So next I’d be checking logs for sata errors, pcie errors and zfs kernel module errors. Anything that could shed light on what’s happening. If the system is locking up could it be some other part of the server with a hardware error, bad ram, out of memory, bad or full boot disk, etc.

The drives in the zpool, are they SMR drives? Slow write speed and disks dropping out are a symptom of I remember correctly

Nah, thanks but I think I’ve got a handle on the options, my original reply was more a tongue-in-cheek “cries in brick wall” type thing. I mean it has its positives, I could hang a wall mounted rack anywhere without any prep or checking :)

Yeah ended up doing that in a couple of places, for me its not practical to have bundles of cable running from a central switch, because of having to run a cable through a hole in the wall, hiding it behind skirting boards (baseboards) and under floors (where there are crawl spaces). My work place is based in a really old building and theres just bundles of ethernet everywhere running across floors and loosely attached to walls etc, wish they spent the time, effort and money of equipment running fewer 10Gb runs to floors then having 10Gb to 1Gb switches for the workstations.

Yeah the correct way to do it is to chisel a channel in the plaster and embed the cable in the plaster, but thats quite an ordeal to do.

Any advice for Victorian era terraced houses in the UK where every wall is solid brick :/