Search results

Thanks again apoc, appreciate the insight. So as far as caching is concerned, for testing, I have sync set to always, so the speeds we're seeing and testing are directly against the drive. I recreated the second pool since its unlikely to be the issue, and it had sync set to standard. Uploads...

Some more information. Ran iostat and arcstat while copying a large file. You can see that transfers stall on the sender side but on the pool side its writing pretty consistently at 100-160MB/s One thing that jumps out to me is that the avail column only shows 1.1G and it went as low as 76MB...

Thanks for the response! So if it were a consistent 70MB/s I'd have less of an issue (I can accept 50% performance loss given the info you provided) but its how its fluctuating during sequential writes that is causing problems. What actually prompted me to look into this was how daily backups...

Can you post the output of the file /etc/samba/smb.conf? Make sure to check for any identifying information first.

Some more testing: I created a new Ubuntu server VM, installed as LVM, everything else default. looked for block size options but didn't see anything. DD reports the same speeds, around 14-70MB/s depending on whether I used urandom or Zero. I got 70MBs when I copied the test file to a new...

Can you download the latest drivers from Nvidia and try installing them again? I wouldn't expect it to be a passthrough issue necessarily if they're showing up in Device Manager. Also, there are two other check boxes in the PCI device passthrough menu in the WebGUI. I dont know what the...

Bump. Let me know if there are any commands, tests, or anything I can do to help troubleshoot this. Thanks everyone.

What are the permissions like on the destination folder? Do normal copies through the CLI work, "cp testfile.txt /path/to/disk/"?

What about if you do it manually through the GUI? Same behavior? Just want to rule out WHCMS here. Also to see logs you can go in the GUI, click on the node, click System then Syslog.

Could it be triggering because max restart in your second screenshot is 1 and starting it up counts as a restart somehow? could you try adjusting max restart to 2 for one of the CTs and see if the behavior is any different?

Yeah, I would think you just need to do the same thing you already did on the Nginx side but w/ port 5006 5900 and the IP of the VM/container in question in addition to the Proxmox hosts IP and port 8006. I don't know much about those specific services though, so maybe it's only capable of doing...

Would it be possible to test with a different monitor to rule out the converters as the problem? Even if you keep the HDMI->DP adapter I think that would help. I'll go test real quick to make sure that connecting a display after booting works at all, one minute! *Edit, all my hosts lack...

Do you see anything in the guest VM that crashes right before it crashes completely? As in, connect to the console of the guest in question, then try to create a new VM and observe. What about the old syslog after the crash? if you have three VMs spun up (just deal with a crash or two to get...

That is very weird that it doesn't show up to the host with the correct name, but I'm used to consumer GPUs so maybe it's different with the A4000.Do you have a video cable plugged into the card at the moment? Years ago I remember having to tell the host OS explicitely not to map the GPU as it's...

Another quick follow-up. interestingly, when I moved the disk from the SMB VM on local-vm-zfs2 to local-vm-zfs2 that write process happened at the expected speed - ~160MB/s. Since I'm seeing the slow VM level write speeds on both local-vm-zfs2 and local-vm-zfs, but not at the ZFS level when...

@odalmach3 could you post a screenshot of your passthrough and VM/container settings if you configure it through the GUI? also run "dmesg | grep IOMMU" on the host node and post that output.

Can you connect a display to your node and confirm what the IP is? It should display it when it boots up. Better yet, login and run "ip addr" without the quotes and post the output. Ping should work to a Proxmox node by default assuming you're on the same subnet and you're pinging the correct...

I just had this same problem, a node called "pve-htpc" was stuck in the webgui and pvecm delnode pve-htpc said the node was not found in the cluster. I checked /etc/pve/nodes/ and there was a folder for that node. I ran "rm -rf pve-htpc" from that folder and after a few seconds it was gone...

What motherboard do you have? Also check this thread out https://forum.proxmox.com/threads/task-error-iommu-not-present.95274/ Looks like there are quite a few gotchas when setting the intel_iommu=on line.

Does proxmox.mydomain.com use a different IP than you would use than if you connected directly? As in, does it use your public IP and you port forward on your home router to make it work? If you port forward, have you made sure that you also have port 5900 forwarded to the appropriate...