June 11, 20251 yr Hello all,On my system I have 2 x 512 GB nvme sticks acting as pool devices. The filesystem is ZFS.I noticed that one of the 2 nvme sticks is doing nothing. The ZFS master plugin shows that the cache health is "degraded" without any additional information. Do you have any idea of what is going on here and how to fix it?Thanks.
June 11, 20251 yr Author I tried to online the second nvme and then clear errors but it did not help...
June 11, 20251 yr Author Ok after a cold reboot things are back to normal. Not sure what happened here. I have set the "spin down" to never on that nvme to see if it prevents it from disappearing.. Edited June 11, 20251 yr by googleg
June 11, 20251 yr Community Expert Solution NVMe device dropped offline:May 23 13:19:14 Nas3 kernel: nvme nvme0: controller is down; will reset: CSTS=0xffffffff, PCI_STATUS=0x10May 23 13:19:14 Nas3 kernel: nvme nvme0: Does your device have a faulty power saving mode enabled?May 23 13:19:14 Nas3 kernel: nvme nvme0: Try "nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off" and report a bugMay 23 13:19:14 Nas3 kernel: nvme 0000:01:00.0: enabling device (0000 -> 0002)May 23 13:19:14 Nas3 kernel: nvme nvme0: Disabling device after reset failure: -19Try adding those options to syslinux.cfg, also you should scrub the pool now.
June 11, 20251 yr Author Ok, please help me there, where do I add "nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off"Is it under "Uuraid OS" after "append initrd=/bzroot" ?Also do you know I should scrub the pool? Is there an indication showing anywhere? Just curious.
June 11, 20251 yr Community Expert 9 minutes ago, googleg said:Is it under "Uuraid OS" after "append initrd=/bzroot" ?Correct.9 minutes ago, googleg said:Also do you know I should scrub the pool?Click the first pool device, then scroll down to the Pool Status section and you'll see the scrub button.
June 11, 20251 yr Author Thank you, I've implemented the extra kernel parameters and I will monitor the situation.Hopefully this will fix it. If not I've read that others have solved the issue by swapping the NVMEs or simply replacing it with a different brand/model.
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.