Replaced the sata cables to verify that was not the problem...
Last set of errors on the host:
Jul 19 22:04:00 maturin systemd[1]: Finished Proxmox VE replication runner.
Jul 19 22:04:21 maturin kernel: general protection fault, probably for non-canonical address 0x18b01f64c661f70: 0000 [#1]...
This has now occurred on all 5 VMs i've created on the server even though 3 VMs are connected only to the 10 drive spinny ZFS2 array and 2 VMs are only connected to the 3 NVMe ZFS1 array...
Attached are screenshots of the frozen VMs consoles...
If I was to order a subscription, is this...
6 are connected to the mainboard. The main board has 6 sata slots.
The other 4 are connected with one of these https://www.amazon.com/IO-Crest-Controller-Non-Raid-SI-PEX40064/dp/B00AZ9T3OU
I notice in the syslog here... the uncorrectable I/O failure. This is with the spinny drives though. MATURIN_STORAGE is the 10 drive ZFS2 array.
Jul 16 00:17:47 maturin kernel: [ 8451.675973] zio pool=MATURIN_STORAGE vdev=/dev/disk/by-id/ata-WDC_WD4003FFBX-68MU3N0_V1JXTGXK-part1 error=5 type=2...
Hard Disk Sentinel for LINUX console 0.19c.9986 (c) 2021 info@hdsentinel.com
Start with -r [reportfile] to save data to report, -h for help
Examining hard disk configuration ...
HDD Device 0: /dev/nvme0
HDD Model ID : Samsung SSD 970 EVO 1TB
HDD Serial No: S467NX0M836342H
HDD Revision ...
I installed Debian 10.10.0, which is the stable version of debian and the version of linux I am most familiar with onto the VMs. I am not aware of the threadripper not working with this OS/kernel and can't seem to find anything directing me that way on google.
Little more about my setup:
Mainboard: Gigabyte x399 Aorus Extreme
CPU: Threadripper 2990WX
Ram: G.SKILL Ripjaws V Series 128GB (8 x 16GB) 288-Pin DDR4 SDRAM DDR4 3200 (PC4 25600)
Boot Drive & Fast VMs: 3x 1TB Samsung Evo 970 Pro EVO in ZFS1
Storage & Slower VMs: 10x 4TB Western Digital Red Pro...
Debian is installed on all 4 machines.
One machine is currently trying to download the bitcoin blockchain for instance.
after about an hour or so I have the following error:
same thing happens on the other machines downloading other blockchains...
I've tried adjusting the vm.dirty_ratio and...