search

suaefar / ryzen-test

Tools to reproduce randomly crashing processes under load on AMD Ryzen processors on Linux
GNU General Public License v3.0
224 stars 59 forks source link

Seems to be stuck at loop-11 #37

Open Pindacolada opened 3 years ago

Pindacolada commented 3 years ago

Can't get past loop-11 and it just freezes and does nothing anymore

`[pindacolada@moonman ryzen-test-master]$ ./kill-ryzen.sh Create compressed ramdisk 64G Download GCC sources --2021-09-26 20:22:22-- 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 11.0MB/s in 9.3s

2021-09-26 20:22:31 (8.66 MB/s) - 'gcc-7.1.0.tar.bz2' saved [84303533]

Extract GCC sources Download prerequisites 2021-09-26 20:22:47 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/gmp-6.1.0.tar.bz2 [2383840] -> "./gmp-6.1.0.tar.bz2" [1] 2021-09-26 20:22:49 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/mpfr-3.1.4.tar.bz2 [1279284] -> "./mpfr-3.1.4.tar.bz2" [1] 2021-09-26 20:22:51 URL: ftp://gcc.gnu.org/pub/gcc/infrastructure/mpc-1.0.3.tar.gz [669925] -> "./mpc-1.0.3.tar.gz" [1] 2021-09-26 20:22:54 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 : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 model name : AMD Ryzen 5 1600X Six-Core Processor microcode : 0x8001138 sudo dmidecode -t memory | grep -i -E "(rank|speed|part)" | grep -v -i unknown sudo: dmidecode: command not found uname -a Linux moonman 5.14.7-arch1-1 #1 SMP PREEMPT Wed, 22 Sep 2021 21:35:11 +0000 x86_64 GNU/Linux cat /proc/sys/kernel/randomize_va_space 2 / /mnt/ramdisk/workdir /mnt/ramdisk/workdir Using 12 parallel processes [loop-0] Sun Sep 26 20:22:54 CEST 2021 start 0 [KERN] -- Journal begins at Wed 2021-05-12 23:12:39 CEST. -- [KERN] Sep 26 20:22:21 moonman kernel: audit: type=1101 audit(1632680541.607:170): pid=3182 uid=1000 auid=1000 ses=2 msg='op=PAM:accounting grantors=pam_unix,pam_permit,pam_time acct="pindacolada" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [KERN] Sep 26 20:22:21 moonman kernel: audit: type=1110 audit(1632680541.607:171): pid=3182 uid=1000 auid=1000 ses=2 msg='op=PAM:setcred grantors=pam_faillock,pam_permit,pam_env,pam_faillock acct="root" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [KERN] Sep 26 20:22:21 moonman kernel: audit: type=1105 audit(1632680541.607:172): pid=3182 uid=1000 auid=1000 ses=2 msg='op=PAM:session_open grantors=pam_limits,pam_unix,pam_permit acct="root" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [KERN] Sep 26 20:22:21 moonman kernel: zram: Added device: zram0 [KERN] Sep 26 20:22:21 moonman kernel: audit: type=1106 audit(1632680541.614:173): pid=3182 uid=1000 auid=1000 ses=2 msg='op=PAM:session_close grantors=pam_limits,pam_unix,pam_permit acct="root" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [KERN] Sep 26 20:22:21 moonman kernel: audit: type=1104 audit(1632680541.614:174): pid=3182 uid=1000 auid=1000 ses=2 msg='op=PAM:setcred grantors=pam_faillock,pam_permit,pam_env,pam_faillock acct="root" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [KERN] Sep 26 20:22:21 moonman kernel: zram0: detected capacity change from 0 to 134217728 [KERN] Sep 26 20:22:22 moonman kernel: EXT4-fs (zram0): mounted filesystem with ordered data mode. Opts: discard. Quota mode: none. [KERN] Sep 26 20:22:54 moonman kernel: kauditd_printk_skb: 27 callbacks suppressed [KERN] Sep 26 20:22:54 moonman kernel: audit: type=1101 audit(1632680574.942:202): pid=3267 uid=1000 auid=1000 ses=2 msg='op=PAM:accounting grantors=pam_unix,pam_permit,pam_time acct="pindacolada" exe="/usr/bin/sudo" hostname=? addr=? terminal=/dev/pts/1 res=success' [loop-1] Sun Sep 26 20:22:55 CEST 2021 start 0 [loop-2] Sun Sep 26 20:22:56 CEST 2021 start 0 [loop-3] Sun Sep 26 20:22:57 CEST 2021 start 0 [loop-4] Sun Sep 26 20:22:58 CEST 2021 start 0 [loop-5] Sun Sep 26 20:22:59 CEST 2021 start 0 [loop-6] Sun Sep 26 20:23:00 CEST 2021 start 0 [loop-7] Sun Sep 26 20:23:01 CEST 2021 start 0 [loop-8] Sun Sep 26 20:23:02 CEST 2021 start 0 [loop-9] Sun Sep 26 20:23:03 CEST 2021 start 0 [loop-10] Sun Sep 26 20:23:04 CEST 2021 start 0 [loop-11] Sun Sep 26 20:23:05 CEST 2021 start 0`

is this an expected behavior and means that it failed or am i doing something wrong?

suaefar commented 3 years ago

Hi! I don't know if these scripts work with arch. The scripts were developed, used, and tested with a specific version of ubuntu (17.04). They generated a load which was likely to trigger a hardware bug on early first generation ryzen cpus. If you had enough RAM, in theory, the compilation processes should go on forever without any error. But faulty cpus (as well as overclocked RAM) produced segfaults after a few minutes.

Oxalin commented 3 years ago

@Pindacolada you could try this link: https://github.com/Oxalin/ryzen-test

I had to modify the original script to make it work properly under Arch. That said, it was a few years ago and I haven't tested it since I replaced my faulty CPU at the time.