[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20260124135044.366a313b@robin>
Date: Sat, 24 Jan 2026 13:50:44 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: Tomas Glozar <tglozar@...hat.com>
Cc: Masami Hiramatsu <mhiramat@...nel.org>, Mathieu Desnoyers
<mathieu.desnoyers@...icios.com>, Crystal Wood <crwood@...hat.com>, John
Kacur <jkacur@...hat.com>, Luis Goncalves <lgoncalv@...hat.com>, LKML
<linux-kernel@...r.kernel.org>, Linux Trace Kernel
<linux-trace-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH 0/3] rtla: Synchronize sample collection methods
On Fri, 23 Jan 2026 16:25:31 +0100
Tomas Glozar <tglozar@...hat.com> wrote:
> To enable RTLA to analyze samples consistently, the first patch adds two fields
> to the osnoise:timerlat_sample tracepoint: instances_registered and
> instances_on. During the recording of a timerlat sample, timerlat counts
> how many instances are registered and how many are on, and attaches
> the information to the osnoise:timerlat_sample trace event, which is moved
> to occur after the samples are recorded.
Can't RTLA simply write into trace_marker or trace_marker_raw an event
that states "tracing is now active" and ignore anything before that event.
Heck, it will include a timestamp, so you only need to write once and
ignore any event that occurred before that timestamp.
-- Steve
Powered by blists - more mailing lists