Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <CAP045Ap6Mm+r_44YmxNbz6HWtYArg3SAFgzk4Cm_K5HRJaRG7w@mail.gmail.com>
 <20181120194129.GC13936@tassilo.jf.intel.com> <CAP045ApoZamGdgVd=-MJE52rUU5hnOg=j95B1WV2x_bVtRQpWA@mail.gmail.com>
 <20181120201144.GD13936@tassilo.jf.intel.com> <20181120221642.GE2131@hirez.programming.kicks-ass.net>
 <20181120222549.GA2149@hirez.programming.kicks-ass.net> <20181120223854.GH13936@tassilo.jf.intel.com>
 <20181121081420.GF2131@hirez.programming.kicks-ass.net>
In-Reply-To: <20181121081420.GF2131@hirez.programming.kicks-ass.net>
From:   Kyle Huey <me@kylehuey.com>
Date:   Tue, 27 Nov 2018 14:08:46 -0800
Message-ID: <CAP045AqRs4+F5rNKXLYHeuvLCvzd9U=eZY0X0NnHXxz3qk9TUw@mail.gmail.com>
Subject: Re: [REGRESSION] x86, perf: counter freezing breaks rr
To:     "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc:     Andi Kleen <ak@linux.intel.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Ingo Molnar <mingo@kernel.org>,
        "Robert O'Callahan" <robert@ocallahan.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Arnaldo Carvalho de Melo <acme@redhat.com>,
        Jiri Olsa <jolsa@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Stephane Eranian <eranian@google.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Vince Weaver <vincent.weaver@maine.edu>, acme@kernel.org,
        open list <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Nov 21, 2018 at 12:14 AM Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Tue, Nov 20, 2018 at 02:38:54PM -0800, Andi Kleen wrote:
> > > In fact, I'll argue FREEZE_ON_OVERFLOW is unfixably broken for
> > > independent counters, because while one counter overflows, we'll stall
> > > counting on all others until we've handled the PMI.
> > >
> > > Even though the PMI might not be for them and they very much want/need
> > > to continue counting.
> >
> > We stop all counters in any case for the PMI. With freeze-on-PMI it just
> > happens slightly earlier.
>
> Hiding the PMI is fine and good. The PMI is not the workload. Stopping
> it earlier is _NOT_ good, it hides your actual workload.

It does seem that FREEZE_PERFMON_ON_PMI (misnamed as it is) is of
rather limited use (or even negative, in our case) to a counter that's
already restricted to ring 3.

- Kyle