Hi,
i'd like to know how much time does linux kernel run with disabled
interrupts. So i would like to remap the instructions capable of
disabling interrupt to other ones which count how much this time is...
Does already exist a patch or tool capable to give me a magnitude
order of the time spent by the kernel with disables interrupts?
In uniprocessor systems, can i state that the only instruction capable
of disabling interrupts is cli?
Thank u very much
Francesco Oppedisano
On Wed, 2005-04-20 at 18:05 +0000, Francesco Oppedisano wrote:
> Hi,
> i'd like to know how much time does linux kernel run with disabled
> interrupts. So i would like to remap the instructions capable of
> disabling interrupt to other ones which count how much this time is...
> Does already exist a patch or tool capable to give me a magnitude
> order of the time spent by the kernel with disables interrupts?
http://people.redhat.com/mingo/realtime-preempt
Lee
On Wed, 20 Apr 2005, Francesco Oppedisano wrote:
> Hi,
> i'd like to know how much time does linux kernel run with disabled
> interrupts. So i would like to remap the instructions capable of
> disabling interrupt to other ones which count how much this time is...
> Does already exist a patch or tool capable to give me a magnitude
> order of the time spent by the kernel with disables interrupts?
> In uniprocessor systems, can i state that the only instruction capable
> of disabling interrupts is cli?
>
How do you propose to "remap" the CLI instruction? The kernel
isn't going to trap on this perfectly legal instruction in
kernel mode.
Also, interrupts can be disabled by masking them off in the
controller(s) so there are many ways that any/all interrupts
can be disabled.
> Thank u very much
>
> Francesco Oppedisano
> -
Cheers,
Dick Johnson
Penguin : Linux version 2.6.11 on an i686 machine (5537.79 BogoMips).
Notice : All mail here is now cached for review by Dictator Bush.
98.36% of all statistics are fiction.