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;
Subject: Re: [PATCH 2/2] sched/debug: add sched_update_nr_running tracepoint
To:     Peter Zijlstra <peterz@infradead.org>,
        =?UTF-8?B?UmFkaW0gS3LEjW3DocWZ?= <rkrcmar@redhat.com>
Cc:     linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Andy Lutomirski <luto@kernel.org>,
        =?UTF-8?Q?Jirka_Hladk=c3=bd?= <jhladky@redhat.com>,
        =?UTF-8?B?SmnFmcOtIFZvesOhcg==?= <jvozar@redhat.com>,
        x86@kernel.org
References: <20190903154340.860299-1-rkrcmar@redhat.com>
 <20190903154340.860299-3-rkrcmar@redhat.com>
 <20190904131309.GS2332@hirez.programming.kicks-ass.net>
From:   Valentin Schneider <valentin.schneider@arm.com>
Message-ID: <07518d3f-cfa8-d6a5-2a13-4d8a7457ee15@arm.com>
Date:   Wed, 4 Sep 2019 14:21:48 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.8.0
MIME-Version: 1.0
In-Reply-To: <20190904131309.GS2332@hirez.programming.kicks-ass.net>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 04/09/2019 14:13, Peter Zijlstra wrote:
> On Tue, Sep 03, 2019 at 05:43:40PM +0200, Radim Krčmář wrote:
> 
>> Red Hat adapted one of them for the tracepoint framework and created a
>> tool to plot a heatmap of nr_running, where the sched_update_nr_running
>> tracepoint is being used for fine grained monitoring of scheduling
>> imbalance.
> 
> You should be able to reconstruct this from wakeup and switch
> tracepoints.
> 
> 

I never tried to do it myself but know some folks around me gave it a go
(Morten, Qais and maybe even Chris). I can't remember the exact details but
there was something about not getting the right input - duplicated wakeups,
or no migration information (I think sched_migrate doesn't cover all of the
cases) so the information you're building diverges as time progresses.