Lag / stutter in games on kernel linux-tkg-bmq with a Ryzen CPU

Frawo · 19 January 2021 13:42

I'm running the Garuda Linux KDE "Dr4Gonized" Gaming Edition which comes with the tkg-bmq kernel preinstalled. In some games, for example the assassins creed titles, I noticed the game lag /hang for a second, happening about every 20-30 seconds while running perfectly smooth otherwise. After doing some research and trying out potential fixes like disabling the compositor or using gamemode I finally installed the linux-zen kernel, which fixed the issue for me. CPU is a Ryzen 5 3600, btw.

So, why am I posting this when it is apparantly solved? I just want to share my experience here, in case other users should stumble across this. At the same time I would like to ask if there are any disadvantages using the zen-kernel? Are there other kernels you would prefer for a Ryzen CPU? So far, I haven't noticed a difference using the zen kernel instead of tkg-bmq (apart from the lag problem).

jonathon · 19 January 2021 13:54

Different kernels work better for different CPUs, this is a reason why there is a range of TKG kernels to choose from.

I've found linux-xanmod will cause micro-freezes on my system but linux-lqx runs nicely. YMMV.

FGD · 19 January 2021 14:19

Are all the TKG kernel versions available through pacman?
I have severe testing undergoing for a similar issue as the OP (I get the issue when hardware is idling) and I'd like to test different kernels.

FGD · 19 January 2021 14:24

@Frawo, it seems BMQ kernel, which is probably the one you are using, could cause gaming issues.

dr460nf1r3 · 19 January 2021 15:19

As we were contemplating switching to xanmod today, Im very interested in actual feedback using this kernel. Would you be so kind to test if this one causes issues on your end?

Frawo · 19 January 2021 19:08

Of course, glad I can help. I will need some days though, as I'm pretty busy with work right now.

One question, in pamac I see linux-xanmod and linux-xanmod-dr460nized, which one to test?

dr460nf1r3 · 19 January 2021 19:12

The linux-xanmod one, the second one was just a test (compiled with anbox, for haswell archtecture)

FGD · 19 January 2021 20:04

Interesting, it seems Xanmod could be so-so with some Virtualization softwares, which I do use quite often.

https://xanmod.org/

I think I'll try to test it. If yes I'll post somewhere, @dr460nf1r3

pupperemeritus · 20 January 2021 14:34

There are linux tkg kernels specifically optimized for certain architectures. you can search for the linux-tkg kernels that are for zen2. they have zen2 at the end of their package names.

Frawo · 21 January 2021 09:08

Yesterday, I have done my daily work with the new xanmod kernel, no issues, everything went smooth. Today, the system crashed while updating. I had this kind of crash once with the zen kernel, too. Here is the output of inxi -Fxxxa for this machine:

System:    Kernel: 5.10.7-xanmod1-1 x86_64 bits: 64 compiler: gcc v: 10.2.0
           parameters: BOOT_IMAGE=/@/boot/vmlinuz-linux-xanmod
           root=UUID=b2af4f73-857e-4594-800b-edf146a43b6e rw [email protected] quiet splash
           rd.udev.log_priority=3 vt.global_cursor_default=0 systemd.unified_cgroup_hierarchy=1 loglevel=3
           Desktop: KDE Plasma 5.20.5 tk: Qt 5.15.2 info: latte-dock wm: kwin_x11 dm: SDDM
           Distro: Garuda Linux
Machine:   Type: Desktop System: Gigabyte product: X470 AORUS ULTRA GAMING v: N/A serial: <filter>
           Mobo: Gigabyte model: X470 AORUS ULTRA GAMING-CF v: x.x serial: <filter>
           UEFI: American Megatrends v: F41 date: 07/22/2019
Battery:   ID-1: hidpp_battery_0 charge: N/A condition: N/A volts: 4.2/N/A
           model: Logitech G Pro Wireless Gaming Mouse type: N/A serial: <filter> status: Full
CPU:       Info: 6-Core model: AMD Ryzen 5 1600 bits: 64 type: MT MCP arch: Zen family: 17 (23)
           model-id: 1 stepping: 1 microcode: 8001138 L2 cache: 3 MiB
           flags: avx avx2 lm nx pae sse sse2 sse3 sse4_1 sse4_2 sse4a ssse3 svm bogomips: 76799
           Speed: 1550 MHz min/max: 1550/3200 MHz boost: disabled Core speeds (MHz): 1: 1550 2: 1550
           3: 1550 4: 1550 5: 1550 6: 1550 7: 1550 8: 1550 9: 1550 10: 1550 11: 1550 12: 1550
           Vulnerabilities: Type: itlb_multihit status: Not affected
           Type: l1tf status: Not affected
           Type: mds status: Not affected
           Type: meltdown status: Not affected
           Type: spec_store_bypass mitigation: Speculative Store Bypass disabled via prctl and seccomp
           Type: spectre_v1 mitigation: usercopy/swapgs barriers and __user pointer sanitization
           Type: spectre_v2
           mitigation: Full AMD retpoline, IBPB: conditional, STIBP: disabled, RSB filling
           Type: srbds status: Not affected
           Type: tsx_async_abort status: Not affected
Graphics:  Device-1: AMD Ellesmere [Radeon RX 470/480/570/570X/580/580X/590] vendor: Tul driver: amdgpu
           v: kernel bus ID: 09:00.0 chip ID: 1002:67df
           Display: x11 server: X.Org 1.20.10 compositor: kwin_x11 driver: amdgpu,ati
           unloaded: modesetting alternate: fbdev,vesa display ID: :0 screens: 1
           Screen-1: 0 s-res: 3840x1080 s-dpi: 96 s-size: 1016x285mm (40.0x11.2") s-diag: 1055mm (41.5")
           Monitor-1: HDMI-A-0 res: 1920x1080 hz: 60 dpi: 96 size: 510x290mm (20.1x11.4")
           diag: 587mm (23.1")
           Monitor-2: DVI-D-0 res: 1920x1080 hz: 60 dpi: 92 size: 531x298mm (20.9x11.7") diag: 609mm (24")
           OpenGL:
           renderer: AMD Radeon RX 480 Graphics (POLARIS10 DRM 3.40.0 5.10.7-xanmod1-1 LLVM 11.0.1)
           v: 4.6 Mesa 20.3.3 direct render: Yes
Audio:     Device-1: Creative Labs EMU20k2 [Sound Blaster X-Fi Titanium Series] driver: snd_ctxfi
           v: kernel bus ID: 03:00.0 chip ID: 1102:000b
           Device-2: AMD Ellesmere HDMI Audio [Radeon RX 470/480 / 570/580/590] vendor: Tul
           driver: snd_hda_intel v: kernel bus ID: 09:00.1 chip ID: 1002:aaf0
           Device-3: AMD Family 17h HD Audio vendor: Gigabyte driver: snd_hda_intel v: kernel
           bus ID: 0b:00.3 chip ID: 1022:1457
           Device-4: Licensed by Sony Entertainment America Rocksmith Guitar Adapter type: USB
           driver: hid-generic,snd-usb-audio,usbhid bus ID: 1-3:2 chip ID: 12ba:00ff
           Device-5: Logitech Webcam C270 type: USB driver: snd-usb-audio,uvcvideo bus ID: 1-4:3
           chip ID: 046d:0825 serial: <filter>
           Device-6: C-Media CM108 Audio Controller type: USB driver: hid-generic,snd-usb-audio,usbhid
           bus ID: 1-7:4 chip ID: 0d8c:013c
           Sound Server: ALSA v: k5.10.7-xanmod1-1
Network:   Device-1: Intel I211 Gigabit Network vendor: Gigabyte driver: igb v: kernel port: f000
           bus ID: 06:00.0 chip ID: 8086:1539
           IF: enp6s0 state: up speed: 1000 Mbps duplex: full mac: <filter>
Drives:    Local Storage: total: 922.22 GiB used: 234.65 GiB (25.4%)
           SMART Message: Unable to run smartctl. Root privileges required.
           ID-1: /dev/sda maj-min: 8:0 vendor: Samsung model: SSD 840 EVO 250GB size: 232.89 GiB
           block size: physical: 512 B logical: 512 B speed: 6.0 Gb/s serial: <filter> rev: BB0Q
           ID-2: /dev/sdb maj-min: 8:16 vendor: SanDisk model: SDSSDHII240G size: 223.57 GiB block size:
           physical: 512 B logical: 512 B speed: 6.0 Gb/s serial: <filter> rev: 00RL
           ID-3: /dev/sdc maj-min: 8:32 vendor: Western Digital model: WD5000AAKS-08V0A0 size: 465.76 GiB
           block size: physical: 512 B logical: 512 B speed: 3.0 Gb/s serial: <filter> rev: 1D05
Partition: ID-1: / raw size: 50 GiB size: 50 GiB (100.00%) used: 27.18 GiB (54.4%) fs: btrfs
           dev: /dev/sda3 maj-min: 8:3
           ID-2: /boot/efi raw size: 512 MiB size: 511 MiB (99.80%) used: 28.3 MiB (5.5%) fs: vfat
           dev: /dev/sda1 maj-min: 8:1
           ID-3: /home raw size: 50 GiB size: 50 GiB (100.00%) used: 27.18 GiB (54.4%) fs: btrfs
           dev: /dev/sda3 maj-min: 8:3
           ID-4: /var/log raw size: 50 GiB size: 50 GiB (100.00%) used: 27.18 GiB (54.4%) fs: btrfs
           dev: /dev/sda3 maj-min: 8:3
           ID-5: /var/tmp raw size: 50 GiB size: 50 GiB (100.00%) used: 27.18 GiB (54.4%) fs: btrfs
           dev: /dev/sda3 maj-min: 8:3
Swap:      Kernel: swappiness: 10 (default 60) cache pressure: 75 (default 100)
           ID-1: swap-1 type: partition size: 7.81 GiB used: 0 KiB (0.0%) priority: -2 dev: /dev/sda6
           maj-min: 8:6
           ID-2: swap-2 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram0
           ID-3: swap-3 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram1
           ID-4: swap-4 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram2
           ID-5: swap-5 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram3
           ID-6: swap-6 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram4
           ID-7: swap-7 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram5
           ID-8: swap-8 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram6
           ID-9: swap-9 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram7
           ID-10: swap-10 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram8
           ID-11: swap-11 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram9
           ID-12: swap-12 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram10
           ID-13: swap-13 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram11
Sensors:   System Temperatures: cpu: 35.6 C mobo: N/A gpu: amdgpu temp: 61.0 C
           Fan Speeds (RPM): N/A gpu: amdgpu fan: 592
Info:      Processes: 369 Uptime: 16m wakeups: 2 Memory: 15.64 GiB used: 3.74 GiB (23.9%) Init: systemd
           v: 247 Compilers: gcc: 10.2.0 clang: 11.0.1 Packages: pacman: 1845 lib: 545 Shell: fish
           v: 3.1.2 running in: alacritty inxi: 3.2.01

Frawo · 21 January 2021 12:28

Following the output for my second system, which I use primarily for gaming. Everything worked fine, even gaming, and I did not encounter any crashes on the xanmod kernel yet:

System:    Host: gaming-pc Kernel: 5.10.7-xanmod1-1 x86_64 bits: 64 compiler: gcc v: 10.2.0
           parameters: BOOT_IMAGE=/@/boot/vmlinuz-linux-xanmod
           root=UUID=dabcce28-70c9-4f66-b54a-36f50975265e rw [email protected] quiet splash
           rd.udev.log_priority=3 vt.global_cursor_default=0 systemd.unified_cgroup_hierarchy=1 loglevel=3
           Desktop: KDE Plasma 5.20.5 tk: Qt 5.15.2 info: latte-dock wm: kwin_x11 dm: SDDM
           Distro: Garuda Linux
Machine:   Type: Desktop System: Gigabyte product: AB350N-Gaming WIFI v: N/A serial: <superuser required>
           Mobo: Gigabyte model: AB350N-Gaming WIFI-CF serial: <superuser required>
           UEFI: American Megatrends v: F42a date: 07/31/2019
CPU:       Info: 6-Core model: AMD Ryzen 5 3600 bits: 64 type: MT MCP arch: Zen 2 family: 17 (23)
           model-id: 71 (113) stepping: N/A microcode: 8701013 L2 cache: 3 MiB
           flags: avx avx2 lm nx pae sse sse2 sse3 sse4_1 sse4_2 sse4a ssse3 svm bogomips: 86236
           Speed: 3588 MHz min/max: 2200/3600 MHz boost: enabled Core speeds (MHz): 1: 3588 2: 3591
           3: 3848 4: 3837 5: 3590 6: 3588 7: 3449 8: 3858 9: 3867 10: 3598 11: 3771 12: 3843
           Vulnerabilities: Type: itlb_multihit status: Not affected
           Type: l1tf status: Not affected
           Type: mds status: Not affected
           Type: meltdown status: Not affected
           Type: spec_store_bypass mitigation: Speculative Store Bypass disabled via prctl and seccomp
           Type: spectre_v1 mitigation: usercopy/swapgs barriers and __user pointer sanitization
           Type: spectre_v2
           mitigation: Full AMD retpoline, IBPB: conditional, STIBP: always-on, RSB filling
           Type: srbds status: Not affected
           Type: tsx_async_abort status: Not affected
Graphics:  Device-1: NVIDIA GP104 [GeForce GTX 1070] vendor: ZOTAC driver: nvidia v: 460.32.03
           alternate: nvidiafb,nouveau,nvidia_drm bus ID: 0a:00.0 chip ID: 10de:1b81
           Display: x11 server: X.Org 1.20.10 compositor: kwin_x11 driver: nvidia display ID: :0
           screens: 1
           Screen-1: 0 s-res: 3840x2160 s-dpi: 40 s-size: 2439x1372mm (96.0x54.0") s-diag: 2798mm (110.2")
           Monitor-1: HDMI-0 res: 3840x2160 hz: 60 dpi: 80 size: 1220x680mm (48.0x26.8")
           diag: 1397mm (55")
           OpenGL: renderer: GeForce GTX 1070/PCIe/SSE2 v: 4.6.0 NVIDIA 460.32.03 direct render: Yes
Audio:     Device-1: NVIDIA GP104 High Definition Audio vendor: ZOTAC driver: snd_hda_intel v: kernel
           bus ID: 0a:00.1 chip ID: 10de:10f0
           Device-2: AMD Starship/Matisse HD Audio vendor: Gigabyte driver: snd_hda_intel v: kernel
           bus ID: 0c:00.4 chip ID: 1022:1487
           Sound Server: ALSA v: k5.10.7-xanmod1-1
Network:   Device-1: Intel Wireless 3165 driver: iwlwifi v: kernel bus ID: 07:00.0 chip ID: 8086:3165
           IF: wlp7s0 state: down mac: 4e:07:5a:1e:49:eb
           Device-2: Realtek RTL8111/8168/8411 PCI Express Gigabit Ethernet vendor: Gigabyte driver: r8169
           v: kernel port: f000 bus ID: 09:00.0 chip ID: 10ec:8168
           IF: enp9s0 state: up speed: 1000 Mbps duplex: full mac: e0:d5:5e:26:0b:fc
Drives:    Local Storage: total: 2.34 TiB used: 665.89 GiB (27.8%)
           SMART Message: Unable to run smartctl. Root privileges required.
           ID-1: /dev/nvme0n1 maj-min: 259:0 vendor: Samsung model: SSD 970 EVO 500GB size: 465.76 GiB
           block size: physical: 512 B logical: 512 B speed: 31.6 Gb/s lanes: 4 serial: S5H7NG0N323398Z
           rev: 2B2QEXE7 temp: 40.9 C
           ID-2: /dev/sda maj-min: 8:0 vendor: SanDisk model: SDSSDH3512G size: 476.94 GiB block size:
           physical: 512 B logical: 512 B speed: 6.0 Gb/s serial: 183512421924 rev: 7000
           ID-3: /dev/sdb maj-min: 8:16 vendor: Crucial model: M4-CT064M4SSD2 size: 59.63 GiB block size:
           physical: 512 B logical: 512 B speed: 6.0 Gb/s serial: 00000000124209196E71 rev: 010G
           ID-4: /dev/sdc maj-min: 8:32 vendor: Western Digital model: WD10EZEX-75WN4A0 size: 931.51 GiB
           block size: physical: 4096 B logical: 512 B speed: 6.0 Gb/s serial: WD-WCC6Y6CCVY4S rev: 1A01
           ID-5: /dev/sdd maj-min: 8:48 vendor: Samsung model: SSD 860 EVO 500GB size: 465.76 GiB
           block size: physical: 512 B logical: 512 B speed: 6.0 Gb/s serial: S3Z2NB1KA69733E rev: 1B6Q
Partition: ID-1: / raw size: 50 GiB size: 50 GiB (100.00%) used: 24.64 GiB (49.3%) fs: btrfs
           dev: /dev/nvme0n1p3 maj-min: 259:3
           ID-2: /boot/efi raw size: 513 MiB size: 512 MiB (99.80%) used: 100.3 MiB (19.6%) fs: vfat
           dev: /dev/nvme0n1p1 maj-min: 259:1
           ID-3: /home raw size: 50 GiB size: 50 GiB (100.00%) used: 24.64 GiB (49.3%) fs: btrfs
           dev: /dev/nvme0n1p3 maj-min: 259:3
           ID-4: /var/log raw size: 50 GiB size: 50 GiB (100.00%) used: 24.64 GiB (49.3%) fs: btrfs
           dev: /dev/nvme0n1p3 maj-min: 259:3
           ID-5: /var/tmp raw size: 50 GiB size: 50 GiB (100.00%) used: 24.64 GiB (49.3%) fs: btrfs
           dev: /dev/nvme0n1p3 maj-min: 259:3
Swap:      Kernel: swappiness: 10 (default 60) cache pressure: 75 (default 100)
           ID-1: swap-1 type: partition size: 8 GiB used: 0 KiB (0.0%) priority: -2 dev: /dev/nvme0n1p9
           maj-min: 259:9
           ID-2: swap-2 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram0
           ID-3: swap-3 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram1
           ID-4: swap-4 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram2
           ID-5: swap-5 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram3
           ID-6: swap-6 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram4
           ID-7: swap-7 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram5
           ID-8: swap-8 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram6
           ID-9: swap-9 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram7
           ID-10: swap-10 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram8
           ID-11: swap-11 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram9
           ID-12: swap-12 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram10
           ID-13: swap-13 type: zram size: 1.3 GiB used: 0 KiB (0.0%) priority: 32767 dev: /dev/zram11
Sensors:   System Temperatures: cpu: 54.5 C mobo: N/A gpu: nvidia temp: 64 C
           Fan Speeds (RPM): N/A gpu: nvidia fan: 20%
Info:      Processes: 321 Uptime: 23m wakeups: 0 Memory: 15.64 GiB used: 3.24 GiB (20.7%) Init: systemd
           v: 247 Compilers: gcc: 10.2.0 Packages: pacman: 1633 lib: 494 Shell: fish v: 3.1.2
           running in: alacritty inxi: 3.2.01

FGD · 21 January 2021 14:50

Do you have an output of the crash? Error msgs or something?

If I understand you have 2 machines, one for daily work and one for gaming?

Since this seems to be related to xanmod tests, I think it would be good to start a topic on testing xanmod, I was about to do it myself but you have more data than I do so far on testing.

Frawo · 21 January 2021 17:46

Unfortunately, I could not find any error messages with journalctl, just an abrupt restart. Are there other places I can look for errors?

Yes, I have 2 machines where Garuda is installed on. As you said, one is for daily work, and one for gaming. The machine for daily work (Ryzen 5 1600) is very picky when it comes to kernels, for example I have c-states disabled on this machine for a long time now because otherwise I had crashes on every kernel sooner or later. Maybe I should try to turn it on again?

The gaming machine (Ryzen 5 3600) almost never crashes, no matter what kernel I throw at it...

FGD · 21 January 2021 18:05

I'm not much of an expert in log files, maybe dmesg?
That is quite abrupt yes, however maybe it has nothing to do with the kernel. Based on your comment it seems the daily machine might have more sensitive hardware. It's good to test the xanmod against it, but personnaly I would base my impressions of xanmod on a machine you know is not that sensitive. Otherwise it could biaise the results.

I'll start a topic on that testing, I also have accumulated some data I'm ready to share.