From: Fred Klassen <fklassen@appneta.com>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>,
Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>,
Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
Shuah Khan <shuah@kernel.org>,
Network Development <netdev@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-kselftest@vger.kernel.org,
Willem de Bruijn <willemb@google.com>
Subject: Re: [PATCH net 1/4] net/udp_gso: Allow TX timestamp with UDP GSO
Date: Fri, 24 May 2019 15:01:24 -0700 [thread overview]
Message-ID: <90E3853F-107D-45BA-93DC-D0BE8AC6FCBB@appneta.com> (raw)
In-Reply-To: <CAF=yD-Le-eTadOi7PL8WFEQCG=yLqb5gvKiks+s5Akeq8TenBQ@mail.gmail.com>
> On May 24, 2019, at 12:29 PM, Willem de Bruijn <willemdebruijn.kernel@gmail.com> wrote:
>
> It is the last moment that a timestamp can be generated for the last
> byte, I don't see how that is "neither the start nor the end of a GSO
> packet”.
My misunderstanding. I thought TCP did last segment timestamping, not
last byte. In that case, your statements make sense.
>> It would be interesting if a practical case can be made for timestamping
>> the last segment. In my mind, I don’t see how that would be valuable.
>
> It depends whether you are interested in measuring network latency or
> host transmit path latency.
>
> For the latter, knowing the time from the start of the sendmsg call to
> the moment the last byte hits the wire is most relevant. Or in absence
> of (well defined) hardware support, the last byte being queued to the
> device is the next best thing.
>
> It would make sense for this software implementation to follow
> established hardware behavior. But as far as I know, the exact time a
> hardware timestamp is taken is not consistent across devices, either.
>
> For fine grained timestamped data, perhaps GSO is simply not a good
> mechanism. That said, it still has to queue a timestamp if requested.
I see your point. Makes sense to me.
>> When using hardware timestamping, I think you will find that nearly all
>> adapters only allow one timestamp at a time. Therefore only one
>> packet in a burst would get timestamped.
>
> Can you elaborate? When the host queues N packets all with hardware
> timestamps requested, all N completions will have a timestamp? Or is
> that not guaranteed?
>
It is not guaranteed. The best example is in ixgbe_main.c and search for
‘SKBTX_HW_TSTAMP’. If there is a PTP TX timestamp in progress,
‘__IXGBE_PTP_TX_IN_PROGRESS’ is set and no other timestamps
are possible. The flag is cleared after transmit softirq, and only then
can another TX timestamp be taken.
>> There are exceptions, for
>> example I am playing with a 100G Mellanox adapter that has
>> per-packet TX timestamping. However, I suspect that when I am
>> done testing, all I will see is timestamps that are representing wire
>> rate (e.g. 123nsec per 1500 byte packet).
>>
>> Beyond testing the accuracy of a NIC’s timestamping capabilities, I
>> see very little value in doing per-segment timestamping.
>
> Ack. Great detailed argument, thanks.
Thanks. I’m a timestamping nerd and have learned lots with this
discussion.
next prev parent reply other threads:[~2019-05-24 22:01 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-23 21:06 [PATCH net 0/4] Allow TX timestamp with UDP GSO Fred Klassen
2019-05-23 21:06 ` [PATCH net 1/4] net/udp_gso: " Fred Klassen
2019-05-23 21:39 ` Willem de Bruijn
2019-05-24 1:38 ` Fred Klassen
2019-05-24 4:53 ` Willem de Bruijn
2019-05-24 16:34 ` Fred Klassen
2019-05-24 19:29 ` Willem de Bruijn
2019-05-24 22:01 ` Fred Klassen [this message]
2019-05-25 15:20 ` Willem de Bruijn
2019-05-25 18:47 ` Fred Klassen
2019-05-27 1:30 ` Willem de Bruijn
2019-05-27 2:09 ` Willem de Bruijn
2019-05-25 20:46 ` Fred Klassen
2019-05-23 21:59 ` Willem de Bruijn
2019-05-25 20:09 ` Fred Klassen
2019-05-25 20:47 ` Fred Klassen
2019-05-23 21:06 ` [PATCH net 2/4] net/udpgso_bench_tx: options to exercise TX CMSG Fred Klassen
2019-05-23 21:45 ` Willem de Bruijn
2019-05-23 21:52 ` Willem de Bruijn
2019-05-24 2:10 ` Fred Klassen
2019-05-23 21:06 ` [PATCH net 3/4] net/udpgso_bench_tx: fix sendmmsg on unconnected socket Fred Klassen
2019-05-23 21:06 ` [PATCH net 4/4] net/udpgso_bench_tx: audit error queue Fred Klassen
2019-05-23 21:56 ` Willem de Bruijn
2019-05-24 1:27 ` Fred Klassen
2019-05-24 5:02 ` Willem de Bruijn
2019-05-27 21:30 ` Fred Klassen
2019-05-27 21:46 ` Willem de Bruijn
2019-05-27 22:56 ` Fred Klassen
2019-05-28 1:15 ` Willem de Bruijn
2019-05-28 5:19 ` Fred Klassen
2019-05-28 15:08 ` Willem de Bruijn
2019-05-28 16:57 ` Fred Klassen
2019-05-28 17:07 ` Willem de Bruijn
2019-05-28 17:11 ` Willem de Bruijn
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=90E3853F-107D-45BA-93DC-D0BE8AC6FCBB@appneta.com \
--to=fklassen@appneta.com \
--cc=davem@davemloft.net \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=shuah@kernel.org \
--cc=willemb@google.com \
--cc=willemdebruijn.kernel@gmail.com \
--cc=yoshfuji@linux-ipv6.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).