I just recently upgraded the CPU, motherboard, and NVME Cache Drive in my Unraid server. About once a week, I will find my server completely unresponsive...cannot ssh, connect a monitor, get any response.

Out of caution, because I've been using the same USB Flash Boot drive for 12+ years on this system, I decided to replace that hoping it would resolve the issue, but it did not.

I recently enabled the "mirror syslog to flash" on shutdown feature hoping to catch the true cause of this. It happened again last night, 12/20/25 sometime in-between 9pm and 1am server time.

I'm attaching the last few lines of the syslog-previous and a diagnostics I captured this morning in hopes that someone can spot an issue that may be causing it.

Dec 20 14:41:50 tower emhttpd: spinning down /dev/sdf
Dec 20 14:43:00 tower kernel: mdcmd (58): set md_write_method 0
Dec 20 14:43:00 tower kernel: 
Dec 20 21:00:31 tower kernel: nvme nvme0: I/O tag 0 (5000) opcode 0x9 (I/O Cmd) QID 3 timeout, aborting req_op:DISCARD(3) size:250016256
Dec 20 21:00:31 tower kernel: nvme nvme0: I/O tag 1 (9001) opcode 0x9 (I/O Cmd) QID 3 timeout, aborting req_op:DISCARD(3) size:4240388096
Dec 20 21:00:31 tower kernel: nvme nvme0: I/O tag 2 (f002) opcode 0x9 (I/O Cmd) QID 3 timeout, aborting req_op:DISCARD(3) size:3388657664
Dec 20 21:01:01 tower kernel: nvme nvme0: I/O tag 0 (5000) opcode 0x9 (I/O Cmd) QID 3 timeout, reset controller
Dec 20 21:04:13 tower kernel: nvme nvme0: Device not ready; aborting reset, CSTS=0x1
Dec 20 21:04:13 tower kernel: nvme nvme0: Abort status: 0x371
Dec 20 21:04:13 tower kernel: nvme nvme0: Abort status: 0x371
Dec 20 21:04:13 tower kernel: nvme nvme0: Abort status: 0x371
Dec 20 21:06:21 tower kernel: nvme nvme0: Device not ready; aborting reset, CSTS=0x1
Dec 20 21:06:29 tower kernel: r8169 0000:06:00.0 eth0: NETDEV WATCHDOG: CPU: 16: transmit queue 0 timed out 5370 ms
Dec 20 21:06:29 tower kernel: r8169 0000:06:00.0: can't disable ASPM; OS doesn't have ASPM control
Dec 20 21:06:34 tower kernel: r8169 0000:06:00.0 eth0: NETDEV WATCHDOG: CPU: 16: transmit queue 0 timed out 5002 ms

It's obvious this is related to the new hardware I recently upgraded with, but wonder if there is a smoking gun here, maybe like the nvme errors reported above?

Thanks for the help in advance!

tower-diagnostics-20251221-0850.zip

Since it's a 14600K make sure the BIOS is updated, but it could be the Intel 13/14 gen issue.

Because memtest is only definitive if it finds errors, if you have multiple sticks try using the server with just one, if the same try with a different one, that will basically rule out bad RAM, CPU woudl be the next suspect.

The memory is from my old motherboard/CPU setup and never gave me issues, but definitely not ruling that out.

I think I updated the BIOS before I got everything up and running but I will double-check that. What is the Intel 13/14 issue?

Thanks! The more I look into it the more I don't believe I have that issue since I updated the BIOS and applied the "Intel Default Settings" on my ASUS motherboard almost immediately after installing everything.

I think there is an Intel tool I can run to confirm, but would need to boot into Windows to confirm that.

I have two DIMMS in the system, so I'm going to try just one of those to rule out memory.

Because I was in the return window of the CPU, I returned it and swapped with a 12th generation Intel CPU.

I still hit this issue about a week after swapping the CPU out, so my next thing to check is running with one stick of memory instead of 2.

I'm still hitting this every few days with only one stick of memory installed. I removed that one stick and replaced it with another stick in the same slot, but after rebooting the server I'm seeing these errors in the syslog-previous around the same time the system is going down...

Jan 24 17:42:52 tower kernel: usb 1-1: device not accepting address 81, error -71
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 570701952, 32 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 570701952 op 0x0:(READ) flags 0x80700 phys_seg 4 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 514370016, 32 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 514370016 op 0x0:(READ) flags 0x80700 phys_seg 4 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 592434896, 40 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 592434896 op 0x0:(READ) flags 0x80700 phys_seg 5 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 514332032, 8 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 514332032 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 514332048, 16 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 514332048 op 0x0:(READ) flags 0x80700 phys_seg 2 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 575500816, 32 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 575500816 op 0x0:(READ) flags 0x80700 phys_seg 4 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 256711008, 8 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 256711008 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 495931624, 32 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 495931624 op 0x0:(READ) flags 0x80700 phys_seg 4 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 871552688, 8 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 871552688 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 2
Jan 24 21:04:12 tower kernel: nvme0n1: I/O Cmd(0x2) @ LBA 357120, 8 blocks, I/O Error (sct 0x3 / sc 0x71) 
Jan 24 21:04:12 tower kernel: I/O error, dev nvme0n1, sector 357120 op 0x0:(READ) flags 0x81700 phys_seg 1 prio class 2

I'm assuming nvme0n1 is my cache drive ssd? I'm attaching a diagnostics here for any help with this.

tower-diagnostics-20260125-0834.zip

Try this: on the main GUI page click on the flash drive, scroll down to "Syslinux Configuration", make sure it's set to "menu view" (top right) and add this to your default boot option, after "append initrd=/bzroot"

nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off

e.g.:

append initrd=/bzroot nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off

There is also a USB related that is repeating:

Jan 24 14:24:17 tower kernel: usb 1-1: device not accepting address 20, error -71

Jan 24 14:24:17 tower kernel: usb 1-1: new low-speed USB device number 21 using xhci_hcd

Jan 24 14:24:17 tower kernel: usb 1-1: Device not responding to setup address.

...

Jan 24 16:59:11 tower kernel: usb 1-1: device not accepting address 59, error -71

Jan 24 16:59:11 tower kernel: usb usb1-port1: unable to enumerate USB device

Jan 24 16:59:35 tower kernel: usb usb1-port1: Cannot enable. Maybe the USB cable is bad?

I have two areas where there is "append initrd=/bzroot"

Where do I append that nvme line to?

4 hours ago, JorgeB said:

There is also a USB related that is repeating:

Yea. This is the USB connection for the front IO of my case. I just unplugged it from the motherboard since I do not need it.

5 hours ago, JorgeB said:

make sure it's set to "menu view" (top right)

Then add to the default boot option, the one in green.