Recent content by cjones

I've been cross-referencing all kinds of posts and documentation to find a definitive answer to this, but it seems everybody does things just a tad differently with different syntax and I can't lock anything down. I'm trying to understand the proper combination of settings to pin vCPUs to a...

Awesome info, made my understanding of things a whole lot better. If I'm counting on this hook-script, do the equivalent GUI pieces still need to be configured? For example, with pinning the vCPUs, there's a dedicated function for that, but that's also in the GUI. Do we leave the GUI alone and...

The guest was showing the same thing, but I ended up running glxinfo and it shows the right amount of video memory. I guess I misunderstand the lspci output. Thank you for your help.

That's what I would've thought, but listing the PCI details on the VFs reveals that the memory size is still at 256M. This is the same within the guest that a VF is passed-through to. The PF: lspci -s 01:00 -vv 01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Tonga XT...

Thank you for putting this in front of the devs. I changed the MTU to 8999 and the VM booted just fine. Just for clarification for anybody coming across this post, I was initially mistaken that the MTU was controlled from the Proxmox bridge. It's not. It's controlled from within the guest. So...

I am trying to configure 2 VFs and I've tried both an explicit value of 4096 and 0 for vf_fb, same outcome regardless. Here's dmesg: [857541.201982] gim info:(gim_exit:187) Exit AMD open source GIM! [857541.202337] gim info:(idle_all_adapters:1061) idle adapter[1] [857541.202696] gim...

I have configured the GIM module following this. I am able to pass VFs through to VMs and it works great. However, I have been trying to modify the runtime options as indicated here. Some seem to work, and some don't. The default 256M per VF is too low for what I want to use it for, so I am...

Ok, so forgive my naivety to the terminology and what it all means. The vmxnet3 NIC I have attached is connected to a bridge that has an MTU of 9000. Does that mean I've exceeded the limit? Or it's ignored following your last statement that it "is excluded by the assert"?

I am working with nested ESXi 7.0, which I have found is only compatible with the vmxnet3 NIC. When powering on the VM, it eventually crashes quick enough that it doesn't even fully boot and I see this event in syslog: QEMU[1560506]: kvm: ../hw/net/vmxnet3.c:1444: vmxnet3_activate_device...

That seems to have done it. Thank you for your help! Sorry to hear about the pull request, wonder what the reasoning was...

I am on kernel 5.15.39-2-pve and am using the GPUOpen-LibrariesAndSDKs/MxGPU-Virtualization repo.

Am trying to do this too and got up to the dkms build step. Had to install missing headers, but now the logs from that command are saying fatal error: linux/pci-aspm.h: No such file or directory. Any suggestions?

ps auxwf showed me that the sync command was hanging. This led me to investigate my rpool disks. One of the disks had quite a high "Reallocated_Sector_Ct" value relative to the other disk (which was at 0). Ended up replacing the disk and after that the upgrade completed fully. Thanks!

I am unable to update without apt getting stuck on Unpacking pve-kernel-5.4.128-1-pve (5.4.128-2) over (5.4.128-1) .... I end up having to kill the process. I have noticed that there are *.dpkg-tmp files under /boot for config, System.map, and vmlinuz of 5.4-128-1-pve. I've tried removing...

Thank you for the clarification.