mikeyosm
-
Posts
651 -
Joined
-
Last visited
Content Type
Profiles
Forums
Downloads
Store
Gallery
Posts posted by mikeyosm
-
-
9 minutes ago, unrateable said:
was full of hopes for propper isolation when I read about the new AMD release, but lost a bit of faith upon seeing your post. I hope I am wrong and more people will report back soem improvements.
very interesting in your grouping is; this is the first time I see iommu groups breaking up right in between the GPU and its very own audio device.
I wonder do these split groups, and especially the GPUs properly work as they should - and with minimal performance losses inside the VMs ?afaik when using ACS override patches one can expect occasionally some odd system behaviour. due to the "illegally" shared ressources maybe ?
Maybe I'm just lucky but I seem to go days without issues with a bit of light Minecraft gaming, Plex 4k streaming and osx usage. Looking forward to the new agesa to see what impact it has on memory overclocking, I'm on a disappointing 2133mhz atm
-
8 hours ago, ufopinball said:
When you say "onboard audio", do you mean the audio off the motherboard, or off one of the GPUs?
I'm presently using a USB audio device. Looking at my "System Devices", the only audio device is the HDMI audio output from my GPU.
I'd love to reduce another device and work with the motherboard audio chip.
Would you share the necessary details?
Thanks!
- Bill
I'm passing through the audio off the motherboard, absolutely no issues using the asus audio drivers.
append pci-stub.ids=1022:145c,144d:a802 isolcpus=2-9 pcie_acs_override=downstream,multifunction vfio_iommu_type1.allow_unsafe_interrupts=1 initrd=/bzroot
IOMMU group 0 [1022:1452] 00:01.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 1 [1022:1453] 00:01.1 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1453 IOMMU group 2 [1022:1453] 00:01.3 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 1453 IOMMU group 3 [1022:1452] 00:02.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 IOMMU group 4 [1022:1452] 00:03.0 Host bridge: Advanced Micro Devices, Inc. [AMD] Device 1452 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 [144d:a802] 01:00.0 Non-Volatile memory controller: Samsung Electronics Co Ltd NVMe SSD Controller SM951/PM951 (rev 01) IOMMU group 14 [1022:43b9] 03:00.0 USB controller: Advanced Micro Devices, Inc. [AMD] Device 43b9 (rev 02) IOMMU group 15 [1022:43b5] 03:00.1 SATA controller: Advanced Micro Devices, Inc. [AMD] Device 43b5 (rev 02) IOMMU group 16 [1022:43b0] 03:00.2 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b0 (rev 02) IOMMU group 17 [1022:43b4] 1d:00.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 18 [1022:43b4] 1d:04.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 19 [1022:43b4] 1d:06.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 20 [1022:43b4] 1d:07.0 PCI bridge: Advanced Micro Devices, Inc. [AMD] Device 43b4 (rev 02) IOMMU group 21 [10de:128b] 21:00.0 VGA compatible controller: NVIDIA Corporation GK208 [GeForce GT 710B] (rev a1) IOMMU group 22 [10de:0e0f] 21:00.1 Audio device: NVIDIA Corporation GK208 HDMI/DP Audio Controller (rev a1) IOMMU group 23 [1b21:1343] 25:00.0 USB controller: ASMedia Technology Inc. Device 1343 IOMMU group 24 [8086:1539] 26:00.0 Ethernet controller: Intel Corporation I211 Gigabit Network Connection (rev 03) IOMMU group 25 [1002:67ef] 28:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Baffin [Radeon RX 460] (rev cf) IOMMU group 26 [1002:aae0] 28:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Device aae0 IOMMU group 27 [1022:145a] 29:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Device 145a IOMMU group 28 [1022:1456] 29:00.2 Encryption controller: Advanced Micro Devices, Inc. [AMD] Device 1456 IOMMU group 29 [1022:145c] 29:00.3 USB controller: Advanced Micro Devices, Inc. [AMD] Device 145c IOMMU group 30 [1022:1455] 2a:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Device 1455 IOMMU group 31 [1022:7901] 2a:00.2 SATA controller: Advanced Micro Devices, Inc. [AMD] FCH SATA Controller [AHCI mode] (rev 51) IOMMU group 32 [1022:1457] 2a:00.3 Audio device: Advanced Micro Devices, Inc. [AMD] Device 1457
-
1
-
-
On my asus prime i'm passing through the USB 3.0 , onboard audio and 2 x GPUs. Brilliant board IMO.
-
8 hours ago, ufopinball said:
Sounds good, where did you find the details on this setting? I'm curious to know when it is recommended...
- Bill
Tbh, I recalled having to do this same thing last year on my x99 platform, i swear i'v got early signs of dementia.
A quick search of LT forum and bingo, SMB settings is what I needed. Not sure why I specifically need to do this, but other people probably don't realise or maybe even care about a 40-50% drop in performance. Have a go and see if it helps your transfers in any way.
-
3 hours ago, mikeyosm said:
OK
Test 2: copy file from \\unraid\7200RPM to \\unraid\SSD = approx 110MB/s
Test 1: Copying 4GB file from \\unraid\7200RPM to C:\Temp = more or less instant - couldn't measure the speed accurately because so fast.
Obviously caching plays a big part in Test 1:
FYI - I am not using a drive in the cache pool. My SSD is the only drive in the array and the 7200rpm drive is in the unassigned disks plugin pool.
Right, I added max protocol = SMB2_02 to the samba extra config section in settings/SMB and now I have read speeds consistently around the 90MB/s mark, much better.
-
34 minutes ago, ufopinball said:
Interesting, though I'd argue that Test 3 should be a repeat of Test 1. I'm still expecting that the file is being cached after the first copy.
Also, for Test 4 ... I do not my cache drive to buffer writes to the array, all writes to the array are done directly to the array drives (and of course, parity) ... I'm not sure if Test 4 is writing directly to your 7200RPM, or is being cached by your SSD to be moved to the array at a later time.
If I did my math correctly, my Test 1 achieved 63.5MB/s, so maybe that's not out of line ... though my drives are all 5400RPM. Your numbers *should* be faster.
Can we try this? Pick a different 4GB+ file and run the test again, but this time run Test 2 before Test 1? Can probably skip 3 & 4 for now.
- Bill
OK
Test 2: copy file from \\unraid\7200RPM to \\unraid\SSD = approx 110MB/s
Test 1: Copying 4GB file from \\unraid\7200RPM to C:\Temp = more or less instant - couldn't measure the speed accurately because so fast.
Obviously caching plays a big part in Test 1:
FYI - I am not using a drive in the cache pool. My SSD is the only drive in the array and the 7200rpm drive is in the unassigned disks plugin pool.
-
16 hours ago, ufopinball said:
Okay, so here are my test parameters:
The source file comes from a SAMBA share on UNRAID (\\cortex\disk2) and is 4.37 GB (4,695,246,094 bytes).
The first destination is C:\TEMP on my Windows 10 VM, which lives in \\cortex\cache\vDisk
The second destination is also a SAMBA share on UNRAID (\\cortex\cache\inbox)
In my opinion, the two destinations should behave similarly. All tests were performed using "TeraCopy" running on the Windows 10 VM.
Test 1: Copying the file from \\cortex\disk2 to C:\TEMP took 70.50 seconds
Test 2: Copying the file from \\cortex\disk2 to \\cortex\cache\inbox took 32.81 seconds
Test 3: Copying the file from \\cortex\disk2 to C:\TEMP (again) now takes 35.38 seconds
My UNRAID system has 64GB installed, but 16GB is reserved for the Windows 10 VM.
My guess is Test 1 takes longer because the file is read from a HDD. Test 2 & 3 run faster because the file is now cached in RAM (either in UNRAID or the Windows 10 VM).
The difference between Test 2 and 3 is not wholly insignificant, but hardly seems worth worrying about.
Finally, as I understand it, file copies here do not really involve the NIC since none of the data needs to go over the network? My VM is running the Red Hat VirtIO Ethernet Adapter. The hardware NIC is the Intel I211AT Gigabit LAN, integrated into the motherboard. I did not change the MTU settings.
The \\cortex\cache drive runs on dual SAMSUNG 850 EVO 2.5" 1TB SATA SSDs, configured in a cache pool.
The \\cortex\disk2 drive is a Seagate ST4000DM000 4TB SATA HDD.
Let me know if you'd like me to run additional tests.
- Bill
Thanks Bill. Test 1 interests me. I'll follow your test parameters so that my test results become a littler clearer...
My VM is Windows 10 on 950 Pro nvme. nvme drive tested with samsung magician and speeds are great.
Test 1: Copying 4GB file from \\unraid\7200RPM to C:\Temp = approx 50-60MB/s - I expect approx 110MB/s, so way too slow.
Test 2: Copying 4GB file from \\unraid\7200RPM to \\unraid\SSD = approx 110MB/s - Exactly whay I expect, maxing out the 7200RPM spindle speed.
Test 3: Copying 4GB file from \\unraid\SSD to C:\Temp = approx 150MB/s - Not what I expect. 250-400MB/s seems reasonable.
Test 4: Copying 4GB file from C:\Temp to \\UNRAID\7200RPM = 110MB/s - What gives? Why is the speed better copying to the share and not from it?
I am at a loss why transfers to the VM from any SAMBA share are approx 50% slower. And as previously stated, if I copy between SAMBA share using Krusader or mc , i get full drive speed. Really not sure what's going on here.
Having said all of that, I remember only getting 600-700MB/s on my 950 pro nvme when used as an 'unassigned disk' in UNRAID . I should have got 1Gb-1.2Gb/s, so again, 40-50% off the expected speeds. None of these issues were present on my x99 platform, it's only Ryzen and my asus prime x370 that has less performance.
UPDATE - See Test 4 above: Strange why copying to the SAMBA share from the VM is faster than copying from the SAMBA to VM.
-
Can someone please test something for me on their Ryzen setup?
Logged in to your VM, copy a 4GB+ file from a SAMBA share on UNRAID directly to the C:\ drive on your VM.
Compare the transfer speed of this with copying the same file from the same SAMBA share to another SAMBA share (i.e. not the VM volume).
I get a 40-50% drop in transfer speed when copying to the VM but speeds are great directly between the shares, very odd.
The VM is Windows 10 or Windows Server 2012 R2 using 10Gb vNIC and 9000 MTU and the C:\ site on my nvme 950 pro drive.
-
Can anyone confirm which x370 boards have their sensors detected in Unraid? I believe the asrock fatality pro works with the sensor plugin but the Asus prime does not. How about msi, gigabyte etc? Please list your board here if sensors work. Thanks
-
So, finally got around to completing my Ryzen Unraid box. Here is my spec:
Ryzen 1800x Stock 3.6ghz
Asus Prime x370 Pro BIOS 0604
G.Skill 2x16GB 3200 F4-3200C14D-32 gtz @ 2400
Samsung 950 Pro 512GB
Tried to overclock the memory to 2933 with timings 18-16-16-16-36 - System was stable for a few hours before my 1st BSOD, will wait for BIOS updates before stress testing some more. UNRAID 6.3.3 is running perfectly stable for more than a day now with Global C State disabled. Got 2 VMs running at the mo and still UNRAID is rock solid stable.
Will be purchasing my 1080ti for passthrough soon and will feedback my success rate with this. So far, coming from an x99 xeon build, I am very impressed with the overall speed both from UNRAID and my W10 Pro VMs. Happy days so far, now waiting for temperature stats and nvme temps to be added to new UNRAID builds/plugins.
-
13 hours ago, Pauven said:
Happy to help!
Did you notice any increase in power consumption or temperatures with C-states disabled?
I've never been able to get my motherboard to boot above 2400, even when running 3600 memory, so I couldn't even get far enough to get a kernel panic.
I just checked and it looks like you are running QVL'd memory, so I would expect the BIOS support to be good. Have you run Memtest86? You might have bad memory. Sometimes re-installing the memory into different slots can help too.
-Paul
Me too i have an Asus prime and gskill trident z 32gb 2 modules. No matter what i cant post past 2400mhz with our without docp profile. Any clues why?
-
21 minutes ago, Pauven said:
I updated my list above with ufopinball's crash, and added some color coding to highlight problems: https://forums.lime-technology.com/topic/55150-anybody-planning-a-ryzen-build/?do=findComment&comment=548546
So there are now at least 11 Ryzen unRAID boxes currently operational (not counting johnnie.black's system he borrowed for a day, or Akio's system since he's still working out his cooling setup).
Of those 11, 6 have reported issues with unRAID (well, technically 5 have reported, but I'm adding in jonp/Lime-Tech rumored issues).
1 of those 6 that reported isssues is Beancounter, who was having random crashes every 12-36hrs, and he indicated his problems went away after he patched his Win10 VM.
Of the 5 that have not reported issues, it seems they may be running Windows VM's, though in a few cases there's a lack of detail in their posts to make that determination. It could also be that they are experiencing issues and just haven't reported back.
Everyone that has a Ryzen system, please update this thread on your current status with unRAID. Have you had any crashes? Are you running Windows VM's? Have you had any crashes while running Windows VM's? And any other detail you think will help identify the problem.
Since my system crashes so easily on unRAID, often within an hour or two, and I've never seen it go beyond 14 hours, it is an excellent test bed for determining if a Windows10 VM alleviates/resolves the issue. I plan to get it installed in the next day or two, I'm a little busy with work at the moment.
-Paul
Seems like a contributing cause might be any power saving options configurable within the BIOS. Has anyone tried disabling all power saving features and load test Unraid with and without a VM running? I doubt a VM running W10 can help with stability unless the issue is bourne out of resource allocation or lack of. I have an 1800x and Asus prime waiting to be built but probably going to to wait until the 6.4betas to hit the masses.
-
2 hours ago, Akio said:
I've pulled the trigger on a 1700X + crosshair vi.
Will do some testing, i know straight away this board does not support ECC as stated early.
For anyone out there using EKWB evo cpu block that was bought this year mine came with the AM4 fittings.
"Why the hero model akio"? - well i have the asus maxi IX z270 and both have the water cooling stuff i use , since there's no news on the kabylake refresh with 6 or more cores, i'm going back to team red!
My ideal unraid rig would have been an x99 with plenty of pci gen3's loads of lanes and 8/10core cpu but i cant touch the prices of that.
I just downgraded my x99 64gb 2600v3 10 core because I hardly ever used the full capacity of it. I'm now waiting to build my 1800x and asus prime with 32gb gskill. TBH it's not that much of a downgrade since I'll be saving some watts by not using the Xeon...
-
4 hours ago, Bureaucromancer said:
I've got mine more or less up and running at the moment with an 1800x, a new RX 460 and a GTX 560 on the Crosshair VI Hero (which I seem to be about the only person not having issues with, albeit with bios 0902). Seems to be stable on its own, but I've yet to wrangle any GPU into actually initializing with IOMMU and did encounter Naiqus' issue an Ubuntu install bringing down the whole system.. Going to try a manual bios dump on IOMMU and start from scratch on a Linux VM (first attempt was pre bios update, but kernal seems more likely...) tomorrow. Will report back.
Please do report back, I am considering this board as my next UNRAID build. I stripped down my Intel 2660v3 build since I was not using its full potential, got myself a 1800x, gskill 2x32GB - just deciding on a board and cooler now.
-
8 minutes ago, tsouza11 said:
passing through sound card (onboard) works?
Id like to know that too, im really undecided on what is the best board to get at the mo. Torn between asus crosshair, asrock taichi or msi titanium
-
18 hours ago, Beancounter said:
Built in graphics may come in handy when AMD releases their APU lineup. Thinking mostly mGPU vulcan/dx12.
Yeah, future proofing should be the way to go, decisions, decisions...
-
3 hours ago, Naiqus said:
I've managed it, with a Gigabyte X370 Gaming 5 mainboard. IOMMU groupping issue is resolved by AC override. Everything works fine up to now.
Thats good news. I will probably get the asrock x370 gaming pro without built in gfx since the ryzen does not support it.
-
If anyone manages to get 2 x GPUs passed through to seperate VMs let me know. I plan to get an MSI x370 titanium and 1800x with 32GB g.skill.
IOMMU grouping issues is putting me off at the moment.
-
I am isolating cpu's and stubbing an usb pcie card in the syslinux:
append pcie_acs_override=downstream vfio-pci.ids=1b73:1100 isolcpus=2,3,6,7 initrd=/bzroot
I didn't change any clover or xml settings. XML basically comes from Gridrunner's video (Penryn, etc...). Added emulatorpin: <emulatorpin cpuset='1,5'/> and an usb, gpu passthrough to the XML
<vcpu placement='static'>4</vcpu>
<cputune>
<vcpupin vcpu='0' cpuset='2'/>
<vcpupin vcpu='1' cpuset='3'/>
<vcpupin vcpu='2' cpuset='6'/>
<vcpupin vcpu='3' cpuset='7'/>
<emulatorpin cpuset='1,5'/>
</cputune>
It works fine with the patched file, but doesn't if i use the regular clover file.
This is the same issue for me, fixed by using the patched clover. Mind you, this only happens when on 6.3rc6.
-
I upgraded to 6.3RC6 and now my sierra VM is running at half the speed that it was before, very strange!
I did not change a thing, same UEFI clover boot loader. VM boots fine, OSX is usable but very slow.
I have another install using UEFI and enoch boot loader and this is fine, full speed.
any ideas?
downgrade to 6.2.4
And that solves what exactly? 6.3 uses 6.2 ovmf as far as I know.
-
I upgraded to 6.3RC6 and now my sierra VM is running at half the speed that it was before, very strange!
I did not change a thing, same UEFI clover boot loader. VM boots fine, OSX is usable but very slow.
I have another install using UEFI and enoch boot loader and this is fine, full speed.
any ideas?
-
Hi
I am using an NTFS formatted nvme drive in unassigned devices so that I can passthrough the partition in a windows 10 VM.
I do this by using /dev/disk/by-id method. This works well but the UNRAID console keeps outputting a blockdev error....
blockdev: cannot open /dev/nvme1n1p: No such file or directory. This error appears when I rescan or refresh the unassigned devices list in the main webUI. The nvme1n1p device does not exist in /dev/ so I am not sure how to exclude it or where it has manifested from.
Any ideas?
-
Another issue that I have seen in all 6.3.RC releases is that
<alias name='virtio-disk2'/> does not stick after updating the VM XML.
Because of this I cannot use qemu args that use the alias name without an error being thrown up.
-
Anyone come across this error in the log before? nvme passthrough worked fine in 6.2.x.
I am using 6.3RC6.
You should attach your entire diagnostics file if you are expecting someone to be able to figure out what is going on...
OK, I have done this. Would appreciate it if someone could take a look.
Anybody planning a Ryzen build?
in Motherboards and CPUs
Posted
Have to agree with the above. I too use an RX460 is my second PCIe x16 slot on the Asus Prime Pro, no issues with it at all. What score did you get in Ungine Josecitox?