* Perf top always show 0.00
@ 2014-04-18 17:00 Frank Li
2014-04-18 17:48 ` Nathan Lynch
2014-04-23 9:15 ` Jason Liu
0 siblings, 2 replies; 5+ messages in thread
From: Frank Li @ 2014-04-18 17:00 UTC (permalink / raw)
To: linux-arm-kernel
I use mx6dq platform. Found below problem.
Run Perf top. First column always 0, but order look like correct.
0.00% perf [.] 0x00049420
0.00% [kernel] [k] kallsyms_expand_symbol.constprop.5
0.00% [kernel] [k] vsnprintf
0.00% [kernel] [k] arch_cpu_idle
0.00% [kernel] [k] format_decode
0.00% [kernel] [k] number.isra.2
0.00% libc-2.19.so [.] strstr
0.00% libc-2.19.so [.] 0x00072498
0.00% libc-2.19.so [.] memchr
0.00% [kernel] [k] _raw_spin_unlock_irqrestore
0.00% [kernel] [k] string.isra.4
0.00% [kernel] [k] strnlen
0.00% libc-2.19.so [.] getdelim
0.00% libc-2.19.so [.] memcpy
0.00% [kernel] [k] lock_acquire
0.00% libc-2.19.so [.] strchr
0.00% libc-2.19.so [.] strcmp
0.00% [kernel] [k] _raw_spin_unlock_irq
0.00% libc-2.19.so [.] __libc_calloc
0.00% libc-2.19.so [.] _IO_feof
0.00% [kernel] [k] pointer.isra.15
^ permalink raw reply [flat|nested] 5+ messages in thread* Perf top always show 0.00
2014-04-18 17:00 Perf top always show 0.00 Frank Li
@ 2014-04-18 17:48 ` Nathan Lynch
2014-04-23 9:15 ` Jason Liu
1 sibling, 0 replies; 5+ messages in thread
From: Nathan Lynch @ 2014-04-18 17:48 UTC (permalink / raw)
To: linux-arm-kernel
On 04/18/2014 12:00 PM, Frank Li wrote:
> I use mx6dq platform. Found below problem.
>
> Run Perf top. First column always 0, but order look like correct.
>
> 0.00% perf [.] 0x00049420
> 0.00% [kernel] [k] kallsyms_expand_symbol.constprop.5
> 0.00% [kernel] [k] vsnprintf
> 0.00% [kernel] [k] arch_cpu_idle
> 0.00% [kernel] [k] format_decode
> 0.00% [kernel] [k] number.isra.2
> 0.00% libc-2.19.so [.] strstr
> 0.00% libc-2.19.so [.] 0x00072498
> 0.00% libc-2.19.so [.] memchr
> 0.00% [kernel] [k] _raw_spin_unlock_irqrestore
> 0.00% [kernel] [k] string.isra.4
> 0.00% [kernel] [k] strnlen
> 0.00% libc-2.19.so [.] getdelim
> 0.00% libc-2.19.so [.] memcpy
> 0.00% [kernel] [k] lock_acquire
> 0.00% libc-2.19.so [.] strchr
> 0.00% libc-2.19.so [.] strcmp
> 0.00% [kernel] [k] _raw_spin_unlock_irq
> 0.00% libc-2.19.so [.] __libc_calloc
> 0.00% libc-2.19.so [.] _IO_feof
> 0.00% [kernel] [k] pointer.isra.15
The PMU is possibly worthless:
http://lists.infradead.org/pipermail/linux-arm-kernel/2012-August/113802.html
http://lists.infradead.org/pipermail/linux-arm-kernel/2013-February/151945.html
^ permalink raw reply [flat|nested] 5+ messages in thread
* Perf top always show 0.00
2014-04-18 17:00 Perf top always show 0.00 Frank Li
2014-04-18 17:48 ` Nathan Lynch
@ 2014-04-23 9:15 ` Jason Liu
2014-04-23 14:26 ` Frank Li
1 sibling, 1 reply; 5+ messages in thread
From: Jason Liu @ 2014-04-23 9:15 UTC (permalink / raw)
To: linux-arm-kernel
Frank,
2014-04-19 1:00 GMT+08:00 Frank Li <lznuaa@gmail.com>:
> I use mx6dq platform. Found below problem.
>
> Run Perf top. First column always 0, but order look like correct.
>
> 0.00% perf [.] 0x00049420
> 0.00% [kernel] [k] kallsyms_expand_symbol.constprop.5
> 0.00% [kernel] [k] vsnprintf
> 0.00% [kernel] [k] arch_cpu_idle
> 0.00% [kernel] [k] format_decode
> 0.00% [kernel] [k] number.isra.2
> 0.00% libc-2.19.so [.] strstr
> 0.00% libc-2.19.so [.] 0x00072498
> 0.00% libc-2.19.so [.] memchr
> 0.00% [kernel] [k] _raw_spin_unlock_irqrestore
> 0.00% [kernel] [k] string.isra.4
> 0.00% [kernel] [k] strnlen
> 0.00% libc-2.19.so [.] getdelim
> 0.00% libc-2.19.so [.] memcpy
> 0.00% [kernel] [k] lock_acquire
> 0.00% libc-2.19.so [.] strchr
> 0.00% libc-2.19.so [.] strcmp
> 0.00% [kernel] [k] _raw_spin_unlock_irq
> 0.00% libc-2.19.so [.] __libc_calloc
> 0.00% libc-2.19.so [.] _IO_feof
> 0.00% [kernel] [k] pointer.isra.15
This issue has been resolved by the following commit:
commit 9dfd005a3f4e1c648cb4aa1dc70604bb370c5e7b
Author: Michael Hudson-Doyle <michael.hudson@linaro.org>
Date: Thu Oct 31 16:47:45 2013 -0700
perf tools: Remove cast of non-variadic function to variadic
commit 53805eca3d89b095062c11a6798689bb0af09216 upstream.
The 4fb71074a570 (perf ui/hist: Consolidate hpp helpers) cset introduced
a cast of percent_color_snprintf to a function pointer type with
varargs. Change percent_color_snprintf to be variadic and remove the
cast.
The symptom of this was all percentages being reported as 0.00% in perf
report --stdio output on the armhf arch.
Signed-off-by: Michael Hudson-Doyle <michael.hudson@linaro.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/87zjppvw7y.fsf at canonical.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Jason Liu
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 5+ messages in thread* Perf top always show 0.00
2014-04-23 9:15 ` Jason Liu
@ 2014-04-23 14:26 ` Frank Li
2014-04-24 4:58 ` Jason Liu
0 siblings, 1 reply; 5+ messages in thread
From: Frank Li @ 2014-04-23 14:26 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Apr 23, 2014 at 4:15 AM, Jason Liu <liu.h.jason@gmail.com> wrote:
> Frank,
>
> 2014-04-19 1:00 GMT+08:00 Frank Li <lznuaa@gmail.com>:
>> I use mx6dq platform. Found below problem.
>>
>> Run Perf top. First column always 0, but order look like correct.
>>
>> 0.00% perf [.] 0x00049420
>> 0.00% [kernel] [k] kallsyms_expand_symbol.constprop.5
>> 0.00% [kernel] [k] vsnprintf
>> 0.00% [kernel] [k] arch_cpu_idle
>> 0.00% [kernel] [k] format_decode
>> 0.00% [kernel] [k] number.isra.2
>> 0.00% libc-2.19.so [.] strstr
>> 0.00% libc-2.19.so [.] 0x00072498
>> 0.00% libc-2.19.so [.] memchr
>> 0.00% [kernel] [k] _raw_spin_unlock_irqrestore
>> 0.00% [kernel] [k] string.isra.4
>> 0.00% [kernel] [k] strnlen
>> 0.00% libc-2.19.so [.] getdelim
>> 0.00% libc-2.19.so [.] memcpy
>> 0.00% [kernel] [k] lock_acquire
>> 0.00% libc-2.19.so [.] strchr
>> 0.00% libc-2.19.so [.] strcmp
>> 0.00% [kernel] [k] _raw_spin_unlock_irq
>> 0.00% libc-2.19.so [.] __libc_calloc
>> 0.00% libc-2.19.so [.] _IO_feof
>> 0.00% [kernel] [k] pointer.isra.15
>
> This issue has been resolved by the following commit:
>
> commit 9dfd005a3f4e1c648cb4aa1dc70604bb370c5e7b
> Author: Michael Hudson-Doyle <michael.hudson@linaro.org>
> Date: Thu Oct 31 16:47:45 2013 -0700
>
> perf tools: Remove cast of non-variadic function to variadic
>
> commit 53805eca3d89b095062c11a6798689bb0af09216 upstream.
>
> The 4fb71074a570 (perf ui/hist: Consolidate hpp helpers) cset introduced
> a cast of percent_color_snprintf to a function pointer type with
> varargs. Change percent_color_snprintf to be variadic and remove the
> cast.
>
> The symptom of this was all percentages being reported as 0.00% in perf
> report --stdio output on the armhf arch.
>
> Signed-off-by: Michael Hudson-Doyle <michael.hudson@linaro.org>
> Acked-by: Namhyung Kim <namhyung@kernel.org>
> Acked-by: Will Deacon <will.deacon@arm.com>
> Cc: Jean Pihet <jean.pihet@linaro.org>
> Cc: Jiri Olsa <jolsa@redhat.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Link: http://lkml.kernel.org/r/87zjppvw7y.fsf at canonical.com
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>
>
> Jason Liu
I tested it. still 0.00%
0.00% perf [.] 0x000494a0
0.00% [kernel] [k] cpuidle_enter_state
0.00% [kernel] [k] kallsyms_expand_symbol.constprop.7
0.00% libc-2.19.so [.] 0x0006f6a4
0.00% [kernel] [k] vsnprintf
0.00% libc-2.19.so [.] strstr
0.00% [kernel] [k] format_decode
0.00% libc-2.19.so [.] memchr
0.00% [kernel] [k] number.isra.2
0.00% libc-2.19.so [.] memcpy
0.00% libc-2.19.so [.] getdelim
0.00% libc-2.19.so [.] __libc_calloc
0.00% [kernel] [k] _raw_spin_unlock_irq
0.00% libc-2.19.so [.] strchr
0.00% [kernel] [k] strnlen
0.00% [kernel] [k] _raw_spin_unlock_irqrestore
0.00% libc-2.19.so [.] strcmp
0.00% [kernel] [k] __do_softirq
0.00% [kernel] [k] string.isra.4
0.00% libc-2.19.so [.] _IO_feof
0.00% [kernel] [k] tick_nohz_idle_enter
>>
>> _______________________________________________
>> linux-arm-kernel mailing list
>> linux-arm-kernel at lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 5+ messages in thread* Perf top always show 0.00
2014-04-23 14:26 ` Frank Li
@ 2014-04-24 4:58 ` Jason Liu
0 siblings, 0 replies; 5+ messages in thread
From: Jason Liu @ 2014-04-24 4:58 UTC (permalink / raw)
To: linux-arm-kernel
2014-04-23 22:26 GMT+08:00 Frank Li <lznuaa@gmail.com>:
> On Wed, Apr 23, 2014 at 4:15 AM, Jason Liu <liu.h.jason@gmail.com> wrote:
>> Frank,
>>
>> 2014-04-19 1:00 GMT+08:00 Frank Li <lznuaa@gmail.com>:
>>> I use mx6dq platform. Found below problem.
>>>
>>> Run Perf top. First column always 0, but order look like correct.
>>>
>>> 0.00% perf [.] 0x00049420
>>> 0.00% [kernel] [k] kallsyms_expand_symbol.constprop.5
>>> 0.00% [kernel] [k] vsnprintf
>>> 0.00% [kernel] [k] arch_cpu_idle
>>> 0.00% [kernel] [k] format_decode
>>> 0.00% [kernel] [k] number.isra.2
>>> 0.00% libc-2.19.so [.] strstr
>>> 0.00% libc-2.19.so [.] 0x00072498
>>> 0.00% libc-2.19.so [.] memchr
>>> 0.00% [kernel] [k] _raw_spin_unlock_irqrestore
>>> 0.00% [kernel] [k] string.isra.4
>>> 0.00% [kernel] [k] strnlen
>>> 0.00% libc-2.19.so [.] getdelim
>>> 0.00% libc-2.19.so [.] memcpy
>>> 0.00% [kernel] [k] lock_acquire
>>> 0.00% libc-2.19.so [.] strchr
>>> 0.00% libc-2.19.so [.] strcmp
>>> 0.00% [kernel] [k] _raw_spin_unlock_irq
>>> 0.00% libc-2.19.so [.] __libc_calloc
>>> 0.00% libc-2.19.so [.] _IO_feof
>>> 0.00% [kernel] [k] pointer.isra.15
>>
>> This issue has been resolved by the following commit:
>>
>> commit 9dfd005a3f4e1c648cb4aa1dc70604bb370c5e7b
>> Author: Michael Hudson-Doyle <michael.hudson@linaro.org>
>> Date: Thu Oct 31 16:47:45 2013 -0700
>>
>> perf tools: Remove cast of non-variadic function to variadic
>>
>> commit 53805eca3d89b095062c11a6798689bb0af09216 upstream.
>>
>> The 4fb71074a570 (perf ui/hist: Consolidate hpp helpers) cset introduced
>> a cast of percent_color_snprintf to a function pointer type with
>> varargs. Change percent_color_snprintf to be variadic and remove the
>> cast.
>>
>> The symptom of this was all percentages being reported as 0.00% in perf
>> report --stdio output on the armhf arch.
>>
>> Signed-off-by: Michael Hudson-Doyle <michael.hudson@linaro.org>
>> Acked-by: Namhyung Kim <namhyung@kernel.org>
>> Acked-by: Will Deacon <will.deacon@arm.com>
>> Cc: Jean Pihet <jean.pihet@linaro.org>
>> Cc: Jiri Olsa <jolsa@redhat.com>
>> Cc: Will Deacon <will.deacon@arm.com>
>> Link: http://lkml.kernel.org/r/87zjppvw7y.fsf at canonical.com
>> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
>> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>>
>>
>> Jason Liu
>
> I tested it. still 0.00%
> 0.00% perf [.] 0x000494a0
> 0.00% [kernel] [k] cpuidle_enter_state
> 0.00% [kernel] [k] kallsyms_expand_symbol.constprop.7
> 0.00% libc-2.19.so [.] 0x0006f6a4
> 0.00% [kernel] [k] vsnprintf
> 0.00% libc-2.19.so [.] strstr
> 0.00% [kernel] [k] format_decode
> 0.00% libc-2.19.so [.] memchr
> 0.00% [kernel] [k] number.isra.2
> 0.00% libc-2.19.so [.] memcpy
> 0.00% libc-2.19.so [.] getdelim
> 0.00% libc-2.19.so [.] __libc_calloc
> 0.00% [kernel] [k] _raw_spin_unlock_irq
> 0.00% libc-2.19.so [.] strchr
> 0.00% [kernel] [k] strnlen
> 0.00% [kernel] [k] _raw_spin_unlock_irqrestore
> 0.00% libc-2.19.so [.] strcmp
> 0.00% [kernel] [k] __do_softirq
> 0.00% [kernel] [k] string.isra.4
> 0.00% libc-2.19.so [.] _IO_feof
> 0.00% [kernel] [k] tick_nohz_idle_enter
>
Here is my log:
root at imx6qdlsolo:/# perf --version
perf version 3.10.31
root at imx6qdlsolo:/# perf top
PerfTop: 66 irqs/sec kernel:78.8% exact: 0.0% [4000Hz
cycles], (all, 1 CPU)
-------------------------------------------------------------------------------
21.95% perf [.] 0x00025b44
13.73% [kernel] [k] cpuidle_enter_state
5.32% libc-2.19.so [.] strstr
4.64% libc-2.19.so [.] 0x000725d0
3.61% [kernel] [k] _raw_spin_unlock_irqrestore
2.78% libc-2.19.so [.] __libc_calloc
2.41% libc-2.19.so [.] strcmp
2.29% libbfd-2.24.so [.] 0x000819d0
2.17% libc-2.19.so [.] memchr
2.11% libc-2.19.so [.] strchr
1.94% [kernel] [k] finish_task_switch
1.81% [kernel] [k] kallsyms_expand_symbol.constprop.7
1.57% [kernel] [k] vsnprintf
1.46% [kernel] [k] __do_softirq
1.43% libc-2.19.so [.] strlen
1.35% libc-2.19.so [.] vfprintf
1.26% libc-2.19.so [.] strncmp
1.22% [kernel] [k] format_decode
1.21% [kernel] [k] number.isra.2
1.12% libc-2.19.so [.] memset
1.07% libc-2.19.so [.] memcpy
You can try 3.10.31 release branch.
Jason Liu
>>>
>>> _______________________________________________
>>> linux-arm-kernel mailing list
>>> linux-arm-kernel at lists.infradead.org
>>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2014-04-24 4:58 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-04-18 17:00 Perf top always show 0.00 Frank Li
2014-04-18 17:48 ` Nathan Lynch
2014-04-23 9:15 ` Jason Liu
2014-04-23 14:26 ` Frank Li
2014-04-24 4:58 ` Jason Liu
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.