Recent content by dominiaz

I’d be thrilled to see my patches merged into the official Proxmox repository.

Github iothread-vq-mapping updated to support for Proxmox 9.2.2 ISO - https://github.com/dominiaz/iothread-vq-mapping New features: Virtio/SCSI support and Hotplug. You can set VQ Mapping over Proxmox Web Gui. If you want to upgrade Proxmox VE 9.x to the exact ISO version 9.2.2, which is...

It is designed for proxmox 9.0 major version from iso, so it works only with proxmox 9.0.3.

Have you try to use that kernel: https://github.com/KrzysztofHajdamowicz/pve-kernel/releases ?

Can it be used with nvmeof over rdma (with multipath) to maximize iops performance? So I am just connecting the same nvmeof target on 2 or 3 proxmox nodes and set normal LVM?

New kernel from proxmox repo is working fine: 6.14.8-2-pve

Just use kernel: https://github.com/KrzysztofHajdamowicz/pve-kernel/releases

I have exactly that kind of issue.

Kernel is broken with Mellanox 100G Connectx-5 VF on Proxmox 9.0 Beta. That card works fine only on Host without VF, so vfio-pci is broken in that release I think. kvm: -device vfio-pci,host=0000:81:00.1,id=hostpci0,bus=ich9-pcie-port-1,addr=0x0: vfio 0000:81:00.1: error getting device from...

Kernel is broken with Mellanox 100G Connectx-5 VF. kvm: -device vfio-pci,host=0000:81:00.1,id=hostpci0,bus=ich9-pcie-port-1,addr=0x0: vfio 0000:81:00.1: error getting device from group 89: Permission denied Verify all devices in group 89 are bound to vfio-<bus> or pci-stub and not already in...

Patch upgraded to PVE 9.0 Beta 1: https://github.com/dominiaz/iothread-vq-mapping

Yes, it should work with ZFS. You can test it.

I made patch that enables advanced iothread-vq-mapping for virtio-blk devices in Proxmox VE 8.4. https://github.com/dominiaz/iothread-vq-mapping Just add eg. iothread_vq_mapping=8 to your virtio drive configuration.

I made a patch for Proxmox 8.4: https://github.com/dominiaz/iothread-vq-mapping Just add eg. iothread_vq_mapping=8 to your virtio drive configuration.

You have bad point of view. I have fast storage with 8 mln IOPS, so normal 150-200k IOPS per VM (with actual 1x iothread) is very, very bad. If you want sell 200k IOPS or 1mln IOPS then you sell it in fair price. You can always set 1-64 Iothreads per VM, but we need to have a choice.