[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240716090443.GQ14400@noisy.programming.kicks-ass.net>
Date: Tue, 16 Jul 2024 11:04:43 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Rik van Riel <riel@...riel.com>
Cc: "Paul E. McKenney" <paulmck@...nel.org>, linux-kernel@...r.kernel.org,
kernel-team@...a.com, neeraj.upadhyay@...nel.org, mingo@...nel.org,
rostedt@...dmis.org, Leonardo Bras <leobras@...hat.com>
Subject: Re: [PATCH] smp: print only local CPU info when sched_clock goes
backward
On Mon, Jul 15, 2024 at 01:49:41PM -0400, Rik van Riel wrote:
> About 40% of all csd_lock warnings observed in our fleet appear to
> be due to sched_clock() going backward in time (usually only a little
> bit), resulting in ts0 being larger than ts2.
>
> When the local CPU is at fault, we should print out a message reflecting
> that, rather than trying to get the remote CPU's stack trace.
>
> Signed-off-by: Rik van Riel <riel@...riel.com>
> ---
> kernel/smp.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/kernel/smp.c b/kernel/smp.c
> index f085ebcdf9e7..5656ef63ea82 100644
> --- a/kernel/smp.c
> +++ b/kernel/smp.c
> @@ -237,6 +237,14 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
> if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0))
> return false;
>
> + if (ts0 > ts2) {
> + /* Our own sched_clock went backward; don't blame another CPU. */
> + ts_delta = ts0 - ts2;
> + pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta);
> + *ts1 = ts2;
> + return false;
> + }
So I've seen some chatter about this on IRC and was WTF, seeing this
patch I'm still WTF. What is going on with those machines?!?!
Powered by blists - more mailing lists