From: adr <adr@SDF.ORG>
To: 9fans <9fans@9fans.net>
Subject: Re: [9fans] USB3 1Gb ethernet card working on 9legacy (rpi 4)
Date: Wed, 3 Aug 2022 00:34:41 +0000 (UTC) [thread overview]
Message-ID: <9da89c5a-1de5-80bd-25b3-fe4230821@SDF.ORG> (raw)
In-Reply-To: <cb4e176e3c2ad67575ab1fb4e3d7239c@hamnavoe.com>
On Tue, 2 Aug 2022, Richard Miller wrote:
>> So bad maxpkt... etherusb check for maxpkt < 512 which is the max for
>> bulk transfers in usb2 high speed. Using 1024 instead fixes the problem.
>
> Thanks, the code was correct when written but the world has moved on!
> Is your adapter transmitting packets successfully now?
It's working really well. I'm using David du Colombier's nat patch
(I'll post to the list another one without the il stuff in case
someone wants to try it) to share internet to a linux machine, so
I made a test from the browser (speedtest.net) and almost reached
the contracted limit of my fiber connection, although I only have
a crappy 100Mb plan (I don't really need more). So packets are
flowing, but when plan9 is more involved things get worse.
For example with this setup (a small arm linux machine connected
through plan9, using the usb adapter for internet):
linux:
$ wget -O /dev/null https://arch.mirror.constant.com/images/v20220801.71902/Arch-Linux-x86_64-basic-20220801.71902.qcow2
[...]
/dev/null 100%[===================>] 489.88M 10.5MB/s in 51s
2022-08-02 22:56:44 (9.58 MB/s) - ???/dev/null??? saved [513671168/513671168]
real 0m51.875s
user 0m8.594s
sys 0m5.379s
And the progress bar saw me several times the speed reaching my
limit. So the usb and ethernet drivers seem to be working pretty
good (at least for my bandwidth)
plan9:
; time hget -o /dev/null https://arch.mirror.constant.com/images/v20220801.71902/Arch-Linux-x86_64-basic-20220801.71902.qcow2
couldn't set mtime: permission denied
8.06u 35.25s 211.17r hget -o /dev/null https://arch.mirror.constant.com/images/v20220801.71902/Arch-Linux-x86_64-basic-20220801.71902.qcow2
See the difference? That's a little more than 19Mb/s, some 2MiB/s almost 50% slower.
By the way I don't use archlinux but I've always use their servers
to make speed tests, usually they are fast.
> Actually the limit on maxpkt in that context wasn't strictly necessary anyway.
> Just remove the check.
Yes, I thought the same.
adr
------------------------------------------
9fans: 9fans
Permalink: https://9fans.topicbox.com/groups/9fans/T668643d11149fab4-M99ba4fa5f9a9f29941fe318d
Delivery options: https://9fans.topicbox.com/groups/9fans/subscription
next prev parent reply other threads:[~2022-08-03 0:34 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-31 17:58 adr
2022-07-31 18:08 ` hiro
2022-07-31 18:09 ` adr
2022-07-31 21:35 ` Richard Miller
2022-08-01 9:16 ` Richard Miller
2022-08-01 16:29 ` adr
2022-08-02 8:50 ` Richard Miller
2022-08-03 0:34 ` adr [this message]
2022-08-03 3:00 ` adr
2022-08-03 10:57 ` Richard Miller
2022-08-03 18:46 ` adr
2022-08-04 10:13 ` Richard Miller
2022-08-04 11:56 ` ori
2022-08-04 19:34 ` adr
2022-08-05 12:14 ` ori
2022-08-01 16:43 ` adr
2022-08-01 17:06 ` adr
2022-08-02 3:45 ` Lucio De Re
2022-08-02 9:07 ` Richard Miller
2022-08-03 0:52 ` adr
2022-08-03 1:08 ` adr
2022-08-03 12:41 ` Richard Miller
2022-08-03 18:47 ` adr
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=9da89c5a-1de5-80bd-25b3-fe4230821@SDF.ORG \
--to=adr@sdf.org \
--cc=9fans@9fans.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;
as well as URLs for NNTP newsgroup(s).