Big IO Delay

Hello,
what kind of VMs/Containers are you running on your PVE host? I'd first investigate if they produced some sort of unusual IO load.
 
Those BX500 can either be using TLC or QLC NAND. If it is a one with QLC NAND terrible performance wouldn't be unusual, especially when writing after the RAM-/SLC-cache got full or when using sync writes.

When looking at the 2% wear of a new installed PVE I would tend to QLC NAND.
 
Last edited:
  • Like
Reactions: Lukas Wagner
Of course, the issue is that this server is in production. Could I replace the disks using the "zpool replace" command? Or should I reinstall the server?
I mean, if I can change one device at a time, so the ZRAID does the rebuild and the server doesn't have downtime.
 
Get a proper Enterprise/Datacenter grade SSD with TLC or MLC NAND and powerloss protection.
So something like a cheap Samsung PM893, Intel/Solidigm S4520, Micron 5400 PRO. Or something a bit more durable and faster like a Samsung PM897, Intel/Solidigm S4620, Micron 5400 MAX. Something in that range.
 
  • Like
Reactions: RolandK and pvps1
I understand the issue of disks, but is it normal that with these values in the iotop, proxmox has 12% io wait?

1672323287005.png
 

About

The Proxmox community has been around for many years and offers help and support for Proxmox VE, Proxmox Backup Server, and Proxmox Mail Gateway.
We think our community is one of the best thanks to people like you!

Get your subscription!

The Proxmox team works very hard to make sure you are running the best software and getting stable updates and security enhancements, as well as quick enterprise support. Tens of thousands of happy customers have a Proxmox subscription. Get yours easily in our online shop.

Buy now!