unrateable Posted June 25, 2017 Share Posted June 25, 2017 latest from wendel @level1techs regardin iommu GPU Passthrough for Virtualization with Ryzen: Now Working 1 Quote Link to comment
Josecitox Posted June 26, 2017 Share Posted June 26, 2017 Came here to post the same thing lol, hopefully there's a fix for GPU performance with that : / Quote Link to comment
Pauven Posted June 26, 2017 Share Posted June 26, 2017 On 6/25/2017 at 9:15 AM, lionceau said: Are Global C-States stable with the new 6.4-rc? It brings a new Kernel that should fix some Ryzen issues. 22 hours ago, JIM2003 said: I tried enabling Global C-States on 6.4-rc5, and my system ended up crashing within an hour. I can't say for certain, but I disabled it again immediately after and have been rock solid since. I can confirm that the unRAID on Ryzen stability issue has not been addressed. First I upgraded my ASRock motherboard to the latest BIOS release (2.40) which included AGESA 1.0.0.6. All my BIOS settings reverted to stock, including Global C-States reverting to AUTO. I then tested on unRAID 6.3.3, and the system crashed within a few hours. I then installed unRAID 6.4.0-RC6 and tried again to the same result, crashing within a few hours. I think this only further substantiates my previous analysis: This is not a Linux issue, and a newer Kernel won't fix it. This is, undoubtedly, an unRAID issue. My system runs completely stable on any flavor of Windows or Linux, including Kernel versions prior to 4.9. But add unRAID into the mix, and I get constant crashes. Everyone needs to help Limetech understand that this is a problem in their 'secret sauce' that makes unRAID so special. Something in that magnificent code isn't Ryzen compatible. For now, disabling Global C-States Control still prevents the issue, but this has drawbacks: more power consumption, more heat output, less performance due to higher CPU temps, and shorter UPS uptime. Paul 1 Quote Link to comment
Vr2Io Posted June 26, 2017 Share Posted June 26, 2017 (edited) Do you think NOHALT in Syslinux boot loaders would help? http://www.syslinux.org/wiki/index.php?title=Config#NOHALT I haven't try NOHALT but confirm global C-stats disable still need when system in light load. For how much power consumption save I haven't idea, but I think just little. BTW, I running R7 1700 with stock cooler and config one of my case FAN would stop if CPU lower then 45c ( CPU fan running in silent profile ~1200rpm). I found the case FAN always in stop condition, I setting this so I can easy got CPU temp status. NOHALT § NOHALT flag_val If flag_val is 1, do not halt the processor while idle. Halting the processor while idle, significantly reduces the power consumption, but can cause poor responsiveness to the serial console, especially when using scripts to drive the serial console, as opposed to human interaction. Edited June 26, 2017 by Benson Quote Link to comment
Pauven Posted June 26, 2017 Share Posted June 26, 2017 4 minutes ago, Benson said: Do you think NOHALT in Syslinux boot loaders would help? http://www.syslinux.org/wiki/index.php?title=Config#NOHALT I haven't try NOHALT but confirm global C-stats disable still need when system in light load. For how much power consumption save I haven't idea, but I think just little. BTW, I running R7 1700 with stock cooler and config one of my case FAN would stop if CPU lower then 45c ( CPU fan running in silent profile ~1200rpm), the case FAN always in stop condition, I setting this so I can easy got CPU temp status. NOHALT § NOHALT flag_val If flag_val is 1, do not halt the processor while idle. Halting the processor while idle, significantly reduces the power consumption, but can cause poor responsiveness to the serial console, especially when using scripts to drive the serial console, as opposed to human interaction. I'm no expert, but NOHALT sounds like the Linux equivalent of disabling Global C-States in BIOS. Personally, I prefer the BIOS method. Quote Link to comment
Vr2Io Posted June 26, 2017 Share Posted June 26, 2017 (edited) 25 minutes ago, Pauven said: I'm no expert, but NOHALT sounds like the Linux equivalent of disabling Global C-States in BIOS. Personally, I prefer the BIOS method. Yes, I think both may have same function. so I didn't try and I don't want system hang again. Edited June 26, 2017 by Benson Quote Link to comment
JohanSF Posted June 26, 2017 Share Posted June 26, 2017 Paul, thank you for clarifying once more. My strategy is to follow this thread and pull the trigger on an unRAID Ryzen server when you announce that the stability issues have been fixed and not a second before that. Quote Link to comment
Tuftuf Posted June 26, 2017 Share Posted June 26, 2017 17 minutes ago, JohanSF said: Paul, thank you for clarifying once more. My strategy is to follow this thread and pull the trigger on an unRAID Ryzen server when you announce that the stability issues have been fixed and not a second before that. The current limitations have not reduced how useful my new system is. More than happy with the current status. the system is stable when I'm traveling and that's the main part for me. Quote Link to comment
Pauven Posted June 26, 2017 Share Posted June 26, 2017 6 minutes ago, Tuftuf said: The current limitations have not reduced how useful my new system is. More than happy with the current status. the system is stable when I'm traveling and that's the main part for me. I concur. With Global C-State Control disabled, I have about 75 days of consecutive up-time, so it effectively resolves the stability issue, just with the previously mentioned side effects related to power and heat. You have to decide for yourself whether or not the side effects are acceptable. On my system, I notice 9-18 watts of increased idle power consumption. Temperatures also increased 5-10 degrees C. That said, my idle CPU temp is about 38C, and motherboard is about 34C. So both are still acceptable, even if not ideal. I also loose about 10% of my UPS up-time. Paul Quote Link to comment
lionceau Posted June 27, 2017 Author Share Posted June 27, 2017 18 hours ago, JohanSF said: Paul, thank you for clarifying once more. My strategy is to follow this thread and pull the trigger on an unRAID Ryzen server when you announce that the stability issues have been fixed and not a second before that. I am in the same position, looking to replace my quadcore Haswell which idles at only 35W, about 40% of what an overclocked Ryzen system seems to consume. Since Pauven says it's an unRAID specific problem I may just keep my unRAID Haswell system as a strict NAS and build a second Ryzen-based system with a different Linux distribution as my workstation which I'll shut down when it isn't in use. Quote Link to comment
Josecitox Posted June 27, 2017 Share Posted June 27, 2017 On 2017-6-25 at 6:34 PM, unrateable said: latest from wendel @level1techs regardin iommu GPU Passthrough for Virtualization with Ryzen: Now Working I was wondering if it's possible to do the same setup with Unraid, that is, using a hard drive with a windows installed to boot it as VM. Maybe that fixes anything? Quote Link to comment
Stef-dk Posted June 27, 2017 Share Posted June 27, 2017 (edited) Hallo I got my Ryzen a week ago. thanks for all the good reading. I just got the IMMUO a lot better by using "pcie_acs_override=downstream,multifunction" IOMMU group 0 [1022:1452] 00:01.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 1 [1022:1453] 00:01.3 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1453 IOMMU group 2 [1022:1452] 00:02.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 3 [1022:1452] 00:03.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 4 [1022:1453] 00:03.1 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1453 IOMMU group 5 [1022:1453] 00:03.2 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1453 IOMMU group 6 [1022:1452] 00:04.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 7 [1022:1452] 00:07.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 8 [1022:1454] 00:07.1 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1454 IOMMU group 9 [1022:1452] 00:08.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 10 [1022:1454] 00:08.1 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1454 IOMMU group 11 [1022:790b] 00:14.0 SMBus: Advanced Micro Devices, Inc. [AMD] FCH SMBus Controller (rev 59) [1022:790e] 00:14.3 ISA bridge: Advanced Micro Devices, Inc. [AMD] FCH LPC Bridge (rev 51) IOMMU group 12 [1022:1460] 00:18.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1460 [1022:1461] 00:18.1 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1461 [1022:1462] 00:18.2 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1462 [1022:1463] 00:18.3 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1463 [1022:1464] 00:18.4 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1464 [1022:1465] 00:18.5 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1465 [1022:1466] 00:18.6 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1466 [1022:1467] 00:18.7 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1467 IOMMU group 13 [1022:43b9] 03:00.0 USB controller: Advanced Micro Devices, Inc. [AMD] Device 43b9 (rev 02) IOMMU group 14 [1022:43b5] 03:00.1 SATA controller: Advanced Micro Devices, Inc. [AMD] Device 43b5 (rev 02) IOMMU group 15 [1022:43b0] 03:00.2 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b0 (rev 02) IOMMU group 16 [1022:43b4] 1d:00.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 17 [1022:43b4] 1d:02.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 18 [1022:43b4] 1d:03.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 19 [1022:43b4] 1d:04.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 20 [1022:43b4] 1d:06.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 21 [1022:43b4] 1d:07.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 22 [10de:1381] 21:00.0 VGA compatible controller: NVIDIA Corporation GM107 [GeForce GTX 750] (rev a2) IOMMU group 23 [10de:0fbc] 21:00.1 Audio device: NVIDIA Corporation Device 0fbc (rev a1) IOMMU group 24 [1b4b:9230] 23:00.0 SATA controller: Marvell Technology Group Ltd. 88SE9230 PCIe SATA 6Gb/s Controller (rev 11) IOMMU group 25 [1b4b:9230] 24:00.0 SATA controller: Marvell Technology Group Ltd. 88SE9230 PCIe SATA 6Gb/s Controller (rev 11) IOMMU group 26 [1b21:1343] 25:00.0 USB controller: ASMedia Technology Inc. Device 1343 IOMMU group 27 [8086:1539] 26:00.0 Ethernet controller: Intel Corporation I211 Gigabit Network Connection (rev 03) IOMMU group 28 [10ec:8168] 27:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 06) IOMMU group 29 [10de:040e] 28:00.0 VGA compatible controller: NVIDIA Corporation G84GL [Quadro FX 570] (rev a1) IOMMU group 30 [10de:128b] 29:00.0 VGA compatible controller: NVIDIA Corporation GK208 [GeForce GT 710B] (rev a1) IOMMU group 31 [10de:0e0f] 29:00.1 Audio device: NVIDIA Corporation GK208 HDMI/DP Audio Controller (rev a1) IOMMU group 32 [1022:145a] 2a:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Device 145a IOMMU group 33 [1022:1456] 2a:00.2 Encryption controller: Advanced Micro Devices, Inc. [AMD] Device 1456 IOMMU group 34 [1022:145c] 2a:00.3 USB controller: Advanced Micro Devices, Inc. [AMD] Device 145c IOMMU group 35 [1022:1455] 2b:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Device 1455 IOMMU group 36 [1022:7901] 2b:00.2 SATA controller: Advanced Micro Devices, Inc. [AMD] FCH SATA Controller [AHCI mode] (rev 51) IOMMU group 37 [1022:1457] 2b:00.3 Audio device: Advanced Micro Devices, Inc. [AMD] Device 1457 3 GPU and 3 vm running. and soundcard working in vm Card Asus Prime X350 Pro Unraid 6.3.5 Edited June 27, 2017 by Stef-dk 2 Quote Link to comment
Stef-dk Posted June 29, 2017 Share Posted June 29, 2017 I have find a problem. if i run my ram to high (3200) i get a low score in Cinebench on my vm. i can see the cpu is going in a safe mode and down clock to 2,2 ghz. but my vm says 3,8 ghz. after i put the ram til 2999 MHz i have no problem, Score in CB bare metal 1654. Score in VM 1633. Score with the high ram MHz bare metal 1712. Score with the high ram MHz VM 954. So if you have a low score in VM try to look at the clock on the ram and cpu. Quote Link to comment
ufopinball Posted June 30, 2017 Share Posted June 30, 2017 Upgraded the BIOS image for the ASUS Prime X370-PRO motherboard to the latest revision 0805 which was released earlier this week. This is the release version of the BIOS featuring the AMD/Ryzen AGESA 1.0.0.6 update. Like the previous time, I had to reboot a few times to get things settled after the BIOS upgrade. No idea why, but it seems to be running smoothly now. No noticeable changes to the IOMMU groupings between this and the previous 0803 (beta) BIOS version. Not that I would have expected it, but in case anyone was wondering. - Bill Quote Link to comment
Stef-dk Posted June 30, 2017 Share Posted June 30, 2017 (edited) ufopinball Hav you use "pcie_acs_override=downstream,multifunction" in the new bios is it working? I am still on the old and did wanna update if i did get the group like it is in the old. Edited June 30, 2017 by Stef-dk Quote Link to comment
ufopinball Posted July 1, 2017 Share Posted July 1, 2017 On 6/30/2017 at 2:34 AM, Stef-dk said: ufopinball Hav you use "pcie_acs_override=downstream,multifunction" in the new bios is it working? I am still on the old and did wanna update if i did get the group like it is in the old. Yes, I am using the "pcie_acs_override=downstream,multifunction" setting so that I can get the IOMMU group breakdown for my Windows 10 VM. Seems to work fine for me under the latest BIOS and AGESA 1.0.0.6 release. - Bill Quote Link to comment
Greygoose Posted July 2, 2017 Share Posted July 2, 2017 I am awaiting threadripper release and the stability with that CPU. I really hope the c-state can be resolved, ryzen/unraid make a perfect combination. Quote Link to comment
mikeyosm Posted July 2, 2017 Share Posted July 2, 2017 Can someone please share their 3dmark firestrike extreme physics score on a 1800x windows 10 VM? I only get 6000ish and not sure why. I have 4 cores and 8 threads allocated to my w10 VM and performance in physics is pretty dire. My Spec: 1800x 980ti 32GB Gskill at 2400mhz. UNRAID 6.4RC6 Asus Prime latest BIOS Quote Link to comment
yanksno1 Posted July 4, 2017 Share Posted July 4, 2017 Man, should have read this thread before I picked up my Ryzen build. I bought a MSI - B350 PC MATE ATX AM4 Motherboard, Ryzen 7 1700 CPU, and a EVGA - GeForce GT 730 4GB Video Card trying to do a Windows 10 VM on unRaid 6. Enabled KVM in the MB bios and that let me try to setup the VM. But when I click to create, I get this error. You guys have any idea's or am I out of luck with this motherboard? Quote Link to comment
Donach Posted July 5, 2017 Share Posted July 5, 2017 21 hours ago, yanksno1 said: Man, should have read this thread before I picked up my Ryzen build. I bought a MSI - B350 PC MATE ATX AM4 Motherboard, Ryzen 7 1700 CPU, and a EVGA - GeForce GT 730 4GB Video Card trying to do a Windows 10 VM on unRaid 6. Enabled KVM in the MB bios and that let me try to setup the VM. But when I click to create, I get this error. You guys have any idea's or am I out of luck with this motherboard? Do you have ACS Override enabled? If not, do so. See my post (around 10-15th page), where I explain how to enable it for it to work perfectly. Quote Link to comment
JohanSF Posted July 6, 2017 Share Posted July 6, 2017 I wish this thread was consolidated into a wiki page for ryzen by those that know what they're talking about. Quote Link to comment
baddea Posted July 6, 2017 Share Posted July 6, 2017 DID that mean good result or need to waiting to move from intel to Ryzen motherboard ? i need more cache to be king lol for workstation request and NAS . is there any update or stable version from unraid will be releasing yet for fix issues like limited ram or cpu. ? On ٥/١٠/١٤٣٨ هـ at 11:27 PM, Stef-dk said: I have find a problem. if i run my ram to high (3200) i get a low score in Cinebench on my vm. i can see the cpu is going in a safe mode and down clock to 2,2 ghz. but my vm says 3,8 ghz. after i put the ram til 2999 MHz i have no problem, Score in CB bare metal 1654. Score in VM 1633. Score with the high ram MHz bare metal 1712. Score with the high ram MHz VM 954. So if you have a low score in VM try to look at the clock on the ram and cpu. Quote Link to comment
Pauven Posted July 6, 2017 Share Posted July 6, 2017 Heads up: On the 6.4.0-rc6 support thread, the unRAID stability issue with Ryzen has just been brought to Limetech's attention. For those of you who have experienced Ryzen stability issues that are fixed by disabling Global C-State Control, I highly encourage you to drop in and say hi, so that Limetech can see just how many Ryzen systems are affected: https://forums.lime-technology.com/topic/58300-unraid-os-version-640-rc6-available/?do=findComment&comment=574582 I'm fairly certain that there's more than 20 of us at this point, so together our voice becomes a chorus. Paul Quote Link to comment
mikeyosm Posted July 6, 2017 Share Posted July 6, 2017 I'm probably going to sell off my ryen build and get Intel i9. I'm fed up with the crud GPU performance in some gfx intensive games due to npt issue. Quote Link to comment
Josecitox Posted July 6, 2017 Share Posted July 6, 2017 11 minutes ago, mikeyosm said: I'm probably going to sell off my ryen build and get Intel i9. I'm fed up with the crud GPU performance in some gfx intensive games due to npt issue. I'm fed up too but Threadripper is right around the corner so, you're better off waiting a little more to buy another platform. Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.