Received-SPF: pass (google.com: domain of linux-kernel+bounces-65012-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Andi Kleen <ak@linux.intel.com>
To: Ben Gainey <ben.gainey@arm.com>
Cc: linux-perf-users@vger.kernel.org,  linux-kernel@vger.kernel.org,
  linux-arm-kernel@lists.infradead.org,  peterz@infradead.org,
  mingo@redhat.com,  acme@kernel.org,  mark.rutland@arm.com,
  alexander.shishkin@linux.intel.com,  jolsa@kernel.org,
  namhyung@kernel.org,  irogers@google.com,  adrian.hunter@intel.com,
  will@kernel.org
Subject: Re: [RFC PATCH 0/2] A mechanism for efficient support for
 per-function metrics
In-Reply-To: <20240123113420.1928154-1-ben.gainey@arm.com> (Ben Gainey's
	message of "Tue, 23 Jan 2024 11:34:18 +0000")
References: <20240123113420.1928154-1-ben.gainey@arm.com>
Date: Wed, 14 Feb 2024 01:55:23 -0800
Message-ID: <87r0hfwet0.fsf@linux.intel.com>
User-Agent: Gnus/5.13 (Gnus v5.13)
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain

Ben Gainey <ben.gainey@arm.com> writes:

> I've been working on an approach to supporting per-function metrics for
> aarch64 cores, which requires some changes to the arm_pmuv3 driver, and
> I'm wondering if this approach would make sense as a generic feature
> that could be used to enable the same on other architectures?
>
> The basic idea is as follows:
>
>  * Periodically sample one or more counters as needed for the chosen
>    set of metrics.
>  * Record a sample count for each symbol so as to identify hot
>    functions.
>  * Accumulate counter totals for each of the counters in each of the
>    metrics *but* only do this where the previous sample's symbol
>    matches the current sample's symbol.

It sounds very similar to what perf script -F +metric already does
(or did if it wasn't broken currently). It would be a straight forward
extension here to add this "same as previous" check.

Of course the feature is somewhat dubious in that it will have a very
strong systematic bias against short functions and even long functions
in some alternating execution patterns. I assume you did some
experiments to characterize this. It would be important
to emphasize this in any documentation.

> For this to work efficiently, it is useful to provide a means to
> decouple the sample window (time over which events are counted) from
> the sample period (time between interesting samples). This patcheset
> modifies the Arm PMU driver to support alternating between two
> sample_period values, providing a simple and inexpensive way for tools
> to separate out the sample period and the sample window. It is expected
> to be used with the cycle counter event, alternating between a long and
> short period and subsequently discarding the counter data for samples
> with the long period. The combined long and short period gives the
> overall sampling period, and the short sample period gives the sample
> window. The symbol taken from the sample at the end of the long period
> can be used by tools to ensure correct attribution as described
> previously. The cycle counter is recommended as it provides fair
> temporal distribution of samples as would be required for the
> per-symbol sample count mentioned previously, and because the PMU can
> be programmed to overflow after a sufficiently short window; this may
> not be possible with software timer (for example). This patch does not
> restrict to only the cycle counter, it is possible there could be other
> novel uses based on different events.

I don't see anything ARM specific with the technique, so if it's done
it should be done generically IMHO


> Cursory testing on a Xeon(R) W-2145 sampling every 300 cycles (without
> the patch) suggests this approach would work for some counters.
> Calculating branch miss rates for example appears to be correct,
> likewise UOPS_EXECUTED.THREAD seems to give something like a sensible
> cycles-per-uop value. On the other hand the fixed function instructions
> counter does not appear to sample correctly (it seems to report either
> very small or very large numbers). No idea whats going on there, so any
> insight welcome...

If you use precise samples with 3p there is a restriction on the periods
that is enforced by the kernel. Non precise or single/double p should
support arbitrary, except that any p is always period + 1.

One drawback of the technique on x86 is that it won't allow multi record
pebs (collecting samples without interrupts), so the overhead might
be intrinsically higher.

-Andi