Tritech

Well, it's fucked good and proper. CSM disabled is very bad. 0x43192d0d,8) failed: Device or resource busy 2019-02-11T13:59:17.121295Z qemu-system-x86_64: vfio_region_write(0000:42:00.0:region3+0x140f8, spammed the log 100% full in a few seconds, screen garbled. I've undone every change I made, pretty sure, and now every vm is getting error 43 on the video card.

Hold my beer, I'm going in! BTW, the only oddity I see in the windows log when passing through the audio card is : Cannot reset device 0000:09:00.3, depends on group 16 which is not owned. 9:00.3 is the audio card. checked group 16 and thats: AMD Zeppelin/Renoir PCIe Dummy Function | Non-Essential Instrumentation (09:00.0) so I tried to pass that and now Cannot reset device 0000:09:00.0, depends on group 17 and group 17 is a sata controller... so thats not gonna work. audio still works.

Yea, I just noticed that as well. Literally comparing in notepad++ to see if there is anything I missed.

I don't have an EVO in this machine. It's a WD black, and its not using any emulation. The entire NVME controller is passed through and windows installed like on a normal drive. I can dual boot this if I need to to literal bare metal. <hostdev mode='subsystem' type='pci' managed='yes'> <driver name='vfio'/> <source> <address domain='0x0000' bus='0x41' slot='0x00' function='0x0'/> </source> </hostdev> Basically the way you would pass through any USB controller, etc. Unfortunately, none of these fixes worked. Basically in the same boat but now it says I have an Epic. The only differences I can see from your setup to mine is I'm on 6.7rc3 and bios 3.5. Do you have SMT set to auto/enabled (don't remember how it was worded)? My bios setup was basically yours, xmp the memory (had to enable oc mode on the ram to get the xmp to take), iommu, SR-IOV and SVM. I'm still on stock clocks for now, I have a working OC for windows, but trying to take that out of the equation. *sigh*

I figured that was a typo with the '8-24'. I applied all three of those changes, basically the whole top section of your xml and still >2000 latency. https://pastebin.com/aDNwA2P5 You have you main card in the top pcie slot correct? which is node1. Do you isolcpus=8-15,24-31 or do you leave 8/24 out? I think when I changed to numa I switched to "channel", I'd have to go back and take a look. Is there anything else in the bios to check while I'm there? Edit: Double checked my bios and it was "memory interleaving" that I set to channel. I've tested the xml changes on i440 and q35, both with about the same results. Do you have SMT on?

Yea, you've replied to a few of my other threads and I really appreciate the help!. It's the same board. Couple of questions after looking at your .xml. <emulatorpin cpuset='8-24'/> <iothreadpin iothread='1' cpuset='8-24'/> - Are these just unused threads your assigning? Wouldn't some of these be on die 0 and 1? <numatune> <memory mode='preferred' nodeset='1'/> </numatune> are you on numa or uma? I assume this is the epic hack? <cpu mode='custom' match='exact' check='full'> <model fallback='forbid'>EPYC-IBPB</model> <topology sockets='1' cores='7' threads='2'/> <feature policy='require' name='topoext'/> <feature policy='disable' name='monitor'/> <feature policy='require' name='x2apic'/> <feature policy='require' name='hypervisor'/> <feature policy='disable' name='svm'/>

*********************EDIT********************************* Check page 3 for my working .xml ******************************************************** I've got a threadripper 1950x w/ 32gb ram, on a asrock x399 professional board. I'm passing through an NVME controller to a win10 vm. Just updated to RC3 today. 1080ti is passed through, but I'm using onboard for my audio. I'm getting drops in audio and constantly have to switch my microphone inputs in discord (every minute or so, constantly switching from "default" to my mic and vice-versa). When ingame, FPS seems reasonable. I'm running the usual suspects docker wise (plex,sab, radarr etc) and they all seem fine. Bios is up-to-date. HVM and iommu enabled, as well as NUMA. I've tried for the last week to get UMA to work and its all the same things. Currently using OVMF and q35.31. my syslinux line: append isolcpus=12-15,28-31 initrd=/bzroot My gpu is on numa node 1 (the 10de:1b06). my xml: https://pastebin.com/1Em6QQTq Things I've added to the xml <emulatorpin cpuset='0'/> -will test if adding 16 to that helps <smbios mode='host'/> - didn't notice a difference Things I've tried: I've tried both seabios and OVMF and OVMF seemed more responsive and less latency. I've tried the same machine in 1440fx3.1 and that seemed worse as well. I've also tested most of these in new VMs and installing windows each time. I've installed "tips and tweaks" and set 'disable flow control and nic offload' to yes. Gpu scaling govenor to performance (seems slightly better than 'on demand'). Also applied MSI fix for all audio devices and gpu. Does anyone have any suggestions to get this thing running well?

Would like to know this as well, I've only been doing my audio device. And it doesn't seem to do anything.

It was my understanding that a mounted drive can be "released" and passed through bare metal, and then it's returned to the unassigned drives list when the VM is shut down. I probably had the drive mounted when the VM was started. I'll test and see if not mounting first makes a difference.

I've passed through my entire NVME drive/controller to a VM and the unraid logs are just filled with these lines. I've tried chkdsk in windows with no errors and crystaldiskinfo shows none either. Other than the logs, the VM seems to run fine. Should I be worried, or is there a fix? Feb 3 22:52:13 Tower ntfs-3g[24390]: ntfs_attr_pread_i: ntfs_pread failed: Input/output error Feb 3 22:52:13 Tower ntfs-3g[24390]: Failed to read of MFT, mft=83212 count=1 br=-1: Input/output error Feb 3 22:52:13 Tower ntfs-3g[24390]: Could not decode the type of inode 83212 Feb 3 22:52:13 Tower ntfs-3g[24390]: ntfs_attr_pread_i: ntfs_pread failed: Input/output error Feb 3 22:52:13 Tower ntfs-3g[24390]: Failed to read index block: Input/output error Feb 3 22:52:13 Tower kernel: Buffer I/O error on dev nvme0n1p1, logical block 807235, async page read Feb 3 22:52:13 Tower kernel: Buffer I/O error on dev nvme0n1p1, logical block 12251, async page read

I saw someone else mention windscribe in the last page. Did anyone get it to work? I can download, and it's from my windscribe static ip, verified on a private tracker, but can't seed or upload a linuxiso or on a private tracker. I just set two static ports to forward (35821 & 35822) from windscribe, and set these and incoming and outgoing ranges in deluge, and forwarded in my router to 58946 & 58846. Does this sound correct? I've tested Privoxy and that seems to work as well.

I updated the bios to the one that came out earlier this month. It seems to have fixed the crash. I'll add that to my go file, and disable cstates again now that I got this far. Now just struggling with passing through a single 1080ti. I can only manage to black screen, and can never release the screen back to unraid. Got any tips for passing through a single gpu? I've pulled the rom from the card, tried it after hexing and before. Everything seems to look like it should work... no errors in the vm log. Well there is when I try to pass the hdmi audio and onboard(something about group 16,which nothing else is in), but I'd be happy just to have video at this point.

Valiant effort! Unfortunately disabling/enabling cstates it still crashed within a minute. Tried adding rcu_nocbs=0-31 to the syslinux.cfg and still locks up when starting the array. Also tried updating to the newest RC2 and same thing... does look nice though.

CPU:1950x Board:Asrock x399 professional Drives:several mixed ssds, NVME (WD Black), and a few 8tb WD reds (although with this issue I'm only trying to add a single 8tb) So I put this machine together last month and ran windows to make sure everything is stable. Last month I initially tried to setup unraid unsuccessfully as well, but didn't have the 8tb drives so I didn't think much of it, and just installed windows to test. I tried again today and enabled SVM, and IOMMU in the bios and boot to the gui. If I don't click anything I can use the cursor for up to 3-5 minutes or so, but if I click more than a few things or try to add a single drive in the drop down, everything hangs. Cursor becomes unresponsive. Can't access via http or ping the machine, and requires a hard reboot. Am I missing something in the BIOS? Every tutorial I've watched/read has had no issues like this. The board is rock solid in windows. Memtest checks out ok as well.