TopLink 3.6.3 and Oracle hints.

Hi.
I'm wondering if is it possible to alter a TopLink expression build with the ExpressionBuilder API in order to insert an Oracle hint on it (eg: /*+RULE*/) I have done it in some of my "static" sentences as they are pure SQL but I can't find a way to do it in a dynamic query.
Sorry if this is a common issue and it has already been answered but I've searched the forums with no luck.
Thanks in advance.
Ignacio.

This pointer (though old) was quite useful. Thanks to Doug.
We have an issue though. We are using Toplink Cursored Stream for retrieving the results from our queries.
query.useCursoredStream();
When we set a hint (query.setHintString("/*+ FIRST_ROWS */");) we see a vast improvement in the query that is fired by Toplink (wherein the hint is included):
CursoredStream cursor = (CursoredStream) serverSession.executeQuery(query, parameters);
And the problem we have is that when we need to retrieve the size of the cursor (size = cursor.size();), it fires a "select count(*) from ...." query where the hint is not applied and the resulting performance is bad.
Can someone suggest what we else we need to do to suggest hints to the "select count(*)" query that Toplink fires for getting cursor stream size. Using a scrollable cursor is not an option since it is not efficient enough for our requirements.
Thanks in advance
Message was edited by:
potu_s

Similar Messages

Using Clob with TopLink 9.0.4.5 and Oracle 10g RAC

I am trying to store an XML file in a Clob type field of a DB table using TopLink 9.0.4.5 and Oracle 10g RAC and need some guidance about how to do it. I got some directions to start it with the Tip "How-To: Map Large Objects (LOBs) to Oracle Databases with OracleAS TopLink" but still need some more helps.
When using the Oracle JDBC OCI driver, the tip gives the code block for a Clob field:
DirectToField scriptMapping = new DirectToField();
scriptMapping.setAttributeName("script");
scriptMapping.setFieldName("IMAGE.SCRIPT");
descriptor.addMapping(scriptMapping);
As I understand, TopLink creates instances of the Descriptor class at run time for each of the descriptor files and stores them in a database session, where is the proper place (in SessionEvent of TopLinkSessionEventHandler?) for me to get a reference to such an instance of my Descriptor class in Java code so that I can add the above mentioned additional Mapping? Are the above String values of "script" and "IMAGE.SCRIPT" predefined in TopLink API? Can I accomplish the same thing just using the TopLink Workbench tool instead? If yes, please advise the detailed steps to do so.
The tip also states to call the following code in case of using Clob:
DatabaseLogin login = session.getLogin();
login.useStringBinding();
Should the above 2 lines of code be called after the following lines of code?
SessionManager sessionManager = SessionManager.getManager();
Server serverSession = (Server)sessionManager.getSession("MY_SESSION_NAME");
Besides the above extra coding for the Session and Descriptor Mapping, is there any special handling in between Data model and DB table mapping? Can I map a Java String type to a DB Clob field using the Direct-to-field mapping?
Appreciate any help.

Never mind ....... I had already figured it out .....

Sequence caching with toplink and oracle caching

Hi,
In my application, I use toplink as a JPA provider. For performance reasons, I defined an allocationSize on sequence generator for some persistence objects. I read some documentation to understand how it works, the result of my research is that the allocationSize of sequence generator must match with the increment value of the sequence in database.
So if I want to cache 1000 of values, I must define on my sequence generator allocationSize of 1000 and create a sequence like this : create sequence myseq increment by 1000. Am I right ?
Second question, what if my sequence define a cache in the database. For example, create sequence myseq increment by 1000 cache 20.
Does it mean that 20 values will be cached or 1000*20 values will be cached ? Is the cache size defined per session or for all the sessions of the database ?
Thanks.
Will.

Thank you for your response.
I used the default parameter of toplink (increment by 50) and I left a cache size of 20 on database side.
But I noticed that whenever the server restarts, I "lost" between 900 and 1000 ids (nearly 20*50). So even if sequence cache on oracle size is non transactional, I think there is a kind of prefetch somewhere on the server side. I must not lost more than 50 ids when a server restarts.
If I remove the cache on database side, then the behavior is correct (the expected one to be more precise).
Is there any kind of sequence caching in oracle jdbc drivers ?
Thanks.
Will.

Regarding ORACLE HINTS and PARLLELISM

Hi,
Basically i am in ETL tester..Most of clients are asking about experience in ORACLE HINTS and PARALLELISM...Do any one please give basic idea what are those..why are those useful....and if you have any good site with examples with easy understanding...please send it...

Is there any link which is easy to understand...when i see above links i assume i need to know some thing before learning these things....is there any thing i need to learn before learning oracle hints directly

Oracle Hint on Table MKPF and MSEG : force index MSEG~M to be utilize

Hi Experts, I'm quite new to ABAP performance tuning, I try to put details as much as I can in my question below, just to have a quick overview of my problem below, I want to use/force in my SQL below to force the utilization of index MSEG~M.
added an Oracle Hint forcing index MSEG~M
SELECT MATNR BWART MENGE
FROM   MKPF
INNER JOIN MSEG
     ON MKPFMANDT EQ MSEGMANDT
    AND MKPFMBLNR EQ MSEGMBLNR
    AND MKPFMJAHR EQ MSEGMJAHR
   INTO CORRESPONDING FIELDS OF TABLE T_MSEG2
WHERE MKPF~BUDAT IN S_GSTRP    "(index bud should be used)
   AND MSEG~MJAHR IN R_DOCYEAR
   AND BWART IN ('931', '932',
                  '901', '902',
                  '701', '702',
                  '703', '704',
                  '707', '708',
                  '711', '712',
                  '713', '714',
                  '715', '716',
                  '717', '718',
                  '551', '552',
                  '553', '554',
                  '555', '556') "ZZCHK: Constants Not Applicable
         AND MATNR IN R_MATNR3
         AND MATNR IN R_COMPNTS
         AND WERKS EQ P_WERKS
%_hints oracle u2018INDEX(u201CMKPFu201D u201CMSEG~Mu201D)u2019.
Note: I'm assuming that you'll take not some comments on further enhancement:
- " INTO CORRESPONDING FIELDS "
- use of field symbols
- I didn't modify it yet since my focus if for MSEG~M
- cannot make material number as mandatory field
Objective: Force to use index MSEG~M
Problem:
After adding the Oracle Hint, I did the analysis in ST05 and it seems like index M is still not being forcefully
utilize instead MSEG~0 is being used.
I replaced the Oracle Hint with:
%_hints oracle u2018INDEX(u201CT_01u201D u201CMSEG~Mu201D)u2019.
In ST05, I can get see that index MSEG~M is now being utilize BUT worst thing happened after applying this, the program timed out.
I already take a look on the following Notes: 129385, 130480, 772497, 162034, 818321 but nothing seems to be helpful in my problem.
Questions:
1. In syntax %_hints oracle u2018INDEX(u201CT_01u201D u201CMSEG~Mu201D)u2019. T_01 stands for MKPF right which is the first table, do you what's the reason for the program time out after adding this Oracle Hint? Is this the proper syntax?
2. How can I force in my code to use index MSEG~M without any program timeout?
For the whole source code of my question above, please see the link:
http://rapidshare.com/files/211740852/ZDXX0028.txt.html

Hi Thomas, thanks with the prompt reply (even if it's Saturday )
Yes, MKPF~BUD is being used.
The budat selection is narrowed to 28 days though users can input any date range, a warning message will just be displayed if budat selection exceeded.
Yes, optimizer usually chooses the right index; I'm not in as the same experience as you are though, but I find it interesting that after I added the Oracle hints (several combination) the performance of the program was optimize up to 40% to 50%.
I uploaded a detailed SQL trace and the ABAP change done in my program, if you'll notice in the summary of the changes, after adding some hints, the duration of the program was improved..
(SQL Trace Summary of my program) this worth taking a look
http://rapidshare.com/files/211870091/ZD28_SQL_Trace.zip.html
I made a custom index in MSEG, but unfortunately I doubt that it will be approve by our performance capacity team. But I somehow have a hunch that this will further optimize the program.
MSEG~Z03
MANDT     Client
WERKS     Plant
BWART     Movement Type (Inventory Management)
LGORT     Storage Location
What do you think Thomas and SAP experts?
**Sorry for pasting the whole ST05 result
     SELECT STATEMENT          ( Estimated Costs = 131.250 , Estimated #Rows = 450 )
                    6          FILTER
                    Filter Predicates
                    5          NESTED LOOPS
                    ( Estim. Costs = 131.249 , Estim. #Rows = 450 )
          Estim. CPU-Costs = 1.885.249.948 Estim. IO-Costs = 129.700
                    2          TABLE ACCESS BY INDEX ROWID          MKPF
                    ( Estim. Costs = 14.442 , Estim. #Rows = 288.570 )
               Estim. CPU-Costs = 206.401.140 Estim. IO-Costs = 14.272
               1          INDEX RANGE SCAN          MKPF~BUD
                    ( Estim. Costs = 655 , Estim. #Rows = 519.426 )
          Search Columns: 2
          Estim. CPU-Costs = 30.640.783 Estim. IO-Costs = 630
          Access Predicates          Filter Predicates
                    4          TABLE ACCESS BY INDEX ROWID          MSEG
                    Estim. CPU-Costs = 5.818 Estim. IO-Costs = 0
          Filter Predicates
          3          INDEX RANGE SCAN          MSEG~0
               Search Columns: 3
     Estim. CPU-Costs = 1.564 Estim. IO-Costs = 0
     Access Predicates          Filter Predicates

Limitation on SQL executing select statement from ADO and Oracle 8.1.7.1 OleDB Driver

Hi,
we are running a query with a big dunamic select statement from VB code using ADO command object. When Execute method is called system hangs and control won't return back to the application. it seems to be that there is some type limitation on Query string length. Please tell us if there is any?
we are running Oracle 8.1.7 Server on Windows 200 Server and connecting from a W2K professional, ADO 2.6 and Oracle OLEDB 8.1.7.1 OLEDB Driver.
Sample code:
Dim rs As ADODB.Recordset
Dim cmd As ADODB.Command
Set cmd = New Command
With cmd
.CommandText = ' some text with more than 2500 characters
.CommandType = adCmdText
Set rs = .Execute
End With
when i debug using VB6 and when .Execute line is called system hangs or return a message method <<somemethod> of <<some class name>> failed error.
Any help is appreciated.
Thanks,
Anil

A stored procedure would only slow you down here if it was poorly written. I suspect you want to use the translate function. I'm cutting & pasting examples from the documentation-- a search at tahiti.oracle.com will give you all the info you'll need.
Examples
The following statement translates a license number. All letters 'ABC...Z' are translated to 'X' and all digits '012 . . . 9' are translated to '9':
SELECT TRANSLATE('2KRW229',
'0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ',
'9999999999XXXXXXXXXXXXXXXXXXXXXXXXXX') "License"
FROM DUAL;
License
9XXX999
The following statement returns a license number with the characters removed and the digits remaining:
SELECT TRANSLATE('2KRW229',
'0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ', '0123456789')
"Translate example"
FROM DUAL;
Translate example
2229
Also, LIKE '%<string>%' is going to be rather expensive simply because it has to compare the entire string and because it forces full table scans, rather than using indexes. You could speed this sort of query up by using interMedia Text (Oracle Text now in 9i). If you can eliminate one of the '%' options, you could also improve things.
My guess is that your stored procedure is inefficient and that's causing the problem-- 5k rows per table should be pretty trivial.
If you post your query over on the PL/SQL forum, there are better performance tuners than I that might have more hints for you. To get really good advice, though, you'lllikely have to get at least the execution plan for this statement and may need to do some profiling to identify the problem areas.
Justin

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

Using Oracle Hints in Selects......

Hello,
Are there any after effects/side effects by using Oracle Hints in a SQL select ??? (hints such as Cache, NOCache, all_rows)
Can anyone let me know whether there are any good documentation or site on Oracel SQL hints..
thanks
Kanchi

Hi!
There is an exception, that I think is a bug in Oracle, but I4m not sure. If you use the PARALLEL HINT in a select that will be use in a Cursor, in order to insert the results in other table, and the results come in groups built following a group by sentence, there are possibilities that two childs (a child is a parallel process) take portions of this whole group, and built each one one group.
If the new table use certain number of columns as a primary key, this may cause an duplicated primary key trigger.
I4m going to write and document this case, in order to show it to oracle support.
I hope this help. Bye.
<BLOCKQUOTE><font size="1" face="Verdana, Arial, Helvetica">quote:</font><HR>Originally posted by kanchana Hettiarachchi ([email protected]):
Hello,
Are there any after effects/side effects by using Oracle Hints in a SQL select ??? (hints such as Cache, NOCache, all_rows)
Can anyone let me know whether there are any good documentation or site on Oracel SQL hints..
thanks
Kanchi<HR></BLOCKQUOTE>
null

SQL query against tables on MS SQL Server and Oracle using Oracle BI

Hi All
I have two databases Oracle and MS SQL Server. I want to write a query statement which will retrieve data from both databases and publish this data into one report. That is I want to join/merge data from tables in both database into one report with one SQL Statement something like:
Select o.F1,o.F2, m.F1,m.F2
from
table@oracleServer o,
table@microsoftSQLServer m
where o.F1=m.F1;
Can Oracle BI Publisher do this?
Basically I want to query simultaneously two heterogeneous data sources in one SQL statement. Is there such a tool? I don't want to build a warehouse by moving data from SQL Server into Oracle or vice-versa. I don't want to duplicate data. I want to be able to query data at its source via 1 SQL statement.
How would one go about doing such a thing?
Many Thanks
Kubilay.

Hi Matt and Thomas
Many thanks for your replies.
Yes I have to do the join. Even worse I have to write an Aggregate query like this!
Select o.F1,o.F2, m.F1,m.F2, count(*)
from
table@oracleServer o,
table@microsoftSQLServer m
where o.F1=m.F1
group by o.F1,o.F2, m.F1,m.F2;
These are 2 different systems (hardware & software) which actually do the same job, they produce transactions for a common business entity. Kind of, both sell tickets for the same ABC ferry company.
I can not put them side by side on the dashboard, as I need to aggregate the data and present it maybe in a Oracle BI Report for Accounting and Financial reconciliation purposes.
The truth is, as it is. I can't change it, is too late.
I have to device a way to harvest both systems as they are. I don't want to move around data. I thought looking at Oracle BI I could write SQL against multiple Data Sources. I am struggling to find a way. As it seems that it can "SQL query" 1 data source at a time.
I have been hinted on another forum (OracleTURK) to use Oracle Transparent Gateways and Generic Connectivity. http://download.oracle.com/docs/cd/B19306_01/server.102/b14232/toc.htm
Shame, I have to pay licenses for OWB and Oracle Transparent Gateways. I thought DB vendors can do better. Why do I have to pay to access the other 50% of the market.
I can understand the performance implications this might have. Because of it I might even be forced at the end to move data (ETL) into a separate database, slice it into partitions and manage it that way. Pitty because currenlty I only need one report out of these systems but seems like will be dear to get.
Thank you for all your help.
Kubilay

How to insert ORACLE HINT into select statement....

Hi team,
Can you please suggest me how to add an Oracle hint to point the Program to BSAD~1.
Index BSAD1 has all three fields MANDT, BUKRS, AUGDT which are there in the where clause. But as per the execution plan index BSAD0 is being used which is the primary one.
Also the stats for this table are are current.
Thanks in Advance.
Puneet.

Hi punnet, look at this example:
SELECT MAX( kkop~augbd )
INTO it_gen_docs-augbd
FROM ( fkkvkp AS vkp INNER JOIN dfkkop AS kkop
     ON vkpvkont = kkopvkont ) INNER JOIN dfkkko AS kkko
     ON kkopaugbl = kkkoopbel
WHERE vkp~exvko = ti_cuentas-exvko
        AND kkop~bukrs = p_bukrs
        AND kkop~blart IN r_blart
        AND kkop~augst = '9'
        AND kkko~blart IN r_blartd
%_HINTS ORACLE 'INDEX("DFKKOP" "DFKKOP~Z07")'.
DFKKOP is the table name and DFKKOP~Z07 is the index.
I hope this helps you.

Oracle portal 9 and oracle webcenter and SSO

dear team.
we have oracle portal 9 and oracle webcetner in my orgnization. both have different usernames/passwords. is there a way to have only one single username/password (webcenter ones) how can i do that. or even can we implement SSO thrugh windows login.
is there a way to intergrate both in a way to have only one username/password for both.
any hint will help as this topic new to me.
fadi

They are separate products.
Oracle Weblogic Portal and Oracle Portal 11g

Kodo 3.4.1 and Oracle JDBC 11.1.0.6?

Hi,
did anybody already try using Kodo 3.4.1 and Oracle JDBC driver 11.1.0.6?
We have been able to use it by specifying:
kodo.jdbc.DBDictionary=oracle(BatchLimit=1000)
but it does not run very smoothly and we get for example the
following exception (but not always).
NestedThrowablesStackTrace:
[migrate-data] java.lang.ArrayIndexOutOfBoundsException: -32193
[migrate-data] at
oracle.jdbc.driver.OraclePreparedStatement.setupBindBuffers(OraclePreparedS
tatement.java:2677) [migrate-data] at
oracle.jdbc.driver.OraclePreparedStatement.executeBatch(OraclePreparedState
ment.java:9270) [migrate-data] at
oracle.jdbc.driver.OracleStatementWrapper.executeBatch(OracleStatementWrapp
er.java:210) [migrate-data] at
com.solarmetric.jdbc.DelegatingPreparedStatement.executeBatch(DelegatingPre
paredStatement.java:325) [migrate-data] at
com.solarmetric.jdbc.PoolConnection$PoolPreparedStatement.executeBatch(Pool
Connection.java:375) [migrate-data] at
com.solarmetric.jdbc.DelegatingPreparedStatement.executeBatch(DelegatingPre
paredStatement.java:325) [migrate-data] at
com.solarmetric.jdbc.DelegatingPreparedStatement.executeBatch(DelegatingPre
paredStatement.java:325) [migrate-data] at
com.solarmetric.jdbc.DelegatingPreparedStatement.executeBatch(DelegatingPre
paredStatement.java:325)Any hints?
Thanks,
Werner

Disabling SQL batching by specifying BatchLimit = 0 solved the
problem temporarlyOf course this is not what we want, anybody else using this configuration?
Werner

ConnectionPool problems with WLS 7.0 and Oracle 9.2

Hi,
We are using WLS 7.0 SP4, and Oracle 9 and the Oracle thin driver type 4. In our
application on the productive system (and only there) we constantly encounter
a whole set of SQLExceptions which have all in common that the Connection from
the pool is not valid any more when the application tries to use it.
Typical, recurring error messages are:
- Exhausted ResultSet
- Connection has already been closed
- Closed Statement
- Transaction is no longer active - status committing
- NullPointerException at
weblogic.jdbc.pool.Connection.prepareStatement()
There are no special Statements which create these errors. They are spread at
random across practically every query the application creates, and the same queries
sometimes succeed and sometimes fail.
I double and triple checked that all Connections, Statements and ResultSets are
closed immediately after use. As an example, I attached a code snippet and a resulting
StackTrace which.
The problem also seems to occur only with an (unknown) minimum of concurrent usern,
since in the approval tests on an almost identical test system these errors never
occurred.
I also followed the advice from Oracle and installed the latest Oracle JDBC driver
(Oracle 10g) - to no avail.
What else can I do?
Another question: Is it correct that my Oracle JDBC driver is in the application
classpath (via a reference in the Manifest file of the application jar), not in
the system classpath? There has never been a problem with that, but in a Newsgroup
answer from Nov 10, 2003 (subject: "ResultSet closes prematurely"), Joe Weinstein
suggested to "get it listed at the
front of the -classpath argument that the startWebLogic script creates for the
java line that starts the server".
I hesitate to do so, since the driver is in a standard WebApp- directory, WEB-INF/lib.
Is it possible and safe to add a jar located there to the system classpath? If
it is possible, why is it necessary?
Best regards,
Andreas Zehrt
[CodeSnippetsAndStackTraceForConnectionPoolProblem.txt]

Andreas Zehrt wrote:
Hi Joe,
Your hint that there is a threading problem was right:
On further investigation of the code I found out that the class that passes the
Connection to the DAO not only stores it as a member at some point (which is not
a good idea anyway) but is also a singleton - then, of course, it's no surprise
that the Connection gets invalid in a incalculable way when concurrent threads
share it.
The singleton instantiation was not so obvious because the way of instantiation
is controlled by a configuration parameter that can be overridden at different
levels.
I changed it and the productive logfiles indicate that the SQLExceptions related
to that class have disappeared.I am happy to have helped.
So, thanks a lot for the advice.
But I am still wondering why this code has worked for so long a time with WLS
5.1 and Oracle 8 (the system has been productive for over 2 years). Even in the
approval tests with WLS 7.0 and Oracle 9, we did not run into problems, although
it was multi-user environment.Mo idea.
I still believe that there is a difference between WLS 5.1 and 7.0 in the way
it treats pooled Oracle JDBC Connections. I wished both Oracle and Bea could be
a little more explicit about those changes and possible version incompatabilities
beyond the general advice "use the latest thin driver".Though I can think of no change to our pooling which would have had any material
effect in this case, I will certainly do what I can to see that our documentation
is explicit about changes.
Joe
Best regards, Andreas
Joe Weinstein <[email protected]> wrote:
Hi Andreas.
Andreas Zehrt wrote:
Hi,
We are using WLS 7.0 SP4, and Oracle 9 and the Oracle thin driver type4. In our
application on the productive system (and only there) we constantlyencounter
a whole set of SQLExceptions which have all in common that the Connectionfrom
the pool is not valid any more when the application tries to use it.
Typical, recurring error messages are:
- Exhausted ResultSetThat is typically if the statement that created it is either re-executed
or closed.
- Connection has already been closedAs described. If you give a stacktrace, we could make a debug patch which
would show
where it was originally closed.
- Closed Statementsame as above.
- Transaction is no longer active - status committingThat implies your code is obtaining a connection from a transactional
datasource,
and then later trying to use it after the transaction which it was associated
with,
is finished.
- NullPointerException at
weblogic.jdbc.pool.Connection.prepareStatement()Maybe any of the above.
There are no special Statements which create these errors. They arespread at
random across practically every query the application creates, andthe same queries
sometimes succeed and sometimes fail.
I double and triple checked that all Connections, Statements and ResultSetsare
closed immediately after use. As an example, I attached a code snippetand a resulting
StackTrace which.
The problem also seems to occur only with an (unknown) minimum of concurrentusern,
since in the approval tests on an almost identical test system theseerrors never
occurred.
I also followed the advice from Oracle and installed the latest OracleJDBC driver
(Oracle 10g) - to no avail.
What else can I do?
Another question: Is it correct that my Oracle JDBC driver is in theapplication
classpath (via a reference in the Manifest file of the applicationjar), not in
the system classpath? There has never been a problem with that, butin a Newsgroup
answer from Nov 10, 2003 (subject: "ResultSet closes prematurely"),Joe Weinstein
suggested to "get it listed at the
front of the -classpath argument that the startWebLogic script createsfor the
java line that starts the server".
I hesitate to do so, since the driver is in a standard WebApp- directory,WEB-INF/lib.
Is it possible and safe to add a jar located there to the system classpath?If
it is possible, why is it necessary?I was only concerned to ensure we know which driver we are working with.
We also ship
an oracle thin driver, which becomes obsolete soon...
I am concerned that your code creates pool connections to be used later.
The problems
can arise if more than one thread ever gets the same connection, or if
the connection
is used in the same thread, spanning transactions. It does also seem
that there may
be a threading issue, because if two threads each call the code to create
a connection,
and two connections are made, but one over-writes the other, the two
threads can
end up using the same connection, and closing it. The over-written one
never gets closed,
resulting in that leak message you got...
Joe
The Connection parameter is opened by a business component class, ComaServiceProviderClassicImpl.It is propagated through
several classes in the business layer, but not used, until the DAOtakes it to make the query.
So, the Connection is closed where it was opened, not in the DAO class.
public class ConcernDAOImpl extends BaseDAO {
     public Collection getConcernsForIncidents(Connection conn, Collectionincidents)
throws DataAccessException, ConstraintException, ComaParseException{>
sqlMessage.append(")");
String sqlStmt = sqlMessage.toString();
PreparedStatement pstmt = null;
ResultSet rs = null;
try {
pstmt = conn.prepareStatement(sqlStmt);
rs = pstmt.executeQuery();
while (rs != null && rs.next()) {
final Concern concern =
new Concern(DAOUtil.getComaOID(rs, ComaDBNames.KDANR));
concern.setIncidentOID(DAOUtil.getComaOID(rs, ComaDBNames.KDAVGENR));
return concerns;
} catch (SQLException sqle) {
// Wrapps real SQL exception
String[] message = new String[]{sqle.getMessage(), sqlStmt};
throw new DataAccessException(ExpCode.S_ORACLE_SQL, message,
sqle);
} finally {
closeAll(rs, pstmt);
_logger.exitDebug(method);
Here, the Connection is acquired and finally closed
public class ComaServiceProviderClassicImpl {
     public void updateComplaint(
final Request updateRequest,
final ResponseSingleElement response,
final Principal principal)
throws SystemException {
try {
logger.info("updateComplaint", "store incident");
// store the incident in the database
incidentManager.storeIncident(getConnection(), updateIncident);
// reload the incident from Cache and / or the databaseto get the ContactReferences.
Incident returnIncident = incidentManager.loadIncident(//IncidentManager passes the Connection to the DAO
getConnection(), updateIncident.getOID());
} catch (RemoteException rex) {
// remote exceptions
rollbackIfNecessary();
CoreUtils.unwrapRemoteException(rex, logger);
} catch (SystemException e) {
// all other exceptions --> rollback if necessary and rethrow
rollbackIfNecessary();
throw e;
} finally {
removeConnection();
logger.exitDebug("updateComplaint");
This is the resulting StackTrace:
sql exception: [Closed Statement: next] - sql statement: [select *
     at de.deutschepost.ubbrief.coma.persistence.dao.ConcernDAOImpl.getConcernsForIncidents(ConcernDAOImpl.java:363)
     at de.deutschepost.ubbrief.coma.persistence.dao.CachingConcernDAOImpl.getConcernsForIncidents(CachingConcernDAOImpl.java:129)
     at de.deutschepost.ubbrief.coma.persistence.incidentmanager.IncidentManagerImpl.loadConcernStructuresIntoIncidents(IncidentManagerImpl.java:1067)
     at de.deutschepost.ubbrief.coma.persistence.incidentmanager.IncidentManagerImpl.loadStructureForIncident(IncidentManagerImpl.java:320)
     at de.deutschepost.ubbrief.coma.persistence.incidentmanager.IncidentManagerImpl.loadIncidents(IncidentManagerImpl.java:264)
     at de.deutschepost.ubbrief.coma.persistence.taskmanager.TaskManagerImpl.selectTasksForUser(TaskManagerImpl.java:299)
     at de.deutschepost.ubbrief.coma.service.z2.ComaServiceProviderZ2Impl.getTaskList(ComaServiceProviderZ2Impl.java:113)
     at de.deutschepost.ubbrief.coma.service.z2.ComaServiceProviderZ2Bean_1dhrj7_EOImpl.getTaskList(ComaServiceProviderZ2Bean_1dhrj7_EOImpl.java:154)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList.runServiceMethod(CMPGetTaskList.java:64)
     at de.deutschepost.ubbrief.coma.sbbx.sp.BasicMethodProvider.execute(BasicMethodProvider.java:145)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl.execute(CMPGetTaskList_9b9mv5_EOImpl.java:46)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl_WLSkel.invoke(UnknownSource)
     at weblogic.rmi.internal.ServerRequest.sendReceive(ServerRequest.java:159)
     at weblogic.rmi.cluster.ReplicaAwareRemoteRef.invoke(ReplicaAwareRemoteRef.java:263)
     at weblogic.rmi.cluster.ReplicaAwareRemoteRef.invoke(ReplicaAwareRemoteRef.java:230)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl_WLStub.execute(UnknownSource)
     at de.deutschepost.ubbrief.backbone.jazz.impl.core.RequestHandlerImpl.handleRequest(RequestHandlerImpl.java:115)
     at de.deutschepost.ubbrief.backbone.common.impl.core.rpc.server.ServerKernelImpl.handleTransportMessage(ServerKernelImpl.java:270)
     at de.deutschepost.ubbrief.backbone.common.impl.core.messaging.MessageTransport.handleMessage(MessageTransport.java:454)
     at de.deutschepost.ubbrief.backbone.common.impl.core.KernelFacade.handleMessage(KernelFacade.java:209)
     at de.deutschepost.ubbrief.backbone.jazz.impl.backbone.BackboneBean.messageArrived(BackboneBean.java:637)
     at de.deutschepost.ubbrief.backbone.jazz.impl.backbone.BackboneBean_ina9d7_ELOImpl.messageArrived(BackboneBean_ina9d7_ELOImpl.java:105)
     at de.deutschepost.ubbrief.backbone.jazz.impl.transport.receive.LocalQueueReceiveBean.deliverMessage(LocalQueueReceiveBean.java:43)
     at de.deutschepost.ubbrief.backbone.jazz.impl.transport.receive.AbstractMessageReceiveBean.onMessage(AbstractMessageReceiveBean.java:127)
     at weblogic.ejb20.internal.MDListener.execute(MDListener.java:377)
     at weblogic.ejb20.internal.MDListener.transactionalOnMessage(MDListener.java:311)
     at weblogic.ejb20.internal.MDListener.onMessage(MDListener.java:286)
     at weblogic.jms.client.JMSSession.onMessage(JMSSession.java:2351)
     at weblogic.jms.client.JMSSession.execute(JMSSession.java:2267)
     at weblogic.kernel.ExecuteThread.execute(ExecuteThread.java:234)
     at weblogic.kernel.ExecuteThread.run(ExecuteThread.java:210)
####<May 26, 2004 12:18:43 PM CEST> <Warning> <JDBC> <S0048016> <REMA20Z><Finalizer> <kernel identity> <> <001074> <A JDBC pool connection leak
was detected. A Connection leak occurs when a connection obtained from
the pool was not closed explicitly by calling close() and then was disposed
by the garbage collector and returned to the connection pool. The following
stack trace at create shows where the leaked connection was created.
Stack trace at connection create:
     at weblogic.jdbc.pool.Connection.<init>(Connection.java:66)
     at weblogic.jdbc.pool.Driver.allocateConnection(Driver.java:294)
     at weblogic.jdbc.pool.Driver.connect(Driver.java:210)
     at weblogic.jdbc.jts.Driver.getNonTxConnection(Driver.java:373)
     at weblogic.jdbc.jts.Driver.connect(Driver.java:129)
     at weblogic.jdbc.common.internal.RmiDataSource.getConnection(RmiDataSource.java:287)
     at de.deutschepost.ubbrief.coma.core.ComaComponentImpl.getConnectionFromPool(ComaComponentImpl.java:163)
     at de.deutschepost.ubbrief.coma.core.ComaComponentImpl.getConnectionInternal(ComaComponentImpl.java:135)
     at de.deutschepost.ubbrief.coma.core.ComaComponentImpl.getConnection(ComaComponentImpl.java:99)
     at de.deutschepost.ubbrief.coma.persistence.customermanager.CurryCustomerManagerImpl.findCustomers(CurryCustomerManagerImpl.java:73)
     at de.deutschepost.ubbrief.coma.service.z2.ComaServiceProviderZ2BaseImpl.resolveCustomerInstances(ComaServiceProviderZ2BaseImpl.java:808)
     at de.deutschepost.ubbrief.coma.service.z2.ComaServiceProviderZ2Impl.getTaskList(ComaServiceProviderZ2Impl.java:213)
     at de.deutschepost.ubbrief.coma.service.z2.ComaServiceProviderZ2Bean_1dhrj7_EOImpl.getTaskList(ComaServiceProviderZ2Bean_1dhrj7_EOImpl.java:154)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList.runServiceMethod(CMPGetTaskList.java:64)
     at de.deutschepost.ubbrief.coma.sbbx.sp.BasicMethodProvider.execute(BasicMethodProvider.java:145)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl.execute(CMPGetTaskList_9b9mv5_EOImpl.java:46)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl_WLSkel.invoke(UnknownSource)
     at weblogic.rmi.internal.ServerRequest.sendReceive(ServerRequest.java:159)
     at weblogic.rmi.cluster.ReplicaAwareRemoteRef.invoke(ReplicaAwareRemoteRef.java:263)
     at weblogic.rmi.cluster.ReplicaAwareRemoteRef.invoke(ReplicaAwareRemoteRef.java:230)
     at de.deutschepost.ubbrief.coma.sbba.z2.CMPGetTaskList_9b9mv5_EOImpl_WLStub.execute(UnknownSource)
     at de.deutschepost.ubbrief.backbone.jazz.impl.core.RequestHandlerImpl.handleRequest(RequestHandlerImpl.java:115)
     at de.deutschepost.ubbrief.backbone.common.impl.core.rpc.server.ServerKernelImpl.handleTransportMessage(ServerKernelImpl.java:270)
     at de.deutschepost.ubbrief.backbone.common.impl.core.messaging.MessageTransport.handleMessage(MessageTransport.java:454)
     at de.deutschepost.ubbrief.backbone.common.impl.core.KernelFacade.handleMessage(KernelFacade.java:209)
     at de.deutschepost.ubbrief.backbone.jazz.impl.backbone.BackboneBean.messageArrived(BackboneBean.java:637)
     at de.deutschepost.ubbrief.backbone.jazz.impl.backbone.BackboneBean_ina9d7_ELOImpl.messageArrived(BackboneBean_ina9d7_ELOImpl.java:105)
     at de.deutschepost.ubbrief.backbone.jazz.impl.transport.receive.LocalQueueReceiveBean.deliverMessage(LocalQueueReceiveBean.java:43)
     at de.deutschepost.ubbrief.backbone.jazz.impl.transport.receive.AbstractMessageReceiveBean.onMessage(AbstractMessageReceiveBean.java:127)
     at weblogic.ejb20.internal.MDListener.execute(MDListener.java:377)
     at weblogic.ejb20.internal.MDListener.transactionalOnMessage(MDListener.java:311)
     at weblogic.ejb20.internal.MDListener.onMessage(MDListener.java:286)
     at weblogic.jms.client.JMSSession.onMessage(JMSSession.java:2351)
     at weblogic.jms.client.JMSSession.execute(JMSSession.java:2267)
     at weblogic.kernel.ExecuteThread.execute(ExecuteThread.java:234)
     at weblogic.kernel.ExecuteThread.run(ExecuteThread.java:210)

What are the advantages of using CACHE and NOCACHE Hint

What are the advantages of using CACHE and NOCACHE Hint & difference of them.I saw one of oracle.sql script have CACHE & oracle rac script include NOCACHE .Why is that

924250 wrote:
In a SOA product include db scripts,when we install the product we want to execute the db script to create sequence both oracle RAC & Oracle db
Oracle DB
CREATE SEQUENCE REG_LOG_SEQUENCE START WITH 1 INCREMENT BY 1 NOCACHE
Oracle RAC DB
CREATE SEQUENCE REG_LOG_SEQUENCE START WITH 1 INCREMENT BY 1 CACHE 20 ORDERas sb mentioned, this has nothing to do with oracle hints.
you'll want to search the documentation about sequences.

BPEL and Oracle Portal

Hello.
At the moment i try to find a beginning how to display Values from Oracle BPEL Process Manager to Oracle Portal. I would like to use Portlet Specification JSR-168, if it is possible.
For a better understanding: here is a detailed description of the task i try to do:
I have a BPEL Process which uses values via WebService. These values will be modified in the BPEL Process. After the values are modified, they should be displayed in Oracle Portal.
I have installed an Infrastructure, Middle Tier (Portal&Wireless) and Oracle BPEL PM for Middle Tier on a Virtual Machine. At my local PC I installed BPEL PM for Developers to develop BPEL Processes.
I don't find a beginning to display the Values in Oracle Portal... ;)
Can anyone help me or give me a hint to find a beginning?
P.S.: If you don't have an idea about my problem but you
know a guy who might be know sth about it, please
contact me. Althoug if my question is not clear
enough, please contact me, because it is very
important for me.
Thanks a lot!
Message was edited by:
BenSp

Hi all,
Sorry to disturb but I really need help on this, has anybody deployed BPEL portlets 10.1.3 or has anybody developed a portlet with the 10.1.3 workflow services API on Oracle Portal?
All help will be appreciated.. Thanks in advance..
Serkan

TopLink 3.6.3 and Oracle hints.

Similar Messages

Maybe you are looking for