Astror
-
Posts
12 -
Joined
-
Last visited
Content Type
Profiles
Forums
Downloads
Store
Gallery
Bug Reports
Documentation
Landing
Posts posted by Astror
-
-
According to this video it can be done with Linux 5.11:
So I guess we have to wait for Unraid to update the kernel?
-
1 hour ago, gray squirrel said:
So I did a bit of testing with CSGO VM vs BM @1080p and see similar results.
The community benchmark goes from around 400 to 320 average FPS. Playing with bots on one of the maps and there is a same result around 80 FPS drop. But this is such an extreme test and so unrealistic. I bet if I made a 4 core (one CCX) VM it would be much closer. But 300 FPS in a game is a bit ludicrous anyway.
Well thanks for taking the time 🦸, just knowing that you can replicate the same results is a relieve. I guess this is just what you can get in a VM... As you said 300 fps is obviously a lot, but, as a couter point, it is believed that for how the game engine works it is an advantage to have as many fps as possible in this particular game, from a competitive advantage perspective... That said, for my skill level I am good with this performance.
Thanks again
-
7 hours ago, gray squirrel said:
Although I have not tested CSGO this was my results BM 12 core vs 6 core VM. This is with a GTX 1080.
Cinebench R20
BM multi = 6675
VM multi = 3488 (52%)
BM single = 511
VM single = 471 (92%)
Cinebench R15
BM multi = 3010
VM multi = 1457 (49%)
BM single = 192
VM single = 190 (99%)
timespy
BM GPU = 7548
VM GPU = 7446 (98%)
CIV VI
BM turn time = 7.56
VM turn time = 7.63 (99%)
BM FPS = 128
VM FPS = 130 (102%)
F1 2019
BM av FPS 136
BM min FPS 101
VM av FPS 124 (91%) this was gsync on for some reason so probably attributes most of thr differences.
VM min FPS 99
mankind divided
BM av FPS 73.7
VM av FPS 69.7 (95%)
RDR2
Bm av FPS = 62.13
VM av FPS = 63.8 (103%)
at that point I gave up benchmarking and just started gaming as I doubt I will ever notice the difference.
edit: I game at 1440p so am GPU bound in most situations. In games I have 99% GPU utilisation
First thanks for putting the effort in tryng to help me here, I was clearly a bit lost even after a whole year using Unraid. I see that you have made quite a lot of benchmarking to make sure that your VM worked fine. I can also see in all cases your tests were GPU limited (at least in games, Cinebench I guess is another thing but the results are well withing what I would expect). But in the case of CSGO at lowest settings I think that I am being limited by the CPU somehow.
7 hours ago, gray squirrel said:The NUMA stuff is related to threadripper not your 3950x. But the principal is the same.
your 3950x is made up of two CPU dies. Each die has two CCX made up of 4 cores.
if you are gaming. You want to avoid crossing over die to die as this will add significant latancy as the OS isn’t aware of the layout of the CPU (because it’s in a VM)
lowest latency will be one CCX. But this might not be enough CPU power for you. My view with my 3900x was to give the VM one whole die.
in your first layout you have passed all the hyperthreads of all the cores, this will give good for something like rendering as long as the host isn’t doing anything. But will be very bad for latency.
in your second layout you have given two CCX’s across two dies. This will be very poor.
Try giving it 8-15 + the hyper threads and your performance should be good.
remember to isolate the cores and hyper threads from the host.
please also ensure you follow the guidance on this.
I have been reading from that post you mentioned (a lot of interesting stuff about CPU pinning), and I have followed OPs recommendations, some things I hadn´t considered until now (like the 'Disk Cache' settings of Tips and Tweaks), but I guess the most important one has been to isolate the CPU cores that I assign to the VM with isolcpus. I expected this to have some effect but I am afraid that the tests I made after that didn´t show any improvements (all testing has been done with Docker off to ensure no other important tasks affected performance inside the VM). I have tried different combinations of isolated cores ranging from 2 to 8 cores, all had similar scores in the CSGO benchmark withing a +-20 fps, so I guess they can be considered the same. In all cases the cores I chosed where paired threads (not like the first setup I posted, with a thread from every core of the CPU).
At this point I am starting to think that in these extreme cases where the CPU speed (or latency I guess) is so important the VM strategy simply isn´t capable to perform as well as a bare-metal machine. In which case I don´t think this is the end of the world, as 300 fps seems plenty for a good CSGO experience
.
Right now I am using the 8-15 cores + hyperthreads as sugested by @gray squirrel, but the situation is the same as in the OP. If someone else has another idea of what may be causing this (maybe something related with the CPU governor?) I am all ears.
Thanks @gray squirrel again for the guidance, if nothing else I think that I understand a lot more about CPU pinning now.
-
10 hours ago, gray squirrel said:
It’s to do with cross die and CCX latancy. Also setting up the MV for the correct application.
a lot of this is talked about in the thread:
TLDR
workstation - spread load evenly across cores / dies / ccx
gaming - minimise cross die and CCX interaction.
If you are just gaming. You will probably get better performance with 4 cores from one CCX.
I have a 3900x and I use one die (2 CCX) for 6C/12T gaming VM. I can’t tell the difference between BM and VM. Benchmark results (even synthetic ones) are within a few %.
After some reading (that post you mentioned was really usefull thanks), I understand that it is in my best interest for the gaming VM to set the CPU in NUMA mode, and later set the cores of the VM to use the 8 cores of the CCD that the graphics card connects to. That will reduce latency and help in the games that try to push fps to the maximum (like the CSGO case I´m working with).
That said, I have been exploring the BIOS settings, and I can´t find the option mentioned in the post that is suposed to activate the NUMA mode, that being the AMD CBS/DF Common Option/Memory Addressing with 5 different modes: auto, die, channel, socket and none. With Channel being the one that I am looking for.
In my case I see 2 options that (I suppose) are related to this:
.thumb.jpeg.5666a167af0889a6a70f7ddeafbdeb81.jpeg)
I have tried the 8 possible combinations, Memory interleaving AUTO and disabled, and the 4 NUMA nodes options in each case, none made Unraid see more than one node with numactl --hardware. And there is no channel mode to be seen anywhere (either inside AMD CBS or in any other tab), which leads me to believe that maybe the ability to choose NUMA node may be deprecated in thi BIOS version (F31q, the latest one as of December 2020). If thats the case, is this a dead end?
-
Hi everyone, first a little bit about my system. In January I decided to retire my old computer, and I knew of the existence and possibilities of Unraid, so I decided to go for it and assembled a computer with the goal of it being my NAS/Home Server/Gaming-Work machine. Here are the specs:
- Ryzen 3950x
- Gigabyte x570 Aorus Master
- Corsair Vengeance LPX 32 Gb 3200 Mhz (2x16)
- Sabrent 2TB Rocket NVMe PCIe M.2 (Cache pool)
- WD Elements Desktop 10 TB - X2 (Unraid pool)
- Corsair HX1200 1200W
-
MSI Radeon RX 580 Armor 8G OC 8GB (from my old computer, now I´m waiting for new cards to be available
)
From the moment I had it “properly” configured I have been using it as mentioned, I do all my gaming in a Windows 10 VM, and I have been enjoying it a lot, no major problems whatsoever. Of course, at the beginning I did some testing to see the difference in gaming performance between the VM and a bare-metal Win 10 installation. The thing is, I play a lot of CSGO, so it was my go-to benchmark. Even then, I noticed that there was a weirdly big difference (more details in a moment), but other games ran well so I didn’t give it much importance, and CSGO was also perfectly playable so I just kept using this machine as is.
Now I have time so I have been doing some testing again, to see if that difference in CSGO was still a thing, and it is. I though that it may not be the case, because the way I configure the CPU cores assigned to the VM has changed from the moment that I first assembled the system, the reason being that I found a configuration which had a Cinebench multi-core score that was very close to bare-metal. That configuration is the next:
Now
With this configuration Cinebench R23 gives 17.400 (aprox) points, while the bare-metal Win 10 gives 24.000 (aprox). I don’t know why they are so close, given that I have half the CPU working here (I think). But it is how I am using the VM now, versus how I had it during the first months:
Before
Because of this difference I expected to have a closer experience to bare-metal in CSGO, but as you will see now, there is still a 100 fps difference in the CSGO fps Benchmark (a workshop map for testing):
- Bare-metal: 395 fps
- VM: 295 fps
This is the difference in either of the CPU core configuration (approximately of course). In both cases the game is configured so it is never GPU bounded, meaning that the graphical settings are set to the lowest possible.
Suffice to say I don’t have the slightest idea of what is going on here, but I will give more details of my testing in case it is of some help. My suspicion is that whatever the reason, it has to do with the CPU, because when the GPU is the bottleneck the difference in performance is close to cero, even in CSGO. I have made some testing with 3DMark to back this up:
- Bare-metal: Graphics Score 4391 - CPU Score 13445
- VM: Graphics Score 4387 - CPU Score 12477
I think that this result is more representative of what I experience in games in general, as it is usually the GPU what limits the fps in games. For this very reason I am not very worried about this issue, but I am really curious about the big gap in the CSGO benchmark (again, the game runs just well and I find the fps in game more than sufficient in general).
To sum up, I would like to know why there is such difference in this particular case (maybe too niche and not many people here will care I imagine). It is also a good opportunity for me to maybe learn a bit about the CPU core assignation with the 3950x, as I am curious about what is the correct way (or the one that uses the 8 cores inside the same CCX). I have tried to be as detailed as possible, but I am sure there are important aspects of the problem that I haven’t talk about, in which case I will be happy to answer any questions.
Thanks a lot in advance.
-
2 hours ago, itimpi said:
No easy GUI method.
You can revert manually by downloading the zip file for the release and extract all the bz* type files overwriting the ones on the flash.
OK will try thanks¡
-
1 hour ago, itimpi said:
The 6.8 series stable releases are still using a 4.19.x series kernel. The 6.8 rc7 release DID have a 5.x series kernel but rc8 reverted to a 4.19.x series as described here.
You will need to wait for the 6.9.0 rc series to start to get a 5.x series kernel or revert to 6.8.0 rc7. Hopefully' the 6.9.0 rc series starts very soon.
Is there a way to revert to 6.8.0 rc7 from the web gui? I haven't seen any method...
Thanks for the answer
-
Hi everyone, this is my first Unraid system so this could be trivial, but can't find any way to do what I want. I'm running a new system with a Ryzen 3950x and a Gigabyte x570 Aorus Master, two graphics cards (a Geforce GT710 for unraid to boot from and a MSI RX580 Armor 8GB for a Win 10 VM for gaming). Right now I am using Unraid 6.8.1 (started with 6.8.0 five days ago but upgraded just after the stable 6.8.1) and I'v maganed to run a Win 10 VM with the RX580 pass-through, plus a USB controller because I wanted to have usb hotplug (this wasn't easy XD). The thing is that after some testing it seems that I am not getting the performance that I would have expected from the CPU. I have run a CSGO fps test in a win 10 bare metal installation with a 280 fps average as a result, while in the VM (with 12 cores assigned) it gets 230 fps. The task manager always says that the CPU is at 3.5 Ghz, so my first theory was that the VM wasn't boosting the CPU. If that's the case, can it be because the kernel in Unraid 6.8.1 is 4.19?? and if thats the case my main question is: How do I use an Unraid version with a more recent Kernel, say, 5.3?
I know that 6.8 RC7 had a 5.x kernel, and that you could download that with the USB creator not that long ago, but it happened that the very same day that I wanted to install Unraid in this machine, the next branch in the USB creator pointed to 6.8.1, so I just installed 6.8 expecting for it to work fine. It does work fine in general but I expected to have more performance in the VM for gaming. Summing up, right now I'm not sure if there is a problem with the unraid kernel version and the way it uses the CPU or with my expectations of it.
Any ideas, help?
Thanks in advance.
-
3 minutes ago, testdasi said:
Based on the post I cited, that (i.e. add an old 2nd GPU for Unraid) was the solution.
I suggest you can msg the original poster and double check with him/her.
If the SATA ports are important to you then of course, stick with the Asus ROG Crosshair.
Just note the compromise that your cheap 2nd GPU will have to be in the 1st PCIe slot (the RX 580 in the 2nd PCIe slot).
You can boot the VM from a vdisk file saved on the SSD as part of the cache pool. That is fine.
For value options, you might want to consider something like the ADATA XPG SX8200 Pro.
It is at a similar price point to the 660p and it's Micron 3D TLC NAND (and it has DRAM buffer) - that is actual value-for-money.
Intel has the anti-consumer practice of locking up the entire SSD in read-only mode after all the reserve has been used, under the pretext of data loss protection. That doesn't go well with the lower endurance of QLC cells. And then you factor in the lower performance of QLC and you basically are paying brand premium on a budget low-end product.
What's wrong with the Toshiba?
Or to put it differently, what makes you pick the WD Red NAS over the Toshiba X300 Performance?
Toshiba is one of the only 3 HDD manufacturers in the world (together with Seagate and WD) so it's not like they are a value brand.
Thanks for the clarification on the SSD, I will seriously consider the ADATA option
Regarding the Toshiba HDD, the truth is that I haven't put too much thought into it because I was more worried about some compatibility issue I could have (which happens to be the case, but I would have never thought that it was going to be the graphics card
), so I really have no problem with it, I am just worried about disk failure in general (is one of the main reasons for me to go with a NAS solution, for the redundancy options).
I will check the issue of the GPU with the poster you referenced, thanks.
-
46 minutes ago, testdasi said:
There are many topics on the forum with issues passing through the RX 580 as primary / only GPU.
The only [Solved] topic I can find (quoted at end of post), the OP had to have a 2nd GPU.
So I would expect you to have a hard time with your suggested config and use case.
There is a success story with Gigabyte X570 + 3900X + Nvidia GTX 1070 so you might want to consider that config instead for an easier time.
In particular:
-
I generally recommend someone new to Unraid to pick a Gigabyte motherboard because it has the Initial Output Display option in BIOS that allows you to pick any PCIe x16 slot as first GPU (what Unraid boots with).
- This allows you, IF THE NEED ARISES, to plug a 2nd GPU in the slowest PCIe x16 slot (usually only running at x4) to use for Unraid to boot and not waste your fast 1st PCIe slot.
-
Mitigation for error code 43 with Nvidia GPU is generally more reliable than mitigation for reset issues with AMD GPU.
- Usually all it takes is a 2nd GPU (cheap single-slot for about €30-40 or so) for Unraid to boot with (hence my point above about Gigabyte motherboard) to resolve error code 43.
- The 1070 is a bit more expensive than the RX580 but the 1060 should be similarly priced.
Stay away from the Intel 660p (and QLC SSD in general) especially if you want to use it the cache pool.
It's cheap but there's a reason why it's so cheap (it's rubbish - real life performance is comparable to a good SATA SSD, and sometimes worse).
You want 3D-TLC (aka "V-NAND").
Any particular reason why you picked the WD Red NAS?
- Unraid isn't RAID so there isn't really a need to pick a "NAS" (or "Enterprise") model.
- Usually the cheapest you can find from a reputable dealer is good enough.
- Many on here even shuck from cheap external HDD
The only generally available (and updated) patched Unraid is Unraid Nvidia but that is only for those who want to do hardware transcoding in Plex using supported Nvidia GPU (e.g. Quadro P2000 is a popular choice).
If you don't have that need (and from what you said, you don't) then there's no need to run any patched build of Unraid.
A user posted a patched version that has VEGA and NAVI reset patches included but it has not been updated since November.
RX 580 is Polaris though so I don't think that will help if you decide to go ahead with the RX 580.
Referenced posts:
[SOLVED] Can't pass my RX 580 through
Success story with Gigabyte X570 + 3900X + Nvidia GTX 1070
Custom kernel
Thanks for the response, and I have some questions regarding your answer.
My only reason to go with an RX580 for the VM is that it is the graphics card I'm using in my current build (and will have to do for now). If the problem is that I would be using only one graphics card and this one is problematic, I could add another one (a very old one I have lying around) and leave it for Unraid to boot from. Would that solve it?
On the other hand, the reason that I chose the ASUS ROG Crosshair is that it is one of the few AM4 motherboards that I've seen with 8 SATA ports, which I think I need if I want more storage upgrade options in the future for the NAS. There is also the Asus ROG Strix X570-E Gaming, and I wasn't really sure which one I preferred, but if I can afford it I think I would go for the Crosshair (for now at least). If you tell me that the Gigabyte mobos are better for Unraid (I believe you as I know close to nothing about this) then I would have to settle with 6 SATA ports, and research how to expand storage through the PCI express slots (dont now how difficult/expensive it would be to do it in the future).
Regarding the SSD I dont really have a problem with the performance hit of going with QLC instead of TLC, as far as I know (from YouTube videos,
) I am not going to see a difference for my use case most probably, and I want as much SSD storage as possible from the M.2 slot (as the SATA ports are valuable for me for the NAS storage). As far as I know, and I could be wrong, If I do a VM I can chose to use the SSD to run it from it despite the SSD being the cache for the pool (am I wrong?).
Lastly the NAS drives I chose are simply one of the few options I can see for 10TB drives, and one of the cheapest (without considering the chuck option from external HDDs, I don't really like that idea will avoid it in general), the only cheaper that I have seen is the Toshiba X300 Performance 10TB 3.5" SATA3 256MB Bulk.
-
I generally recommend someone new to Unraid to pick a Gigabyte motherboard because it has the Initial Output Display option in BIOS that allows you to pick any PCIe x16 slot as first GPU (what Unraid boots with).
-
I am planing on building my own double duty NAS/gaming machine and from what I have been able to read in the forums I'm not sure if this configuration will give me any problems (see attached image). Will I have to do something weird/difficult for a beginner as using a patched build of Unraid with a different Kernel? If so, Will it have consequences in compatibility with any plugin I may be interested in using (plex, Minecraft server...)?
Thanks in advance, I'm sorry if this is a trivial question but I'm new in this unraid stuff ;)
.
.jpeg.b18ffb78b0409ca71882f743c3f53653.jpeg)
)
Now
Before
[Support] selfhosters.net's Template Repository
in Docker Containers
Posted
Did you manage to fix this? I am trying exactly the same thing and I got to the point that overleaf is up and running locally, but when I try to create the admin account I cannot set a password, I get the coockie error. And I cannot access through the external IP adress (I think it is correctly pointing to the server, but I am not so sure of how to configure it in cloudflare).