Search results

Ok, I am now fully back onboard the ECC camp. Not that I ever left it but I was considering going for extra speed. Non ECC is now off the table for good. ECC for the win

Can you please elaborate? I am about to shut down this particular system and going to do brain surgery.

what would be more optimal in terms of random read/writes? simply adding new nvme's to the mirror-0 or create extra sets of mirrors each containing 2 nvme's? Also will it matter for either scenario if the nvme’s are not the same brand and model? They are the same size, in terms of what is...

current zpool status zpool status pool: rpool state: ONLINE status: Some supported features are not enabled on the pool. The pool can still be used, but some features are unavailable. action: Enable all features using 'zpool upgrade'. Once this is done, the pool may no longer...

@Dunuin thank you for your detailed explanation. Much appreciated. Currently the Samsung SSD's have a wearout of 4 and 3 % after about a year of operation. Are there statistcs available on how many writes have been done in that time? The workload up until this time has been (I'll edit the...

Please forgive my ignorance. What made one think I was looking to do server stuff? (my thread opening post already edited to reflect this) I am looking for a non server workload. Just freakishly fast performance with the stuff that is available to me

OK, so coming back to the disk aspect of it all. One would say that having a single PCIe ssd (consisting of 4 NVMe's in raid 10(mirrored striped)) is better than putting in those same 4 NVMe's in the slots on the Mobo and have proxmox deal with the raid aspect? Ahh Before I make and edit to...

Hyper-V on Windows Server 2019 comes with it's own set of problems. It is simply not able yet (please believe me I have tried for 2 months before I setteled down to proxmox) to do proper GPU passthrough for AMD ryzen, RTX 2060+ setups EDIT: and also the SATA controller passthrough of at least 5...

also, when using PCIe ssds, one sacrifices a PCIe slot. Slots that could be used for GPU pass through. What I failed to mention is that I would like to have a dedicated VM to pass GPU's to so that I can donate to the folding at home or other distributed science projects

I am not trying to be a d*&k but if the mentality remains that proxmox is not for non server workloads then perhaps installing a windows (yeah I know it's evil) machine and go from there with virtualbox? I'd rather prevent that route as I have spend more than a year getting to know proxmox and...

ok understood now. So ZFS, although I said it was not a requirement, then now it is. Never I intended to suggest that ZFS was off limits. Sorry for the confusion. That particular document I have read indeed. I also did not find much regarding NVMe's. I did see an Intel Optane on the top of the...

or with 256 GB of ECC memory. perhaps load an entire VM in ramfs? that would mean that loading a VM is no longer fast but for one or two specific VM's that would be no problem

for example do I use the AORUS Gen4 AIC Adaptor (1 PCI device for 4 x NVMe SSD) with 4 x WD black SSD's in raid0 mode? Or put them in the 4 xNVMe slots of the mobo and then see if I can raid 0 them?

understood. Important data on a VM goes to a TrueNas. The VM it self gets backed up to TrueNas. So I can always roll back to a previous snapshot if need be. wow, I am now considering your drives. Is there any benchmark I can see? All I found and use was something along the lines of...

I'd like to setup proxmox 7 to be as fast as it can possibly be with the hardware I have and that I am considering to get; EDIT: (this will be for non critical, non server related workloads) Edit 2: I would like to have a dedicated VM to pass GPU's to so that I can donate to the folding at home...

the keyboard was usb added using vendor id. so changing port does not matter it will always be passed through. Anyway I luily found a spare keyboard and got it sorted.

During a non scheduled network change I lost the ability to connect to the PVE GUI. But because one of my VM's, with keyboard and mouse passthrough, has autostart I can also no longer log into the host CLI. Yeah I know, rookie mistake this configureation :( How can I get into the CLI? It's ok...

can one please expand on smtp relay part of the first answer? how to do that?

i think it is dmesg. because when looking at; https://unix.stackexchange.com/questions/641021/identifying-physical-memory-slots-from-dmesg-ecc-error-outputs shows an output similar to the one I saw on the pve host monitor

Not entirely sure what log one sees when looking at the monitor connected to the pve host. That is one of the places one can confirm. Can you please have a look at; https://serverfault.com/questions/643542/how-do-i-get-notified-of-ecc-errors-in-linux ? one of the comments mentions 'Running...