Multipool with weblogic 8.1 sp3 and Oracle RAC

Hi,
I have an Oracle RAC define with 2 node.
For each node I defined a simple ConnectionPool using the Oracle thin driver 10 g.
Then I set a multipool that contains those conections pool.
This is a good solution: It works... :-)
Now I would like to use a XA Driver. The documentation say that it is not supported...
I would like to figure out why?
Does it mean that an EJB that connect to this multipool cannot participate in a XA transaction?
Will it work if I use the param KeepXAConnTillTXComplete="true" on the connectionpool? which means that I will use the same conection throughout the transaction.
Thank you
Yann.

Yann Albou wrote:
Hi,
I have an Oracle RAC define with 2 node.
For each node I defined a simple ConnectionPool using the Oracle thin driver 10 g.
Then I set a multipool that contains those conections pool.
This is a good solution: It works... :-)
Now I would like to use a XA Driver. The documentation say that it is not supported...
I would like to figure out why?
Does it mean that an EJB that connect to this multipool cannot participate in a XA transaction?
Will it work if I use the param KeepXAConnTillTXComplete="true" on the connectionpool? which means that I will use the same conection throughout the transaction.
Thank you
Yann.Hi. The trouble with XA and multipools is that sometimes XA must recover after failures,
and if a multipool is involved, the transaction coordinator cannot know whether the
connection it gets from the multipool for recovery is talking to the same DBMS that was
involved in the transaction that has to be recovered.
Do check the 81sp3 documents on this issue.
Joe

Similar Messages

Problems with Weblogic 8.1 SP3 and Toplink 10.1.3

Hi!
I'm runnning into two problems when using toplink 10.1.3 and weblogic 8.1 SP3.
I mapped my classes with the mapping workbench, where I defined also the optimistic locking properties.
When I export that project for bean compiling there are entries like store-version-in-cache.
When i compile the beans i get an exception that store-version-in-cache is a unexpected element.
Ok, next problem: i leave out the locking properties, beans are compiling.
When i start the server and call a named query i get the following exception:
[TopLink Warning]: 2004.11.12 05:25:13.437--ServerSession(697447)--java.lang.AbstractMethodError: weblogic.jdbc.wrapper.
Statement_COM_ibm_db2_jdbc_app_DB2Statement.setFetchSize(I)V
I think I configured the server correctly (but of course i'm not absolutly sure). Where is the fault?
Any help? Thanx.
Greetings volker

Not sure on the first problem, store-version-in-cache is a valid element. Make sure you are using the same version of the Mapping Workbench and the runtime library. Please attach the XML for the version locking policy that was generated and the error message.
The abstract method error seems to indicate that the setFetchSize method is missing on your driver.
setFetchSize has been part of JDBC and JDK since JDBC 2.0/JDK 1.2, how old is the driver that you are trying to use? I noticed the COM is uppercase, so I assume this is a very old driver, can you use the more update version? TopLink requires JDK 1.3 support as a minimum.

WebLogic 6.1 SP4 and Oracle 8/9i

Hi,
Background:
We're currently running WebLogic 6.1 SP4 and Oracle 8.1.7. Also, we don't use
anything other than the weblogic.jar in the class path - it's a standard configuration.
I'm anticipating incorporating some Oracle 9i in the mix and also an eventual
migration to WebLogic 7.
Questions:
1a. Are there any issues from a WebLogic perspective in a heterogeneous Oracle
environment (both 8i and 9i connection pools)?.
1b. Will the supplied driver with 6.1 SP4 handle this?
1c. How about Web Logic 7?
2a. If we need to use an updated thin driver for 9i to use additional features,
is there a supported one for Web Logic 6?
2b. Web Logic 7?
Thanks for your help, Jeff

You should get the latest driver from oracle that will work fine with both 8 and
9.
"Jeff Ryan" <[email protected]> wrote:
>
Hi,
Background:
We're currently running WebLogic 6.1 SP4 and Oracle 8.1.7. Also, we
don't use
anything other than the weblogic.jar in the class path - it's a standard
configuration.
I'm anticipating incorporating some Oracle 9i in the mix and also an
eventual
migration to WebLogic 7.
Questions:
1a. Are there any issues from a WebLogic perspective in a heterogeneous
Oracle
environment (both 8i and 9i connection pools)?.
1b. Will the supplied driver with 6.1 SP4 handle this?
1c. How about Web Logic 7?
2a. If we need to use an updated thin driver for 9i to use additional
features,
is there a supported one for Web Logic 6?
2b. Web Logic 7?
Thanks for your help, Jeff

Our Java application is built with java 1.4 version and oracle 10g

Our Java application is built with java 1.4 version and oracle 10g version database, is it possible to upgrade oracle database to 11g?

is it possible to upgrade
Yes. SE and the other editions have a migration/upgrade utility, not seeing any mention of that program in the XE license docs. To upgrade to 11gR2 from 10g, the 10g instance must be at patch 10.2.0.2 or higher.
So if you're a GUI dba, might be out of luck. But the the XE install has the catalog upgrade scripts that need to be run, there is a MOS note explaining the manual upgrade steps.
Or set up a brand new 11g database instance and datapump your user schema(s) from the 10g instance to the new 11g instance. The database doesn't care what java version you're using, it just does what its told with the data. DDL, DCL, DML ... its not much different. Quite a few new features in 11g.
But if you're after JVMs that piece is not supported with XE.

Install SAP ERP 6.0 with Linux and Oracle RAC

Hi Guru,
I want to install SAP ERP 6.0 with Linux and Oracle RAC. Is this possible?
Where do I find information?
Thanks,
Hugo.

Hello Hugo,
You can use either RAC or dataguard. On note [105047|http://service.sap.com/sap/support/notes/105047]:
14. Data Guard
    o You can use "Physical Standby".
    o You cannot use "Logical Standby".
    o You can use Data Guard Broker.
    o You can use Maximum Performance Mode, Maximum Availability Mode and Maximum Protection Mode.
    o In the case of Maximum Availability and Maximum Protection, you must pay particular attention to a fast network connection in order to avoid performance problems.
    o Maximum Protection causes the primary database to terminate if problems occur in the standby database.
60. Real Application Cluster (RAC)
    o You can use this feature in accordance with Note 527843.
Regards,
Eduardo Rezende

BODS and Oracle RAC

Do we know of any problems with BODS and Oracle Real Application Clusters architecture? For example, a RAC TNS entry would specify one service name but multiple hosts for load balancing and failover. In BODS the connections are specified in many places (web console, datastores, job server). As far as I remember in some of those places we do have to enter the host name. Would this disqualify BODS from benefiting from RAC or would it (even worse) cause problems? Any official note by SAP on BODS and Oracle RAC?
Thanks.

Hi Mahir,
As far as I know it's only the web console that requires the hostname, however I am using DS XI 3.1 and when selecting database type Oracle in the web console there is a checkbox for 'Oracle RAC'. If you check this box then you do not require to enter the hostname.

Weblogic 8.1.6 and Oracle 9.2.0.8 - query performance

Folks,
We are upgrading WebLogic from 8.1.5 to 8.1.6 and Oracle from 9.2.0.6 to 9.2.0.8. We use the Oracle thin client driver for 9.2.0.8 to connect from the application to Oracle.
When we use the following combination of the stack we see SQL query performance degradation: -
Oracle 9.2.0.8 database, Oracle 9.2.0.8 driver, WL 8.1.6
Oracle 9.2.0.8 database, Oracle 9.2.0.1 driver, WL 8.1.6
We do not see the degradation in case of the following: -
Oracle 9.2.0.8 database, Oracle 9.2.0.1 driver, WL 8.1.5
Oracle 9.2.0.6 database, Oracle 9.2.0.1 driver, WL 8.1.5
This shows that the problem could be with the WL 8.1.6 version and I was wondering if any of you have faced this before? The query retrieves a set of data from Oracle none of which contain the AsciiStream data type, which is noted as a problem in WL 8.1.6, but that too, only for WL JDBC drivers.
Any ideas appreciated.

Folks,
We are upgrading WebLogic from 8.1.5 to 8.1.6 and Oracle from 9.2.0.6 to 9.2.0.8. We use the Oracle thin client driver for 9.2.0.8 to connect from the application to Oracle.
When we use the following combination of the stack we see SQL query performance degradation: -
Oracle 9.2.0.8 database, Oracle 9.2.0.8 driver, WL 8.1.6
Oracle 9.2.0.8 database, Oracle 9.2.0.1 driver, WL 8.1.6
We do not see the degradation in case of the following: -
Oracle 9.2.0.8 database, Oracle 9.2.0.1 driver, WL 8.1.5
Oracle 9.2.0.6 database, Oracle 9.2.0.1 driver, WL 8.1.5
This shows that the problem could be with the WL 8.1.6 version and I was wondering if any of you have faced this before? The query retrieves a set of data from Oracle none of which contain the AsciiStream data type, which is noted as a problem in WL 8.1.6, but that too, only for WL JDBC drivers.
Any ideas appreciated.

Weblogic 10.3.1 and Oracle AQ

Hello all.
I have the following error:
javax.jms.IllegalStateException: JMS-227: Invalid attempt to commit you to a non-transactional JMS Session
     at oracle.jms.AQjmsError.throwIllegalStateEx(AQjmsError.java:471)
     at oracle.jms.AQjmsSession.commit(AQjmsSession.java:1009)
     at com.gvt.itss.controlf2.core.jms.listener.CF2OracleAQListener.onMessage(CF2OracleAQListener.java:68)
     at oracle.jms.AQjmsListenerWorker.dispatchOneMsg(AQjmsListenerWorker.java:321)
     at oracle.jms.AQjmsListenerWorker.run(AQjmsListenerWorker.java:134)
     at java.lang.Thread.run(Thread.java:619)
I can get the objects from my AQ Queue, but when I try to Commit, this exception appear.
What can I do to resolve this problem?
Thanks!
Edited by: user6494356 on Jul 20, 2009 6:05 AM

It's unclear whether you're using a supported method for Oracle AQ integration with WebLogic Server. Have you examined the related documentation? Specifically:
[ Configuring and Managing JMS for Oracle WebLogic Server - Chapter 8 - Interoperating with Oracle AQ JMS | http://download.oracle.com/docs/cd/E12839_01/web.1111/e13738/aq_jms.htm#JMSAD565 ]
Tom

Weblogic and Oracle RAC + DataGuard

Hi,
I am testing Weblogic 9.2 with Oracle 10g RAC (2 nodes) and Oracle DataGuard and I am trying to figure out the best possible data source configuration that would handle load balancing between RAC nodes and failover/switchback between RAC nodes and the standby database. The problem that I see is that all Oracle instances have to be open in order to successfully deploy the data sources on Weblogic. This means that at creation/deployment time and after every Weblogic reboot all Oracle instances have to be up and running and accepting connections, because otherwise the data sources won't be instantiated and therefore not accessible to the consuming application.
Is there any way to smoothly deploy the data sources without having to go through the hassle of making sure that all RAC nodes and DataGuard are open?
What I would expect is that the data source would be instantiated but disabled if no connection is available. Having to redeploy the data source once the database instance is again available is a limitation in providing transparent high availability.
Thanks.

Hi, yes. Configure the pool to have an initial capacity of zero. Then it will
deploy and not try to make any connections. It will only try when/if
it is asked for one at runtime. Even if the DBMS is not up, the
DataSource will just throw an exception until the DBMS is up.

Problem with Linus Ubuntu 7.04 and Oracle-Xe debian package

Hi all,
Installed Oracle 10g XE on my Ubuntu 7.04 using universal Debian Package : oracle-xe-universal_10.2.0.1-1.0_i386.deb. No problem during the installation . After finished the installation, I configured the database to use port 6000 and its password (Listener port set to default).
But when I tried to access the database home page using "http://127.0.0.1:6000/apex", it cannot be accessed. Then I tried to verify my database server using /etc/init.d/oracle-xe status and here's the output:(before it, I make user the database was realy online by typing /etc/init.d/oracle-xe start)
###########################333###
LSNRCTL for Linux: Version 10.2.0.1.0 - Production on 09-AUG-2007 22:45:07
Copyright (c) 1991, 2005, Oracle. All rights reserved.
Connecting to (DESCRIPTION=(ADDRESS=(PROTOCOL=IPC)(KEY=EXTPROC_FOR_XE)))
TNS-12541: TNS:no listener
TNS-12560: TNS:protocol adapter error
TNS-00511: No listener
Linux Error: 2: No such file or directory
Connecting to (DESCRIPTION=(ADDRESS=(PROTOCOL=TCP)(HOST=wks-082)(PORT=1521)))
TNS-12545: Connect failed because target host or object does not exist
TNS-12560: TNS:protocol adapter error
TNS-00515: Connect failed because target host or object does not exist
Linux Error: 110: Connection timed out
then I tried to open the log in /usr/lib/oracle/xe/app/oracle/admin/xe/bdump/alert_XE.log and here is the output
Thu Aug 9 14:54:14 2007
Starting ORACLE instance (normal)
Cannot determine all dependent dynamic libraries for /proc/self/exe
Unable to find dynamic library libocr10.so in search paths
RPATH = /ade/aime1_build2101/oracle/has/lib/:/ade/aime1_build2101/oracle/lib/:/ade/aime1_build2101/oracle/has/lib/:
LD_LIBRARY_PATH is not set!
The default library directories are /lib and /usr/lib
Unable to find dynamic library libocrb10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Shared memory segment for instance monitoring created
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 Aug 9 14:54:27 2007
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
sga_target = 146800640
control_files = /usr/lib/oracle/xe/oradata/XE/control.dbf
compatible = 10.2.0.1.0
db_recovery_file_dest = /usr/lib/oracle/xe/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
background_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/bdump
user_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/udump
core_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/cdump
audit_file_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/adump
db_name = XE
open_cursors = 300
os_authent_prefix =
pga_aggregate_target = 41943040
Thu Aug 9 14:54:33 2007
Errors in file /usr/lib/oracle/xe/app/oracle/admin/XE/udump/xe_ora_7532.trc:
ORA-00600: internal error code, arguments: [keltnfy-ldmInit], [46], [1], [], [], [], [], []
USER: terminating instance due to error 600
Instance terminated by USER, pid = 7532
Thu Aug 9 14:54:35 2007
Starting ORACLE instance (normal)
Cannot determine all dependent dynamic libraries for /proc/self/exe
Unable to find dynamic library libocr10.so in search paths
RPATH = /ade/aime1_build2101/oracle/has/lib/:/ade/aime1_build2101/oracle/lib/:/ade/aime1_build2101/oracle/has/lib/:
LD_LIBRARY_PATH is not set!
The default library directories are /lib and /usr/lib
Unable to find dynamic library libocrb10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
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 Aug 9 14:54:46 2007
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
sga_target = 146800640
control_files = /usr/lib/oracle/xe/oradata/XE/control.dbf
compatible = 10.2.0.1.0
db_recovery_file_dest = /usr/lib/oracle/xe/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)
background_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/bdump
user_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/udump
core_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/cdump
audit_file_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/adump
db_name = XE
open_cursors = 300
os_authent_prefix =
pga_aggregate_target = 41943040
Thu Aug 9 14:54:51 2007
Errors in file /usr/lib/oracle/xe/app/oracle/admin/XE/udump/xe_ora_7551.trc:
ORA-00600: internal error code, arguments: [keltnfy-ldmInit], [46], [1], [], [], [], [], []
USER: terminating instance due to error 600
Instance terminated by USER, pid = 7551
Thu Aug 9 14:54:53 2007
Are there anyone who can help me? I really have no idea since I'm a newbie here, both linux and oracle. Any hint are welcome, thanks in advance.
Regards,
Rudi Sadria

Thx for the help, I already verify the /etc/hosts and these are the output:
127.0.0.1 localhost
127.0.0.1 wks-082
127.0.0.1 localhost.localdomain localhost localhost.domain
127.0.0.1 hostname hostname.domain
# The following lines are desirable for IPv6 capable hosts
::1 ip6-localhost ip6-loopback
fe00::0 ip6-localnet
ff00::0 ip6-mcastprefix
ff02::1 ip6-allnodes
ff02::2 ip6-allrouters
ff02::3 ip6-allhosts
I check the listener status and here's the output:
LSNRCTL for Linux: Version 10.2.0.1.0 - Production on 10-AUG-2007 15:14:45
Copyright (c) 1991, 2005, Oracle. All rights reserved.
Connecting to (DESCRIPTION=(ADDRESS=(PROTOCOL=IPC)(KEY=EXTPROC_FOR_XE)))
STATUS of the LISTENER
Alias LISTENER
Version TNSLSNR for Linux: Version 10.2.0.1.0 - Production
Start Date 10-AUG-2007 15:14:39
Uptime 0 days 0 hr. 0 min. 6 sec
Trace Level off
Security ON: Local OS Authentication
SNMP OFF
Default Service XE
Listener Parameter File /usr/lib/oracle/xe/app/oracle/product/10.2.0/server/network/admin/listener.ora
Listener Log File /usr/lib/oracle/xe/app/oracle/product/10.2.0/server/network/log/listener.log
Listening Endpoints Summary...
(DESCRIPTION=(ADDRESS=(PROTOCOL=ipc)(KEY=EXTPROC_FOR_XE)))
(DESCRIPTION=(ADDRESS=(PROTOCOL=tcp)(HOST=wks-082)(PORT=1521)))
Services Summary...
Service "PLSExtProc" has 1 instance(s).
Instance "PLSExtProc", status UNKNOWN, has 1 handler(s) for this service...
Service "XE" has 1 instance(s).
Instance "XE", status BLOCKED, has 1 handler(s) for this service...
Service "XE_XPT" has 1 instance(s).
Instance "XE", status BLOCKED, has 1 handler(s) for this service...
The command completed successfully
and here's the alert_XE.log
Fri Aug 10 15:30:59 2007
Starting ORACLE instance (normal)
Cannot determine all dependent dynamic libraries for /proc/self/exe
Unable to find dynamic library libocr10.so in search paths
RPATH = /ade/aime1_build2101/oracle/has/lib/:/ade/aime1_build2101/oracle/lib/:/ade/aime1_build2101/oracle/has/lib/:
LD_LIBRARY_PATH is not set!
The default library directories are /lib and /usr/lib
Unable to find dynamic library libocrb10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
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
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 = 41943040
__large_pool_size = 0
sga_target = 146800640
control_files = /usr/lib/oracle/xe/oradata/XE/control.dbf
__db_cache_size = 96468992
compatible = 10.2.0.1.0
db_recovery_file_dest = /usr/lib/oracle/xe/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
background_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/bdump
user_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/udump
core_dump_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/cdump
audit_file_dest = /usr/lib/oracle/xe/app/oracle/admin/XE/adump
db_name = XE
open_cursors = 300
os_authent_prefix =
pga_aggregate_target = 41943040
PMON started with pid=2, OS id=7328
PSP0 started with pid=3, OS id=7330
MMAN started with pid=4, OS id=7332
DBW0 started with pid=5, OS id=7334
LGWR started with pid=6, OS id=7336
CKPT started with pid=7, OS id=7338
SMON started with pid=8, OS id=7340
RECO started with pid=9, OS id=7342
CJQ0 started with pid=10, OS id=7344
MMON started with pid=11, OS id=7348
MMNL started with pid=12, OS id=7350
Fri Aug 10 15:31:00 2007
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
starting up 4 shared server(s) ...
Oracle Data Guard is not available in this edition of Oracle.
Fri Aug 10 15:31:01 2007
ALTER DATABASE MOUNT
Fri Aug 10 15:31:01 2007
ORA-00202: control file: '/usr/lib/oracle/xe/oradata/XE/control.dbf'
ORA-27037: unable to obtain file status
Linux Error: 2: No such file or directory
Additional information: 3
Fri Aug 10 15:31:01 2007
ORA-205 signalled during: ALTER DATABASE MOUNT...
and then I open the SQL* plus and type some command
/usr/lib/oracle/xe/app/oracle/product/10.2.0/server/bin/nls_lang.sh: 114: [[: not found
/usr/lib/oracle/xe/app/oracle/product/10.2.0/server/bin/nls_lang.sh: 114: [[: not found
SQL*Plus: Release 10.2.0.1.0 - Production on Fri Aug 10 15:32:38 2007
Copyright (c) 1982, 2005, Oracle. All rights reserved.
SQL> conn / as sysdba
Connected.
SQL> select status from v$instance
2 ;
STATUS
STARTED
But I'm still cannot accessed my "http://localhost:6000/apex". Are there any possibilities that my browser block it? or I need to change the port?
Thx a lot for your help
Regards,
Rudi Sadria

Problem with weblogic 8.1 sp3 XAConnection

Hi,
I am getting the following exception and once this exception is encountered, same exception is thrown for all subsequesnt transactions.
I am using weblogic 8.1 SP3, jdbc tx datasource for ms sql server.
Can anyone help?
Unexpected exception while enlisting XAConnection java.sql.SQLException: XA error: XAER_PROTO : Routine was invoked in an inproper context start() failed on resource 'TXConnectionPoll': XAER_PROTO : Routine was invoked in an inproper context
javax.transaction.xa.XAException: [BEA][SQLServer JDBC Driver]Transaction has to commit/rollback before another transaction starts.
Regds.
DJ

Hi,
The application consists of struts1.1 in the web layer.
All user entered data are wrapped in a map and using
dispatcher controller (session bean) the respective
business objectss (session beans - Tx attribute is
'Required') are called by passing the map data which
in turn, executes the business logic based on the user
provided data.
The session beans calling the entity beans to do
create/update/delete jobs in database.
To retrieve data from database, we are using iBatis
framework and queries are being fired from session
beans.
In some of the functionality, we are using stored
procedure (SQL server 2000), which are being called
from within session bean.
I think, wherever, we are calling SP from session bean.
some local transactions are being created, which I
could not identify so far.We did not create any nested
transaction within stored procedure.
Please ignore the same posting I did in another topic.
Regds.
DJ

Running Weblogic 8.1 SP3 and IPlanet 6.0 on same machine

I have requirement to run Weblogic Platform SP3 and IPlanet 6.0 servers on same Solaris machine
for a client of ours.
Please let me if we can do this. What kind of issues we may run into.
Thanks,
Sanjay

Hi
Of course, you can install both at the same machine.
Only remember the memory required ... and the real memory available ... this for don't have swap problems.
Remember too if you are planning to create WLS clusters ... BEA recommends 1 cluster per CPU ... and reserve 1 CPU for the iPlanet web Server. Even, you can install all clusters and web server as your machine support ( under load, try to mantain the CPU usage under 70-80%).
Jin

Weblogic 5.1 SP3 and Apache 1.3.12 Config Question

Hello;
Can someone tell me how I might make this configuration work? I'm trying to
run multiple Weblogic Process on one box and 1 Apache Process on another
box. I would like to utilize the "VirtualHosting by name" via the HTTP1.1
protocol and use the weblogic plugin.
*** HTTPD.CONF FILE ***
LoadModule weblogic_module libexec/mod_wl.so
<VirtualHost 1stVirtual.host.com>
<Location /weblogic>
SetHandler weblogic-handler
PathTrim weblogic
</Location>
<Location /servletimages>
SetHandler weblogic-handler
Pathtrim something
</Location>
<IfModule mod_weblogic.c>
Include conf/1stVirtual.conf
</IfModule>
</VirtualHost>
<VirtualHost 2ndVirtual.host.com>
<Location /weblogic>
SetHandler weblogic-handler
PathTrim weblogic
</Location>
<Location /servletimages>
SetHandler weblogic-handler
Pathtrim something
</Location>
<IfModule mod_weblogic.c>
Include conf/2ndVirtual.conf
</IfModule>
</VirtualHost>
AddModule mod_weblogic.c
*** 1stVIRTUAL.CONF File ****
WebLogicHost 1stVirtual.host.com
WebLogicPort 7003
When I try to call the website:
http://1stVirtual.host.com/weblogic/ I get this:
Failure of WebLogic APACHE bridge:
Neither WebLogicCluster nor WebLogicHost parameter was specified in
httpd.conf. Cannot continue.
Anyhelp would be greatly appreciated.
-Bob
P.S.- My Configuration is as follows:
WEBLOGIC SERVER
Solaris 2.6
Weblogic 5.1 SP3
APACHE SERVER
Solaris 2.6
Apache 1.3.12

Bob:
Fixed in SP 4. Out very, very soon.
mbg
In article <3969eabe$[email protected]>, [email protected] says...
Hello;
Can someone tell me how I might make this configuration work? I'm trying to
run multiple Weblogic Process on one box and 1 Apache Process on another
box. I would like to utilize the "VirtualHosting by name" via the HTTP1.1
protocol and use the weblogic plugin.
SNIP
When I try to call the website:
http://1stVirtual.host.com/weblogic/ I get this:
Failure of WebLogic APACHE bridge:
Neither WebLogicCluster nor WebLogicHost parameter was specified in
httpd.conf. Cannot continue.
Anyhelp would be greatly appreciated.
-Bob--
==================================================
NewsGroup Rant
==================================================
Rant 1.
The less info you provide about your problem means
the less we can help you. Try to look at the
problem from an external perspective and provide
all the data necessary to put your problem in
perspective.

UTL_FILE_DIR and Oracle RAC

Gentlemen,
I have installed with sucess an environment with Oracle RAC with two servers. The application that runs in these servers, has batch procedures, and it has to save flat files during these processes. When the processes run with both servers something goes wrong and the system stops. It doesn´t happen when I shutdown one of the servers. I tried to setup directories in the storage system (external disks) but it wasn´t allowed too.
Does anyone know how can I setup utl_file_dir to work with both servers? Is there another parameter to set?
Thank you all,
Best regards.
Roberto Cavalcante
Brazil

VCFS/CFS/NFS are just filesystems and UTL_FILE does file i/o. If you have sessions in multiple instances that write to the same file on a cluster filesystem, the outcome would be unpredictable. Most likely, the last person to write to the file would have their changes saved. Oracle DB (RAC or not) doesn't handle any concurrency related to UTL_FILE writes. So, even if you were in the same instance (non-RAC) and had two sessions writing to the same file, I don't think you'd get the desired results :). The file would likely be a mess and you'd have to use different file names or control concurrency yourself manually.

Java application (tomcat) and Oracle RAC 10gR2

Hi, I have an Oracle RAC 10gR2 (10.2.0.3) on Suse Linux Enterprise Server (3 nodes).
I have several application running on tomcat 5.X and tomcat 6.X with java 1.5 and java 1.6. Sometimes, because of hardware fail, network problems,... one of the nodes fails, and then the other 2 nodes still working and my database is up. However, the most of applications lose the connection with the database, and I must to restart the tomcat. I want to have a system more reliable and robust, and I want to prepare the tomcat's and java application for prevent it. I have read the http://drdobbs.com/java/222700353?pgno=1 and http://db360.blogspot.com/2007/01/is-your-java-application-failoverproof.html. I've been tried the example of the first url, but I don't connect with my database. However, I've probe the sample on another oracle rac (10.2.0.4) and it works. In the samples, it use the ucp.jar (11g) and ons.jar (10g) and ojdbc6.jar (11g driver).
Anyone can help me how can I configure my application for I must not to restart the tomcats??
Thanks you very much!!.

The best solution for your problem is ORACLE SUPPORT.. Please raise an SR and coordinate with them.. GoodLuck!

Multipool with weblogic 8.1 sp3 and Oracle RAC

Similar Messages

Maybe you are looking for