Re: Wrong Perf Backtraces

Thanks.
I checked "perf script -D", and it contains repeated addresses in 
itself. The problem seems to occur at the sampling instant. Does anybody 
know the location of the sampling handler?
I am looking forward to the answer.
Regards.

On 2020-03-31 20:40, Arnaldo Carvalho de Melo wrote:

> Em Tue, Mar 31, 2020 at 05:29:17PM +0200, Milian Wolff escreveu: On 
> Dienstag, 31. März 2020 17:02:37 CEST ahmadkhorrami wrote: Hi Milian,
> Thanks for the detailed answer. Well, the bug you mentioned is bad 
> news.
> Because I sample using uppp. Perhaps this leads to these weird traces.
> Please read the full thread from here on:
> 
> https://lkml.org/lkml/2018/11/2/86
> 
> But as I said - it should be easy to check if this is really the issue 
> are
> running into or not: Try to see if you see the problem when you sample 
> without
> `ppp`. If not, then you can be pretty sure it's this issue. If you 
> still see
> it, then it's something different.
> 
> Is this a purely software bug?
> I wouldn't call it that, personally. Rather, it's a limitation in the 
> hardware
> and software. We would need something completely different to "fix" 
> this, i.e.
> something like a deeper LBR. That's btw another alternative you could 
> try:
> `perf record --call-graph lbr` and live with the short call stacks. But 
> at
> least these should be correct (afaik). For me personally they are 
> always far
> too short and thus not practical to use in reality.

Probably this may help:

   From: Kan Liang <[email protected]>
   Subject: [PATCH V4 00/17] Stitch LBR call stack (Perf Tools)
   Date: Thu, 19 Mar 2020 13:25:00 -0700
   
https://lore.kernel.org/lkml/[email protected]/

- Arnaldo