Corey,
I haev fixed all the issue you noted. I also updated task.c:print_counts()
to print a warning in case count delta turn negative due to scaling errors
due to multiplexing.
On Wed, May 5, 2010 at 12:16 AM, Corey Ashford
wrote:
> I just noticed one other thing. I'm pretty sure the line task
I just noticed one other thing. I'm pretty sure the line task.c:239 is
extraneous. The group leader's fd doesn't need to be initialized to -1.
- Corey
On 5/4/2010 2:53 PM, stephane eranian wrote:
> On Tue, May 4, 2010 at 11:44 PM, Corey Ashford
> wrote:
>> Almost perfect. It worked correctly
On Tue, May 4, 2010 at 11:44 PM, Corey Ashford
wrote:
> Almost perfect. It worked correctly for the first test cases I tried, and
> there's a nice touch on the print that separates groups (I like it!).
> However, when I tried adding the -f switch, just to see what would happen, I
> get this:
Almost perfect. It worked correctly for the first test cases I tried, and
there's a nice touch on the print that separates groups (I like it!). However,
when I tried adding the -f switch, just to see what would happen, I get this:
% ./task -f -e PM_RUN_CYC,PM_CYC -e PM_RUN_CYC,PM_FXU_IDLE,PM_C
On Tue, May 4, 2010 at 11:17 PM, Corey Ashford
wrote:
>
>
> On 5/4/2010 2:13 PM, stephane eranian wrote:
>> Corey,
>>
>> I have not yet pushed the patch, I wanted to get your opinion first.
>
> Push away! it looks good to me.
>
Done, try now.
Thanks for your contribution.
> Thanks,
>
> - Corey
>
On 5/4/2010 2:13 PM, stephane eranian wrote:
> Corey,
>
> I have not yet pushed the patch, I wanted to get your opinion first.
Push away! it looks good to me.
Thanks,
- Corey
--
_
On 5/4/2010 1:25 PM, Stephane Eranian wrote:
> Corey,
>
> I reworked your patch a little bit. I promoted certain helper functions
> to perf_util.h.
>
> I did not really like the extra max_fds parameter to the perf_setup_*().
I was hesitant on that design decision too.. I thought about squirre
Corey,
I reworked your patch a little bit. I promoted certain helper functions
to perf_util.h.
I did not really like the extra max_fds parameter to the perf_setup_*().
I thought it was too much to carry around. Instead, I stash this value
into the fds[] first entry. I kept num_fds as a parameter
