AnsweredAssumed Answered

Does my Ryzen have the segfault bug?

Question asked by hufter on Oct 19, 2017
Latest reply on Oct 23, 2017 by amdmatt

Suspicions arose when my new Ryzen build crashed in a weird way while gaming on Linux, playing Black Mesa. I decided to test is

I have updated my bios to the latest and ran that kill-ryzen stress test, earlier on Linux Mint 18.2 with kernel 4.11, and now also with the new Ubuntu 17.10 on 4.13.

here are some results:

 

atommi@tommi-aardvark:/home2/tommi/Lataukset/ryzen-test-master$ inxi -v2

System:    Host: tommi-aardvark Kernel: 4.13.0-16-generic x86_64 bits: 64 Desktop: Gnome 3.26.1

           Distro: Ubuntu 17.10

Machine:   Device: desktop Mobo: ASUSTeK model: PRIME B350-PLUS v: Rev X.0x serial: N/A

           UEFI [Legacy]: American Megatrends v: 0902 date: 09/08/2017

CPU:       Hexa core AMD Ryzen 5 1600X Six-Core (-HT-MCP-) speed/max: 3593/3600 MHz

Graphics:  Card: NVIDIA GP106 [GeForce GTX 1060 6GB]

           Display Server: x11 (X.Org 1.19.5 )

           drivers: nvidia (unloaded: modesetting,fbdev,vesa,nouveau)

           Resolution: 1920x1080@60.00hz

           OpenGL: renderer: GeForce GTX 1060 6GB/PCIe/SSE2 version: 4.5.0 NVIDIA 384.90

Network:   Card: Realtek RTL8111/8168/8411 PCIE Gigabit Ethernet Controller driver: r8169

Drives:    HDD Total Size: 2120.4GB (36.6% used)

           ID-1: model: N/A

           ID-2: model: TOSHIBA_DT01ACA2

           ID-3: model: WDC_WD1200BEVS

Info:      Processes: 327 Uptime: 4 min Memory: 1026.8/16043.6MB Client: Shell (bash) inxi: 2.3.37

atommi@tommi-aardvark:/home2/tommi/Lataukset/ryzen-test-master$ ./kill-ryzen.sh

Install required packages

[sudo] password for atommi:

Reading package lists... Done

Building dependency tree      

Reading state information... Done

build-essential is already the newest version (12.4ubuntu1).

0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.

Create compressed ramdisk

64G

Download GCC sources

--2017-10-19 22:49:25--  ftp://ftp.fu-berlin.de/unix/languages/gcc/releases/gcc-7.1.0/gcc-7.1.0.tar.bz2

           => 'gcc-7.1.0.tar.bz2'

Resolving ftp.fu-berlin.de (ftp.fu-berlin.de)... 130.133.3.130

Connecting to ftp.fu-berlin.de (ftp.fu-berlin.de)|130.133.3.130|:21... connected.

Logging in as anonymous ... Logged in!

==> SYST ... done.    ==> PWD ... done.

==> TYPE I ... done.  ==> CWD (1) /unix/languages/gcc/releases/gcc-7.1.0 ... done.

==> SIZE gcc-7.1.0.tar.bz2 ... 84303533

==> PASV ... done.    ==> RETR gcc-7.1.0.tar.bz2 ... done.

Length: 84303533 (80M) (unauthoritative)

 

gcc-7.1.0.tar.bz2         100%[==================================>]  80.40M   990KB/s    in 83s    

 

2017-10-19 22:50:49 (986 KB/s) - 'gcc-7.1.0.tar.bz2' saved [84303533]

 

Extract GCC sources

Download prerequisites

2017-10-19 22:51:09 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/gmp-6.1.0.tar.bz2 [2383840] -> "./gmp-6.1.0.tar.bz2" [1]

2017-10-19 22:51:14 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/mpfr-3.1.4.tar.bz2 [1279284] -> "./mpfr-3.1.4.tar.bz2" [1]

2017-10-19 22:51:18 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/mpc-1.0.3.tar.gz [669925] -> "./mpc-1.0.3.tar.gz" [1]

2017-10-19 22:51:24 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/isl-0.16.1.tar.bz2 [1626446] -> "./isl-0.16.1.tar.bz2" [1]

gmp-6.1.0.tar.bz2: OK

mpfr-3.1.4.tar.bz2: OK

mpc-1.0.3.tar.gz: OK

isl-0.16.1.tar.bz2: OK

All prerequisites downloaded successfully.

cat /proc/cpuinfo | grep -i -E "(model name|microcode)"

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

model name    : AMD Ryzen 5 1600X Six-Core Processor

microcode    : 0x8001129

sudo dmidecode -t memory | grep -i -E "(rank|speed|part)" | grep -v -i unknown

    Speed: 2400 MT/s

    Part Number: F4-2400C16-8GFX

    Rank: 2

    Configured Clock Speed: 1200 MT/s

    Speed: 2400 MT/s

    Part Number: F4-2400C16-8GFX

    Rank: 2

    Configured Clock Speed: 1200 MT/s

uname -a

Linux tommi-aardvark 4.13.0-16-generic #19-Ubuntu SMP Wed Oct 11 18:35:14 UTC 2017 x86_64 x86_64 x86_64 GNU/Linux

cat /proc/sys/kernel/randomize_va_space

2

/ /mnt/ramdisk/workdir

/mnt/ramdisk/workdir

Using 12 parallel processes

[KERN] -- Logs begin at Thu 2017-10-19 22:44:26 EEST. --

[KERN] Oct 19 22:44:28 tommi-aardvark kernel: nvidia-modeset: Allocated GPU:0 (GPU-abdf15a7-5e20-61f0-8612-4d2d2d8ccf08) @ PCI:0000:22:00.0

[KERN] Oct 19 22:44:31 tommi-aardvark kernel: r8169 0000:1e:00.0 enp30s0: link up

[KERN] Oct 19 22:44:31 tommi-aardvark kernel: IPv6: ADDRCONF(NETDEV_CHANGE): enp30s0: link becomes ready

[KERN] Oct 19 22:44:49 tommi-aardvark kernel: Bluetooth: RFCOMM TTY layer initialized

[KERN] Oct 19 22:44:49 tommi-aardvark kernel: Bluetooth: RFCOMM socket layer initialized

[KERN] Oct 19 22:44:49 tommi-aardvark kernel: Bluetooth: RFCOMM ver 1.11

[KERN] Oct 19 22:44:50 tommi-aardvark kernel: rfkill: input handler disabled

[KERN] Oct 19 22:49:24 tommi-aardvark kernel: zram: Added device: zram0

[KERN] Oct 19 22:49:24 tommi-aardvark kernel: zram0: detected capacity change from 0 to 68719476736

[KERN] Oct 19 22:49:25 tommi-aardvark kernel: EXT4-fs (zram0): mounted filesystem with ordered data mode. Opts: discard

[loop-0] Thu Oct 19 22:51:25 EEST 2017 start 0

[loop-1] Thu Oct 19 22:51:26 EEST 2017 start 0

[loop-2] Thu Oct 19 22:51:27 EEST 2017 start 0

[loop-3] Thu Oct 19 22:51:28 EEST 2017 start 0

[loop-4] Thu Oct 19 22:51:29 EEST 2017 start 0

[loop-5] Thu Oct 19 22:51:30 EEST 2017 start 0

[loop-6] Thu Oct 19 22:51:31 EEST 2017 start 0

[loop-7] Thu Oct 19 22:51:32 EEST 2017 start 0

[loop-8] Thu Oct 19 22:51:33 EEST 2017 start 0

[loop-9] Thu Oct 19 22:51:34 EEST 2017 start 0

[loop-10] Thu Oct 19 22:51:35 EEST 2017 start 0

[loop-11] Thu Oct 19 22:51:36 EEST 2017 start 0

[loop-6] Thu Oct 19 22:53:22 EEST 2017 build failed

[loop-6] TIME TO FAIL: 117 s

[KERN] Oct 19 22:53:22 tommi-aardvark kernel: show_signal_msg: 13 callbacks suppressed

[KERN] Oct 19 22:53:22 tommi-aardvark kernel: bash[22922]: segfault at 15d4068 ip 00000000015d4068 sp 00007ffe4c82d878 error 15

[loop-1] Thu Oct 19 23:09:38 EEST 2017 build failed

[loop-1] TIME TO FAIL: 1093 s

[loop-4] Thu Oct 19 23:09:38 EEST 2017 build failed

[loop-4] TIME TO FAIL: 1093 s

[loop-3] Thu Oct 19 23:09:38 EEST 2017 build failed

[loop-3] TIME TO FAIL: 1093 s

[loop-2] Thu Oct 19 23:09:39 EEST 2017 build failed

[loop-2] TIME TO FAIL: 1094 s

[loop-7] Thu Oct 19 23:09:40 EEST 2017 build failed

[loop-7] TIME TO FAIL: 1095 s

[loop-5] Thu Oct 19 23:09:40 EEST 2017 build failed

[loop-5] TIME TO FAIL: 1095 s

[loop-0] Thu Oct 19 23:09:42 EEST 2017 build failed

[loop-0] TIME TO FAIL: 1097 s

[loop-9] Thu Oct 19 23:09:47 EEST 2017 build failed

[loop-9] TIME TO FAIL: 1102 s

[loop-10] Thu Oct 19 23:09:48 EEST 2017 build failed

[loop-10] TIME TO FAIL: 1103 s

[loop-8] Thu Oct 19 23:09:49 EEST 2017 build failed

[loop-8] TIME TO FAIL: 1104 s

[loop-11] Thu Oct 19 23:09:49 EEST 2017 build failed

[loop-11] TIME TO FAIL: 1104 s

^C

atommi@tommi-aardvark:/home2/tommi/Lataukset/ryzen-test-master$ exit

exit

 

This is on Mint:

Using 12 parallel processes

[KERN] -- Logs begin at Thu 2017-10-19 23:36:38 EEST. --

[KERN] Oct 19 23:36:40 tommi-incredible kernel: nvidia-modeset: Allocated GPU:0 (GPU-abdf15a7-5e20-61f0-8612-4d2d2d8ccf08) @ PCI:0000:22:00.0

[KERN] Oct 19 23:36:43 tommi-incredible kernel: r8169 0000:1e:00.0 enp30s0: link up

[KERN] Oct 19 23:36:43 tommi-incredible kernel: IPv6: ADDRCONF(NETDEV_CHANGE): enp30s0: link becomes ready

[KERN] Oct 19 23:36:49 tommi-incredible kernel:  sdb: sdb1 sdb2 sdb3

[KERN] Oct 19 23:36:53 tommi-incredible kernel: Bluetooth: RFCOMM TTY layer initialized

[KERN] Oct 19 23:36:53 tommi-incredible kernel: Bluetooth: RFCOMM socket layer initialized

[KERN] Oct 19 23:36:53 tommi-incredible kernel: Bluetooth: RFCOMM ver 1.11

[KERN] Oct 20 00:00:28 tommi-incredible kernel: zram: Added device: zram0

[KERN] Oct 20 00:00:28 tommi-incredible kernel: zram0: detected capacity change from 0 to 68719476736

[KERN] Oct 20 00:00:28 tommi-incredible kernel: EXT4-fs (zram0): mounted filesystem with ordered data mode. Opts: discard

[loop-0] Fri Oct 20 00:02:29 EEST 2017 start 0

[loop-1] Fri Oct 20 00:02:30 EEST 2017 start 0

[loop-2] Fri Oct 20 00:02:31 EEST 2017 start 0

[loop-3] Fri Oct 20 00:02:32 EEST 2017 start 0

[loop-4] Fri Oct 20 00:02:33 EEST 2017 start 0

[loop-5] Fri Oct 20 00:02:34 EEST 2017 start 0

[loop-6] Fri Oct 20 00:02:35 EEST 2017 start 0

[loop-7] Fri Oct 20 00:02:36 EEST 2017 start 0

[loop-8] Fri Oct 20 00:02:37 EEST 2017 start 0

[loop-9] Fri Oct 20 00:02:38 EEST 2017 start 0

[loop-10] Fri Oct 20 00:02:39 EEST 2017 start 0

[loop-11] Fri Oct 20 00:02:40 EEST 2017 start 0

[loop-7] Fri Oct 20 00:03:15 EEST 2017 build failed

[loop-7] TIME TO FAIL: 46 s

[KERN] Oct 20 00:03:15 tommi-incredible kernel: show_signal_msg: 3 callbacks suppressed

[KERN] Oct 20 00:03:15 tommi-incredible kernel: bash[15813]: segfault at 543c08 ip 000000000041d989 sp 00007ffe7d9ca018 error 6 in bash[400000+f4000]

[loop-8] Fri Oct 20 00:03:45 EEST 2017 build failed

[loop-8] TIME TO FAIL: 76 s

[KERN] Oct 20 00:03:45 tommi-incredible kernel: bash[15401]: segfault at 78f710 ip 00000000004b9080 sp 00007ffda5a6f860 error 4 in bash[400000+f4000]

[loop-5] Fri Oct 20 00:04:53 EEST 2017 build failed

[loop-5] TIME TO FAIL: 144 s

[KERN] Oct 20 00:04:53 tommi-incredible kernel: bash[663]: segfault at 19b8be8 ip 00007fd8ee4ded73 sp 00007ffe4dee4850 error 6 in libc-2.23.so[7fd8ee378000+1c0000]

[loop-4] Fri Oct 20 00:07:10 EEST 2017 build failed

[loop-4] TIME TO FAIL: 281 s

[KERN] Oct 20 00:07:10 tommi-incredible kernel: genattr-common[24751]: segfault at 7fdafd1d3120 ip 00007fdafcf8d590 sp 00007ffc665d59b8 error 4 in libc-2.23.so[7fdafce3f000+1c0000]

^C

 

It seems on kernel 4.13 it produces fails less frequently than on 4.11, but still does.

Is the kill-ryzen script reliable in determining faulty CPU's? Should I RMA?

It is annoying for me, for my retailer specifically asked if I want to wait for a new CPU or take the known buggy right away. I waited, but did they send me a buggy one anyway?

 

Edit: removed serial number

Outcomes