Menu
▾
▴
ci-linux-devel — Discussion about Cluster Infrastructure for Linux
You can subscribe to this list here.
| 2001 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
(25) |
Jul
(13) |
Aug
(11) |
Sep
(14) |
Oct
(5) |
Nov
(7) |
Dec
(4) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2002 |
Jan
(14) |
Feb
(10) |
Mar
(30) |
Apr
(9) |
May
(20) |
Jun
(12) |
Jul
(7) |
Aug
(6) |
Sep
(6) |
Oct
(34) |
Nov
(14) |
Dec
(9) |
| 2003 |
Jan
|
Feb
(9) |
Mar
(2) |
Apr
(2) |
May
(5) |
Jun
(14) |
Jul
(1) |
Aug
(7) |
Sep
(6) |
Oct
(5) |
Nov
|
Dec
|
| 2004 |
Jan
|
Feb
(1) |
Mar
(1) |
Apr
|
May
|
Jun
(1) |
Jul
(2) |
Aug
(2) |
Sep
(4) |
Oct
|
Nov
(7) |
Dec
(1) |
| 2005 |
Jan
(1) |
Feb
(2) |
Mar
|
Apr
(4) |
May
(5) |
Jun
|
Jul
|
Aug
|
Sep
(1) |
Oct
|
Nov
|
Dec
|
| 2006 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(11) |
Jun
(2) |
Jul
|
Aug
(5) |
Sep
(5) |
Oct
(1) |
Nov
(1) |
Dec
|
| 2007 |
Jan
|
Feb
(1) |
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2008 |
Jan
(2) |
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2009 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(1) |
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(2) |
Nov
|
Dec
|
| 2011 |
Jan
(1) |
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: Aneesh K. <ane...@gm...> - 2006-05-11 15:37:40
|
On 5/11/06, Aneesh Kumar <ane...@gm...> wrote: > Hi John and Brian, > > What is the specific requirment of using XDR within ICS. ? I see > structures like pt_regs being encoded using ics directly. As per our > last discussion most of these structures are marked OOL. So with XDR > we encode them with XDR routines and out then as OOL data. But then if > all the nodes involved in clustering are of same endian do we need to > encode them using XDR routines ? > After looking at the code again i guess i understand what is happening. For structures carrying pointers to another data type we need the XDR param type. I have dropped from the latest ICS code the openssirpcgen. I am right now looking at NFS and understanding how to do the work the same way they are doing. -aneesh |
|
From: Aneesh K. <ane...@gm...> - 2006-05-11 08:23:05
|
Hi John and Brian, What is the specific requirment of using XDR within ICS. ? I see structures like pt_regs being encoded using ics directly. As per our last discussion most of these structures are marked OOL. So with XDR we encode them with XDR routines and out then as OOL data. But then if all the nodes involved in clustering are of same endian do we need to encode them using XDR routines ? -aneesh |
|
From: Aneesh K. <ane...@gm...> - 2006-05-02 15:48:11
|
On 5/2/06, Greg Freemyer <gre...@gm...> wrote: > > > > What does Red Hat's Cluster Suite use? > > I thought it was cman (cluster manager) and that it had a kernel componen= t. > > Heartbeat from linux-ha is compatible with AIS now. I'm not sure if > AIS is a kernel communication solution that heartbeat can sit above, > or if AIS is a userland capability that heartbeat exports to ais > clients. > That is the membership part. I am looking at using CMAN for the reworked CI. What CI should provide is a framework for writing cluster services without worrying about the transport part. -aneesh |
|
From: Greg F. <gre...@gm...> - 2006-05-02 15:28:34
|
On 5/2/06, Aneesh Kumar <ane...@gm...> wrote: > On 5/2/06, Greg Freemyer <gre...@gm...> wrote: > > > > > > That can be a very political process given the number of projects > > interested in cluster infrastructure. Do you have any reason to think > > upstream will accept CI from openSSI? > > > > > > I don't know of any other project that implement a cluster > infrastructure. OCFS2 uses tcp and GFS uses sctp. That to they do the > entire coding using socket interface. The way i look at it is CI is > what VFS to file system. It allows a transport independent framework > for writing cluster services. > > -aneesh > What does Red Hat's Cluster Suite use? I thought it was cman (cluster manager) and that it had a kernel component. Heartbeat from linux-ha is compatible with AIS now. I'm not sure if AIS is a kernel communication solution that heartbeat can sit above, or if AIS is a userland capability that heartbeat exports to ais clients. Greg -- Greg Freemyer The Norcross Group Forensics for the 21st Century |
|
From: Aneesh K. <ane...@gm...> - 2006-05-02 14:35:38
|
On 5/2/06, Greg Freemyer <gre...@gm...> wrote: > > > That can be a very political process given the number of projects > interested in cluster infrastructure. Do you have any reason to think > upstream will accept CI from openSSI? > > I don't know of any other project that implement a cluster infrastructure. OCFS2 uses tcp and GFS uses sctp. That to they do the entire coding using socket interface. The way i look at it is CI is what VFS to file system. It allows a transport independent framework for writing cluster services. -aneesh |
|
From: Greg F. <gre...@gm...> - 2006-05-02 12:30:07
|
On 5/2/06, Aneesh Kumar <ane...@gm...> wrote: > Hi All, > > I am looking at cleaning up CI code and getting it ready for > submission to upstream. The motivation is to get a transport > independent cluster communication framework. > > You can find more info at > http://kvaneesh.livejournal.com/22205.html > > I have uploaded the work at > http://www.radian.org/~kvaneesh/gitweb.cgi > > the ci-to-linus project. > > Let me know what you think. Also if anybody like to help let me know. > > -aneesh That can be a very political process given the number of projects interested in cluster infrastructure. Do you have any reason to think upstream will accept CI from openSSI? Greg -- Greg Freemyer The Norcross Group Forensics for the 21st Century |
|
From: Aneesh K. <ane...@gm...> - 2006-05-02 05:02:13
|
Hi All, I am looking at cleaning up CI code and getting it ready for submission to upstream. The motivation is to get a transport independent cluster communication framework. You can find more info at http://kvaneesh.livejournal.com/22205.html I have uploaded the work at http://www.radian.org/~kvaneesh/gitweb.cgi the ci-to-linus project. Let me know what you think. Also if anybody like to help let me know. -aneesh |
|
From: Aneesh K. <ane...@gm...> - 2005-09-02 07:10:56
|
I decided to go give git a try.=20 http://debian.openssi.org/ci-linux.git/ BTW git clone won't work with http:// so you may need to use cogito=20 cg clone http://debian.openssi.org/ci-linux.git/ test-ci-linux.git That is the complete project history.=20 -aneesh |
|
From: Brian J. W. <Bri...@hp...> - 2005-05-13 17:32:01
|
Fixed.
Thanks,
Brian
Aneesh Kumar wrote:
> Hi Brian,
>
> The only change we have in this file is covered by CONFIG_SSI. (The
> diff is attached below )
> I guess we can move this file to OpenSSI repository.
>
> -aneesh
>
>
> ------------------------------------------------------------------------
>
> kvaneesh@satan:/home/build/xen/26/ci/kernel/arch/i386/kernel$ cvs diff -u5 -r LINUX-2-6-10 process.c
>
> Index: process.c
> ===================================================================
> RCS file: /cvsroot/ci-linux/ci/kernel/arch/i386/kernel/process.c,v
> retrieving revision 1.1.1.2
> retrieving revision 1.5
> diff -u -5 -r1.1.1.2 -r1.5
> --- process.c 9 Feb 2005 03:14:02 -0000 1.1.1.2
> +++ process.c 24 Mar 2005 19:49:01 -0000 1.5
> @@ -277,10 +277,18 @@
>
> /*
> * Create a kernel thread
> */
> int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
> +#ifdef CONFIG_SSI
> +{
> + return kernel_thread_with_pid(fn, arg, flags, 0);
> +}
> +
> +int kernel_thread_with_pid(int (*fn)(void *), void * arg, unsigned long flags,
> + pid_t pid)
> +#endif
> {
> struct pt_regs regs;
>
> memset(®s, 0, sizeof(regs));
>
> @@ -293,11 +301,16 @@
> regs.eip = (unsigned long) kernel_thread_helper;
> regs.xcs = __KERNEL_CS;
> regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
>
> /* Ok, create the new process.. */
> +#ifdef CONFIG_SSI
> + return __do_fork(flags | IS_KTHREAD | CLONE_VM | CLONE_UNTRACED, 0,
> + ®s, 0, NULL, NULL, pid);
> +#else
> return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL);
> +#endif
> }
>
> /*
> * Free current thread data structures etc..
> */
> kvaneesh@satan:/home/build/xen/26/ci/kernel/arch/i386/kernel$
|
|
From: Aneesh K. <ane...@gm...> - 2005-05-12 10:09:20
|
Hi All,
I got CI working with Xen.=20
The current status is shown by the below command.=20
sarge-xen:~# uname -a=20
Linux sarge-xen 2.6.10-xenU #2 Wed May 11 14:13:58 IST 2005 i686 GNU/Linux
sarge-xen:~# cluster -V
Node 1:
State: UP
Previous state: COMINGUP
Reason for last transition: API
Last transition ID: 2
Last transition time: Wed May 11 14:41:41.865347 2005
First transition ID: 1
First transition time: Wed May 11 14:41:41.835347 2005
Number of CPUs: 1
Number of CPUs online: 1
Node 2:
State: UP
Previous state: COMINGUP
Reason for last transition: API
Last transition ID: 4
Last transition time: Wed May 11 14:41:45.595347 2005
First transition ID: 3
First transition time: Wed May 11 14:41:45.565347 2005
Number of CPUs: 1
Number of CPUs online: 1
sarge-xen:~#=20
node2:/home/kvaneesh# xm list=20
Name Id Mem(MB) CPU State Time(s) Console
Domain-0 0 123 0 r---- 50.8 =20
sarge 3 31 0 -b--- 1.1 9603
sarge-node2 4 31 0 -b--- 1.1 9604
node2:/home/kvaneesh#
|
|
From: SAMPATHKUMAR K. K. <sam...@in...> - 2005-05-11 20:06:34
|
Aneesh, =20 I have been going through Xen as well. I wanted to know: What did it take to get CI working with Xen? =20 Thanks, - Kishore =20 > Hi All, >=20 > I got CI working with Xen.=20 >=20 > The current status is shown by the below command.=20 >=20 > sarge-xen:~# uname -a=20 > Linux sarge-xen 2.6.10-xenU #2 Wed May 11 14:13:58 IST 2005 i686 GNU/Li= nux > sarge-xen:~# cluster -V > Node 1: > State: UP > Previous state: COMINGUP > Reason for last transition: API > Last transition ID: 2 > Last transition time: Wed May 11 14:41:41.865347 2005 > First transition ID: 1 > First transition time: Wed May 11 14:41:41.835347 2005 > Number of CPUs: 1 > Number of CPUs online: 1 > Node 2: > State: UP > Previous state: COMINGUP > Reason for last transition: API > Last transition ID: 4 > Last transition time: Wed May 11 14:41:45.595347 2005 > First transition ID: 3 > First transition time: Wed May 11 14:41:45.565347 2005 > Number of CPUs: 1 > Number of CPUs online: 1 > sarge-xen:~#=20 >=20 > node2:/home/kvaneesh# xm list=20 > Name Id Mem(MB) CPU State Time(s) Console > Domain-0 0 123 0 r---- 50.8 =20 > sarge 3 31 0 -b--- 1.1 9603 > sarge-node2 4 31 0 -b--- 1.1 9604 > node2:/home/kvaneesh# >=20 >=20 > ------------------------------------------------------- > This SF.Net email is sponsored by Oracle Space Sweepstakes > Want to be the first software developer in space? > Enter now for the Oracle Space Sweepstakes! > http://ads.osdn.com/?ad_ids93&alloc_id=16281&op=CCk > _______________________________________________ > Ssic-linux-users mailing list > Ssi...@li... > https://lists.sourceforge.net/lists/listinfo/ssic-linux-users >=20 |
|
From: Brian J. W. <Bri...@hp...> - 2005-05-11 18:58:27
|
Great job, Aneesh! I guess the next steps are to form an OpenSSI/XEN cluster, then to demonstrate process migration on it. Brian Aneesh Kumar wrote: > Hi All, > > I got CI working with Xen. > > The current status is shown by the below command. > > sarge-xen:~# uname -a > Linux sarge-xen 2.6.10-xenU #2 Wed May 11 14:13:58 IST 2005 i686 GNU/Linux > sarge-xen:~# cluster -V > Node 1: > State: UP > Previous state: COMINGUP > Reason for last transition: API > Last transition ID: 2 > Last transition time: Wed May 11 14:41:41.865347 2005 > First transition ID: 1 > First transition time: Wed May 11 14:41:41.835347 2005 > Number of CPUs: 1 > Number of CPUs online: 1 > Node 2: > State: UP > Previous state: COMINGUP > Reason for last transition: API > Last transition ID: 4 > Last transition time: Wed May 11 14:41:45.595347 2005 > First transition ID: 3 > First transition time: Wed May 11 14:41:45.565347 2005 > Number of CPUs: 1 > Number of CPUs online: 1 > sarge-xen:~# > > node2:/home/kvaneesh# xm list > Name Id Mem(MB) CPU State Time(s) Console > Domain-0 0 123 0 r---- 50.8 > sarge 3 31 0 -b--- 1.1 9603 > sarge-node2 4 31 0 -b--- 1.1 9604 > node2:/home/kvaneesh# > > > ------------------------------------------------------- > This SF.Net email is sponsored by Oracle Space Sweepstakes > Want to be the first software developer in space? > Enter now for the Oracle Space Sweepstakes! > http://ads.osdn.com/?ad_ids93&alloc_id281&op=click > _______________________________________________ > Ssic-linux-users mailing list > Ssi...@li... > https://lists.sourceforge.net/lists/listinfo/ssic-linux-users > > |
|
From: Aneesh K. <ane...@gm...> - 2005-05-11 18:52:25
|
Hi Brian,=20 The only change we have in this file is covered by CONFIG_SSI. (The diff is attached below ) I guess we can move this file to OpenSSI repository.=20 -aneesh |
|
From: Brian J. W. <Bri...@hp...> - 2005-04-28 21:03:39
|
BTW, this does not apply to files in the contrib/ directory of the CI or OpenSSI websites. CVS is configured to ignore these directories, so changes to them should be made directly on the web servers. Brian Brian J. Watson wrote: > For a long time, the OpenSSI and CI websites have been under CVS > control. The standard practice for making changes has been to edit the > appropriate files on the web server (which immediately changes what > users see on the website), then commit (checkin) the changes to CVS. > This was not necessarily the best practice, but it was convenient. > > SourceForge has recently made a change preventing "developer" CVS > checkouts from being done on their web servers. Only "anonymous" > checkouts are allowed. What this means is that CVS is now strictly > read-only on the web servers, so we should no longer directly make > changes there. > > Instead, each of us should checkout a local copy of the website on our > own computers under our own developer accounts. Whenever we need to make > changes, do them in this local copy then commit the changes. After that, > login to the web server using the openssi-web account (you already know > the password if you need it) and do a `cvs update' on the website to > place your latest changes online. > > In the next few days, I'll figure out how to add a cron job to > automatically update the website every 15 minutes or so. Then you'll > only need to manually update it if you want to see your changes online > immediately. > > Also, there are a lot of unknown and modified files on the OpenSSI > website that were never properly checked in. In the next few days, I'll > commit them to CVS through my own local checkout of the website. > > Regards, > > Brian > > > ------------------------------------------------------- > SF.Net email is sponsored by: Tell us your software development plans! > Take this survey and enter to win a one-year sub to SourceForge.net > Plus IDC's 2005 look-ahead and a copy of this survey > Click here to start! http://www.idcswdc.com/cgi-bin/survey?id=105hix > _______________________________________________ > ssic-linux-devel mailing list > ssi...@li... > https://lists.sourceforge.net/lists/listinfo/ssic-linux-devel > > |
|
From: Brian J. W. <Bri...@hp...> - 2005-04-28 20:57:05
|
For a long time, the OpenSSI and CI websites have been under CVS control. The standard practice for making changes has been to edit the appropriate files on the web server (which immediately changes what users see on the website), then commit (checkin) the changes to CVS. This was not necessarily the best practice, but it was convenient. SourceForge has recently made a change preventing "developer" CVS checkouts from being done on their web servers. Only "anonymous" checkouts are allowed. What this means is that CVS is now strictly read-only on the web servers, so we should no longer directly make changes there. Instead, each of us should checkout a local copy of the website on our own computers under our own developer accounts. Whenever we need to make changes, do them in this local copy then commit the changes. After that, login to the web server using the openssi-web account (you already know the password if you need it) and do a `cvs update' on the website to place your latest changes online. In the next few days, I'll figure out how to add a cron job to automatically update the website every 15 minutes or so. Then you'll only need to manually update it if you want to see your changes online immediately. Also, there are a lot of unknown and modified files on the OpenSSI website that were never properly checked in. In the next few days, I'll commit them to CVS through my own local checkout of the website. Regards, Brian |
|
From: Brian J. W. <Bri...@hp...> - 2005-04-20 19:55:14
|
Yuck! Duplication. I understand why you had to do this, but I don't like it. It's making me think that perhaps we should spin off a libssi that contains all the OpenSSI-specific libcluster routines and make it part of openssi-tools. Then this source file, which would be part of libssi, could properly depend on <net/ip_vs.h>. Another solution that's uglier, but easier to implement, is to move kernel/include/net/ip_vs.h from the OpenSSI repository to the CI repository, for no reason other than to properly satisfy this dependency. Anybody else have opinions on the matter? Brian Aneesh Kumar K.V wrote: > Update of /cvsroot/ci-linux/ci/cluster-tools/libcluster > In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv3965 > > Modified Files: > Tag: OPENSSI-DEBIAN > set_ipvsportweight.c > Log Message: > fix build break. With CI we don't have ip_vs.h > > > Index: set_ipvsportweight.c > =================================================================== > RCS file: /cvsroot/ci-linux/ci/cluster-tools/libcluster/set_ipvsportweight.c,v > retrieving revision 1.4 > retrieving revision 1.5 > diff -u -d -r1.4 -r1.5 > --- set_ipvsportweight.c 14 Apr 2005 07:26:59 -0000 1.4 > +++ set_ipvsportweight.c 20 Apr 2005 11:36:22 -0000 1.5 > @@ -24,7 +24,10 @@ > #include <netinet/in.h> > #include <arpa/inet.h> > #include <errno.h> > -#include <net/ip_vs.h> > + > +/* SSI_XXX This should match the def in net/ip_vs.h */ > +#define IP_VS_SCHEDNAME_MAXLEN 16 > + > > > /* This should actually go in a header */ > > > > ------------------------------------------------------- > This SF.Net email is sponsored by: New Crystal Reports XI. > Version 11 adds new functionality designed to reduce time involved in > creating, integrating, and deploying reporting solutions. Free runtime info, > new features, or free trial, at: http://www.businessobjects.com/devxi/728 > _______________________________________________ > Ci-linux-checkins mailing list > Ci-...@li... > https://lists.sourceforge.net/lists/listinfo/ci-linux-checkins > > |
|
From: Brian J. W. <Bri...@hp...> - 2005-04-13 01:57:44
|
Sorry if any developers run into a CVS message like the following: cvs update: [01:55:38] waiting for bjbrew's lock in /cvsroot/ci-linux/ci/kernel/kernel I've requested that SourceForge clear my errant lock, which hopefully they'll do by tomorrow. Brian |
|
From: Brian J. W. <Bri...@hp...> - 2005-02-17 00:50:00
|
Hi Binoy, CI is a basic infrastructure for programmers to develop a more complete cluster solution. All it contains is a cluster membership subsystem (CLMS) and an internode communication service (ICS). If what you want to do is build a cluster for your mail solution, then you might want to look at OpenSSI (OpenSSI.org). It includes CI and much, much more for managing your cluster like a single, highly-available machine. Regards, Brian hp wrote: > > > > sir > > i am binoy from india > > could u explain this for using 2 servers ,please explaine it with > sample ip adress,so i can assign ipadress like that,please i am a > newcomer in cluster .i want to make a cluster for a mail solution > > binoy > skylarkinformation technologies > chennai > india > ph:9109840768247 > |
|
From: hp <hp...@sk...> - 2005-02-04 16:46:51
|
sir i am binoy from india could u explain this for using 2 servers ,please explaine it with sampl= e =20 ip adress,so i can assign ipadress like that,please i am a newcomer in =20 cluster .i want to make a cluster for a mail solution binoy skylarkinformation technologies chennai india ph:9109840768247 --=20 Using Opera's revolutionary e-mail client: http://www.opera.com/mail/ |
|
From: Carlos F. <ca...@lf...> - 2005-01-17 15:25:12
|
|
From: Brian J. W. <Bri...@hp...> - 2004-12-08 21:35:20
|
John Byrne wrote: > Roger Tsang wrote: > >> I'm building CI (OPENSSI-RH branch) against OPENSSI >> rpm/linux-fc-2.4.22-1.2199.nptl.tar.bz2 module (OPENSSI-FC branch). >> >> I looked into the CVS tree for ci module. OPENSSI-FC-1-1-1 tag is on the >> OPENSSI-RH branch so I think there is something wrong with that patch or >> with the ci/kernel code. > > > If you are trying to build a SSI kernel, you need to do the "make > fullkern" in the openssi directory. There is no separate ci build/module. I added the ability to build a CI kernel RPM a few months ago. I can't remember why. > I don't know the state of CI. It is frequently not kept up to date to > build separately since we almost always use it as a part of SSI. I replaced the broken CI patches with their corresponding versions from the OpenSSI repository, adjusting context as necessary. Everything applies cleanly, but I'm not certain it will be able to build or run correctly. Feel free to try it out, Roger, if you're interested. As John says, the state of the CI patches don't matter as far as OpenSSI is concerned. It has its own set of kernel patches. > The instructions for building from CVS can be found in > openssi/docs/fedora/devel/INSTALL.cvs in the CVS repository. This document also explains the temporary weirdness of OPENSSI-FC using kernel code from the OPENSSI-RH branch, hence OPENSSI-FC-1-1-1 being on the OPENSSI-RH for all kernel files (and the OPENSSI-FC branch for everything else). OPENSSI-DEBIAN is also using the kernel on the OPENSSI-RH branch. This will change when we start doing the OpenSSI 1.9.x releases with the 2.6.x kernel. Regards, Brian |
|
From: Brian J. W. <Bri...@hp...> - 2004-11-30 22:46:58
|
To the OpenSSI and CI community- As of the next 1.1/1.2 release of OpenSSI, libcluster will be under the LGPL, so that ISVs may link proprietary applications with libcluster to make them cluster-aware, without having to open-source them: http://www.gnu.org/licenses/lgpl.html The rest of OpenSSI and CI will continue to be under the GPL, which requires that all derived work also be open-sourced: http://www.gnu.org/licenses/gpl.html Regards, Brian |
|
From: Aneesh K. K.V <ane...@hp...> - 2004-11-26 15:21:34
|
Eduardo Sanz Martin wrote: > Hello, > > I just check eth1 config file and it was desactived, upss!! > I changed eth1 configuration and I stared cluster_start command and it > works. How can i probe that it is working? use cluster command to find details of nodes in the cluster. You can write small application that use different cluster API's and see what happens when a nodes goes down. You can find the necessary documentation at ci-linux.sf.net page. > > I have a quiestion. I installed CI cluster software on two machines. > Where I can find documentation about how to set up services as NFS > server cluster, BIND server cluster .... because CI cluster software is > just to provide a cluster infrastructure, right? > Thanks, For that you will have to install the OpenSSI packages which you can find on www.openssi.org. > > Eduardo > > > >>Eduardo Sanz Martin wrote: >> >>>Hello, >>> >>>The contents of cluster.conf is: >>> >>>IFCONFIG=eth1:172.16.1.1:255.255.255.224 >>>CLUSTER_MASTER=1:172.16.1.1 >>>CLUSTER_NODENUM=1 >>> >>>I am using the 0.9.9 version. >> >> >>Can you send me the output of below commands >> >>just before you run the cluster_start command. >> >>ifconfig eth1 >>netstat -a >> >> >>-aneesh |
|
From: Eduardo S. M. <ed...@ci...> - 2004-11-26 13:15:32
|
Hello, The contents of cluster.conf is: IFCONFIG=eth1:172.16.1.1:255.255.255.224 CLUSTER_MASTER=1:172.16.1.1 CLUSTER_NODENUM=1 I am using the 0.9.9 version. Eduardo > Eduardo Sanz > Martin wrote: > > Hello, > > > > My system is a cluster pack of DL380 with MSA500 G2. DL380 is two > > processors with Hyperthreading. > > > > I installed CI software and I boot with CI kernel. I got a kernel panic > > just before run cluster_start. > > > > I got this message: > > > > Kernel panic: ics_llunack_open: bind error -99 > > Instruction(i) breakpoint #0 at 0xc0122760 (adjusted) > > 0xc0122760 panic_hook: int3 > > Entering kdb (current=0xf7062000, pid 625) on processor 0 due to > > Breakpoint @ 0xc0122760 > > > > What is the contents of /etc/cluster.conf . Are you used a CVS checked > out code or is this a released version ? > > > -aneesh -- Eduardo Sanz Martin (ed...@ci...) Ingeniero Informatico Fundacion CIDAUT -- Parque Tecnologico de Boecillo, P.209. Boecillo Departamento de Informatica Valladolid 47151 Tlfno.(34)983 54 80 35 Ext.410 Fax. (34) 983 54 80 62 |
|
From: Aneesh K. K.V <ane...@hp...> - 2004-11-26 13:10:31
|
Eduardo Sanz Martin wrote: > Hello, > > My system is a cluster pack of DL380 with MSA500 G2. DL380 is two > processors with Hyperthreading. > > I installed CI software and I boot with CI kernel. I got a kernel panic > just before run cluster_start. > > I got this message: > > Kernel panic: ics_llunack_open: bind error -99 > Instruction(i) breakpoint #0 at 0xc0122760 (adjusted) > 0xc0122760 panic_hook: int3 > Entering kdb (current=0xf7062000, pid 625) on processor 0 due to > Breakpoint @ 0xc0122760 > What is the contents of /etc/cluster.conf . Are you used a CVS checked out code or is this a released version ? -aneesh |
1 message has been excluded from this view by a project administrator.
