mirror of
https://github.com/ryan4yin/nix-config.git
synced 2026-11-13 12:13:46 +01:00
ryan4yin | 二花
dc3ec8c159
* fix(ai): relax NVMe power-management workarounds and enable smartd Logs show no NVMe errors, so allow APST again (capped at 100 ms), restore the default io_timeout, and drop pcie_aspm=off. Add smartd for drive health visibility. * feat(storage): add drive/SSD SMART monitoring on physical hosts node_exporter's nvme collector only exposes node_nvme_info and namespace capacity, not SMART health, so SSD wear/lifespan and drive temperature were not observable anywhere. - enable services.prometheus.exporters.smartctl on physical hosts, gated on modules.hardwareTools (off on QEMU/MicroVM guests), bound to the host's LAN address on port 9633 - firewall: drop 9633 from anything but the monitoring host - youko: scrape smartctl-<host> for the physical hosts - alert rules (storage.yml): SMART health, NVMe wear, available spare, media errors, critical warning, and drive temperature (warn 70 / crit 80 C) - Grafana dashboard "Drive SMART (smartctl)"
93 lines
3.6 KiB
Nix
93 lines
3.6 KiB
Nix
# Do not modify this file! It was generated by ‘nixos-generate-config’
|
||
# and may be overwritten by future invocations. Please make changes
|
||
# to /etc/nixos/configuration.nix instead.
|
||
{
|
||
config,
|
||
lib,
|
||
pkgs,
|
||
modulesPath,
|
||
...
|
||
}:
|
||
{
|
||
imports = [
|
||
(modulesPath + "/installer/scan/not-detected.nix")
|
||
];
|
||
|
||
boot.kernelParams = [
|
||
# === NVMe power management (relaxed 2026-10) ===
|
||
#
|
||
# These began as a hard workaround for NVMe freezes on the KINGBANK KP260
|
||
# (a DRAM-less QLC drive, prone to slow APST wakeups): APST fully disabled,
|
||
# the command timeout pushed to the maximum, and PCIe ASPM turned off.
|
||
# Kernel logs from 2026-09-19..10-03 (8 boots) show no NVMe
|
||
# timeout/reset/AER, so it is relaxed to reclaim idle power and let the
|
||
# kernel recover a stuck command instead of hanging on it:
|
||
#
|
||
# - APST allowed again, capped at a wide 100 ms latency (was: disabled).
|
||
# - io_timeout back to the kernel default 30 s (was: ~49 days, which let
|
||
# a stuck command wait forever instead of resetting the controller).
|
||
# - pcie_aspm removed: PCIe link power saving is unrelated to the drive's
|
||
# own APST.
|
||
#
|
||
# If freezes return under heavy read/write, restore the old workaround:
|
||
# nvme_core.default_ps_max_latency_us=0 nvme_core.io_timeout=4294967295 pcie_aspm=off
|
||
# See https://community.frame.work/t/nvme-timeout-woes/54999
|
||
"nvme_core.default_ps_max_latency_us=100000"
|
||
];
|
||
|
||
# Use the EFI boot loader.
|
||
boot.loader.efi.canTouchEfiVariables = true;
|
||
# depending on how you configured your disk mounts, change this to /boot or /boot/efi.
|
||
boot.loader.efi.efiSysMountPoint = "/boot";
|
||
boot.loader.systemd-boot.enable = true;
|
||
|
||
# https://github.com/NixOS/nixpkgs/blob/nixos-unstable/pkgs/top-level/linux-kernels.nix
|
||
boot.kernelPackages = pkgs.linuxPackages_latest;
|
||
|
||
boot.initrd.availableKernelModules = [
|
||
"xhci_pci"
|
||
"ahci"
|
||
"nvme"
|
||
"usbhid"
|
||
"usb_storage"
|
||
"sd_mod"
|
||
];
|
||
# clear /tmp on boot to get a stateless /tmp directory.
|
||
boot.tmp.cleanOnBoot = true;
|
||
|
||
# Enable binfmt emulation of aarch64-linux, this is required for cross compilation.
|
||
boot.binfmt.emulatedSystems = [
|
||
"aarch64-linux"
|
||
"riscv64-linux"
|
||
];
|
||
# This enables the kernel to preload the emulator binaries when the binfmt registrations are added,
|
||
# obviating the need to make the emulator binaries available inside chroots and chroot-like sandboxes.
|
||
boot.binfmt.preferStaticEmulators = true; # required to work with podman
|
||
|
||
# supported file systems, so we can mount any removable disks with these filesystems
|
||
boot.supportedFilesystems = [
|
||
"ext4"
|
||
"btrfs"
|
||
"xfs"
|
||
"ntfs"
|
||
"fat"
|
||
"vfat"
|
||
"exfat"
|
||
];
|
||
|
||
# LUKS initrd, all fileSystems (/, /boot, /btr_pool, /nix, /persistent, /snapshots, /tmp, /swap)
|
||
# and swap (including /swap/swapfile bind and swapDevices) are managed by disko (disko-fs.nix).
|
||
|
||
# Enables DHCP on each ethernet and wireless interface. In case of scripted networking
|
||
# (the default) this is the recommended approach. When using systemd-networkd it's
|
||
# still possible to use this option, but it's recommended to use it in conjunction
|
||
# with explicit per-interface declarations with `networking.interfaces.<interface>.useDHCP`.
|
||
networking.useDHCP = lib.mkDefault true;
|
||
# networking.interfaces.enp5s0.useDHCP = lib.mkDefault true;
|
||
# networking.interfaces.wlo1.useDHCP = lib.mkDefault true;
|
||
|
||
nixpkgs.hostPlatform = lib.mkDefault "x86_64-linux";
|
||
powerManagement.cpuFreqGovernor = lib.mkDefault "performance"; # ondemand / powersave / performance
|
||
hardware.cpu.intel.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
|
||
}
|