Date: Mon, 01 Dec 2025 08:39:26 +0000 From: Bernard Spil <brnrd@freebsd.org> To: Adrian Chadd <adrian@freebsd.org> Cc: Florian Smeets <flo@freebsd.org>, FreeBSD Net <freebsd-net@freebsd.org>, current <freebsd-current@freebsd.org>, Alex Dupre <ale@freebsd.org> Subject: Re: looking for testers for if_rge - RTL8125/8126/8127 ethernet driver Message-ID: <edc5ebbaf6099c323a585e1bd5c51fdf@freebsd.org> In-Reply-To: <CAJ-Vmo=CcHaoYpZiBKSsTCX47%2BUfp4ctapyQ7bkeZLWS57xPGA@mail.gmail.com> 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>
index | next in thread | previous in thread | raw e-mail
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 >> > >home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?edc5ebbaf6099c323a585e1bd5c51fdf>