JTA with WLS 8.1 sp5 and Oracle 10.1.0.4
Hi,
I am testing a global transaction involving two EJBs (stateless session beans) running on two separate WebLogic servers. Each ejb calls an Oracle stored procedure against a different datbase. One ejb is deployed on one server the other one on the second server.
I want to know if it is mandatory to set up a trust relationship between the two servers. The reason I ask is that it seems the transaction is working without it (with the SecurityIdentity automatically downgraded to 'anonymous').
However it only seems to consistently work between certain servers and randomly failing when using a different pair of servers.
Thanks
Cristian
Cristian Mihaila wrote:
> Hi Joe,
>
> Here is the stack trace :
Ok, you should make sure you're using consistent SecurityInteropMode settings
on the different servers. Trust is only needed if the servers are on different
domains otherwise trust is not needed. We made many changes to correct a downgrade
issue on different subsystems JTA, JMS, EJB in 81sp6. There is a patch
available for 81sp5 for this.
Please read: http://e-docs.bea.com/wls/docs81/ConsoleHelp/jta.html#1120356
Joe
>
> <Feb 20, 2007 11:53:54 AM EST> <Error> <EJB> <BEA-010026> <Exception occurred during commit of transaction Name=[EJB com.loyalty.arrow.services.epin.ejb.EPinFacadeSession.authenticate(java.lang.String,java.lang.String,java.lang.String,java.lang.String)],Xid=BEA1-02DD480140BE7F28EDB9(12622847),Status
> =Rolling Back. [Reason=weblogic.transaction.internal.TimedOutException: Transaction timed out after 29 seconds
> BEA1-02DD480140BE7F28EDB9],numRepliesOwedMe=0,numRepliesOwedOthers=0,seconds since begin=89,seconds left=10,XAServerResourceInfo[OmdbXMultiPool]=(ServerResourceInfo[OmdbXMultiPool]=(state=new,assigned=pinpp2),xar=null,re-Registered = false),SCInfo[pinpp+pinpp2]=(state=rolling-back),SCInfo[mydomain+m
> yserver]=(state=rolledback),properties=({weblogic.transaction.name=[EJB com.loyalty.arrow.services.epin.ejb.EPinFacadeSession.authenticate(java.lang.String,java.lang.String,java.lang.String,java.lang.String)]}),OwnerTransactionManager=ServerTM[ServerCoordinatorDescriptor=(CoordinatorURL=myserver+159
> .175.18.251:7001+mydomain+t3+, XAResources={JMS_FileStore, shadbConnectionPool, arrow1lclprdPool},NonXAResources={})],CoordinatorURL=myserver+159.175.18.251:7001+mydomain+t3+): weblogic.transaction.internal.TimedOutException: Transaction timed out after 29 seconds
> BEA1-02DD480140BE7F28EDB9
> at weblogic.transaction.internal.ServerTransactionImpl.wakeUp(ServerTransactionImpl.java:1600)
> at weblogic.transaction.internal.ServerTransactionManagerImpl.processTimedOutTransactions(ServerTransactionManagerImpl.java:1147)
> at weblogic.transaction.internal.TransactionManagerImpl.wakeUp(TransactionManagerImpl.java:1882)
> at weblogic.transaction.internal.ServerTransactionManagerImpl.wakeUp(ServerTransactionManagerImpl.java:1064)
> at weblogic.transaction.internal.WLSTimer.trigger(WLSTimer.java:31)
> at weblogic.time.common.internal.ScheduledTrigger.run(ScheduledTrigger.java:243)
> at weblogic.security.acl.internal.AuthenticatedSubject.doAs(AuthenticatedSubject.java:321)
> at weblogic.security.service.SecurityManager.runAs(SecurityManager.java:121)
> at weblogic.time.common.internal.ScheduledTrigger.executeLocally(ScheduledTrigger.java:229)
> at weblogic.time.common.internal.ScheduledTrigger.execute(ScheduledTrigger.java:223)
> at weblogic.kernel.ExecuteThread.execute(ExecuteThread.java:224)
> at weblogic.kernel.ExecuteThread.run(ExecuteThread.java:183)
> --------------- nested within: ------------------
> weblogic.transaction.RollbackException: Transaction timed out after 29 seconds
> BEA1-02DD480140BE7F28EDB9 - with nested exception:
> [weblogic.transaction.internal.TimedOutException: Transaction timed out after 29 seconds
> BEA1-02DD480140BE7F28EDB9]
> at weblogic.transaction.internal.TransactionImpl.throwRollbackException(TransactionImpl.java:1684)
> at weblogic.transaction.internal.ServerTransactionImpl.internalCommit(ServerTransactionImpl.java:311)
> at weblogic.transaction.internal.ServerTransactionImpl.commit(ServerTransactionImpl.java:228)
> at weblogic.ejb20.internal.BaseEJBObject.postInvoke(BaseEJBObject.java:320)
> at weblogic.ejb20.internal.StatelessEJBObject.postInvoke(StatelessEJBObject.java:168)
> at com.loyalty.arrow.services.epin.ejb.EPinFacade_y6z7xe_EOImpl.authenticate(EPinFacade_y6z7xe_EOImpl.java:110)
> at com.loyalty.arrow.services.epin.ejb.EPinFacade_y6z7xe_EOImpl_WLSkel.invoke(Unknown Source)
> at weblogic.rmi.internal.BasicServerRef.invoke(BasicServerRef.java:492)
> at weblogic.rmi.cluster.ReplicaAwareServerRef.invoke(ReplicaAwareServerRef.java:108)
> at weblogic.rmi.internal.BasicServerRef$1.run(BasicServerRef.java:435)
> at weblogic.security.acl.internal.AuthenticatedSubject.doAs(AuthenticatedSubject.java:363)
> at weblogic.security.service.SecurityManager.runAs(SecurityManager.java:147)
> at weblogic.rmi.internal.BasicServerRef.handleRequest(BasicServerRef.java:430)
> at weblogic.rmi.internal.BasicExecuteRequest.execute(BasicExecuteRequest.java:35)
> at weblogic.kernel.ExecuteThread.execute(ExecuteThread.java:224)
> at weblogic.kernel.ExecuteThread.run(ExecuteThread.java:183)
>
> Thanks
> Cristian
Similar Messages
-
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. -
Oracle XA driver problem with WLS 7.0.1.0, Oracle 9.0.1
We are using simplified chinese, after swith to bea jdriver, it messed up
all the encoding. So we cannot display Chinese character correctly.
We are using WLS 7.0.1.0, Oracle 9.0.1 on both Windows and Solaris 8
environment, BEA supplied JDK 1.3.1_03.
We have many diffrent problems with oracle drivers:
1. We want to use XA driver to support distributed transaction, However:
* bea jdriver xa messes up with encoding
* when using oracle 901 driver, everything works fince except webservices.
Workshop application access the ejb, then the workshp application sets
isolation level, but oracle driver does not support it and gives error. Is
there a way to turn off isolation level in workshop? I tried manually edit
weblogic-ejb-jar.xml, however,workshop cannot redeploy it after that.
2. When not using XA, oracle thin driver works fine. But we lost XA
capability.
Any work around?I did try to change the value in this config file as well, but did not help.
In fact, the installation default setting is with
'<transaction-isolation-level>' commented out.
And when I use bea oracle jdriver, it somehow messed up with database
character set encoding, so our Chinese characters could not be retrieved
correctly. And I try to set the encoding of jdriver to 'GBK', it did not
work.
"Anurag Pareek" <[email protected]> дÈëÏûÏ¢ÐÂÎÅ
:[email protected]..
Hello Ma,
The transaction isolation level value for EJBs backing the JWS files is
specified in the <transaction-isolation-level> tag in the
WEB-INF/weblogic-jws-config.xml file of a Workshop project. You can
manipulate this value to serve your purpose.
Please do let me know how it goes.
Regards,
Anurag
Workshop Support
"Ma Jie" <[email protected]> wrote in message
news:[email protected]..
We are using simplified chinese, after swith to bea jdriver, it messed
up
all the encoding. So we cannot display Chinese character correctly.
We are using WLS 7.0.1.0, Oracle 9.0.1 on both Windows and Solaris 8
environment, BEA supplied JDK 1.3.1_03.
We have many diffrent problems with oracle drivers:
1. We want to use XA driver to support distributed transaction, However:
* bea jdriver xa messes up with encoding
* when using oracle 901 driver, everything works fince exceptwebservices.
Workshop application access the ejb, then the workshp application sets
isolation level, but oracle driver does not support it and gives error.Is
there a way to turn off isolation level in workshop? I tried manuallyedit
weblogic-ejb-jar.xml, however,workshop cannot redeploy it after that.
2. When not using XA, oracle thin driver works fine. But we lost XA
capability.
Any work around? -
Installation of webgate on Solaris (sparcv9) with WLS 10.3.5 and Apache2
Problem Description: We have installed IDM 11g and OAM 10.1.4.3 on RHEL5.5 hosts, respectively. We have successfully installed all the components:
Environment Details:
- Server1 -- 64 bit Intel RHEL5
Fusion Middleware Identity Management - 11.1.1.2
WLS 10.3.2
ODSM,OID,OVD
DB 10.2.0.4
- Server 2 32-bit Intel RHEL5
OAM 10.1.4.3
OHS 11.1.1.2
After successfully installing these hosts, we needed to create a webhost from where we could test our protected resources. This host would have a sparc v9 OS, include WLS 10.3.5, and use apache2 as its web server. These have all been successfully installed by root and are running.
Our next step was to create the webgate/access gate on the OAM host and setup the necessary policy. This was successful.
We then copied Oracle_Access_Manager10_1_4_3_0_sparc-s2_APACHE2_WebGate to the host and started the installation. Since the host is headless (just a host -- no keyboard, mouse, or gui attached to it) we have to ssh to the host and execute all the installs from the command line without gui. When we got to entering the webgate id and hit return... the process just ended without any error or logfiles. We are assuming that at that point the webgate software was installed but not configured.
We went ahead and tried the configureWebGate script:
./start_configureWebGate -i /opt/oracle/middleware/webgate -l WebGate
ld.so.1: configureWebGate: fatal: /opt/oracle/middleware/webgate/access/oblix/tools/configureWebGate/../../../oblix/lib/libstdc++.so.5: wrong ELF data format: ELFDATA2LSB
Killed
We have successfully installed OAM and IDM many times and have installed webhosts as well... but the webhosts have always been RHEL5 with WLS and OHS instead of Sparc, wls, and apache. Is there anything special about a sparc or apache install?
WLS and apache were installed as root... we have tried installing the webgate as root, oracle, even apache... but get the same results. The gcc libs are downloaded and available, but the error we see during configuration seems to indicate that they are not found. We have tried seting the LD_LIBRARY_PATH to include the directory containing the libs.
Edited by: OldGuy on Jul 7, 2011 4:04 AMOn another note... is there a Sparc equivalent for the mod_wl_ohs.conf where we would place
<Location /<deployed app>>
SetHandler weblogic-handler
WebLogicHost <weblogichost>
WebLogicPort 7001
</Location>
It appears that this goes into the apache httpd.conf file, correct? Or does the mod_wl_ohs.conf equivalent exist?
We have just about completed everything in regard to being able to include a solaris host in our list of hosts that are tied to OAM. The webgate was created and software installed, the deployed app protected, etc... Everything that we have done for Linux and XP in the past we have done for this Sparc host.
When we try to access the Sparc's protected uri... nothing happens. The browser stays blank... the url does not change to display the oamsso login.html (as the other installs do)... nothing is returned... no error, no remarks, no logfile entries... just a blank browser. -
WLS V6.1 SP6 and Oracle 10
Does anyone know if WebLogic Server V6.1 Service Pack 6 can run ok with Oracle 10G using oracles thin driver?
Regards,
Terje SchjonnebergWe are having no problems using WLS 6.1 SP7 and 10G on Solaris.
-
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 SadriaThx 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 -
Compatibility error with WLS 10.3.5 and OSB 11.1.1.4.0
As per out project requirement I am using WLS 10.3.5, OSB 11.1.1.4.0, and OEPE 11.1.1.6.1, but this oepe does not support these two WLS and OSB.
when I am trying to create a new Oracle Service Bus Configuration Project, i am getting a error:
Plug-in "com.bea.alsb.ui" was unable to instantiate class "com.bea.alsb.ui.wizards.NewALSBContainerWizard".
com/bea/alsb/core/containers/exceptions/ContainerException
Can anyone please suggest the correct version of OEPE if any.
Thanks in advance,
JaiThanks Rene, but as I said we are not using the same version of WLS and OSB so in that case is there any option that which version of OEPE i should download which support these two versions of WLS 10.3.5 and OSB 11.1.1.4.0.
-
Accesing protectred URIs on Solaris (sparcv9) with WLS 10.3.5 and Apache2
I had started to ask questions about this on another thread of mine, but since I had listed that one as answered and this being different from the original question on that thread...I felt it better to create its own thread.
Problem Description: Environment Details:
- Server1 -- 64 bit Intel RHEL5
Fusion Middleware Identity Management - 11.1.1.2
WLS 10.3.2
ODSM,OID,OVD
DB 10.2.0.4
- Server 2 32-bit Intel RHEL5
OAM 10.1.4.3
OHS 11.1.1.2
- Server 3 64-bit SparcV9 Webhost -- deployed app as protected uri
WLS 10.3.5
Apache2
Webgate 10.1.4.3
We believe we have completed everything in regard to being able to include a solaris host in our list of hosts that are tied to OAM. We have installed webhost with XP and RHEL5.6 successfully using OHS 11.1.1.2. This is the first time creating a webhost on Sparc. The webgate was created and software installed, the deployed app protected, etc... Everything that we have done for Linux and XP in the past we have done for this Sparc host. The only differences are the SUN OS, Apache2, and WLS 10.3.5. I believe those are all acceptable for these Oracle products and versions.
When we try to access the Sparc's protected uri... nothing happens. The browser stays blank... the url does not change to display the oamsso login.html (as the other installs do)... nothing is returned... no error, no remarks, ... just a blank browser.
Doing an apachectl -l I receive the following:
Compiled in modules:
core.c
prefork.c
http_core.c
mod_so.c
So mod_so.c is included.
If I go directly to the protected uri through 7001 instead of the 8890 -- the port httpd.conf has configured to listen on -- the page displays. If I open the oamsso/login.html using 8890... it displays. But if I use 8890 to bring up the protected uri... as described above nothing displays.
One other thing, since the Sparc host is "headless" -- as described by our SysAdmin... no access directly through the sun console and no gui access via the sun host since there is no sun console just the server -- we have to access the gui via a browser on the same network. The browser is actually on the OAM host.
From apache2 error_log on SUN host:
15-7-2011 14:35:51Sending message: 0 13
protocol=NAP version=3 oldest=1
15-7-2011 14:35:51Received message: 0 13
protocol=NAP version=3 oldest=1
15-7-2011 14:35:51Sending NMP STS negotiation message: 0 0
sts=open
15-7-2011 14:35:51Received NMP STS negotiation message: 0 0
sts=open
15-7-2011 14:35:51Sending message: 0 14
cm=mtisunfireHost_AG challenge=b516f1a00c2a95ee
15-7-2011 14:35:51Received message: 0 14
cm=access_svrid1 challenge=95520d6315ad3865 st=ma%3d25 rt=1
15-7-2011 14:35:51Sending message: 0 15
response=531be0a851cb2773c90aa0c91d9f779c
15-7-2011 14:35:51Received message: 0 15
response=2b62c22a9458e962c35d8d7d358f4fc1 st=ma%3d25 rt=1
15-7-2011 14:35:51Sending message: 0 8
cm=mtisunfireHost_AG ct=0 version=3
15-7-2011 14:35:51Received message: 0 8
ci=id%3dmtisunfireHost_AG%20maxConnections%3d1%20debug%3d0%20maxSessionTime%3d24%20sleepFor%3d60%20security%3dopen%20failoverThreshold%3d1%20aaaTimeoutThreshold%3d%20cookieSessionTime%3d3600%20maxCacheElems%3d100000%20cacheTimeout%3d1800%20configLastUpdateTime%3d1310754351%20preferredHost%3dmtisunfire:8890%20state%3dEnabled%20primaryCookieDomain%3d%20idleSessionTimeout%3d3600%20accessClientPasswd%3d02434564584046435641510409%20primaryServer1%3dhost%253dirsam-oam.dchc.smil.mil%2520port%253d8887%2520numOfConnections%253d1%20denyOnNotProtected%3d0%20cachePragmaHeader%3dno-cache%20cacheControlHeader%3dno-cache%20ipValidation%3d1 st=ma%3d25%20mi%3d2%20sg%3d32%20sm%3d rt=1
[Fri Jul 15 14:35:52 2011] [notice] child pid 18581 exit signal Segmentation fault (11)
[Fri Jul 15 14:35:58 2011] [notice] child pid 18582 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:01 2011] [notice] child pid 18583 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:04 2011] [notice] child pid 18585 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:07 2011] [notice] child pid 18586 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:11 2011] [notice] child pid 18590 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:12 2011] [notice] child pid 18591 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:14 2011] [notice] child pid 18592 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:15 2011] [notice] child pid 18593 exit signal Segmentation fault (11)
[Fri Jul 15 14:36:16 2011] [notice] child pid 18594 exit signal Segmentation fault (11)
[Fri Jul 15 14:38:35 2011] [notice] child pid 18595 exit signal Segmentation fault (11)
[Fri Jul 15 14:38:38 2011] [notice] child pid 18596 exit signal Segmentation fault (11)
I believe that apache is currently setup correctly at this point, but cannot understand what we are missing.I would say that OAM does support Apache (according to the certified Apache versions and OS's). However, there are so many distributions out there and it can be configured with countless options, be compiled with a number of different compilers, and include any number of modules that some compatibility issues are bound to arise. The Solaris distribution - also Oracle - is a case in point. I have also encountered issues with the Apache version bundled with some Linux versions (for different reasons than the Solaris bundle) for which the easiest solution has also been to download and build from source. I would imagine that is the reason for what you were told about support for generic Apache, though of course I do not know the context.
Regards,
Colin -
UOO sequencing along with WLS high availability cluster and fault tolerance
Hi WebLogic gurus.
My customer is currently using the following Oracle products to integrate Siebel Order Mgmt to Oracle BRM:
* WebLogic Server 10.3.1
* Oracle OSB 11g
They use path service feature of a WebLogic clustered environment.
They have configured EAI to use the UOO(Unit Of Order) Weblogic 10.3.1 feature to preserve the natural order of subsequent modifications on the same entity.
They are going to apply UOO to a distributed queue for high availability.
They have the following questions:
1) When during the processing of messages having the same UOO, the end point becomes unavailable, and another node is available in order to migrate, there is a chance the UOO messages exist in the failed endpoint.
2) During the migration of the initial endpoint, are these messages persisted?
By persisted we mean that when other messages arrive with the same UOO in the migrated endpoint this migrated resource contains also the messages that existed before the migration?
3) During the migration of endpoints is the client receiving error messages or not?
I've found an entry on the WLS cluster documentation regarding fault tolerance of such solution.
Special Considerations For Targeting a Path Service
When the path service for a cluster is targeted to a migratable target, as a best practice, the path
service and its custom store should be the only users of that migratable target.
When a path service is targeted to a migratable target its provides enhanced storage of message
unit-of-order (UOO) information for JMS distributed destinations, since the UOO information
will be based on the entire migratable target instead of being based only on the server instance
hosting the distributed destinations member.
Do you have any feedback to that?
My customer is worry about loosing UOO sequencing during migration of endpoints !!
best regards & thanks,
MarcoFirst, if using a distributed queue the Forward Delay attribute controls the number of seconds WebLogic JMS will wait before trying to forward the messages. By default, the value is set to −1, which means that forwarding is disabled. Setting a Forward Delay is incompatible with strictly ordered message processing, including the Unit-of-Order feature.
When using unit-of-order with distributed destinations, you should always send the messages to the distributed destination rather than to one of its members. If you are not careful, sending messages directly to a member destination may result in messages for the same unit-of-order going to more than one member destination and cause you to lose your message ordering.
When unit-of-order messages are processed, they will be processed in strict order. While the current unit-of-order message is being processed by a message consumer, the next message in the unit-of-order will not be delivered unless it is to the same transaction or session. If no message associated with a particular unit-of-order is processing, then a message associated with that unit-of-order may go to any session that’s consuming from the message’s destination. This guarantees that all messages will be processed one at a time and in order, and any rollback or recover will not prevent ordered processing of the messages.
The path service uses a persistent store to save the state of which member destination a particular unit-of-order is currently using. When a Path Service receives the first message for a particular unit-of-order bound for a distributed destination, it uses the normal JMS load balancing heuristics to select which member destination will handle the unit and writes that information into its persistent store. The Path Service ensures that a new UOO, or an old UOO that has no messages currently on any destination, can be enqueued anywhere in the cluster. Adding and removing member destinations will not disrupt any existing unit-of-order because the routing decision is made dynamically and those decisions are persistent.
If the Path Service is unavailable, any requests to create new units-of-order will throw the JMSOrderException until the Path Service is available. Information about existing units-of-order are cached in the connection factory and destination servers so the Path Service availability typically will not prevent existing unit-of-order messages from being sent or processed.
Hope this helps. -
Oracle JAAS with roles from database tables and Oracle SSO integration
I have the following requirement for user authentication and authorization. The applications are build using ADF Faces and BC4J. User authentication should be done using Oracle SSO. User roles and functions will be stored in custom tables. These roles will be used on ADF application pages to restrict access to the UI components on a page. Example: User will "Employee" role cannot create a new employee; however, user with "HR" role can create a new employee.
In this case, "Create" button will be visible on the ADF page.
1. How can we use Oracle JAAS to use custom tables for roles instead of using flat XML files?
2. How does ADF applications use these roles to restrict components on a page?
3. For authentication, I guess we should be able to use SSO and integrate with Oracle JAAS?
Thanks.Hi,
I can give you the answers to 1 and 2 but haven't tried 3.
1) Oracle OC4J since 10.1.3.1 has a database LoginModule that is explained in the OC4J security guide.
I have a how-to document in review that will be published probaby next week and that explains how to set this LogiNModule up for JDeveloper and stand alone OC4J, though the OC4J documentation is pretty good as well
http://download-west.oracle.com/docs/cd/B32110_01/web.1013/b28957/loginmod.htm#BABCDDAI
2) Create a managed bean with boolan methods like isUserManager, isUserEmployee, isUserTechnician etc. In this methods check for the security role on teh request object's isUserInRole() method. Then access this methods from the disabled or rendered property using ExpressionLanguage
A custom Login ModuleDoesn't use Oracle JAAS but plugs into it. So I am not sure if SSO would work with this because the custom LoginModule wouldn't get a username password pair but only a username that it has to trust.
Frank -
Problems with WLS 4.5.1 and F5 Big IP HA+ Switch
Hello. We're having problems with our F5 Big IP HA+ switch and pool of WLS
4.5.1 servers (two in the pool currently). At seemly random intervals the
Big IP believes the one or both of the servers are not responding, so they
are removed from the pool. We have a growing body of anecdotal evidence to
suggest that the servers are actually on-line and available during the
event. Either the switch is confused or the WLS servers aren't always
responding correctly to the HTTP requests sent by the switch for polling.
We're having problems catching the problem with the right diagnostics.
Has anyone out there observed similar behavior with these components?
Thanks.
- Sean McRae
Sort of,
I use iplanet between the 2, so I havent had this problem, but I have had
several problems with clustering, here is what I recomend doing:
write a simple java program (or whatever your prefered language) to do a HTTP
ping on your distinct weblogic servers every X seconds/minutes where X is less
than Big IPs death tolerance. Time how long/or if ever each of your pings take.
turn on verbose gc.
My guess is its one of 3 things:
1.) your have a big gc going on and your server isnt responding quick enough
and big ip is marking it dead
2.) you have thread contention that is causing your server not to respond quick
enough
3.) your network has some issues and the packets arent making it there, or not
quick enough.
the ping program will prove/disprove #2 and lead you to or away from 3. Verbose
gc will prove/disprove #1.
hope this helps
-Joel
Sean wrote:
> Hello. We're having problems with our F5 Big IP HA+ switch and pool of WLS
> 4.5.1 servers (two in the pool currently). At seemly random intervals the
> Big IP believes the one or both of the servers are not responding, so they
> are removed from the pool. We have a growing body of anecdotal evidence to
> suggest that the servers are actually on-line and available during the
> event. Either the switch is confused or the WLS servers aren't always
> responding correctly to the HTTP requests sent by the switch for polling.
> We're having problems catching the problem with the right diagnostics.
>
> Has anyone out there observed similar behavior with these components?
>
> Thanks.
>
> - Sean McRae
-
Problem with Date - Text File Source and Oracle Target
Hi All,
I have a source data (text file) with date column in the format of 'MM/DD/YYYY'. My target is oracle. I am using the LKM FILE TO SQL and IKM SQL Control Append. When i execute this interface, i am getting an error as
7000 : null : com.sunopsis.jdbc.driver.file.b.i
com.sunopsis.jdbc.driver.file.b.i
at com.sunopsis.jdbc.driver.file.b.f.getColumnClassName(f.java)
at the Load Data step.
How to load date columns from text file to oracle tables? Please help me in resolving this...
Thanks in Advance,
Ram Mohan TThe worst solution is to define for your text file the date as a string and then to rebuild your date type in Oracle.
something like
convert(Substr(myfield,4,2)||Substr(myfield,1,2)||Substr(myfield,7,4) ,'MMDDYYYY')
this is maybe the worst solution but it should work.
Regards
Brice -
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 -
Is ojdbc14.jar the correct driver to use with Java 1.6.0 and Oracle 10?
I have a customer using Oracle 10.2.0.3 and a JVM of 1.6.0. They are using ojdbc14.jar as their JDBC driver. I am confused because while ojdbc14.jar is listed as the driver for Oracle 10.2.0.3, it is not listed as compatible with JDK1.6.
the 14 part means it is for Java 1.4. You should use a driver from either the ODJBC5 (Java 5) or OJDBC6 range (Java 6). All drivers are backwards compatible, so you can use the latest drivers to connect with older Oracle releases. Just don't assume that the latest one is the best one, check Google for specific problems before using a specific driver release.
-
Boolean types with entity framework code first and oracle provider
Working in a application that has to work in oracle and sqlServer. In SqlServer we have used "Bit" to store booleans and in oracle number(1).
Have check other threads in this forum, but didnt find any that fix my problem, sorry if this may have been discused before.
We have created a code first model were we find few bool properties mapped to database fields.
for example:
public partial class ZPruebaBooleano
public int Numero { get; set; }
public bool Booleano { get; set; }
Mapped as:
this.ToTable("ZPRUEBABOOLEANO", schema);
this.HasKey<int>(t => t.Numero);
this.Property(t => t.Numero).HasColumnName("NUMERO");
this.Property(t => t.Booleano).HasColumnName("BOOLEANO");
Also, sw added to the application configuration file (for simplicity we have test it without the use of any additional dll):
<oracle.dataaccess.client>
<settings>
<add name="bool" value="edmmapping number(1,0)" />
<add name="byte" value="edmmapping number(3,0)" />
<add name="int16" value="edmmapping number(4,0)" />
<add name="int32" value="edmmapping number(9,0)" />
<add name="int64" value="edmmapping number(18,0)" />
</settings>
</oracle.dataaccess.client>
I am confident that the provider factory read it when creating the model, because it provokes an exception if i add an invalid entry in any of the type names mapped in the file.
As i have find in other forums, this should work. But now i am not sure if should work always, including code first.
I have this exception when i excecute the code (translated from spanish, sorry for any mistake):
Type 'Edm.Boolean[Nullable=False,DefaultValue=]' from 'Booleano' to type'PruebaBooleanos.ZPruebaBooleano' is not compatyble with 'OracleEFProvider.number[Nullable=False,DefaultValue=,Precision=38,Scale=0]'
Its funy that says Precision=38. The database is Number(1), i am sure about that, in fact this is the script:
CREATE TABLE ZPRUEBABOOLEANO
NUMERO NUMBER(15),
BOOLEANO NUMBER(1)
Also, i find it interesting that i was having this mistake even when i was not informing the table i was maping, like if the oracle provider didnt even check if the column was number(anything). Right now is well maped, table and schema.
I have test to create an integer property wrapped by the boolean one, as we can see in this code.
namespace PruebaBooleanos
public partial class ZPruebaBooleano
public int Numero { get; set; }
public bool Booleano
get
return iBooleano == 1 ? true : false;
set
iBooleano = value ? 1 : 0;
public int iBooleano { get; set; }
in this last case i ignored the boolean and mapped the integer.
That worked ok in oracle. But added 2 problems:
1. It fails in SqlServer, because in sql server is bit
2. Cant query the entity model using the boolean property as it is not maped to Database.
I could change the bit field in SqlServer to Number.
But i would like to keep bit in sqlserver and number(1) in oracle.
Anyone had a similar problem?
I am open to any ideas, thanks !!!
liboIt's cool. :)
Sure. I can upload an EDMX file that works against my database if you want to look at it. The relevant parts are probably much like you'd expect. I've removed some columns from this version to make it easier to read.
From the SSDL:
<EntityType Name="PARAMETER">
<Key>
<PropertyRef Name="PARAMETER_CD" />
</Key>
<Property Name="PARAMETER_CD" Type="number" Nullable="false" Precision="4" />
<Property Name="PARAMETER_ACTIVE_INDR" Type="number" Nullable="false" Precision="1" />
</EntityType>From the CSDL:
<EntityType Name="PARAMETER">
<Key>
<PropertyRef Name="PARAMETER_CD" />
</Key>
<Property Type="Int16" Name="PARAMETER_CD" Nullable="false" />
<Property Type="Boolean" Name="PARAMETER_ACTIVE_INDR" Nullable="false" />
</EntityType>From the C-S mapping:
<EntitySetMapping Name="PARAMETER">
<EntityTypeMapping TypeName="Model.PARAMETER">
<MappingFragment StoreEntitySet="PARAMETER">
<ScalarProperty Name="PARAMETER_ACTIVE_INDR" ColumnName="PARAMETER_ACTIVE_INDR" />
<ScalarProperty Name="PARAMETER_CD" ColumnName="PARAMETER_CD" />
</MappingFragment>
</EntityTypeMapping>
</EntitySetMapping>Also worth noting that the EDMX mapper probably won't set the provider and token correctly:
<Schema Namespace="Model.Store" Alias="Self" Provider="Oracle.DataAccess.Client" ProviderManifestToken="11.2" xmlns:store="http://schemas.microsoft.com/ado/2007/12/edm/EntityStoreSchemaGenerator" xmlns="http://schemas.microsoft.com/ado/2009/02/edm/ssdl">Full version is available at http://www.hiredgoons.ca/DataImport.edmx . This is an early development one so I make no apologies for not renaming columns to something readable. ;) It does work correctly as I've had it in testing (taking data from a 170MB excel file and putting it into Oracle using the model). It was created using DB First.
When you have it load at runtime, you need the application configuration settings to map bool to number(1). If that's in app.config or web.config it'll pick it up. Probably worth noting that if you don't have the configuration setting and you load this, the model doesn't validate correctly. As soon as you try to create a DbContext from it, you get an immediate exception that number(1) doesn't map to boolean.
Edited by: Tridus on Nov 21, 2012 3:37 PM
Maybe you are looking for
-
Editable DataGrid With DateField
I'm new to flex and struggling with the editable DataGrid. I have a DataGrid with an ItemRenderer that outputs a DateField. I can't figure out how to get the new value of the DateField after the edit. Here is my DataGrid (the endDate column): <mx:Dat
-
What is the code at the top of new pages?
DW inserts this code at the top of new pages: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> Any reason to have it? Most of my inne
-
Dear Guru's Our customer is looking for a solution for travel expenses based on the express expense sheet. However they want to skip the first screen where trip specifications are described and go directly towards the expense screen. SAP technicaly a
-
Add valuation type in access sequence
Hi, i like to add valuation type in access sequence JST1 which is belongs to access sequence for taxinn, i want material/plant/vendor/valuation type cominiation table plese help me is there any othe way to add field in field catalogue of taxinn, is
-
Premiere El. 11 crashes
I am running into the same issue with Premiere El. 11 as I did with imovie. Every time I am editing a video the program crashes. Always near the end of the session for maximum frustration. Can I please get a little help?