Proxmox 5.4: host crashes during heavy writes in a VM


May 9, 2019

I am running Proxmox 5.4 on a Dell T110 ii with 32gb of ram and 4 SATA drives in a ZFS raid10-like configuration. I am experiencing host crashes/reboots when a VM is under heavy write load such as running CrystalDiskMark benchmark inside a Windows Server 2019 VM. At first, I thought this was a problem with using sparse bundles + Virtio SCSI + Discard, but now that I have reconfigured the system to not use sparse volumes and am using Virtio Block instead, the issue still persists.

Looking at output of TOP, it seems like the host runs out of memory just before freezing and rebooting. I am using the default of "No Cache" on the VM drives (I actually just read that having Writeback enabled can cause this very problem), so how do I tune my way around this? If I don't want to enable directsync is adding more RAM and/or swap my only option?

Some years ago I was using ZFS on FreeBSD on an underpowered rig that got really unresponsive under heavy IO and I tuned my way out of the problem by adjusting ZFS tunables that dictate how often and in how big chunks writes actually happen. How are these adjusted in Proxmox?
Last edited:


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!