Re: [PATCH v1 1/2] perf auxtrace: Add 'T' itrace option for timestamp trace

From: Adrian Hunter
Date: Tue Nov 07 2023 - 05:16:40 EST


On 7/11/23 11:48, Leo Yan wrote:
> Hi Adrian,
>
> On Tue, Nov 07, 2023 at 09:19:10AM +0200, Adrian Hunter wrote:
>> On 6/11/23 23:52, Arnaldo Carvalho de Melo wrote:
>>> Em Thu, Oct 19, 2023 at 01:47:15PM +0300, Adrian Hunter escreveu:
>>>> On 14/10/23 10:45, Leo Yan wrote:
>>>>> An AUX trace can contain timestamp, but in some situations, the hardware
>>>>> trace module (e.g. Arm CoreSight) cannot decide the traced timestamp is
>>>>> the same source with CPU's time, thus the decoder can not use the
>>>>> timestamp trace for samples.
>>>>>
>>>>> This patch introduces 'T' itrace option. If users know the platforms
>>>>
>>>> "If users know" <- how would users know? Could the kernel
>>>> or tools also figure it out?
>>>
>>> Adrian, I'm trying to go all the outstanding patches, do you still have
>>> any issues with this series?
>>
>> No, although the question wasn't actually answered. I presume users
>> just have to try the 'T' option and see if it helps.
>
> Sometimes, users are software developers in SoC companies, they can
> know well for the hardware design but are confused why current
> implementation cannot use timestamp trace. This is the main reason
> I sent this patch set.
>
> An example hardware platform is DB410c [1], we know its CoreSight can
> support timestamp trace, but if without this adding option 'T', we
> have no chance to use it due to it its CPU arch is prior to Armv8.4.

perf config might be better than an itrace option, but you decide.

>
> @Arnaldo, since James gave comments in his replying, I will respin new
> patch set and send out. Thanks for popping up this patch set!
>
> Leo
>
> [1] https://developer.qualcomm.com/hardware/dragonboard-410c