Oracle on debian?

Is there any problems with running oracle on debian/GNU linux? I have tried installing it on woody (testing release) and sid (unstable release). however whenever I start ./runInstaller it hangs with: Initializing Java Virtual Machine from ../stage/Components/oracle.swd.jre/1.1.8/1/DataFiles/Expanded/linux/bin/jre. Please wait...
Additionally, when checking top, jre has 98.8% cpu usage.
If anyone has successfully installed oracle on any recent release of debian (potato, woody, sid), please let me know what you did to get it working.

To All on this thread.
I am running Oracle 8i (8.1.7) and 9i (9.0.1) on the following Debian versions without any problems.
2.2.12 (only 8.1.7)
2.4.12 glibc 2.2 (8.1.7 and 9.0.1 and 9iAS)
2.4.17 glibc 2.2 (8.1.7 and 9.0.1 and 9iAS)
Downgrading compilers and binutils like on redhat is not necessary.
Main things to look for
- Make sure you have 500-600 M free in your /tmp.
- Make sure that your swap file is big enough > 1.5 Gb due to memory leak in some versions of Oracle Universal Installer
- check your locale settings in /etc/locale.gen. Make sure you don't have UTF8 or UTF16 there becuase java 1.1.8 doesn't support it and your runInstaller will crash with sigsegv 11 error
For 8.1.7 under 2.4 kernel perform normal installation
Download glibc-2.1.3-stubs.tar.gz and follow instructions in the README file
For 9.0.1
Follow standard instructions. When it gets to the stage of linking you will get an error reported.
Now cd to the bin directory and edit genclntsh
replace
# Original line
SYSLIBS=`cat ${ORACLE_HOME}/lib/sysliblist`" -ldl -lm -lc"
by
# New line
SYSLIBS=`cat ${ORACLE_HOME}/lib/sysliblist`" -L/usr/lib/gcc-lib/i386-linux/2.95.4 -lgcc -ldl -lm -lc /lib/ld-linux.so.2"
Doublecheck in /usr/lib/gcc-lib directory for the directory i386-linux and the version nr of the file in that directory. On Redhat for example it is /usr/lib/gcc-lib/redhat-linux/2.93.2 .
Save and exit
run genclntsh
when finished click retry in the installer program. It should be all working ok now.

Similar Messages

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

Oracle on Debian Linux

Oracle doesn't support Debian Linux. Has anyone gotten it to successfully run on Debian Linux? What would I need to do to get it working?

Oracle works nice on Debian 2.2 ;-)
Install 8.1.6 because comes with jre
you should install following debian packages:
libg++2.8.2-glibc2.1
libstdc++2.9-glibc2.1
once installed you should fixed up file dbstart (follow instructions on www.oralinux.org)
see ya
null

Problems installing Oracle under Debian 2.2

Hi. I wasn't able to install Oracle 9i under Debian 2.2.
It seems that the JRE that Oracle instalation uses generate a segementation fault in the very beginning of the instalation. I've already posted something about it and still hasn't got any answers. But that's not what this post is about.
I'd like to know if someone was succesfull where I failed. I'd like to know if someone was able to install Oracle 9i under Debian, the version of the distribuiton, version of the kernel, version of the glib-c, version of gcc, and any other relevant version!
Moreover, I'd like to know if someone knows if there's a list with the Linux distribuitions that works with Oracle 9i and over which Linux you had already installed Oracle 9i. You can send me it by e-mail to not polute the forum. If I have a good number of replies, I can post a list here of successfull cases!
Thanks for attention and sorry for my poor english,
RGB

there is no listener.ora file and TNSNAMES.ora file. These files you can create using net configuration assistant (netca).

Running ORACLE on Debian Linux

Hi!
I have installed ORACLE 10g. When I run "oracle" command from oracle user account, nothing's doing. When I run "sqlplus" and login as "/ as sysdba" then I receive a message "Connected to an idle instance.". So, what have I do to run ORACLE?
Thanks in advance.
Ps. Sorry for my bad english.

Connected to an idle instance.This message means that your DB is not running, or ORACLE_SID environment variable is not set properly. Be sure that ORACLE_SID has correct value, then, if you get that message, type "startup".

How to install oracle on ubuntu 8.04 server amd64

i have a question. is it possible to install on Ubuntu 8.04 amd64 server any oracle server?
my purpose is to make a database with oracle on any other computer that runs on my ubuntu server.
i followed few tutorials and everytime i got this error:
Hit http://oss.oracle.com unstable Release
W: Failed to fetch http://oss.oracle.com/debian/dists/unstable/Release Unable to find expected entry main/binary-amd64/Packages in Meta-index file (malformed Release file?)
E: Some index files failed to download, they have been ignored, or old ones used instead.
sources.list is ok i think:
deb http://oss.oracle.com/debian unstable main non-free

First of all thanks for your help,
I tried again with ./runInstall -ignoreSysPrereqs but I got another error...
"Starting Oracle Universal Installer...
Checking Temp space: must be greater than 120 MB. Actual 63827 MB Passed
Checking swap space: must be greater than 150 MB. Actual 6233 MB Passed
Checking monitor: must be configured to display at least 256 colors
>>> Could not execute auto check for display colors using command /usr/X11R6/bin/xdpyinfo. Check if the DISPLAY variable is set. Failed <<<<
Ignoring required pre-requisite failures. Continuing...Preparing to launch Oracle Universal Installer from /tmp/OraInstall2009-02-19_12-16-16PM. Please wait ...sh: /home/octopus/downloads/database/install/unzip: not found"
every time I try another way to install I get another error or something...
I tried the installations with the response file but I got the same error...
"Preparing to launch Oracle Universal Installer from /tmp/OraInstall2009-02-19_12-16-16PM. Please wait ...sh: /home/octopus/downloads/database/install/unzip: not found"
When I search for that file in " /home/octopus/downloads/database/install/" "unzip" is there.....
Any ideas???
Thanks in advance!

Installation problem of 8.1.6 on RH 6.* try DEBIAN

HI guys,
For now 2 weeks I've been tring to install Oracle 8.1.5 on Redhat 6.0, 6.1 and 6.2! None of them worked for me! Either linking and files no present were the problem everything was worst with the patches... I then tried Oracle 8.1.6 on Redhat 6.2 no luck again.
Talking with Linux Gurus of a beer at the en of last week they suggested me to install it on Oracle on Debian (Frozen Potato)!... I tried it while following the exact same steps as with Redhat and the installation went perfectly without a single error message!!!!
ORACLE 8.1.6 is supposed to be certified to run on a server wearing a Red Hat but it prefers to eat Frozen POTATO!
Good luck and to give up!
ps Debian seems to be there for us!

I received the sigsegv as well when exporting the display to my macintosh using MI/X. There were no apparent reasons for this. I then exported the display to X-WIN32 4.1.1 and it worked fine. I can't tell you why it failed in MI/X, but this worked for us. BTW we are using Red Hat 6.2 and Oracle 8.1.6. Prior we were using Red Hat 6.1 with Oracle 8.1.5 (now that is an installation nightmare!).

Installing oracle xe on centos ci environment

Hi,
I have a CI environment that run automated tests on my application every time a commit is pushed to github, the tests are run on a matrix of environments to check if the application is able to run with different databases.
I currently have tests running with sqlite, mysql and postgres and would like to add oracle to the matrix.
The application is in python, (for those curious it is here: https://github.com/treeio/treeio) so on top of the oracle xe database itself I need to install the appropriate driver (cx_oracle)
The current CI I'm using is travis (https://travis-ci.org/), the tests run in a debian (or maybe ubuntu, I'm not sure) environment, they already have mysql and postgres installed
Installing oracle xe on debian proved to be a headache, I've found https://oss.oracle.com/debian/ unstable main non-free which contains only and old 32 bits version, while this wouldn't be a problem for me it generate conflicts when I tried to install cx_oracle dependencies
In any case I've found another CI (snap-ci.com) which uses centos, I've managed to install oracle-xe from the rpm and pip install cx_oracle finally works, but when I try to run anything that uses sqlplus it fails:
echo "CREATE USER treeio IDENTIFIED BY treeio;" | sqlplus -S -L sys/admin AS SYSDBA
sqlplus: command not found
it seems it was not added to the path or maybe I should have installed yet another rpm.
Ideally I would like to run the tests with oracle DB on both services (so I can test my application runs fine on debian and centos the same) but I can settle on running it on just one of them if you tell me it is not possible
by the way, does anyone runs oracle or any of its tools on debian? they seems to provide only RPMs. do everyone that works with oracle uses read hat only?
thanks
Avraham

Hi,
The CI service have a interactive shell, I was able to further debug. I fixed the command not found problem and then it complained about permissions, but running with root gives me yet another exception.
currently my script is as below:
#set paths:
export ORACLE_VERSION="11.2"
export ORACLE_HOME="/usr/lib/oracle/$ORACLE_VERSION/client64"
export PATH=$PATH:"$ORACLE_HOME/bin"
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:"$ORACLE_HOME/lib"
. /u01/app/oracle/product/11.2.0/xe/bin/oracle_env.sh
# create user
echo "CREATE USER treeio IDENTIFIED BY treeio;" | sudo sqlplus -S -L sys/admin AS SYSDBA
It gives me
Error 6 initializing SQL*Plus
SP2-0667: Message file sp1<lang>.msb not found
SP2-0750: You may need to set ORACLE_HOME to your Oracle software directory
I also noticed that I was insalling oracle xe 11.2 and client libraries 12.1, I'm not sure if that would cause problems but I'm installing libraries and clients with the same version (11.2.x)

Difficulties installing oracle xe under Ubuntu

Here's what I did:
1) added this to /etc/apt/sources.list: deb http://oss.oracle.com/debian unstable main non-free
2) ran: wget http://oss.oracle.com/el4/RPM-GPG-KEY-oracle -O- | sudo apt-key add -
3) ran: sudo apt-get update
4) via the Synaptic package manager, clicked on "oracle xe". This package was installed along with libaio.
5) checked my applications menu and saw that oracle had appeared.
6) ran: sudo /etc/init.d/oracle-xe configure (I changed the port for Oracle Application Express to 9090 so it wouldn't conflict with Tomcat, which uses port 8080. I indicated that I didn't want the database server to launch on boot. I was planning launching as needed from the applications menu).
Now I thought that I was ready to go. So I went to the applications menu and selected start database. A terminal window popped up warning me that I wasn't a member of the dba group. I added myself to the dba group. I restarted my computer and tried starting the database once again from the applications menu.
This time no warning terminal came up. Basically I didn't get any feedback as to whether the database server was actually running. So I tried accessing:
http://127.0.0.1:9090/apex. I was told the browser couldn't establish a connection with the database. I selected "run sql from the command line" from the applications menu. This didnt' work either. The terminal window that came up began like this:
/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
I also checked my logs:
Oracle Database 10g CRS Release 10.2.0.1.0 Production Copyright 1996, 2005 Oracle. All rights reserved.
[ OCRUTL][3067549888]u_set_comp_error: Parameter was NULL
[ OCRUTL][3067549888]u_set_ocr_error: Parameter was NULL
2008-07-18 22:18:24.502: [ OCROSD][3067549888]utgdv:2:ocr loc file cannot be opened
2008-07-18 22:18:24.502: [ OCROSD][3067549888]utopen:1: Couldnt find ocr,[ocrmirror] location in config file
[ OCRUTL][3067549888]u_set_gbl_comp_error: Parameter was NULL
2008-07-18 22:18:24.502: [ OCRRAW][3067549888]proprinit: Could not open raw device
2008-07-18 22:18:24.502: [ default][3067549888]a_init:7!: Backend init unsuccessful : [33]
[ OCRUTL][3067549888]u_set_ocr_error: Parameter was NULL
2008-07-18 22:18:24.502: [ CSSCLNT][3067549888]clsssinit: error(33 ) in OCR initialization
Any suggestions?
Deb

You are trying to install on an unsupported o/s.
My recommendation would be to download Oracle Enterprise Linux and then follow the installation instructions provided by Oracle.
PS: There is a dedicated XE forum here at OTN. You will likely get more responsive answers if you post there in the future.

Difficulties installing oracle xe under Ubuntu (7.10)

I laid out the difficulties I was having in the Installation forum, and a responder said I would have better luck getting a response in this forum.
Here's what I did:
1) added this to /etc/apt/sources.list: deb http://oss.oracle.com/debian unstable main non-free
2) ran: wget http://oss.oracle.com/el4/RPM-GPG-KEY-oracle -O- | sudo apt-key add -
3) ran: sudo apt-get update
4) via the Synaptic package manager, clicked on "oracle xe". This package was installed along with libaio.
5) checked my applications menu and saw that oracle had appeared.
6) ran: sudo /etc/init.d/oracle-xe configure (I changed the port for Oracle Application Express to 9090 so it wouldn't conflict with Tomcat, which uses port 8080. I indicated that I didn't want the database server to launch on boot. I was planning launching as needed from the applications menu).
Now I thought that I was ready to go. So I went to the applications menu and selected start database. A terminal window popped up warning me that I wasn't a member of the dba group. I added myself to the dba group. I restarted my computer and tried starting the database once again from the applications menu.
This time no warning terminal came up. Basically I didn't get any feedback as to whether the database server was actually running. So I tried accessing:
http://127.0.0.1:9090/apex. I was told the browser couldn't establish a connection with the database. I selected "run sql from the command line" from the applications menu. This didnt' work either. The terminal window that came up began like this:
/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
I also checked my logs:
Oracle Database 10g CRS Release 10.2.0.1.0 Production Copyright 1996, 2005 Oracle. All rights reserved.
[ OCRUTL][3067549888]u_set_comp_error: Parameter was NULL
[ OCRUTL][3067549888]u_set_ocr_error: Parameter was NULL
2008-07-18 22:18:24.502: [ OCROSD][3067549888]utgdv:2:ocr loc file cannot be opened
2008-07-18 22:18:24.502: [ OCROSD][3067549888]utopen:1: Couldnt find ocr,[ocrmirror] location in config file
[ OCRUTL][3067549888]u_set_gbl_comp_error: Parameter was NULL
2008-07-18 22:18:24.502: [ OCRRAW][3067549888]proprinit: Could not open raw device
2008-07-18 22:18:24.502: [ default][3067549888]a_init:7!: Backend init unsuccessful : [33]
[ OCRUTL][3067549888]u_set_ocr_error: Parameter was NULL
2008-07-18 22:18:24.502: [ CSSCLNT][3067549888]clsssinit: error(33 ) in OCR initialization
Any suggestions?
Deb

Any suggestions?http://ubuntuforums.org/showthread.php?t=697357
Also:
http://www.debian-administration.org/articles/430
HTH

Oracle XE - Just can't login after install

On Lubuntu 10.10, I did:
echo "deb http://oss.oracle.com/debian unstable main non-free" >> /etc/apt/sources.list
apt-get update ; apt-get install oracle-xe
That brings me Oracle XE 10.2.0.1. And then:
/etc/init.d/oracle-xe configure
Everything looks ok, including the password prompt and so. After that, I go to http://127.0.0.1:port/apex, and when I try to login with the username "SYSTEM", and the password I just typed. I get a "Invalid Login Credentials" error.
I also tried:
sqlplus /nolog
CONNECT
[ .. login and password .. ]
ERROR:
ORA-01017: invalid username/password; logon denied
Setting the environment variables also don't help.
sh oracle_env.sh
Well.. I just don't know what's happening. I repeated this procedure trying to find peculiar things, but always got the same results. Also tried some other users as "SYS". useless...
Thanks in advance.

Oracle 10g Express on Ubuntu 10.10 AMD 64-bit howto
Oracle 10g Express on Ubuntu 10.10 AMD 64-bit howto
Oracle 10g Express on Fedora 14 64-bit howto
Oracle 10g Express on Fedora 14 64-bit howto
Install Oracle 11gR2 Express Edition on Ubuntu Linux 11.04 (64-bit) Howto
Install Oracle 11gR2 Express Edition on Ubuntu Linux 11.04 (64-bit) Howto
Oracle 11gR2 Express Edition on Linux Ubuntu 11.10 how-to (revised)
Oracle 11gR2 Express Edition on Linux Ubuntu 11.10 howto

Problem using Instant Client 10g with PHP4.3.10-16 on Debian Sarge

Hello,
My current email is [email protected]
I am trying to use PHP on Debian box using Oracle 10gR2 on a RH 4 server. Everything works fine individually, but I cannot get PHP4 to use InstantClient to connect to the Oracle Server. This is what I've done:
Oracle 10gR2 works fine on the RH 4 server. Listener is running and all required OS security is in place and works (TCP_wrappers, etc.).
Client machine runs Debian 3.1 (Sarge). It works fine and SSH connectivity to RH4 server works.
Instant Client 10gR2 installed on Debian client and works fine. Tested SQL*Plus connection to the RH server. I installed Instant Client from the zip file.
I did have to add libclntsh.so to /etc/ld.so.conf and run ldconfig to get Debian to use it, though.
Apache2.0.54-5 on Debian client works fine. Web pages on it can be opened in browsers from other machines.
Installed PHP4.3.10-16 on Debian client using following:
./configure --with-oci8-instant-client=<dir of my choice>
--enable-sigchild
I first checked ./configure help and the option with-oci8-instant-client was there.
Configure went well. Log showed checking for Instant Client files.
Ran make. Saw numerous Instant Client message as words scrolled.
Ran make install. Successful.
Restarted Apache2 with following env variables:
LD_LIBRARY_PATH=<my Instant Client directory)
TNS_ADMIN=<same directory where I put my sqlnet.ora and tnsnames.ora files).
SQLPATH=<same directory>
I know this is correct because Instant Client SQL*Plus can connect.
Browsers on other machines can view simple php scripts run from the Debian box.
BUT, phpinfo does NOT show an OCI8 section.
phpinfo does show the correct extension directory, though.
Somehow, my PHP4 configure and make is not using the --with-oci8-instant-client option.
I checked $PHP4HOME/ext/oci8/config.m4 file and the verbiage IS in there to use the --with-oci8-instant-client option, either with the default location or the extension_dir location.
I tried using the new ZendCore product, even though it is not certified for Debian. It installed okay but I could not get PHP5 to work. I uninstalled it successfully and redid all of the above.
So, any ideas as to what else I can do here? Other than not use Debian (which is probably the wisest thing to do). And I suppose I could install a thick Oracle client, assuming that Debian would take it. But I prefer the Instant Client.
I tried the PHP ./configure syntax I've seen several places on this forum.
./configure --with-oci8=instantclient,<directory>
This syntax may work on Red Hat machines but it throws a syntax error on Debian and aborts the configure.
Thanks for any help.

Thanks, but that did not work. Configure aborts because it cannot find the required OCI8 libraries. The --with-oci8 option is for the Oracle "thick" client. I have only the Instant Client...and am not interested in loading the older client.
I may have my own solution next week, though. I will be loading RH4 on a new server and will then install ZendCore and forget all about using Oracle with Debian.
Update on trying ZendCore on Debian Sarge:
I tried installing it again yesterday. The install seemed go to well, and said it was successful.
It did NOT load PHP5, however. Nor did it load the Instant Client. My previously installed PHP4 and Instant Client remained in my original directories.

ERP 2004 SR1 with Oracle: unable to allocate MINEXTENTS

Hello Everybody,
I'm trying to install SAP ERP 2004 SR1 with Oracle on Debian Sarge (I know that it is not supported). The installation was prety straight forward. But now in the step "Database Load (Post processing)" i get this Errors:
/tmp/sapinst_instdir/ECC_50_ABAP_NUC/DB/SAPSSEXC.log:
(DB) ERROR: DDL statement failed
(CREATE INDEX "T100~001" ON "T100" ( "ARBGB" , "MSGNR" ) TABLESPACE PSAPIDS640 STORAGE (INITIAL 363889471 NEXT 0000002560K MINEXTENTS 0000000001 MAXEXTENTS 2147483645 PCTINCREASE 0 ) )
DbSlExecute: rc = 99
(SQL error 1659)
error message returned by DbSl:
ORA-01659: unable to allocate MINEXTENTS beyond 17 in tablespace PSAPIDS640
(DB) INFO: disconnected from DB
/tmp/sapinst_instdir/ECC_50_ABAP_NUC/DB/SAPAPPL2.log:
(DB) ERROR: DDL statement failed
(CREATE UNIQUE INDEX "T512G~0" ON "T512G" ( "MANDT", "SPRSL", "MOLGA", "FORML", "WINDO", "GRPPE", "KENNZ", "LFDNR" ) TABLESPACE PSAPIDS STORAGE (INITIAL 11615742 NEXT 0000000080K MINEXTENTS 0000000001 MAXEXTENTS 2147483645 PCTINCREASE 0 ) )
DbSlExecute: rc = 99
(SQL error 1659)
error message returned by DbSl:
ORA-01659: unable to allocate MINEXTENTS beyond 4 in tablespace PSAPIDS
(DB) INFO: disconnected from DB
/tmp/sapinst_instdir/ECC_50_ABAP_NUC/DB/SAPSLEXC.log
(DB) ERROR: DDL statement failed
(CREATE INDEX "DDFTX~1" ON "DDFTX" ( "ROLLNAME" ) TABLESPACE PSAPIDS640 STORAGE (INITIAL 52072826 NEXT 0000002560K MINEXTENTS 0000000001 MAXEXTENTS 2147483645 PCTINCREASE 0 ) )
DbSlExecute: rc = 99
(SQL error 1659)
error message returned by DbSl:
ORA-01659: unable to allocate MINEXTENTS beyond 24 in tablespace PSAPIDS640
I think the tablespace is to small. Which commands do I need to extend them? I've alredy tried:
su oraids
sqlplus /nolog
connect / as sysdba
SELECT * FROM DBA_TABLESPACES WHERE TABLESPACE_NAME = 'PSAPIDS';
ALTER TABLESPACE PSAPIDS DEFAULT STORAGE
(INITIAL 11615742 NEXT 0000000080K MINEXTENTS 0000000001 MAXEXTENTS 2347483645 PCTINCREASE 0);
Hope that anybody can help me out. I will publish the installation instructions here on SDN.
Regards
Gregor

Hi Gregor. The text of the Oracle message ORA-01659 is as follows. As you can see it recommends adding a data file first.
01659, 00000, "unable to allocate MINEXTENTS beyond %s in tablespace %s"
// *Cause: Failed to find sufficient contiguous space to allocate MINEXTENTS
//          for the segment being created.
// *Action: Use ALTER TABLESPACE ADD DATAFILE to add additional space to the
//          tablespace or retry with smaller value for MINEXTENTS, NEXT or
//          PCTINCREASE
The syntax for adding a datafile would be
alter tablespace PSAPIDS add datafile '/your/path/psapids99.dbf' size 100m;

Implication of missing makefiles during installation

I was trying to install Oracle 64-bit on Debian at home (test purposes only, therefore, and no official support expected).
The install failed (as expected) with the following errors:
error in invoking target 'agent nmo nmb' of makefile
'u/01/app/oracle/ctx/lib/ins_sysman.mk'.
error in invoking target 'all_no_orcl' of makefile
'u/01/app/oracle/ctx/lib/ins_rdbms.mk'.
Having reviewed every post on these forums I could, I found there to be no way of fixing these errors (not on Debian, at any rate), so I clicked 'ignore' and carried on, simply wondering whether anything at all useful would result.
At the end of the installation process, I have a working 64-bit database, a working Enterprise Manager and -so far as I can tell- working pretty much everything.
So I'm wondering: what is the significance of 'agent nmo nmb' and 'all_no_orcl'? I mean, clearly my installation is fundamentally broken. But not obviously so. Something mustn't be right, though... so what is it? What bit of functionality in Oracle must I attempt to use before I discover the thing is broken?
I'm not asking about how to fix the errors or for comments on the insanity of trying to install Oracle onto Debian 64-bit. It's a strictly quarantined enquiry: what was broken when my two error messages were ignored, since the basic database itself very clearly wasn't?

Well, yes I probably could do all of that, but then there's this mad idea I had that help/support forums might actually offer some help and support instead of telling people asking for help and support that they should "put the time in" to solve their own queries. Makes you wonder what anyone is doing here at all, really, doesn't it?!
I'll say it just one more time then: this thing is referred to quite frequently (those specific errors crop up quite often in various forums, including here, going back to posts in 2003 or therabouts) and so I wondered whether the specifics of what they mean (their consequences) would long since have been worked out by others.
Or does the sum total investigative capability of people installing Oracle onto Linux for the past 6 years amount to "it's broken, let's move on"?
It's actually OK to say, 'no we never bothered to look into it that far'. If that's the "answer" to my question (which it seems to be) then that's informative enough in its own right. But I don't think it's OK to say 'put some time into it and work it out for yourself'. The fact that I posted here is evidence that I am putting my time into it -but that doesn't mean I wouldn't appreciate some informed help at various points if it's available. I'll skip your brand of help in the future though, if that's alright with you.

Linux 10g: large SGA on tmpfs and swap

hello.
i'm try to use large (more than 1,7G) SGA with tmpfs. oracle start-up and starting massive swap (in/out) operation (swap usage about 2G). What oracle placed in swap immediatly after startup ?
PS. SGA size about 2.5G, RAM 4G, swap 4G.
wbr, Dmitry

okay. i'm reboot server and this is result of free command immediatly after reboot:
oxygen:~# free
total used free shared buffers cached
Mem: 3948680 270608 3678072 0 4088 214776
-/+ buffers/cache: 51744 3896936
Swap: 3212920 0 3212920
as you see, server have more than 2.5G free RAM for SGA.
Before buy RHAS, i'm try test Oracle on Debian. /proc/sys/vm/pagecache not found in Debian /proc/sys/vm :(
X not started on server at all, slocate too.

Oracle on debian?

Similar Messages

Maybe you are looking for