Supermicro X12STL-IF-O
WD_BLACK SN850X 4000GB
TrueNAS-SCALE-23.10.0.1
I am experiencing intermittent system crashes. The console produces an error like this:
[58013.996053] nvme nvme0: controller is down; will reset: CSTS=0xffffffff, PCI_STATUS=0xffff
[58013.996053] nvme nvme0: Does your device have a faulty power saving mode enabled?
[58013.996243] nvme nvme0: Try "nvme_core.default_ps_max_latency_us=0 pcie_aspm=off" and report a bug
I tried adding the sysctl param via UI/Advanced/sysctl, but received an error.
"Sysctl 'nvme_core.default_ps_max_latency_us' does not exist in kernel."
Am I doing this in the wrong place?
EDIT:
This appears to have successfully added the params
This seems to survive reboots. Time will tell if it survives upgrades.
WD_BLACK SN850X 4000GB
TrueNAS-SCALE-23.10.0.1
I am experiencing intermittent system crashes. The console produces an error like this:
[58013.996053] nvme nvme0: controller is down; will reset: CSTS=0xffffffff, PCI_STATUS=0xffff
[58013.996053] nvme nvme0: Does your device have a faulty power saving mode enabled?
[58013.996243] nvme nvme0: Try "nvme_core.default_ps_max_latency_us=0 pcie_aspm=off" and report a bug
I tried adding the sysctl param via UI/Advanced/sysctl, but received an error.
"Sysctl 'nvme_core.default_ps_max_latency_us' does not exist in kernel."
Am I doing this in the wrong place?
EDIT:
This appears to have successfully added the params
root@truenas[~]# midclt call system.advanced.update '{"kernel_extra_options": "nvme_core.default_ps_max_latency_us=0 pcie_aspm=off"}'
This seems to survive reboots. Time will tell if it survives upgrades.
admin@truenas[~]$ cat /proc/cmdline
BOOT_IMAGE=/ROOT/23.10.0.1@/boot/vmlinuz-6.1.55-production+truenas root=ZFS=boot-pool/ROOT/23.10.0.1 ro libata.allow_tpm=1 amd_iommu=on iommu=pt kvm_amd.npt=1 kvm_amd.avic=1 intel_iommu=on zfsforce=1 nvme_core.multipath=N nvme_core.default_ps_max_latency_us=0 pcie_aspm=off
admin@truenas[~]$
Last edited: