With the Intel issues exposed in meltdown, we were looking at possibly deploying some Ryzen based servers for FreeBSD. We got a pair of ASUS PRIME X370-PRO and CPU: AMD Ryzen 5 1600X Six-Core Processor (3593.34-MHz K8-class CPU) Origin="AuthenticAMD" Id=0x800f11 Family=0x17 Model=0x1 Stepping=1 Everything is at its default in the BIOS, no overclocking etc. However, we are seeing random lockups on both boxes. It doesnt seem to correspond with load/activity. And its a hard lockup. Keyboard not responsive and I cant break to serial debugger, so it doesnt seem to be an issue with something in the kernel going into deadlock. It sort of feels like a hardware issue, but it seems odd that both boxes are showing the same issue with random lockups like that. It could be twice in a day or once every 3 days. Anyone have any insights ? Anyone have any suggestions about better motherboards out there ? We are waiting for Supermicro's Epyc availability, but nothing yet. It would be nice if we could find a board with at least some hardware watchdog on it. ---Mike -- ------------------- Mike Tancsa, tel +1 519 651 3400 Sentex Communications, mike at sentex.net Providing Internet services since 1994 www.sentex.net Cambridge, Ontario Canada http://www.tancsa.com/
I am in much the same situation as you (want to deploy Epyc, waiting for SM stuff to become available). I currently have here a set of parts to make a test Ryzen box, so you are ahead of me on that though. Should have that gong this week I hope. Are you running the latest STABLE ? There were some patches for Ryzen which went in I belive, and might affect te stability. Specificly the chnages to stop it locking up when executing code in the top page ? I'll get back to you when I have done some more testing... -pete. On 17/01/2018 13:38, Mike Tancsa wrote:> With the Intel issues exposed in meltdown, we were looking at possibly > deploying some Ryzen based servers for FreeBSD. We got a pair of > ASUS PRIME X370-PRO and > > CPU: AMD Ryzen 5 1600X Six-Core Processor (3593.34-MHz > K8-class CPU) > Origin="AuthenticAMD" Id=0x800f11 Family=0x17 Model=0x1 Stepping=1 > > Everything is at its default in the BIOS, no overclocking etc. > > However, we are seeing random lockups on both boxes. It doesnt seem to > correspond with load/activity. And its a hard lockup. Keyboard not > responsive and I cant break to serial debugger, so it doesnt seem to be > an issue with something in the kernel going into deadlock. > > It sort of feels like a hardware issue, but it seems odd that both boxes > are showing the same issue with random lockups like that. It could be > twice in a day or once every 3 days. > > Anyone have any insights ? Anyone have any suggestions about better > motherboards out there ? We are waiting for Supermicro's Epyc > availability, but nothing yet. It would be nice if we could find a > board with at least some hardware watchdog on it. > > > ---Mike >
I've been seeing similar issues on Ryzen and asked some questions, here https://lists.freebsd.org/pipermail/freebsd-stable/2017-December/088121.html My previous queries didn't go anywhere. -- Nimrod On Wed, Jan 17, 2018 at 8:38 AM Mike Tancsa <mike at sentex.net> wrote:> With the Intel issues exposed in meltdown, we were looking at possibly > deploying some Ryzen based servers for FreeBSD. We got a pair of > ASUS PRIME X370-PRO and > > CPU: AMD Ryzen 5 1600X Six-Core Processor (3593.34-MHz > K8-class CPU) > Origin="AuthenticAMD" Id=0x800f11 Family=0x17 Model=0x1 Stepping=1 > > Everything is at its default in the BIOS, no overclocking etc. > > However, we are seeing random lockups on both boxes. It doesnt seem to > correspond with load/activity. And its a hard lockup. Keyboard not > responsive and I cant break to serial debugger, so it doesnt seem to be > an issue with something in the kernel going into deadlock. > > It sort of feels like a hardware issue, but it seems odd that both boxes > are showing the same issue with random lockups like that. It could be > twice in a day or once every 3 days. > > Anyone have any insights ? Anyone have any suggestions about better > motherboards out there ? We are waiting for Supermicro's Epyc > availability, but nothing yet. It would be nice if we could find a > board with at least some hardware watchdog on it. > > > ---Mike > > -- > ------------------- > Mike Tancsa, tel +1 519 651 3400 <(519)%20651-3400> > Sentex Communications, mike at sentex.net > Providing Internet services since 1994 www.sentex.net > Cambridge, Ontario Canada http://www.tancsa.com/ > _______________________________________________ > freebsd-stable at freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe at freebsd.org" >-- -- Nimrod
I have an Asus Prime X370-pro and a Ryzen 7 1700 that I bought in late April. Make sure you have the latest BIOS for these boards or else it will randomly freak out. While i haven't used it much with FreeBSD, I can confirm that I had a lot of stability issues solved with a December BIOS update on MidnightBSD. I back ported the shared page fix and amdtemp. (it's basically FreeBSD 9.1) I couldn't even get it to boot until the August BIOS update. I've had my box stay up at least a week, and it's my primary development box so I'm mostly doing src/ports builds all the time on it. If you have the latest BIOS, check the memory timings too. It's rather picky with some memory modules. Luke
On 01/17/18 14:38, Mike Tancsa wrote:> However, we are seeing random lockups on both boxes. [...]go into your BIOS: - load default settings - disable SMT - disable Cool&Quiet - disable global C-state control - disable anything with C-states only with SMT _and_ Cool&Quiet _and_ C-state-stuff all together disabled, my system is still running (uptime now is 49 days). Every other fiddling around with RAM, PSU and timing settings is fruitless. Before, my system locked up after a run time of six to ten days. And, yes, I have a replacement CPU and the shared page fix active - these didn't help. This does not help with your compilation problems though... BR, Nils