Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 1 Dec 2025 14:05:22 -0300
From:      Mario Lobo <lobo@bsd.com.br>
To:        Bernard Spil <brnrd@freebsd.org>
Cc:        Adrian Chadd <adrian@freebsd.org>, FreeBSD Net <freebsd-net@freebsd.org>,  current <freebsd-current@freebsd.org>
Subject:   Re: looking for testers for if_rge - RTL8125/8126/8127 ethernet driver
Message-ID:  <CA%2ByoEx806hfissEfDpnhGiH%2B3LGztya9waaZdU=yVbrOH=14Yw@mail.gmail.com>
In-Reply-To: <edc5ebbaf6099c323a585e1bd5c51fdf@freebsd.org>
References:  <CAJ-VmonP4%2BQmpSUfM6Xatta83e6zkjMShzL7ob1nJVOH=Tjwhg@mail.gmail.com> <cfd43166-a287-4ea0-97f5-dbbf08856bdc@FreeBSD.org> <CAJ-Vmo=nj8TvjMg_XFkNZ6MC28DcOzdKKqVOqboCr0T7eTQO-g@mail.gmail.com> <CAEJyAvNsJt5t3JVRRDOtTFvZBEySR4mH-aENLrFMC_WtJm6G-w@mail.gmail.com> <CAEJyAvOB7dg8bumBVyiMnjakBxzyoMCOC=9N9jh=A1dxWrB8YA@mail.gmail.com> <CAJ-Vmo=CcHaoYpZiBKSsTCX47%2BUfp4ctapyQ7bkeZLWS57xPGA@mail.gmail.com> <edc5ebbaf6099c323a585e1bd5c51fdf@freebsd.org>

index | next in thread | previous in thread | raw e-mail

[-- Attachment #1 --]
On Mon, Dec 1, 2025, 05:40 Bernard Spil <brnrd@freebsd.org> wrote:

> Hi!
>
> Happy to be of service! Anything else we can do to get more testers?
> (I'll see if I can make some noise on Mastodon).
> Should there be some instruction on providing feedback in the port?
>
> Let's make this a very short-lived port.
>
> Cheers, Bernard.
>
> On 2025-12-01 02:42, Adrian Chadd wrote:
> > hi!
> >
> > Thanks! My goal is to get this into a review next week, so hopefully
> > this is a short lived port!
> >
> >
> > -a
> >
> > On Sun, 30 Nov 2025 at 10:48, Bernard Spil <brnrd@freebsd.org> wrote:
> >>
> >> Hi,
> >>
> >> Turns out the realtek-re-kmod wasn't working out for me after all,
> >> machine started repeatedly crashing.
> >>
> >> Committed the port net/realtek-rge-kmod hoping to attract more
> >> testers.
> >> So far, works out great for me. GMKTek M5 Plus / AMD 5825U / Dual
> >> RTL8215
> >> FreeBSD 15.0-RC4-p1 releng/15.0-n280991-c7ccd5b3f879 GENERIC amd64
> >>
> >> Testing with 2 clients, both 100 parallel streams iperf3 bidirectional
> >> for 10 minutes showed negligible load.
> >>
> >> rge0@pci0:1:0:0:        class=0x020000 rev=0x05 hdr=0x00 vendor=0x10ec
> >> device=0x8125 subvendor=0x10ec subdevice=0x8125
> >>     vendor     = 'Realtek Semiconductor Co., Ltd.'
> >>     device     = 'RTL8125 2.5GbE Controller'
> >>     class      = network
> >>     subclass   = ethernet
> >> rge1@pci0:2:0:0:        class=0x020000 rev=0x05 hdr=0x00 vendor=0x10ec
> >> device=0x8125 subvendor=0x10ec subdevice=0x8125
> >>     vendor     = 'Realtek Semiconductor Co., Ltd.'
> >>     device     = 'RTL8125 2.5GbE Controller'
> >>     class      = network
> >>     subclass   = ethernet
> >>
> >> Cheers, Bernard.
> >>
> >> On Sun, Nov 30, 2025 at 2:51 PM Bernard Spil <brnrd@freebsd.org>
> >> wrote:
> >> >
> >> > Hi all,
> >> >
> >> > Thanks to flo for notifying me that there's an alternative to
> >> > net/realtek-re-kmod.
> >> >
> >> > I've had crashes running realtek-re-kmod and realtek-re-kmod198
> >> > before, none of the switches seemed to help.
> >> > After upgrading to from 14.3 to 15.0-RC4-p1, I thought I'd test again.
> >> > So far so good, no crashes. Generating load with iperf for 5 minutes
> >> > from 2 machines to the server works OK with the 1101.00 for now.
> >> >
> >> > Nice to have this if_rge in the back pocket when things don't work out
> >> > with 1101.00. Started porting it, find the patch at
> >> > https://brnrd.eu/bsd/patch-net_realtek-rge-kmod-20251129
> >> > Seeing that this is supposed to land in base, I'm holding back on
> committing it.
> >> >
> >> > Thanks all! Bernard (brnrd@)
> >> >
> >> > On Fri, Nov 28, 2025 at 5:48 PM Adrian Chadd <adrian@freebsd.org>
> wrote:
> >> > >
> >> > > On Thu, 27 Nov 2025 at 10:13, Florian Smeets <flo@freebsd.org>
> wrote:
> >> > > >
> >> > > > On 23.11.25 03:16, Adrian Chadd wrote:
> >> > > > > hi!
> >> > > > >
> >> > > > > i've ported Kevin Lo's openbsd driver for these realtek
> chipsets to FreeBSD.
> >> > > > > It works well enough for me to use on my laptop w/ RTL8125B /
> Killer E3000.
> >> > > > > I'm now opening it up to others who are willing to build/run a
> kernel
> >> > > > > module to test the driver out and report back.
> >> > > > >
> >> > > > This is great. Finally, an in tree driver for these very common
> NICs.
> >> > > > The 1100.00 version of the net/realtek-re-kmod was just
> unreliable for
> >> > > > me (constant hangs, no matter which options I turned off and on).
> I've
> >> > > > only done light testing with the official 1101.00 driver. I was
> able to
> >> > > > wedge it with less than a minute of iperf3, and the ifconfig
> down/up
> >> > > > dance that was able to revive the interface with 1100.00 was not
> able to
> >> > > > recover the interface.
> >> > > >
> >> > > > I ran if_rge on my NAS and did some testing. I haven't had one
> hang with
> >> > > > this driver, even after pounding the network for hours. That's a
> big
> >> > > > plus for me. Thanks.
> >> > > >
> >> > > > I was able to achieve close to 2.5Gb/s TX and close to 1Gb/s RX
> with
> >> > > > iperf3 --bidir.
> >> > > >
> >> > > > CPU usage appears to be substantially higher than with the
> official
> >> > > > Realtek driver.
> >> > >
> >> > > That's a good data point.
> >> > >
> >> > > >
> >> > > > [intr{irq59: rge0}] goes to around 50% of one core, and
> [kernel{rge0
> >> > > > taskq thread}] hovers between 20-25% when running the above
> iperf3 tests.
> >> > > >
> >> > > > With the official 1101.00 driver, the only process using > 1% CPU
> is
> >> > > > this one [kernel{re0 taskq}] and it is around 10% with the test
> >> > > > mentioned above.
> >> > >
> >> > > I'll go dig into that a bit. It shouldn't be taking very much CPU
> to process
> >> > > this number of packets; the bulk of the CPU should be used by the
> IP stack.
> >> > >
> >> > > I'll go run some profiling over the next few days and see if I can
> nail down
> >> > > what I'm doing poorly. Hopefully it's something stupid on my end.
> ;-)
> >> > >
> >> > >
> >> > >
> >> > > -adrian
> >> > >
>

Hi!

Compiled successfully from the git project page,  and I've been testing it
on a 14.3 stable.

Really great!

Thanks, Adrian!
Mario Lobo
http://www.mallavoodoo.com.br
FreeBSD since version 2.2.8 [not Pro-Audio.... YET!!]

[-- Attachment #2 --]
<div dir="auto"><div><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Mon, Dec 1, 2025, 05:40 Bernard Spil &lt;<a href="mailto:brnrd@freebsd.org">brnrd@freebsd.org</a>&gt; wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi!<br>
<br>
Happy to be of service! Anything else we can do to get more testers? <br>
(I&#39;ll see if I can make some noise on Mastodon).<br>
Should there be some instruction on providing feedback in the port?<br>
<br>
Let&#39;s make this a very short-lived port.<br>
<br>
Cheers, Bernard.<br>
<br>
On 2025-12-01 02:42, Adrian Chadd wrote:<br>
&gt; hi!<br>
&gt; <br>
&gt; Thanks! My goal is to get this into a review next week, so hopefully<br>
&gt; this is a short lived port!<br>
&gt; <br>
&gt; <br>
&gt; -a<br>
&gt; <br>
&gt; On Sun, 30 Nov 2025 at 10:48, Bernard Spil &lt;<a href="mailto:brnrd@freebsd.org" target="_blank" rel="noreferrer">brnrd@freebsd.org</a>&gt; wrote:<br>
&gt;&gt; <br>
&gt;&gt; Hi,<br>
&gt;&gt; <br>
&gt;&gt; Turns out the realtek-re-kmod wasn&#39;t working out for me after all,<br>
&gt;&gt; machine started repeatedly crashing.<br>
&gt;&gt; <br>
&gt;&gt; Committed the port net/realtek-rge-kmod hoping to attract more <br>
&gt;&gt; testers.<br>
&gt;&gt; So far, works out great for me. GMKTek M5 Plus / AMD 5825U / Dual <br>
&gt;&gt; RTL8215<br>
&gt;&gt; FreeBSD 15.0-RC4-p1 releng/15.0-n280991-c7ccd5b3f879 GENERIC amd64<br>
&gt;&gt; <br>
&gt;&gt; Testing with 2 clients, both 100 parallel streams iperf3 bidirectional<br>
&gt;&gt; for 10 minutes showed negligible load.<br>
&gt;&gt; <br>
&gt;&gt; rge0@pci0:1:0:0:        class=0x020000 rev=0x05 hdr=0x00 vendor=0x10ec<br>
&gt;&gt; device=0x8125 subvendor=0x10ec subdevice=0x8125<br>
&gt;&gt;     vendor     = &#39;Realtek Semiconductor Co., Ltd.&#39;<br>
&gt;&gt;     device     = &#39;RTL8125 2.5GbE Controller&#39;<br>
&gt;&gt;     class      = network<br>
&gt;&gt;     subclass   = ethernet<br>
&gt;&gt; rge1@pci0:2:0:0:        class=0x020000 rev=0x05 hdr=0x00 vendor=0x10ec<br>
&gt;&gt; device=0x8125 subvendor=0x10ec subdevice=0x8125<br>
&gt;&gt;     vendor     = &#39;Realtek Semiconductor Co., Ltd.&#39;<br>
&gt;&gt;     device     = &#39;RTL8125 2.5GbE Controller&#39;<br>
&gt;&gt;     class      = network<br>
&gt;&gt;     subclass   = ethernet<br>
&gt;&gt; <br>
&gt;&gt; Cheers, Bernard.<br>
&gt;&gt; <br>
&gt;&gt; On Sun, Nov 30, 2025 at 2:51 PM Bernard Spil &lt;<a href="mailto:brnrd@freebsd.org" target="_blank" rel="noreferrer">brnrd@freebsd.org</a>&gt; <br>
&gt;&gt; wrote:<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; Hi all,<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; Thanks to flo for notifying me that there&#39;s an alternative to<br>
&gt;&gt; &gt; net/realtek-re-kmod.<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; I&#39;ve had crashes running realtek-re-kmod and realtek-re-kmod198<br>
&gt;&gt; &gt; before, none of the switches seemed to help.<br>
&gt;&gt; &gt; After upgrading to from 14.3 to 15.0-RC4-p1, I thought I&#39;d test again.<br>
&gt;&gt; &gt; So far so good, no crashes. Generating load with iperf for 5 minutes<br>
&gt;&gt; &gt; from 2 machines to the server works OK with the 1101.00 for now.<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; Nice to have this if_rge in the back pocket when things don&#39;t work out<br>
&gt;&gt; &gt; with 1101.00. Started porting it, find the patch at<br>
&gt;&gt; &gt; <a href="https://brnrd.eu/bsd/patch-net_realtek-rge-kmod-20251129" rel="noreferrer noreferrer" target="_blank">https://brnrd.eu/bsd/patch-net_realtek-rge-kmod-20251129</a><br>;
&gt;&gt; &gt; Seeing that this is supposed to land in base, I&#39;m holding back on committing it.<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; Thanks all! Bernard (brnrd@)<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt; On Fri, Nov 28, 2025 at 5:48 PM Adrian Chadd &lt;<a href="mailto:adrian@freebsd.org" target="_blank" rel="noreferrer">adrian@freebsd.org</a>&gt; wrote:<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; On Thu, 27 Nov 2025 at 10:13, Florian Smeets &lt;<a href="mailto:flo@freebsd.org" target="_blank" rel="noreferrer">flo@freebsd.org</a>&gt; wrote:<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; On 23.11.25 03:16, Adrian Chadd wrote:<br>
&gt;&gt; &gt; &gt; &gt; &gt; hi!<br>
&gt;&gt; &gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; &gt; i&#39;ve ported Kevin Lo&#39;s openbsd driver for these realtek chipsets to FreeBSD.<br>
&gt;&gt; &gt; &gt; &gt; &gt; It works well enough for me to use on my laptop w/ RTL8125B / Killer E3000.<br>
&gt;&gt; &gt; &gt; &gt; &gt; I&#39;m now opening it up to others who are willing to build/run a kernel<br>
&gt;&gt; &gt; &gt; &gt; &gt; module to test the driver out and report back.<br>
&gt;&gt; &gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; This is great. Finally, an in tree driver for these very common NICs.<br>
&gt;&gt; &gt; &gt; &gt; The 1100.00 version of the net/realtek-re-kmod was just unreliable for<br>
&gt;&gt; &gt; &gt; &gt; me (constant hangs, no matter which options I turned off and on). I&#39;ve<br>
&gt;&gt; &gt; &gt; &gt; only done light testing with the official 1101.00 driver. I was able to<br>
&gt;&gt; &gt; &gt; &gt; wedge it with less than a minute of iperf3, and the ifconfig down/up<br>
&gt;&gt; &gt; &gt; &gt; dance that was able to revive the interface with 1100.00 was not able to<br>
&gt;&gt; &gt; &gt; &gt; recover the interface.<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; I ran if_rge on my NAS and did some testing. I haven&#39;t had one hang with<br>
&gt;&gt; &gt; &gt; &gt; this driver, even after pounding the network for hours. That&#39;s a big<br>
&gt;&gt; &gt; &gt; &gt; plus for me. Thanks.<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; I was able to achieve close to 2.5Gb/s TX and close to 1Gb/s RX with<br>
&gt;&gt; &gt; &gt; &gt; iperf3 --bidir.<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; CPU usage appears to be substantially higher than with the official<br>
&gt;&gt; &gt; &gt; &gt; Realtek driver.<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; That&#39;s a good data point.<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; [intr{irq59: rge0}] goes to around 50% of one core, and [kernel{rge0<br>
&gt;&gt; &gt; &gt; &gt; taskq thread}] hovers between 20-25% when running the above iperf3 tests.<br>
&gt;&gt; &gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; &gt; With the official 1101.00 driver, the only process using &gt; 1% CPU is<br>
&gt;&gt; &gt; &gt; &gt; this one [kernel{re0 taskq}] and it is around 10% with the test<br>
&gt;&gt; &gt; &gt; &gt; mentioned above.<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; I&#39;ll go dig into that a bit. It shouldn&#39;t be taking very much CPU to process<br>
&gt;&gt; &gt; &gt; this number of packets; the bulk of the CPU should be used by the IP stack.<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; I&#39;ll go run some profiling over the next few days and see if I can nail down<br>
&gt;&gt; &gt; &gt; what I&#39;m doing poorly. Hopefully it&#39;s something stupid on my end. ;-)<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt;<br>
&gt;&gt; &gt; &gt; -adrian<br>
&gt;&gt; &gt; &gt;<br></blockquote></div></div><div dir="auto"><br></div><div dir="auto">Hi!</div><div dir="auto"><br></div><div dir="auto">Compiled successfully from the git project page,  and I&#39;ve been testing it on a 14.3 stable.</div><div dir="auto"><br></div><div dir="auto">Really great!</div><div dir="auto"><br></div><div dir="auto">Thanks, Adrian!</div><div dir="auto">Mario Lobo<br><a href="http://www.mallavoodoo.com.br/">http://www.mallavoodoo.com.br</a><br>FreeBSD since version 2.2.8 [not Pro-Audio.... YET!!]</div><div dir="auto"><br></div><div dir="auto"><div class="gmail_quote gmail_quote_container"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"></blockquote></div></div></div>
help

Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2ByoEx806hfissEfDpnhGiH%2B3LGztya9waaZdU=yVbrOH=14Yw>