Search results

TL;DR: change kernel to ubuntu's `linux-image-6.8.0-32-generic` seems fix the soft lockup # pveversion pve-manager/8.2.2/9355359cd7afbae4 (running kernel: 6.8.0-32-generic) # fastfetch-linux-amd64/usr/bin/fastfetch -l small _____ root@gigabyte-7 / __ \ --------------- | / |...

So..... I switch to new 6.2.16-5-pve kernel and the softlockup comes backup ! all locked up vm is running with aio=native and virtio-single e.g. acpi: 1 agent: enabled=1 bios: seabios boot: order=scsi0 cicustom: vendor=cephfs:snippets/ci-k8s.yaml cores: 64 cpu: host ide2...

Switch to threads seems fix the softlockup issue. Still, I hope io_uring can be enabled one day since it seems have better io performance

Thank you for your reply! My VMs has virtio-single enable, all disks is on scsi and has asyncio=Default(io_uring) and iothread=1. From https://bugzilla.kernel.org/show_bug.cgi?id=199727#c8. it suggests enabling aio=threads could fix this. I will make a test and see what will happen

Switch to 5.15.108-1-pve seems fine

I recently came across VM soft lockups when running heavy loads with compute and io. It began with PVE 7.4 and with 6.1 kernel. When the PVE 8.0 was released. I upgraded all nodes with kernel 6.2 but nothing seems to change . The CPU running is two socket 7742 & 7702 systems. I tried upgrade the...

agent: 1 boot: order=ide2;scsi0 cores: 12 cpu: host hotplug: disk,network,usb,memory,cpu ide2: none,media=cdrom memory: 10240 name: arch-dev net0: virtio=9A:54:F2:C7:A5:DA,bridge=vmbr0,firewall=1,tag=1015 numa: 1 onboot: 1 ostype: l26 runningcpu: host,+kvm_pv_eoi,+kvm_pv_unhalt runningmachine...

Resuming suspended VM activating and using 'hp13hdd:171/vm-171-state-suspend-2023-07-01.raw' as vmstate qemu: qemu_mutex_unlock_impl: Operation not permitted TASK ERROR: start failed: QEMU exited with code 1 # pveversion --verbose proxmox-ve: 8.0.1 (running kernel: 6.2.16-3-pve) pve-manager...

I used to have some code interactive with vncwebsocket via the following procedure. It's used to connect VM serial directly to the user terminal. 1. generate a PVEVNC ticket via /api2/json/nodes/{node}/qemu/{vmid}/termproxy 2. Submit Ticket and user to...

I notice there is a new kernel package version pve-kernel-5.4.55-1-pve but I can not find related commit on https://git.proxmox.com/?p=pve-kernel.git;a=summary Where should I look for?

So, I decided to yolo it. and patched the `/usr/share/perl5/PVE/Storage/GlusterfsPlugin.pm` with `snippets => 1, `, and it seems works just fine.

I checked the wiki[1]. it says glusterfs should support snippets. [1] https://pve.proxmox.com/wiki/Storage:_GlusterFS

I am playing around with glusterfs and live migration today. and find out you can not add snippets type to gluster volume. pvedaemon.services logs `storage does not support content type 'snippets'` I check the code found there is a commit says 'enable snippets content type for all directory...