Manually allocate SGA and PGA to a Instance?

1) Can we Manually allocate SGA and PGA to a Instance after . startup
sql>show user
connected to idle instance
2) In which type of memory user is stored in oracle mem or windows memory.
Thanx

If you are using 10g, you can modify PGA size after instance startup by alter system to change PGA_AGGREGATE_TARGET
You can't increase SGA_MAX_SIZE while instance is running. However you can change effective SGA size by alter SGA_TARGET if you are using ASMM
to find out what's current logon user,
select user from dual;
Don't quite understand your second question.

Similar Messages

Suggestion in increasing the SGA and PGA after increase in the RAm of the machine .

Hi All,
Need an expert suggestion on the change's in the SGA and PGA of the oracle database after increasing the size of the machines RAM .
We have 64G of RAM in the machine .
There are 9 DB's running on oracle 10g and 11g on this machine
The total SGA of all the database's is around 18G .
DB1 has 2G of MAX_SGA_SIZE
DB2 has 8G of MAX_SGA_SIZE
DB3 has 1G   of MAX_SGA_SIZE
DB4 has 2G    of MAX_SGA_SIZE
DB5 has 676M   of MAX_SGA_SIZE
DB6   has 1.5G   of MAX_SGA_SIZE
DB7 has 1.2 G   of MAX_SGA_SIZE
DB8 has 675M   of MAX_SGA_SIZE
DB9 has 672 M   of MAX_SGA_SIZE
Now the machine RAM is up to 96G 64+ 32
what would be the suggestion on the increase in the SGA and PGA max size .
Any expert suggestion is highly apprciated .
Thanks in Advance

Thanks for this Justin.
Here the exercise is to add 4 CPU's and 32G RAM to the server earlier it was with 4 CPU's and 64G RAM this was decided by the server support team .
here is the stats from SAR   command ..
The platform is
Oracle Database 11g Enterprise Edition Release 11.2.0.2.0 - 64bit Production
PL/SQL Release 11.2.0.2.0 - Production
CORE    11.2.0.2.0      Production
TNS for Linux: Version 11.2.0.2.0 - Production
NLSRTL Version 11.2.0.2.0 - Production
04:00:01          CPU     %user     %nice   %system   %iowait    %steal     %idle
04:10:02          all     86.47      0.00     12.52      0.99      0.00      0.02
04:20:01          all     84.83      0.01     11.80      3.21      0.00      0.15
04:30:01          all     76.23      0.00     10.30     12.34      0.00      1.12
04:40:01          all     79.14      0.00     12.07      8.30      0.00      0.49
04:50:01          all     77.63      0.00     12.19      9.40      0.00      0.77
05:01:01          all     75.95      0.00     10.50     12.80      0.00      0.75
05:11:01          all     83.21      0.00     11.98      4.54      0.00      0.26
05:21:01          all     76.37      0.01     11.20     11.49      0.00      0.94
05:31:01          all     77.97      0.00      9.04     10.30      0.00      2.69
Average:          all     79.72      0.00     11.28      8.20      0.00      0.80
Now that the 4 CPU's and RAM is been added , my request is how to calculate the required kernal parameters for oracle to this new configuration for some improvement in the oracle performance .
like kernal.shmmax
      kernal.shmall
/dev/shm file system
largest value of MEMORY_MAX_TARGET or MEMORY_TARGET of all instances
the oracle is set as automatic memory management . it is not an RAC environment .
Any Expert suggestion is highly apprciated .
Thanks in advance .

How to change SGA and PGA in 10g r2 RAC

Hi,
How to change SGA and PGA in 10g r2 RAC, its Linux.

Hi,
Here is the way i followed to change SGA and PGA in RAC.
Action Plan to change the memory parameter in the production environment(5/21/2010)
Note:
=====
Practice should be done in the DEV/TST environment before moving to Production;
Although the procedure could be applied in the testing environment the changing values
used in the testing environment should be modified since RAM number are not the
same between the testing servers and production servers.
1.     Make changes to these two parameters in one of
     the prod instance, e.g. PROD1
     ====================================================
     login as sysdba on sqlplus
Change :
alter system set sga_target=28G scope=spfile sid='*';
Change :
alter system set pga_aggregate_target=4G scope =spfile sid='*';
     sql>alter system set pga_aggregate_target=4G scope=both;
     sql>show parameter pga_aggregate_target;
          -- should see the altered number on both instances
Change:
sql>alter system set sga_max_size=28G scope=spfile sid='*';
sql>alter system set sga_max_size=28G scope=spfile ;
sql>alter system set sga_target=28G scope=spfile;
3.     shutdown database PROD (two instances should be shut down)
     $>srvctl stop database -d PROD
     $>. /$ORA_CRS_HOME/bin/crs_stat -- to check for the database status
4.     bring up database PROD (two instance should be brought up)
     $>srvctl START database -d PROD
     $>. /$ORA_CRS_HOME/bin/crs_stat -- to check for the database status
     login into both instances as sysdba to check
     sql>show parameter pga_aggregate_target
     sql>show parameter sga_max_size
          -- should see the altered number still there in both instances
          -- from step 1
     -- After confirming above two parameters are altered on both instances,
     -- then issue the syntax below in one instance
5)     check everything is ok

How to know the amount of ora 11g page-out memory (sga and pga)?

How to know the amount of oracle 11g page-out memory ( sga and pga) in the SunSolaris 10 Unix and Linux.
I need to know how many oracle memory are being page-out ( all and for a one oracle server process).
thanks

You can monitor the paging with vmstat or sar commands.
http://download.oracle.com/docs/cd/B28359_01/server.111/b32009/tuning.htm#sthref500
You can also get the paging information on OEM home page if configured for your database.
But I don't know if there exists a method with which one can find out how much memory per session/server process is getting paged out.

Increase the SGA and PGA size

Hello Guru,
How do i check what is my SGA and PGA..I am using TOAD..
I need to increase the SGA and PGA size...Please help..
I have a table having 200 million records, all indexes are there for the column..But it hang on in the debugging mode and also compile mode..
So i believe, I need to increase the SGA and PGA size...
Thanks,
Haraprasad...

805936 wrote:
Hello Guru,
How do i check what is my SGA and PGA..I am using TOAD..
I need to increase the SGA and PGA size...Please help..
The current size for both SGA and PGA can be shown depending on the version of the db. For 10g, the SGA size is shown by sga_target parameter and PGA size is shown by pga_aggregate_target parameter. For 11g, the parameter memory_target sets them both.
I have a table having 200 million records, all indexes are there for the column..But it hang on in the debugging mode and also compile mode..
So i believe, I need to increase the SGA and PGA size...No, IMO, your believe doesn't hold much base as the evidence that you have used is insufficient. What is the debugging mode or compile mode ? For what purpose you are using these modes? 200 million is not a very large number if you ask me. Tell us your db version and based on it, generate a Statspack or AWR report and post here.
HTH
Aman....

Guidelines for SGA and PGA tuning for 10gR2 RAC and ASM ?

I am looking for tuning information on SGA and PGA tuning for Oracle 10g (10.2) RAC and ASM for a 4TB OLTP and DSS mixed environment on Solaris 10 platform.

We are running Solaris 10 SPARC 64 bit with Oracle 10gR2 RAC Enterprise Edition and ASM on Sun servers with 32GB of RAM for memory for a 4TB OLTP database.
It is in design phase so I do not have an existing AWR or Statspack report yet. Is there a best practices guideline on how to size parameters for the SGA (ie: shared_pool_size, etc) and PGA for this environment from Oracle?

Lost connection to XE after adjusting SGA and PGA

I lowered SGA from 170M to 50M, and PGA from 60M to 10M. Now I can not connect to XE using apex. Toad also reports ora-12514. I rebooted the pc and also manually cycled the db. But nothing works. In Service the oracle servies appear to be fine.
Thanks for any help.
Sorry for posting XE question here. I can't access the XE forum.
xmk

I reboot it again and this time I can get in sqlplus by using
sqlplus "/ as sysdba"
The following is the bottom part of aler_xe.log, a bit long.
^^^^^^^^^^^^^^^^^^^^
Instance terminated by USER, pid = 2432
Dump file c:\oraclexe\app\oracle\admin\xe\bdump\alert_xe.log
Thu Oct 12 13:29:15 2006
ORACLE V10.2.0.1.0 - Production vsnsta=0
vsnsql=14 vsnxtr=3
Windows XP Version V5.1 Service Pack 2
CPU : 2 - type 586
Process Affinity : 0x00000000
Memory (Avail/Total): Ph:698M/1014M, Ph+PgF:2232M/2440M, VA:1944M/2047M
Thu Oct 12 13:29:15 2006
Starting ORACLE instance (normal)
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Picked latch-free SCN scheme 2
Using LOG_ARCHIVE_DEST_10 parameter default value as USE_DB_RECOVERY_FILE_DEST
Autotune of undo retention is turned on.
IMODE=BR
ILAT =10
LICENSE_MAX_USERS = 0
SYS auditing is disabled
Thu Oct 12 13:29:26 2006
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.1.0.
System parameters with non-default values:
sessions = 49
__shared_pool_size = 16777216
__large_pool_size = 0
__java_pool_size = 4194304
__streams_pool_size = 0
spfile = C:\ORACLEXE\APP\ORACLE\PRODUCT\10.2.0\SERVER\DBS\SPFILEXE.ORA
sga_target = 54525952
control_files = C:\ORACLEXE\ORADATA\XE\CONTROL.DBF
__db_cache_size = 29360128
compatible = 10.2.0.1.0
db_recovery_file_dest = C:\oraclexe\app\oracle\flash_recovery_area
db_recovery_file_dest_size= 10737418240
undo_management = AUTO
undo_tablespace = UNDO
remote_login_passwordfile= EXCLUSIVE
dispatchers = (PROTOCOL=TCP) (SERVICE=XEXDB)
shared_servers = 4
job_queue_processes = 4
audit_file_dest = C:\ORACLEXE\APP\ORACLE\ADMIN\XE\ADUMP
background_dump_dest = C:\ORACLEXE\APP\ORACLE\ADMIN\XE\BDUMP
user_dump_dest = C:\ORACLEXE\APP\ORACLE\ADMIN\XE\UDUMP
core_dump_dest = C:\ORACLEXE\APP\ORACLE\ADMIN\XE\CDUMP
db_name = XE
open_cursors = 300
os_authent_prefix =
pga_aggregate_target = 10485760
PSP0 started with pid=3, OS id=2316
PMON started with pid=2, OS id=2312
MMAN started with pid=4, OS id=2320
DBW0 started with pid=5, OS id=2492
LGWR started with pid=6, OS id=2496
CKPT started with pid=7, OS id=2508
SMON started with pid=8, OS id=2472
RECO started with pid=9, OS id=2476
CJQ0 started with pid=10, OS id=2516
MMON started with pid=11, OS id=2524
Thu Oct 12 13:29:28 2006
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
MMNL started with pid=12, OS id=1704
Thu Oct 12 13:29:28 2006
starting up 4 shared server(s) ...
USER: terminating instance due to error 12853
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_pmon_2312.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_dbw0_2492.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_mman_2320.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_lgwr_2496.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_reco_2476.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_smon_2472.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:34 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_ckpt_2508.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Thu Oct 12 13:29:35 2006
Errors in file c:\oraclexe\app\oracle\admin\xe\bdump\xe_psp0_2316.trc:
ORA-12853: insufficient memory for PX buffers: current K, max needed K
Instance terminated by USER, pid = 1544

Lost connection after adjusting SGA and PGA

I lowered SGA from 170M to 50M, and PGA from 60M to 10M. Now I can not connect to XE using apex. Toad also reports ora-12514. I rebooted the pc and also manually cycled the db. But nothing works. In Service the oracle servies appear to be fine.
Thanks for any help.
I didn't register to the private forum for XE. So I post my question here. Hope people are not offended.
xmk

Problem solved!
1. Stop db and rename
C:\ORACLEXE\APP\ORACLE\PRODUCT\10.2.0\SERVER\DBS\SPFILEXE.ORA
to
C:\ORACLEXE\APP\ORACLE\PRODUCT\10.2.0\SERVER\DBS\OLD_SPFILEXE.ORA
2. Start db.
3. sqlplus "/ as sysdba"
4. In sqlplus:
startup pfile='C:\oraclexe\app\oracle\product\10.2.0\server\config\scripts\init.ora';
This brings up the database.
5. In sqlplus:
create spfile from pfile='C:\oraclexe\app\oracle\product\10.2.0\server\config\scripts\init.ora';
This creates 'C:\oraclexe\app\oracle\product\10.2.0\server\database\SPFILEXE.ORA'
6. Stop db, move SPFILEXE.ORA to C:\oraclexe\app\oracle\product\10.2.0\server\dbs
7. Start db. Now it is working.
Thoughts:
1. I probably don't have to do 4. And I can combine 5 and 6 and generate SPFILEXE.ORA from init.ora in one step by specifying the destination.
2. In C:\oraclexe\app\oracle\product\10.2.0\server\config\scripts there is a initXETemp.ora which is very similar to init.ora. You may use it to recover as well.
Thanks everyone!
xmk

RMAN ERROR ORA-04030 out of process memory allocate 1049100 bytes pga heap

Hello,
I have this problem with a production database 9.2.0.8.
I attach the parameters from production database and repository rman database (9.2.0.8).
PRODUCTION DB SERVER 9.2.0.8
WINDOWS SERVER 2003 R2 SP1
SQL> SHOW PARAMETER SGA
NAME VALUE
lock_sga FALSE
pre_page_sga FALSE
sga_max_size 1888562548
SQL>
SQL> SHOW PARAMETER PGA
NAME VALUE
pga_aggregate_target 335544320
SQL> SHOW PARAMETER POOL
NAME VALUE
java_pool_size 33554432
large_pool_size 134217728
shared_pool_reserved_size 13421772
shared_pool_size 268435456
SQL> SHOW PARAMETER CACHE
NAME VALUE
db_cache_advice ON
db_cache_size 1073741824
REPOSITORY RMAN DB SERVER 9.2.0.8
WINDOWS SERVER 2000 SP4
SQL> SHOW PARAMETER SGA
NAME VALUE
lock_sga FALSE
pre_page_sga FALSE
sga_max_size 1074865628
SQL> SHOW PARAMETER PGA
NAME VALUE
pga_aggregate_target 134217728
SQL> SHOW PARAMETER POOL
NAME VALUE
java_pool_size 33554432
large_pool_size 134217728
shared_pool_reserved_size 6710886
shared_pool_size 134217728
SQL> SHOW PARAMETER CACHE
NAME VALUE
db_cache_size 134217728
SCRIPT RMAN
run {
allocate channel t1 type disk;
allocate channel t2 type disk;
backup skip readonly filesperset = 1 format 'E:\rman\BDWEBEXT\BD_%d_%u_%s_%p.rmn' tag 'Backup Completo BDWEBEXT' database;
release channel t1;
release channel t2;
ERROR
RMAN-00571: ===========================================================
RMAN-00569: =============== ERROR MESSAGE STACK FOLLOWS ===============
RMAN-00571: ===========================================================
RMAN-03009: failure of backup command on t2 channel at 02/09/2008 14:46:58
ORA-04030: out of process memory when trying to allocate 1049100 bytes (pga heap,KSFQ Buffers)
Recovery Manager complete.
Does someone know that it can be?
Thank you

how solve ORA-04030: out of process memory when trying to allocate
Sybrand Bakker
Senior Oracle DBA

Cannot change sga or pga value

Hello,
i've got a problem with changing the sga or pga values on oracle xe installed on windows xp.
When i log on to the administration page, set a new sga target, restart xe and go to the page where i can set the sga target size i still see the old values. My new values are not set.
What can i do to change the sga target value?
Thanks for help in advance,
Dirk

You don't need to restart instance when you set new value.
If you want to have that value permanently (I wouldn't) then you must change initialization parameter.
E.g.:
http://download.oracle.com/docs/cd/B19306_01/server.102/b14231/start.htm#sthref512
HTH

Diagnosing an ASM space issue for a primary and a standby database instance with external redundancy.

I've received an alert from Enterprise manager saying "Disk Group DATA_SID requires rebalance because at least one disk
is low on space". My colleague who I would go to with this question is unavailable, so this is a learning opportunity
for me. So far google and Oracle documentation have provided lots of information, but nothing that answers my questions.
I've run the following query on both the primary and standby databases ASM instances:
select name, disk_number, sector_size,os_mb, total_mb, free_mb, redundancy from v$asm_disk;
On the primary I get 4810M Free space and 18431M Total Space
on the standby I get 1248M Free space and 18431M Total Space -- this is the one that complained via OEM
When I run the following query in the database instance:
select sum(bytes)/1024/1024 MB from dba_segments;
I get 3736.75M as a result.
My questions are:
1. Will OEM's suggestion to rebalance the disk actually help in this situation since the instance is set up with external redundancy?
2. If I've got 18G of space and only 3.7G of data, why is OEM complaining?
3. How can I reclaim what I presume is allocated but unused space in my problem disk group?
4. How can I determine what extra data the standby has that the primary doesn't since both have the same total space allocation, but different amounts of free space?

Thank you for the reply. That link is very good.
We are an 11.1 version of our database. Linus is OEL 5.6.
So, looking at the portion of the link that refers to 'Add Standby database and Instances to the OCR' - If we use SRVCTL to give the STANDBY the role of ‘physical_standby’ and the start option of ‘mount’, what effect will that have if the STANDBY becomes our PRIMARY?
Would these database settings need to be modified manually with SRVCTL each time?
We understand why the instance is not starting when the node is rebooted, we are looking for a best practice of how this is implemented.
Thank you.

How to allocate the processor to oracle ebs instances

dear all
we are using solaris 10 on sparc t3 server.
we want to allocate some processor to oracle ebs instances for the multi instance environment
so please suggest us how should we go for it..
regards

In addition to the above, increasing the number of processors should not impact the functionality of the application and your only concern should be the licensing, and for this matter you will need to contact your Oracle sales representative.
http://www.oracle.com/us/corporate/pricing/price-lists/index.html
Global Pricing and Licensing
Thanks,
Hussein

IOncrease size of buffer pool and PGA

Dear All,
Currently my DB is on Automatic Memory Management,
I want to increase the size of Buffer cache and PGA, so do I need to move the DB out of Automatic Memory Managemen and manually manage the memory?
Please help
Thanks

Wrong forum. This is for SQL and PL/SQL questions.
Try General Database Discussions

Help on 10g 64 bit --Sizing SGA and sysctl.conf

Dear Sir,
I have an oracle10g installed on a 64 bit OS and want to allocate 8GB to SGA and want to confirm if i am using the right settings
My sysctl.conf settings are :
cat /etc/sysctl.conf
# Kernel sysctl configuration file for Red Hat Linux
# For binary values, 0 is disabled, 1 is enabled. See sysctl(8) and
# sysctl.conf(5) for more details.
# Controls IP packet forwarding
net.ipv4.ip_forward = 0
# Controls source route verification
net.ipv4.conf.default.rp_filter = 1
# Do not accept source routing
net.ipv4.conf.default.accept_source_route = 0
# Controls the System Request debugging functionality of the kernel
kernel.sysrq = 0
# Controls whether core dumps will append the PID to the core filename
# Useful for debugging multi-threaded applications
kernel.core_uses_pid = 1
# Controls the use of TCP syncookies
net.ipv4.tcp_syncookies = 1
# Controls the maximum size of a message, in bytes
kernel.msgmnb = 65536
# Controls the default maxmimum size of a mesage queue
kernel.msgmax = 65536
kernel.shmmax = 8589934592
kernel.shmmni = 4096
kernel.shmall = 2097152
kernel.sem = 3000 32000 100 128
net.core.rmem_default=262144
net.core.rmem_max=262144
net.core.wmem_default=262144
net.core.wmem_max=262144
My init Settings are :
*._DB_BLOCK_LRU_LATCHES=16
*._spin_count=7000
*.archive_lag_target=1800
*.audit_sys_operations=TRUE
*.BACKGROUND_DUMP_DEST='/redf/DB/dbf/dump'
*.circuits=10000
*.COMPATIBLE='10.2.0.4'
*.CONTROL_FILES='/redf/DB/dbf/cntl1/DB_cntl1_01.ctl','/redf/DB/dbf/cntl2/DB_cntl2_02.ctl','/redf/DB/dbf/cntl3/DB_cntl3_03.ctl'
*.CORE_DUMP_DEST='/redf/DB/dbf/dump'
*.cursor_sharing='FORCE'
*.DB_BLOCK_SIZE=8192
*.DB_CACHE_SIZE=1024M
*.db_file_multiblock_read_count=64
*.db_file_name_convert='/redf/DB/dbf','/redf/DB/dbf'
*.DB_NAME='DB'
*.db_writer_processes=8
*.dispatchers='(PROTOCOL=TCP)(DISPATCHERS=10)'
*.FAST_START_MTTR_TARGET=300
*.INSTANCE_NAME='DB'
*.JAVA_POOL_SIZE=64M
*.JOB_QUEUE_PROCESSES=1
*.large_pool_size=150M
*.LOCAL_LISTENER='(ADDRESS_LIST=(ADDRESS=(PROTOCOL=TCP)(HOST=XX.XX.XX.XXX)(PORT=1521)))'
*.LOG_ARCHIVE_DEST_1='LOCATION=/redf/DB/arch'
*.LOG_ARCHIVE_DEST_2='LOCATION=/orabackup/redf/DB/arch_new'
*.log_archive_dest_state_2='ENABLE'
*.log_archive_format='DB%t_%r_%s.arc'
*.log_archive_max_processes=2
*.log_archive_min_succeed_dest=1
*.LOG_ARCHIVE_START=TRUE
*.log_buffer=50000000
*.MAX_DISPATCHERS=40
*.max_shared_servers=40
*.O7_DICTIONARY_ACCESSIBILITY=FALSE
*.open_cursors=10000
*.optimizer_index_cost_adj=20
*.parallel_adaptive_multi_user=TRUE
*.parallel_automatic_tuning=TRUE
*.parallel_max_servers=20
*.parallel_min_servers=2
*.processes=4000
*.QUERY_REWRITE_ENABLED='TRUE'
*.QUERY_REWRITE_INTEGRITY='ENFORCED'
*.recovery_parallelism=5
*.recyclebin='OFF'
*.remote_archive_enable='TRUE'
*.REMOTE_LOGIN_PASSWORDFILE='EXCLUSIVE'
*.remote_os_authent=FALSE
*.resource_limit=TRUE
*.session_cached_cursors=200
*.sessions=4000
*.SGA_MAX_SIZE=8000M
*.SGA_TARGET=6500M
*.shared_pool_size=1024M
*.shared_servers=10
*.sort_area_size=10485760
*.sql92_security=TRUE
*.standby_archive_dest='/redf/DB/arch'
*.standby_file_management='AUTO'
*.statistics_level='TYPICAL'
*.timed_statistics=TRUE
*.UNDO_MANAGEMENT='AUTO'
*.undo_retention=1800
*.undo_tablespace='UNDOTBS'
*.USER_DUMP_DEST='/redf/DB/dbf/dump'
Want to confirm is this a proper tuend settings as per memory provided ?
I am aware that it also depends on my appication behaviour , but i just want to check whether the above settings would suffice for a 16GB RAM machine and 64 bit oracle10g
Also let me know if any other setttings apart from this are required , i choose to use SGA Target .Further my application is read intensive . Your suggestions will be highly appreciated.
Thanx

Hi,
I suggest you to increase the value kernel.shmmax = 8589934592 of this parameter in sysctl.conf to kernel.shmmax = 1288490188
Later if you want to increase the size of SGA then you need to modify the kernel.shmmax = 8589934592 value. In general practice we keep kernel.shmmax value little greater then the value of SGA.
Refer MOS tech note:
*ORA-27102 Database Will Not Start With SHMMAX Set To 8589934592 (8GB) [ID 461519.1]*
*Linux Big SGA, Large Memory, VLM - White Paper [ID 260152.1]*
thanks,
X A H E E R
Edited by: ora_tech on Dec 26, 2010 10:14 AM

Difference between RMAN Allocate channel and Configure Channel

Hello Sir,
It is a very small problem that the more I study about RMAN I get more confused that what is the difference between Allocate Channel and Configure Channel.
The thing I understand is that first we allocate channel and then after we configure it for uses.
Pl. anybody make me clear if it is wrong and please tell me the right theory.
Thanks and regards

Hi,
As Already Aman and Hemant K Chitale .. described the difference..
Let me put up one thing one thing Ahead... !!
CONFIGURE CHANNEL takes the same options used to specify one-time options with the ALLOCATE CHANNEL command. You can configure generic channel settings for a device type, that is, a template that is used for any channels created based on configured settings for that device.
Example :-
Note that if you use CONFIGURE CHANNEL to specify generic channel settings for a device, any previous settings are discarded, even if the settings are not in conflict. For example, after the second CONFIGURE CHANNEL command, which specifies only the FORMAT for configured disk channels, the MAXPIECESIZE for the disk channel is returned to its default value:
CONFIGURE CHANNEL DEVICE TYPE DISK MAXPIECESIZE 2G;
CONFIGURE CHANNEL DEVICE TYPE DISK FORMAT /tmp/%U;
If you manually allocate a channel during a job, then RMAN disregards any configured channel settings. For example, assume that the default device type is SBT, and you execute the following command:
RUN
ALLOCATE CHANNEL c1 DEVICE TYPE DISK;
BACKUP TABLESPACE users;
Ever thing is in ORACLE Documentation.. . (Pick out the things....)
http://download-uk.oracle.com/docs/cd/B28359_01/backup.111/b28270/rcmconfb.htm
Study or Go through Slow and Study... you can understnad ever thing...
- Pavan Kumar N

Manually allocate SGA and PGA to a Instance?

Similar Messages

Maybe you are looking for