freebsd stable - Jun 2018 - Ryzen issues on FreeBSD ? (with sort of workaround)

On 6/14/2018 6:30 AM, Pete French wrote:
>> Check out this thread on current. I re-ran the tests I did in Feb to
>> lockup the Ryzen box, and they are ok now with the latest micro code
>> updates from AMD.  I will let the tests run a good 48hrs, but in the
>> past it would only take 5-10 min to cause a hard lockup
>>
>>
https://lists.freebsd.org/pipermail/freebsd-current/2018-June/069799.html
> 
> Ah, excellent, tanksf for the pinter. I was already running the latest
> microcode, but have also now flashed my BIOS and applied the shell
> script fixes from that thread. Will try running with SMT re-enabled
> next week, as I need the machine not to lockup the next few days
> when I am not in the office, but it looks very promising.
FYI, both my Epyc and Ryzen system have been running 2+ days with the
tests that would normally hard lock the system in 5-60 min. The combo of
Microcode updates and system settings

https://lists.freebsd.org/pipermail/freebsd-current/2018-June/069799.html

seem to have fixed the last issue I was seeing

	---Mike

-- 
-------------------
Mike Tancsa, tel +1 519 651 3400 x203
Sentex Communications, mike at sentex.net
Providing Internet services since 1994 www.sentex.net
Cambridge, Ontario Canada

On 18/06/2018 14:59, Mike Tancsa wrote:
> FYI, both my Epyc and Ryzen system have been running 2+ days with the
> tests that would normally hard lock the system in 5-60 min. The combo of
> Microcode updates and system settings
Thats for the update - I turned all the default motherboard settings 
back on when I got into work this morning, and it has been running fine 
so far. WIll run like this all week.
> https://lists.freebsd.org/pipermail/freebsd-current/2018-June/069799.html
> 
> seem to have fixed the last issue I was seeing
Yes, those are the chnages I have applied. I went through that list over 
the weekend cross-referncing them to the errata document, and there are 
a couple of things in there which made me think 'aha!' - particularly 
the MWWAIT causing lockups on SMT, as it was disbling SMT that made it 
stable for me.

I also have access to a cpuple of (virtualised) Epyc machines which I am 
going to run up later in the week and try the workarounds there. But it 
does look very much like its fixed, which is excellent.

Preseumably in the slightly longer term these workarounds go into the 
actual kernel if it detects Ryzen ?

-pete.