Re: [PATCH v2] perf doc: Document ring buffer mechanism

From: Leo Yan
Date: Fri Aug 04 2023 - 05:14:19 EST


On Thu, Aug 03, 2023 at 05:53:29PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Fri, Aug 04, 2023 at 12:56:36AM +0800, Leo Yan escreveu:
> > Hi Jon,
> >
> > On Thu, Aug 03, 2023 at 08:34:50AM -0600, Jonathan Corbet wrote:
> > > Leo Yan <leo.yan@xxxxxxxxxx> writes:
> > >
> > > > In the Linux perf tool, the ring buffer serves not only as a medium for
> > > > transferring PMU event data but also as a vital mechanism for hardware
> > > > tracing using technologies like Intel PT and Arm CoreSight, etc.
> > > >
> > > > Consequently, the ring buffer mechanism plays a crucial role by ensuring
> > > > high throughput for data transfer between the kernel and user space
> > > > while avoiding excessive overhead caused by the ring buffer itself.
> > > >
> > > > This commit documents the ring buffer mechanism in detail. It provides
> > > > an in-depth explanation of the implementation of both the generic ring
> > > > buffer and the AUX ring buffer. Additionally, it covers how these ring
> > > > buffers support various tracing modes and explains the synchronization
> > > > with memory barriers.
> > > >
> > > > Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
> > > > ---
> > >
> > > So this seems like good material from a very brief scan. I do have to
> > > ask, though: why is it not in RST, and why not put it into the
> > > user-space API book?
> >
> > This documentation is Perf related topic, so my instinct is to place
> > it into the folder tools/perf/Documentation/.
> >
> > Strictly to say, the doc doesn't give formal introduction for the
> > user-space APIs. Given perf ring buffer is a mechanism for exchanging
> > data between the kernel and user space, I am open for placing it in the
> > folder Documentation/userspace-api/.
> >
> > I would like get opinions from the perf maintainers if possible, if we
> > have agreenment I am glad to convert it to RST format.
>
> Yeah, I agree with Jon.

Okay, I will spin a new patch based on this discussion.

Thanks for confirmation.

Leo