Some Ryzen Linux Users Are Facing Issues With Heavy Compilation Loads

[chithanh]

I mean all the models are "equally" affected?

If by models you mean R3 1200, ..., R7 1800X then no. This mostly or entirely affects models with SMT, models without SMT (1200, 1300X) are not affected.

Also a number of users have Ryzen CPUs which are stable even with SMT and uOP cache enabled.

[scorpio810]

oleyska Thanks for the report. scorpio810 I got a little confused by your post, did you try the kill_rizen.sh test I suggest. It is very reliable to spot systems with problems. Just let it run for some hours.

.

Yes, I tried the kill_rizen.sh test on my custom kernel 4.11.12, it run nice during 3 or 4 hours and freeze my DE after, not free memory (I have only 16GB of RAM) !

[donbastiano]

If by models you mean R3 1200, ..., R7 1800X then no. This mostly or entirely affects models with SMT, models without SMT (1200, 1300X) are not affected.

Also a number of users have Ryzen CPUs which are stable even with SMT and uOP cache enabled.

Ok, thank you!

[creative]

Glad I went Intel this past go round. I built AMD systems for years, not going back.

[bridgman]

Yes, I tried the kill_rizen.sh test on my custom kernel 4.11.12, it run nice during 3 or 4 hours and freeze my DE after, not free memory (I have only 16GB of RAM) !

Were you using the ramdisk (USE_RAMDISK=true near the top of the script) ? If so then you almost certainly ran out of memory.

[Constantin]

I have Ryzen 1700, stock speed, never overclocked, bought on 21st of July. I won't remove the cooler to see the production date.
64Gb RAM, 2933 Mhz.
I use Debian, latest version (9.1), KDE Plasma desktop.

I've run the kill-ryzen.sh script, and I can reproduce the segfault error with SMT on. But if I switch SMT off, it no longer appears.
As I don't use SMT, and this is my main computer, I'll keep the processor for now. I'll probably send it for replacement eventually, if no permanent solution is found.

The results of my tests, run on 25th of August, are:
-run 1h 37m, no error, SMT off
-run 22 minutes, SMT on, 1 thread (loop-4) quickly gave an error "TIME TO FAIL: 263 s" (no additional error message shown)
-run 6 minutes, SMT on, 1 thread (loop-0) quickly gave an error "TIME TO FAIL: 104 s" (also segfault error message appeared)
-run 16 minutes, no error, SMT off

For the next tests I kept SMT off, but I increased the number of threads by editing the script:
-run 40 minutes, no error, SMT off, 32 threads
-run 1h 32m, no error, SMT off, 64 threads
-run 39 minutes, no error, SMT off, 16 threads

[Constantin]

I ran more tests and was able to reproduce the error with SMT off as well, after a 35 minutes run.
[KERN] Aug 26 09:44:06 host kernel: as[31164]: segfault at 7c00000077 ip 0000007c00000077 sp 00007ffca8334bf1 error 14 in x86_64-linux-gnu-as[55de2995f000+5b000]
The loop didn't appear to die though (no "TIME TO FAIL: " message).

[lem79]

Since I added CONFIG_RCU_NOCB_CPU and CONFIG_RCU_NOCB_CPU_ALL and Norandmaps in my kernel of vanilla 4.11.x, I have never seen a freeze ...
Thanks for the tip !

I added CONFIG_RCU_NOCB_CPU=y to M-Bab's 4.14.0-ubuntu kernel (https://github.com/M-Bab/linux-kernel-amdgpu) and have been running it on my Ryzen 5 1600X (I think the manufacturing date code on it is 1703SUS) for two weeks, and haven't had one freeze. I was getting occasional freezes before then. Running Ubuntu Studio 17.04 with the Oibaf PPA, and Unity desktop.