From: Miroslav Lichvar <mlichvar@redhat.com>
To: Rodolfo Giometti <giometti@enneenne.com>
Cc: David Woodhouse <dwmw2@infradead.org>,
Richard Cochran <richardcochran@gmail.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
John Stultz <jstultz@google.com>,
Thomas Gleixner <tglx@kernel.org>,
Stephen Boyd <sboyd@kernel.org>,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
Alexander Gordeev <agordeev@linux.ibm.com>
Subject: Re: [PATCH v4 3/4] pps: Always use ktime_get_snapshot_id() for pps_get_ts()
Date: Thu, 1 Oct 2026 15:14:19 +0200 [thread overview]
Message-ID: <ar5cq0vslvQ00Pek@localhost> (raw)
In-Reply-To: <4afec82e-9e3d-4615-9657-7d467d8dc3e7@enneenne.com>
On Mon, Sep 28, 2026 at 09:58:02AM +0200, Rodolfo Giometti wrote:
> On Sat, 2026-09-26 at 21:38 +0100, David Woodhouse wrote:
> > So yes, the specific code path you're looking at *does* get slightly
> > longer (50ns to the counter read instead of 30ns).
> [...]
> > However, they are *entirely* in the noise, as there's about 600 ns of
> > hardware and 2-4 *microseconds* of software latency before we even get
> > there.
>
> Thanks for measuring it, and on real hardware with a real edge. That
> answers my concern: ~20 ns of constant cost against microseconds of
> latency upstream of the handler is not something PPS can see, and
> trading it for the removal of a non-constant error is the right
> trade.
FWIW, there are some polling versions of the pps-gpio driver (out of
tree), which provide much more stable measurements by trading
interrupts for higher CPU use and where this additional delay might be
visible.
--
Miroslav Lichvar
next prev parent reply other threads:[~2026-10-01 13:14 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-29 20:56 [PATCH v4 0/4] Add ntp_error to clock snapshot, enable NTP_PPS on tickless kernel David Woodhouse
2026-08-29 20:56 ` [PATCH v4 1/4] timekeeping: Apply extrapolated ntp_error to clock snapshots David Woodhouse
2026-08-29 20:57 ` [PATCH v4 2/4] pps: Drop the !NO_HZ_COMMON dependency from NTP_PPS David Woodhouse
2026-09-01 15:35 ` Rodolfo Giometti
2026-09-02 0:13 ` David Woodhouse
2026-09-28 13:37 ` David Woodhouse
2026-09-28 16:41 ` Rodolfo Giometti
2026-09-28 19:28 ` David Woodhouse
2026-09-29 6:33 ` Rodolfo Giometti
2026-09-29 9:32 ` David Woodhouse
2026-09-29 11:48 ` Rodolfo Giometti
2026-09-29 12:02 ` David Woodhouse
2026-09-30 1:28 ` David Woodhouse
2026-09-30 12:57 ` Rodolfo Giometti
2026-09-30 10:37 ` David Woodhouse
2026-09-30 12:57 ` Rodolfo Giometti
2026-09-30 14:05 ` David Woodhouse
2026-09-30 18:24 ` David Woodhouse
2026-10-01 8:20 ` Rodolfo Giometti
2026-10-01 9:08 ` David Woodhouse
2026-08-29 20:57 ` [PATCH v4 3/4] pps: Always use ktime_get_snapshot_id() for pps_get_ts() David Woodhouse
2026-09-01 15:35 ` Rodolfo Giometti
2026-09-01 23:56 ` David Woodhouse
2026-09-26 20:38 ` David Woodhouse
2026-09-28 7:58 ` Rodolfo Giometti
2026-09-28 12:59 ` David Woodhouse
2026-09-28 16:41 ` Rodolfo Giometti
2026-10-01 13:14 ` Miroslav Lichvar [this message]
2026-10-01 15:38 ` David Woodhouse
2026-10-02 7:04 ` Rodolfo Giometti
2026-10-02 9:07 ` David Woodhouse
2026-10-02 12:29 ` David Woodhouse
2026-10-02 13:44 ` David Woodhouse
2026-10-03 11:29 ` David Woodhouse
2026-10-05 9:16 ` Miroslav Lichvar
2026-08-29 20:57 ` [PATCH v4 4/4] [DO NOT MERGE] ptp: ptp_vmclock: Add simulated 1PPS support David Woodhouse
2026-09-01 15:35 ` [PATCH v4 0/4] Add ntp_error to clock snapshot, enable NTP_PPS on tickless kernel Rodolfo Giometti
2026-09-01 23:37 ` David Woodhouse
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ar5cq0vslvQ00Pek@localhost \
--to=mlichvar@redhat.com \
--cc=agordeev@linux.ibm.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=dwmw2@infradead.org \
--cc=edumazet@google.com \
--cc=giometti@enneenne.com \
--cc=jstultz@google.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=richardcochran@gmail.com \
--cc=sboyd@kernel.org \
--cc=tglx@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.