uni-processor kernel on SMP machine
I attempted to boot a 2.4.0-test9 kernel compiled without SMP support on an MP Lion, but it would not boot. I did the same experiemnt with older kernels and it appears this broke between test7 and test8. Has anyone else noticed this? Is there a work around / solution?
I noticed the problem on both a 2-way lion w/ B1 cpus and a 4-way lion with A2 cpus.
Thanks,
Pat
Signature · 2 lines
Patrick O'Rourke [email protected]
Both UP and SMP kernels (2.4.0-test9) work fine on at least two 4-way Lions (A2-stepping CPUs each with latest and a bit old firmware) at our site. Can you be more specific about the problem you are seeing?
Quoted 13 lines · Pat O'Rourke
I attempted to boot a 2.4.0-test9 kernel compiled without SMP support on an MP Lion, but it would not boot. I did the same experiemnt with older kernels and it appears this broke between test7 and test8. Has anyone else noticed this? Is there a work around / solution?
I noticed the problem on both a 2-way lion w/ B1 cpus and a 4-way lion with A2 cpus.
Thanks,
Pat
Signature · 4 lines
Jun U Nakajima Core OS Development SCO/Murray Hill, NJ Email: [email protected], Phone: 908-790-2352 Fax: 908-790-2426
In my case I am having problems with the B0 stepping procs...
Should the B-step and the A-step kernel choices BOTH be set?
--ken
Quoted 36 lines
-----Original Message-----
From: Jun Nakajima [SMTP:[email protected]]
Sent: Tuesday, October 17, 2000 1:34 PM
To: Pat O'Rourke
Cc: [email protected]
Subject: Re: [Linux-ia64] uni-processor kernel on SMP machineBoth UP and SMP kernels (2.4.0-test9) work fine on at least two 4-way Lions (A2-stepping CPUs each with latest and a bit old firmware) at our site. Can you be more specific about the problem you are seeing?
Quoted 13 lines · Pat O'Rourke
I attempted to boot a 2.4.0-test9 kernel compiled without SMP support on an MP Lion, but it would not boot. I did the same experiemnt with older kernels and it appears this broke between test7 and test8. Has anyone else noticed this? Is there a work around / solution?
I noticed the problem on both a 2-way lion w/ B1 cpus and a 4-way lion with A2 cpus.
Thanks,
Pat
Signature · 9 lines
Jun U Nakajima Core OS Development SCO/Murray Hill, NJ Email: [email protected], Phone: 908-790-2352 Fax: 908-790-2426 _______________________________________________ Linux-IA64 mailing list [email protected] http://lists.linuxia64.org/lists/listinfo/linux-ia64
Quoted 3 lines
Both UP and SMP kernels (2.4.0-test9) work fine on at least two 4-way Lions (A2-stepping CPUs each with latest and a bit old firmware) at our site. Can you be more specific about the problem you are seeing?
The system appears to hang right after printing "POSIX conformance testing by UNIFIX", i.e. just before the creation of the init thread. The kernel is pretty locked up, alt-sysrq doesn't work. I have not really tried to debug it yet, so that is about all I can say at the moment.
Pat
Signature · 2 lines
Patrick O'Rourke [email protected]
Are you using a kernel with ptc.g enabled? A problem similar to the one you are seeing has shown up B1-based systems running kernels that include ptc.g. Thanks,
Chris
-----Original Message-----
From: Pat O'Rourke [mailto:[email protected]]
Sent: Wednesday, October 18, 2000 6:23 AM
To: Jun Nakajima
Cc: [email protected]
Subject: Re: [Linux-ia64] uni-processor kernel on SMP machine
Quoted 3 lines
Both UP and SMP kernels (2.4.0-test9) work fine on at least two 4-way Lions (A2-stepping CPUs each with latest and a bit old firmware) at our site. Can you be more specific about the problem you are seeing?
The system appears to hang right after printing "POSIX conformance testing by UNIFIX", i.e. just before the creation of the init thread. The kernel is pretty locked up, alt-sysrq doesn't work. I have not really tried to debug it yet, so that is about all I can say at the moment.
Pat
Signature · 9 lines
Patrick O'Rourke [email protected] _______________________________________________ Linux-IA64 mailing list [email protected] http://lists.linuxia64.org/lists/listinfo/linux-ia64
Quoted 3 lines
Are you using a kernel with ptc.g enabled? A problem similar to the one you are seeing has shown up B1-based systems running kernels that include ptc.g. Thanks,
Yes.
It turns out the kernels I was having the problem with were being cross compiled whereas if I built it natively the problem went away. Both the cross compiler and native toolchain report their version as 2.9-ia64-000216-final.
FWIW,
Pat
Signature · 2 lines
Patrick O'Rourke [email protected]