Re: [PATCH v4 2/6] perf record: Get the first sample time and last sample time

From: Jin, Yao
Date: Thu Oct 19 2017 - 18:49:18 EST




On 10/20/2017 4:25 AM, Arnaldo Carvalho de Melo wrote:
Em Thu, Oct 19, 2017 at 05:21:27PM -0300, Arnaldo Carvalho de Melo escreveu:
Em Tue, Oct 03, 2017 at 10:22:34PM +0800, Jin Yao escreveu:
In perf record, it's walked on all samples yet. So it's very easy to get

You're saying that perf record walks all samples always? That only
happens when we generate the build-id table, right? And people disable
that to speed up the process, knowing that some limitations will come
from that, for doing analysis right after running it is mostly OK to
disable the build-id processing.

So either you add a new option that processes all events without doing
build-id processing (and all the locking, struct thread, map, etc
processing it entails) and just looks at the sample->time, and when
build id processing is enabled, just do as you're doing in this patch,
then, at perf report --time you should look to see if those start/end
times were filled in and if not tell that to the user, i.e. that
either --record-time-boundaries (or a better name :-) ) has to be used,
or, that build-id process, with a short explanation that
--record-time-boundaries is a bit cheaper.

- Arnaldo

Hi Arnaldo,

Thanks so much for reminding me that the walking only happens when build-id processing is enabled. Yes, the step is same as what you said so there will be an issue when the build-id processing is disabled.

According to your suggestion, I will provide a new option "--record-time-boundaries" in perf record. If user disables the build-id processing, the perf record will ask user to set the "--record-time-boundaries". If user enables the build-id processing, the perf record will not ask user to set the "--record-time-boundaries".

Also in perf report, if it doesn't see start/end time filled in the perf file header, it will show some information to let user know he should set "--record-time-boundaries" or enable the build-id processing in perf record.

I will provide v5 patch series, maybe some days later.

Thanks
Jin Yao