From: Richard Cochran <richardcochran@gmail.com>
To: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Cc: Miroslav Lichvar <mlichvar@redhat.com>,
Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>,
netdev@vger.kernel.org, john.stultz@linaro.org,
Richard Cochran <rcochran@linutronix.de>,
jiri@resnulli.us, ivan.briano@intel.com, henrik@austad.us,
jhs@mojatatu.com, levi.pearson@harman.com,
intel-wired-lan@lists.osuosl.org, xiyou.wangcong@gmail.com,
tglx@linutronix.de, anna-maria@linutronix.de
Subject: Re: [Intel-wired-lan] [RFC v2 net-next 01/10] net: Add a new socket option for a future transmit time.
Date: Thu, 25 Jan 2018 18:12:24 -0800 [thread overview]
Message-ID: <20180126021224.cfu632wbghf6blik@localhost> (raw)
In-Reply-To: <87607qzxhb.fsf@intel.com>
On Wed, Jan 24, 2018 at 02:46:24PM -0800, Vinicius Costa Gomes wrote:
> The only robust way that we could think of about keeping the the packets
> in order for the device queue is re-ordering packets in the Qdisc.
Right, but you cannot afford the overhead of the timerqueue when using
HW offload, when the HW device sits on a PCIe bus. Many serious TSN
applications (like industrial controls) will want to have just one
packet queued, readying the next one just in time for the next
deadline. The control loops are sensitive to the feedback interval.
> Even if we reach a decision that the Qdisc should not re-order packets
> (we wouldn't have any dependency on hrtimers in the offload case, as you
> pointed out), we still need hrtimers for the software implementation.
Fine.
> So, I guess, the problem remains, if it's possible for the user to
> express a /dev/ptp* clock, what should we do?
Thinking a bit more, it doesn't make sense to have a user choice for
the HW offloading case. The clock should implicitly be the device
clock, always. Using any other clock would make no sense.
Thanks,
Richard
next prev parent reply other threads:[~2018-01-26 2:12 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-17 23:06 [RFC v2 net-next 00/10] Time based packet transmission Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 01/10] net: Add a new socket option for a future transmit time Jesus Sanchez-Palencia
2018-01-18 8:42 ` [Intel-wired-lan] " Miroslav Lichvar
2018-01-18 17:13 ` Richard Cochran
2018-02-01 0:49 ` Jesus Sanchez-Palencia
2018-02-01 4:16 ` Richard Cochran
2018-02-01 9:27 ` Miroslav Lichvar
2018-02-01 20:55 ` Jesus Sanchez-Palencia
2018-01-23 21:22 ` Vinicius Costa Gomes
2018-01-24 3:04 ` Richard Cochran
2018-01-24 22:46 ` Vinicius Costa Gomes
2018-01-26 2:12 ` Richard Cochran [this message]
2018-02-12 22:39 ` Jesus Sanchez-Palencia
2018-02-13 9:56 ` Miroslav Lichvar
2018-01-18 17:11 ` Richard Cochran
2018-01-23 18:12 ` Jesus Sanchez-Palencia
2018-01-19 21:15 ` Willem de Bruijn
2018-01-20 2:09 ` Richard Cochran
2018-01-25 9:12 ` [Intel-wired-lan] " Miroslav Lichvar
2018-01-25 16:52 ` Richard Cochran
2018-01-23 18:24 ` Jesus Sanchez-Palencia
2018-01-23 20:02 ` Willem de Bruijn
2018-01-17 23:06 ` [RFC v2 net-next 02/10] net: ipv4: raw: Hook into time based transmission Jesus Sanchez-Palencia
2018-01-18 0:28 ` Eric Dumazet
2018-01-17 23:06 ` [RFC v2 net-next 03/10] net: ipv4: udp: " Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 04/10] net: packet: " Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 05/10] net/sched: Allow creating a Qdisc watchdog with other clocks Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 06/10] net/sched: Introduce the TBS Qdisc Jesus Sanchez-Palencia
2018-01-18 13:35 ` Jamal Hadi Salim
2018-01-18 13:44 ` Jamal Hadi Salim
2018-01-23 21:45 ` Jesus Sanchez-Palencia
2018-01-18 17:18 ` Richard Cochran
2018-01-23 22:01 ` Jesus Sanchez-Palencia
2018-01-19 21:18 ` Willem de Bruijn
2018-01-17 23:06 ` [RFC v2 net-next 07/10] igb: Refactor igb_configure_cbs() Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 08/10] igb: Only change Tx arbitration when CBS is on Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 09/10] igb: Refactor igb_offload_cbs() Jesus Sanchez-Palencia
2018-01-17 23:06 ` [RFC v2 net-next 10/10] igb: Add support for TBS offload Jesus Sanchez-Palencia
2018-01-23 5:23 ` [RFC v2 net-next 00/10] Time based packet transmission Richard Cochran
2018-01-23 5:26 ` Richard Cochran
2018-01-23 18:07 ` Jesus Sanchez-Palencia
2018-01-24 1:43 ` Levi Pearson
2018-01-27 0:04 ` Jesus Sanchez-Palencia
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=20180126021224.cfu632wbghf6blik@localhost \
--to=richardcochran@gmail.com \
--cc=anna-maria@linutronix.de \
--cc=henrik@austad.us \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=ivan.briano@intel.com \
--cc=jesus.sanchez-palencia@intel.com \
--cc=jhs@mojatatu.com \
--cc=jiri@resnulli.us \
--cc=john.stultz@linaro.org \
--cc=levi.pearson@harman.com \
--cc=mlichvar@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rcochran@linutronix.de \
--cc=tglx@linutronix.de \
--cc=vinicius.gomes@intel.com \
--cc=xiyou.wangcong@gmail.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox