From: Jonathan Morton <chromatix99@gmail.com>
To: Dave Taht <dave.taht@gmail.com>
Cc: Charles Rothschild <ccroth3@yahoo.com>,
"cerowrt-devel@lists.bufferbloat.net"
<cerowrt-devel@lists.bufferbloat.net>
Subject: Re: [Cerowrt-devel] Looking for MORE SQM Router Recommendations !
Date: Wed, 17 Mar 2021 00:14:14 +0200 [thread overview]
Message-ID: <4A515BE9-AEE5-40D1-AEC6-2B0C3BCBA142@gmail.com> (raw)
In-Reply-To: <CAA93jw6ZmWkCKr7hpV5aG+RLQNBY5qJB8nxz0qpcchwbLTpPag@mail.gmail.com>
> On 17 Mar, 2021, at 12:04 am, Dave Taht <dave.taht@gmail.com> wrote:
>
> Is that based on measurements?
Yes, Pete did some.
> I did not care for the pi3's behavior much.
Unlike the Pi 3, the Pi 4 has a true GigE MAC built into the SoC, and the USB3 controller has enough throughput to actually support a second GigE port; it's attached to a real PCIe lane. This means it can move packets from one to the other, in both directions at once, at wire speed without relying on an offload engine (which it doesn't have). That's perfect for SQM.
In older Pis, the Ethernet port was attached over USB2. That doesn't have enough throughput to support GigE, and most models had a 100base-TX port as a consequence. There's a similar bottleneck in most CPE routers between the CPU and the Ethernet hardware complex, with the offload engine being part of the latter. That bottleneck is why SQM can't reach wire speed on that class of hardware.
- Jonathan Morton
next prev parent reply other threads:[~2021-03-16 22:14 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1287379027.1155590.1615919208363.ref@mail.yahoo.com>
2021-03-16 18:26 ` Charles Rothschild
[not found] ` <mailman.2387.1615919214.24343.cerowrt-devel@lists.bufferbloat.net>
2021-03-16 22:03 ` [Cerowrt-devel] " Jonathan Morton
2021-03-16 22:04 ` Dave Taht
2021-03-16 22:14 ` Jonathan Morton [this message]
2021-03-16 22:58 ` Michael Richardson
2021-03-17 1:01 ` David Lang
2021-03-17 2:57 ` Jonathan Morton
2021-03-17 6:11 ` Sebastian Moeller
2021-03-17 3:06 ` Matt Taggart
2021-03-17 10:54 ` Toke Høiland-Jørgensen
[not found] ` <mailman.2393.1615978451.24343.cerowrt-devel@lists.bufferbloat.net>
2021-03-19 4:23 ` Aaron Wood
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/cerowrt-devel.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4A515BE9-AEE5-40D1-AEC6-2B0C3BCBA142@gmail.com \
--to=chromatix99@gmail.com \
--cc=ccroth3@yahoo.com \
--cc=cerowrt-devel@lists.bufferbloat.net \
--cc=dave.taht@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