Recent content by bferrell

I'm getting this same error on all of my 5 nodes now as well, but only in Firefox (on MacOS), Chome does not give it to me. I tried the fix in this other thread, but it does not seem to have helped. https://forum.proxmox.com/threads/server-disconnected-code-1006.20036/ UPDATE: That's...

Thanks for the pointer... I might try this myself, but would be great if it were an option in the Backup UI settings...

I have set network queues=32 (same as host) and CPU to host. Guest load was 1/3 of CPU and Memory or less. With CPU=HOST it does pretty well, although I'd still expect a bit better. A similar Ubuntu 22.04 guest on this box, as given 32 cpu and 32 network threads only did 177/292. Changed cpu...

Here is some more data. My ISP gives out 2 IPs, and I have 2 10G Unifi routers, so I connected both of them to an unmanaged 2.5G switch, and had my MacBook run OpenSpeedTest on the 'other/external' (UXG) router's network so I could test my VM all the way across the WAN port of the main rounter...

One more data point, I just installed OpenSpeedTest on one of my FreeNAS servers (this is the PVE cluster primary backup NAS) on VLAN101, and it can get full speed through the WAN. OpenSpeedtest on the GUEST VM (192.168.100.186) to my M1 MacMini (192.168.100.183) with 10G port (VLAN100, same...

Update: so, when I looked at the routing, I knew that wasn't right, so I popped by trusty XG-8 back into the network, I'd "upgraded" to the new UXG (it was limiting me to about 2.5Gbps) from Ubiquiti/Unifi as the XG-8 is EOL, but it has double the inter-VLAN routing performance that the UXG...

OK, it is something in the routing, if I host iperf3 on my VMs and put my Mac on VLAN101, I get just over 3 Gbps, so cross the VLAN is cutting the speed by half for some reason. Not nearly as much I'm losing to the WAN, but there's something there, just not sure what. It's also interesting...

Well, to be fair, if you look at the VM client's IPERF to my M1 Mac on the LAN I get pretty close to line speed, I just don't get it to the WAN with Speedtest on the web or CLI. That's why I was trying to make the distinction, the host and VM are both able to pass traffic and near 10G line...

Nobody has any ideas? This is just typical?

I'm having a similar difficulty to this thread that I'm hoping someone can help me with. I have a cluster of Dell servers, each with 512G ram, and they are not stressed (screenshot at bottom). Each has a 1G NIC for corosync, and a 10G each for Image traffic (VLAN 101) and 10G for VM traffic...

Cool, will check that out... thanks.

I see on the roadmap that improvements are planned for larger installations, and was curious if this was (or could be) included in the coming updates? I find that if I'm going to take a host down for maintenance I sometimes want to move several guest VMs at the same time, and would like to be...

Nevermind, I had to remove the ceph sources entry (/etc/apt/sources.list.d/ceph.list) and then was able to complete the upgrade.

I am having a dependency issue. The following packages have unmet dependencies: python3-cephfs : Depends: python3-ceph-argparse (= 15.2.14-pve1) but it is not installed E: Unmet dependencies. Try 'apt --fix-broken install' with no packages (or specify a solution). root@svr-00:~# apt install...

Great tutorial, and I have tested on my primary node (the one I use to monitor my cluster), but should this be done on every node in the cluster?