|
:: damentz wrote :: 1) Install / enable irqbalance if you haven't already. That'll help distribute interrupts to all your different cores, reducing general CPU usage.It's already installed and activated. :: Quote :: 2) Add mitigations=off to your default grub command line. A mitigation may be currently affecting performance in some unusual way.I tried that as well, without any success. :: Quote :: 3) Try updating your BIOS[1]. You're on version 1201, while the latest is 5220. It's 18 updates newer than what you're running and might include some fixes that affect your current situation... which leads toYes I know that there are many newer bios version, but I use this version for a reason. I can't use newer Bios versions, otherwise my whole system will go unstable, as this is the latest version where my memory is running stable at rated speed. This is a known issue in the community and I know from forums that the situation with Zen1 CPUs got even worse with newer firmwares on this motherboard, as the newer AGESA version only focused on Zen+ and Zen2. :: Quote :: 4) Can you show me the output of journalctl -k | grep -i clocksource? One thing on my mind is the clock source doesn't like being polled at 1000hz. That might indicate that you're running hpet instead of tsc, which is known to have higher latency per time request. If you're on tsc, then that's something we can easily rule out.:: Code :: Dez 21 05:42:52 NoXP-PC kernel: clocksource: refined-jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 1910969940391419 ns
Dez 21 05:42:52 NoXP-PC kernel: clocksource: hpet: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 133484873504 ns Dez 21 05:42:52 NoXP-PC kernel: clocksource: tsc-early: mask: 0xffffffffffffffff max_cycles: 0x6d887208779, max_idle_ns: 881591156039 ns Dez 21 05:42:52 NoXP-PC kernel: clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 1911260446275000 ns Dez 21 05:42:52 NoXP-PC kernel: clocksource: Switched to clocksource tsc-early Dez 21 05:42:52 NoXP-PC kernel: clocksource: acpi_pm: mask: 0xffffff max_cycles: 0xffffff, max_idle_ns: 2085701024 ns Dez 21 05:42:52 NoXP-PC kernel: tsc: Refined TSC clocksource calibration: 3799.999 MHz Dez 21 05:42:52 NoXP-PC kernel: clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x6d8cadf3fd9, max_idle_ns: 881590557866 ns Dez 21 05:42:52 NoXP-PC kernel: clocksource: Switched to clocksource tsc Back to top |
|||||
|
I just want to confirm, my system got radically unstable, almost unbootable, with a bios/uefi update, luckily I was able to revert back to the original one, that barely supports the ram I have, but does it ok.
:: Code :: inxi -MCIxxxy80
Machine: Type: Desktop System: Gigabyte product: X470 AORUS ULTRA GAMING v: N/A serial: <root required> Mobo: Gigabyte model: X470 AORUS ULTRA GAMING-CF v: x.x serial: <root required> UEFI [Legacy]: American Megatrends v: F2 date: 03/14/2018 CPU: Topology: 6-Core model: AMD Ryzen 5 2600 bits: 64 type: MT MCP arch: Zen+ rev: 2 L2 cache: 3072 KiB flags: avx avx2 lm nx pae sse sse2 sse3 sse4_1 sse4_2 sse4a ssse3 svm bogomips: 81590 Speed: 1655 MHz min/max: 1550/3400 MHz Core speeds (MHz): 1: 1594 2: 1667 3: 1569 4: 1571 5: 1570 6: 1567 7: 1562 8: 1569 9: 1556 10: 1557 11: 1771 12: 1893 Info: Processes: 653 Uptime: 37d 2h 24m Memory: 31.43 GiB used: 17.14 GiB (54.5%) Init: systemd v: 241 runlevel: 5 Compilers: gcc: 8.3.0 alt: 5/6/7/8 Shell: bash v: 5.0.3 running in: xfce4-terminal inxi: 3.0.37 but I'm glad to see that this appears to be a known issue, my fault for having bought a 'gaming board', lol, oh well. Back to top |
|||||
|
It's actually not an issue with ASUS but with the AGESA, which is the AMD firmware for the CPUs.
Back to top |
|||||
|
Oh, an AMD issue!!! Even less surprising. Thanks for the update though, that had really freaked me out when I was trying to fix slightly broken Ram support when I first set up this system, and the entire thing totally freaked out on reboot with the updated firmware. On the bright side, it didn't brick, and I was able to revert. But AMD, yes, that's zero surprise to me sad to say. But I'm glad to know what it is, there wasn't a lot to be found when it happened to me, at least not readily, so my conclusion was to just never update the firmware again and leave it at that.
Back to top |
|||||
|
NoXPhasma, can you try the latest version? Should be 5.4.0-13.4 / 5.4-19. This version restores 250 hz but leaves tickless idle enabled.
There's an open ticket on the liquorix package github page too if you want to follow along there: github.com/damentz/liquorix-package/issues/24 EDIT: Also, can you try booting with nohz=n enabled if the 250hz tick rate doesn't help? Back to top |
|||||
|
All times are GMT - 8 Hours
|
|||||