Recent content by StarkWiz

It's good to know this worked as well. I had tried running VM using 1GB hugepage and it does work on promox once you add the entry in grub. So, yeah something must've screwed up before. Virtualization has improved so much that you actually won't see any difference in performance when using pci...

That's awesome. I am glad it worked for you. Re beer: Not really expecting but I'll PM you later on. :) I hope this helps @adamb as well, if he is still interested in resolving the issue. I think this is also possible by enabling transparent hugepages which I noticed is disabled by default on...

I was just checking the qemu command line and noticed this parameter. -numa 'node,nodeid=0,cpus=0-3,memdev=ram-node0' It seems node0 is only being assigned to the VM which means CPU1 and memory directly accessible to CPU1 is only available. Hopefully changing to dual socket configuration should...

Re memory-backend error it seems 1GB hugepages is not allocated at boot time for some reason, there is a different process to do that. Anyways page size doesn't appear to be important in this case, so lets stick to 2MB hugepages for now.

I am running out of suggestions but this is last one. Try changing sockets to 2 instead of 1 in VM config and test it with 64GB and 96GB and hugepages set to 2 and 1024. You normally dont need to change the default hugepage size as we had already added the 1GB parameter so it should be...

Trying random number on hugepages won't work only specific page size supported by your system works, its mostly either 2MB or 1GB for 64-bit linux. 1GB page size is supported only on Xeon and Intel HEDT processors. Not exactly sure what must be causing it to fail when it goes above 64 GB, it...

I too recently started using proxmox in home lab and without subscription :) Unfortunately I haven't added lot of memory yet to test your scenario. Update the line below in /etc/default/grub (Please take backup of this file before updating if necessary, let me know if you had made any...

I see, I think it should be allocate by default unless there isn't enough memory available. Can you please post output for this command "cat /proc/meminfo | grep -i huge" Also just to be sure, can you confirm if you've configured non-subscription or enterprise repository accordingly...

I would like to suggest removing the balloon parameter and update the config as below. numa: 1 hugepages: 2

I noticed you are using q35 machine type on which adding pcie=1 is important. Try changing the hostpci0 to below. hostpci0: 09:00.0,pcie=1 Also I hope the balloon parameter is not actually missing the b in the configuration as seen here.

Thanks @spirit for updating the wiki. I would really like if it works like before as it's more easier, unless it's known to cause any issues with latest qemu updates or anything else. I have one query about the old behavior though. I am not quite sure how many virtual functions can one device...

Yes, they changed the code in April 2016. property string update: hostpci* This commit changes the listing of virtual functions from multiple host= entries to one semicolon-separated host list. It seems the PCI Passthrough wiki page hasn't been updated with latest syntax and multi-function...

Hi Spirit, I was hoping it would work like that but it doesn't, I am not sure if this is related to pcie and q35 machine type. I can confirm it's working correctly, when we specify all the multi-function devices using semi-colon. Is the code from 2014 you mentioned part of latest updates from...

Thanks probably I was looking too hard for examples and use of word "multi-function". So, I didn't try to understand the syntax.

Hi Dominik, Thanks and yes that works :) I figured it when I went through the qemuserver.pm perl code while ago. It's strange that this is not mentioned anywhere. I'll mark this thread as solved.