Hello Kelvin,
Thanks for the reply.

opcontrol --event=CPU_CLK_UNHALTED_P:10000:1:1:1
No such event "CPU_CLK_UNHALTED_P"

I have tried many other events, but the same error comes up.

Error: counter 0 not available nmi_watchdog using this resource ? Try:
opcontrol --deinit
echo 0 > /proc/sys/kernel/nmi_watchdog

What exactly are programmable variants?
Please let me know if  I should include any other log file messages.

Thanks for the help.
Naresh Rapolu.

Kelvin Fong wrote:

Is there a programmable variant of “CPU_CLK_UNHALTED” (possibly “CPU_CLK_UNHALTED_P”), and can you see if that works?

 


From: Naresh Rapolu [mailto:nrapolu@purdue.edu]
Sent: Tuesday, March 23, 2010 2:03 PM
To: oprofile-list@lists.sourceforge.net
Subject: counter 0 not available error on Xeon 5530 dual socket processor

 

Hi,
 
I`ve compiled  kernel  2.6.31-12  from this tree 
git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen.git,  with the 
oprofile options set:
CONFIG_OPROFILE=y
CONFIG_OPROFILE_IBS=y
CONFIG_HAVE_OPROFILE=y
 
But when I try to start ,  I get the following error:
 
opcontrol --start --verbose
Parameters used:
SESSION_DIR /var/lib/oprofile
LOCK_FILE /var/lib/oprofile/lock
SAMPLES_DIR /var/lib/oprofile/samples
CURRENT_SAMPLES_DIR /var/lib/oprofile/samples/current
CPUTYPE i386/core_i7
BUF_SIZE default value
BUF_WATERSHED default value
CPU_BUF_SIZE default value
SEPARATE_LIB 0
SEPARATE_KERNEL 0
SEPARATE_THREAD 0
SEPARATE_CPU 0
CALLGRAPH 0
VMLINUX /usr/src/linux-2.6-xen/vmlinux
KERNEL_RANGE ffffffff81009000,ffffffff81472f77
XENIMAGE /boot/xen-syms-3.4.2
XEN_RANGE ffff828c80100000,ffff828c801cfa9c
Using default event: CPU_CLK_UNHALTED:100000:0:1:1
 
Error: counter 0 not available nmi_watchdog using this resource ? Try:
opcontrol --deinit
echo 0 > /proc/sys/kernel/nmi_watchdog
 
I`ve tried --deinit and setting up again, but of no use.  I`ve also 
tried rebooting with "lapic" option.. but still it was of no use.
 
Configuration :  Oprofile 0.9.5, Xeon 5530 processor. Ubuntu 8.04 LTS
 
 
Any help would be greatly appreciated.
 
Thanks,
Naresh Rapolu.