[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231003163300.GF1539@noisy.programming.kicks-ass.net>
Date: Tue, 3 Oct 2023 18:33:00 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Andi Kleen <ak@...ux.intel.com>
Cc: "Liang, Kan" <kan.liang@...ux.intel.com>, mingo@...hat.com,
acme@...nel.org, linux-kernel@...r.kernel.org,
mark.rutland@....com, alexander.shishkin@...ux.intel.com,
jolsa@...nel.org, namhyung@...nel.org, irogers@...gle.com,
adrian.hunter@...el.com, eranian@...gle.com,
alexey.v.bayduraev@...ux.intel.com, tinghao.zhang@...el.com,
Sandipan Das <sandipan.das@....com>,
Ravi Bangoria <ravi.bangoria@....com>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>
Subject: Re: [RESEND PATCH V3 1/6] perf: Add branch stack extra
On Tue, Oct 03, 2023 at 08:06:59AM -0700, Andi Kleen wrote:
> > I'm thinking we should do something like expose branch_counter_nr and
> > branch_counter_width in the sysfs node, and then rename this extra field
> > to counters.
> >
> > Then userspace can do something like:
> >
> > for (i = 0; i < branch_counter_nr; i++) {
> > counter[i] = counters & ((1 << branch_counter_width) - 1);
> > counters >>= branch_counter_width;
> > }
> >
> > to extract the actual counter values.
>
> perf script/report won't necessarily have access to the sysfs
> values if they run on a different system
>
> It would need extra PT style metadata written by perf record to
> perf.data and read by the user tools.
>
> Seems complicated. It would be better if it just parsed on its own.
Well, you really don't want to repeat the 4,2 thing in every event, that
seems daft (and a waste of space, because how large do we want those
fields to be etc..).
We don't really have a better place for these sorts of things. And yeah,
the PT thing sets precedent here.
Powered by blists - more mailing lists