You are on the right way already. You need the statement,
that goes to dba_extents to check what object the block belongs to.
Has the DB been recovered recently, so the block might possibly belong to an index created with nologging ?
(this could be the case on BW systems).
If the last good backup of that file is still available and the redologs belonging to this backup up to current time are as well, you could try to recover that file. But I'd do this only after a good backup without rman and by not destroying the original file.
If the last good backup was an rman backup, you can do a verify restore of that datafile in advance, to check if the corruption is really not inside the file to be restored.
Check out the -w (verify) option of brrestore first, to understand how it works.
(I am not sure it this is already available in version 7.00, may be you need to switch to 7.10 or 7.20)
brrestore -c -m /oracle/SHD/sapdata4/sr3_16/sr3.data16 -b xxxxxxxx.ffr -w only_rmv
You should do a dbv check of that file as well, to check if it gets more information. I.E if more blocks are
affected. rman stops right after the first corruption, but usually you have a couple of those in line, esp. if these are
zeroed ones. (This one would also work with version 7.00 brtools)
brbackup -c -u / -t online -m /oracle/SHD/sapdata4/sr3_16/sr3.data16 -w only_dbv
Good luck.
Volker

ASM pfile lost in Oracle RAC 11gr2

Hello Gurus,
I am new to Oracle RAC 11gr2 and facing some issues. our spfile/pfile for asm instance is lost and I am not able to startup the asm instance.
Environment is as below:
RAC 2 nodes
Oracle RAC 11gr2
Enterprise Linux Server release 5.5 (Carthage)
ORA-01078: failure in processing system parameters
LRM-00109: could not open parameter file '/u01/app/oracle/product/11.2.0/db_1/dbs/init+ASM1.ora'
Is there any way to recover the spfile/pfile ?
Also getting following error while try to connect " sqlplus / as sysasm"
$ sqlplus / as sysasm
SQL*Plus: Release 11.2.0.1.0 Production on Sun Mar 27 11:26:02 2011
Copyright (c) 1982, 2009, Oracle. All rights reserved.
ERROR:
ORA-01031: insufficient privileges
Enter user-name:
Thanks and Regards,

Hi,
Do we need to Set variable ORACLE_HOME properly (Grid Home) while starting RDBMS instance?
e.g ORACLE_HOME=/u01/app/11.2.0/grid*I recommend you set ORACLE_HOME properly for each Oracle Installation when you use SQLPLUS.
i.e: cat /etc/oratab
orcl:/u01/app/oracle/product/11.2.0/db_1
db10g:/u01/app/oracle/product/10.2.0/db_1
+ASM1:/u01/app/11.2.0/gridAlso you can startup/shutdown our database with SQLPLUS using ORACLE NET*, but it must be configured properly.
My recommendation <s>is always</s> use SRVCTL and CRSCTL to manage to your environment. Track all the process of initialization processes through the logs using ADRCI utility (only 11.1 or later).
When use SRVCTL or CRSCTL to manage I recomend you use (GRID HOME).
SQL> alter database open;
alter database open
ERROR at line 1:
ORA-16038: log 3 sequence# 1067 cannot be archived
ORA-19809: limit exceeded for recovery files
ORA-00312: online log 3 thread 2: '+FRA/yyy/onlinelog/group_3.259.738489481'
SQL>I give to you three options:
1° - Add more asmdisk on Diskgroup +FRA
2° - Make backup of all archivelog using RMAN and option delete input (i.e backup archivelog delete all input;)
3° - If this database is for TEST ONLY and you not need backup or recovery of then you can delete all archivelog using RMAN (i.e delete archivelog all;)
I recommend you create routine of backups of the database and archivelog to prevent this area becomes exhausted.
If you need the database in archivelog but it is only to test then create routine to delete archivelogs periodically.
If you dont need the database in archivelog, then just disable it.
Regards,
Levi Pereira

Oracle RAC on Solarais Configuration Issue

Hi,
We are trying to install Oracle RAC 10g R2 on Solaris 10.
Following are the products
1=> Soalris 10 OS
2=> Sun Cluster 3.1
3=> Veritas Volume Manager
4=> Veritas Cluster File System
Can i deploy Oracle RAC using the above listed Software.
Here we have not purchase any of the Cluster Volume Manager.
Is the CVM required to install Oracle RAC.
Is there any alternative wherein we can install Oracle RAC without using CVM like for example using the RAW device where the VM will manage storage from a single node rather than buying the CVM that will allow to manage the storage from multiple nodes.
Also i would like to highlight is suggestion for using ASM is rule out hence ASM would not be used.
Can anyone suggest me some solution to the above problem.

Well, my impression is that you don't really know what your requirements are and you are trying to fit the technologies somehow. Worse yet, there is no clear understanding how those technologies fit together and as long as you explain what your vendor is saying you (which vendor?) they don't have clear idea either.
I would also suggest to review your decision to use Sun Network Data Replicator for DR site. Consider Oracle Physical Standby database instead - it's more flexible solution and doesn't limit your choice of storage stack.
1) Do Oracle RAC 10gR2 requires any Veritas Cluster Volume Manager
Words "any" and "Veritas" contradict in your question. But the answer is no. RAC require shared storage which can generally be one of those:
- raw devices with or without some kind of cluster volume manager
- cluster file system
- NAS storage (NFS mounted)
- ASM with raw devices for CRS files (OCR and voting disks)
2) Does Oracle RAC 10g R2 require any Vertias Cluster File System or it can sit on normal Vertias File System
Again, Oracle database files MUST reside on shared storage and non-clustered file system is not an option.
3) Is there any solution where we can use the Sun Cluster with Veritas Componets to configure RAC.
If I recall correctly, Sun Cluster includes in it's license some of component of Veritas storage stack. So you might be all set. You should turn to documentation on that stage and see exactly what you have licensed and if your stack allows shared storage. You might want to have a look at http://www.sun.com/software/whitepapers/solaris10/solaris_cluster.pdf
and Oracle Certification Matrix on Metalink.

Oracle RAC one node

why Oracle introduced Oracle RAC one node in 11gR2?
I have gone through oracle documents on oracle rac one node, but i couldn't find much added advantage than instance failover. We have already some technologies like datagaurd and some third party softwares for instance failover.
Then why oracle introduced this RAC one node in the new release i.e 11gR2?
What exactly oracle wants to provide from oracle RAC one node?
Thanks...
Bharath

Why RAC one node?
Oracle RAC one node is a single instance of Oracle RAC that runs on the node in a cluster. The benefit of the RAC one node option is that it allows you to consolidate many databases into one cluster without a lot of overhead, while also providing high availbilty benefits of failover protection, as well as for Online rolling patch application and rolling upgrades for the Oracle clusterware.
Another aspect of RAC one node allows you to limit th CPU utilization of individual database instances within the cluster through a feature called resource manager instance caging, which gives you the ability to dynamilcally change the limit as required.
Furhtermore , with RAC one node there is no limitation for server scalabilty such that if applications outgrow the current resources than a single node can supply, you can then upgrade the applications online to Oracle RAC.
In tthe event that the node which is runnig Oracle RAc one node becomes saturated and out of resources, you can migrate the instance to another node in the cluster using Oracle rac one node and another new utilty called OMOTION feature.OMOTION feature for Oracle RAC 11g R2 rac allows you to migrate a running instance to another server without downtime or distrubtion in service for your enviornment.
Hope you're understand.

Standby Limit

Hello,
Is there any limit of configuring / creating physical and/or logical standby database in different oracle versions and different OSs?
regards.

user12050217 wrote:
Ok, Thanks much again. Now following questions are in my mind :
1.My be this 9 limit is due to log_arch_dest_n parameters, but when i am going to create standby through RMAN, there is no talk for log_arch_dest_n parameter?
Yes.Actually with createing standby database there do not talk log_archive_dest_n.But to automatically applying archivelogs to standby database need setting this parameter.
2.Will this 30 for 11g and 9 for 10g limit works same in RAC environment?Yes
3.It means in 11g we can have 30 log_arch_dest_n parameters ?Yes.Read below link
http://download.oracle.com/docs/cd/E11882_01/server.112/e10700/log_arch_dest_param.htm#i109594

Limit parralel in rac

Similar Messages

Maybe you are looking for