From: Gert Doering <gert@space.net>
To: "David Fernández" <davidfdzp@gmail.com>
Cc: starlink@lists.bufferbloat.net
Subject: Re: [Starlink] Packet losses in a router
Date: Mon, 24 Oct 2022 22:54:48 +0200 [thread overview]
Message-ID: <Y1b7mLiG68NWKiI0@Space.Net> (raw)
In-Reply-To: <CAC=tZ0rJJkhbi7jVR7LO4+Mj4PpvdY2D6RSK2b3s2Ni2UwaR_A@mail.gmail.com>
Hi,
On Mon, Oct 24, 2022 at 10:13:35PM +0200, David Fernández via Starlink wrote:
> Dear participants of this list,
>
> If you had a router that in lab conditions, with Gigabit Ethernet
> interfaces, that losses 1 or 2 out of a few thousands of UDP packets
> of a few hundreds of bytes each one, during a test of 1 minute, at
> only 50 packets/s using iperf2, I am sure that you would investigate
> why, wouldn't you?
If there isn't some reasonable explanation (like GigE -> 100M stepdown
and bursty traffic overflowing buffers), there must not be loss. Never.
When we test new circuits we do Cisco ping "sweep rate of sizes",
which pings with 38...18000 bytes, 5 times - including fragments, this
is very many packets. The expected result is "0 packet lost".
(Arguably this test is only exercising the circuit half-duplex, so
the notorious 100Mbit half-duplex / full-duplex mismatch is not caught,
but any sort of one-way error is)
Gert Doering
-- NetMaster
--
have you enabled IPv6 on something today...?
SpaceNet AG Vorstand: Sebastian v. Bomhard, Michael Emmer
Joseph-Dollinger-Bogen 14 Aufsichtsratsvors.: A. Grundner-Culemann
D-80807 Muenchen HRB: 136055 (AG Muenchen)
Tel: +49 (0)89/32356-444 USt-IdNr.: DE813185279
next prev parent reply other threads:[~2022-10-24 20:54 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-24 20:13 David Fernández
2022-10-24 20:22 ` Jeff Tantsura
2022-10-25 9:30 ` David Fernández
2022-10-24 20:54 ` Gert Doering [this message]
2022-10-24 21:15 ` Ricky Mok
2022-10-24 21:21 ` David Lang
2022-11-04 12:54 David Fernández
2022-11-05 12:05 ` Gert Doering
2022-11-07 8:34 ` David Fernández
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
List information: https://lists.bufferbloat.net/postorius/lists/starlink.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Y1b7mLiG68NWKiI0@Space.Net \
--to=gert@space.net \
--cc=davidfdzp@gmail.com \
--cc=starlink@lists.bufferbloat.net \
/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