Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230716193000.231406-1-costa.shul@redhat.com> <9b212c49-ab51-0cd9-5871-c145c5f41b48@kernel.org>
In-Reply-To: <9b212c49-ab51-0cd9-5871-c145c5f41b48@kernel.org>
From:   Costa Shulyupin <costa.shul@redhat.com>
Date:   Sat, 22 Jul 2023 11:04:29 +0300
Message-ID: <CADDUTFx+tfdkLp=wp-XH-U1iB3ZM90W=ktbR4ckp62pDmUGPMg@mail.gmail.com>
Subject: Re: [PATCH] tracing/timerlat: Add latency threshold
To:     Daniel Bristot de Oliveira <bristot@kernel.org>
Cc:     linux-rt-users@vger.kernel.org,
        Steven Rostedt <rostedt@goodmis.org>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Jonathan Corbet <corbet@lwn.net>,
        "open list:TRACING" <linux-kernel@vger.kernel.org>,
        "open list:TRACING" <linux-trace-kernel@vger.kernel.org>,
        "open list:DOCUMENTATION" <linux-doc@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> rtla timerlat has the --aa-only that ignores the trace until
> the tracing stops, and then do the auto-analysis based on the
> tail of the trace.

> So, as I said, I am not convinced that adding this interface file is
> better than setting the stop-tracing option... and then waiting for
> the trace to stop... parsing only the tail of the buffer.

I see. Stop-tracing option of rtla timerlat solves the problem for
most of the cases.

Thank you very much!
Costa