Michael_Nat

Once again, thank you so much @bmartino1! I appreciate the various options that you have shared - it is good to know what are the alternatives available so that I can weigh my options and decide based on my needs. I think for now, I want to keep running Unraid because I want the NAS functionality with the option to use whatever hardware I like. While there is a greater possibility of getting the vGPU option on Proxmox to work, I think it is a bit risky to rely on unofficial GPU drivers. My worry is that the GPUs or the system might get damaged due to the drivers. That's why I don't think I will go with this. However, I might set up a separate machine for playing around in Proxmox to learn about it cause it seems quite interesting. The Windows / WSL seems to be a decent option for Nvidia vGPU functionality. However, after going through all of the pros and cons, I am leaning towards just staying with Unraid and running a VM with GPU passthrough and rebooting when I shutdown the VM. I will probably only use the VMs once in a while so it shouldn't be too disruptive plus the Unraid server really only serves me personally so a reboot isn't too disruptive. I saw online that it may be possible to run commands to unbind the GPU from the VM's drivers without a reboot so I might explore that - though I note that such options may have stability issues. All in all, thanks so much for the advice and comments. I've learnt a lot and I may revisit this as my needs change!

Hi @bmartino1, First off, thank you so much for your very detailed and helpful response! It is very kind of you to spend time explaining how this works and sharing your views this to me which is helpful especially since I'm new to all of this. I stumbled upon Unraid last year when I was looking for a NAS solution with old hardware. Then I got into experimenting with LLM interfaces this year and various hosted LLMs and now I want to experiment with local LLMs, which is why I have a setup that is overkill for NAS and docker use... The two GPUs are for running larger local LLMs giving me a total of 48 GB VRAM - this is my priority. The reason for my post was to see if there is a way for me to have both GPUs assigned to LLM use for most of the time and occasionally temporary unbind a GPU and passthrough a GPU to the gaming VM. I would then reassigned the GPU back to the host for use by the LLM inferencing engine when I shut down the VM. Please correct me if I've misunderstood, your reply suggests that a GPU passthrough is not helpful in my situation because I will need to reboot the host to unbind the GPU - this applies to both Proxmox and Unraid baremetal. You mentioned exploring vGPU and when I looked it up, it seems exactly what I hope to do since I don't want to connect a monitor directly and was planning to use dummy HDMI plugs - I will explore this further although I note that the RTX 3090 does not support vGPU. I appreciate that vGPU is better supported on proxmox than on Unraid. I will think about it but I'm leaning towards sticking with Unraid bare metal because I'm comfortable with it plus it is super flexible hardware wise for a NAS - Proxmox scares me a little given my non-IT background. Lastly, I appreciate the recommendation to run Promox with one GPU passed to the gaming VM, the other GPU passed to the local AI docker with Unraid. Unfortunately, as explained above, this does not suit my use case because my main goal is to have both GPUs for LLM use most of the time and occasionally temporarily allocate one GPU to VM upon start up for gaming & photo/video editing. Once again, thank you @bmartino1!

Hi everyone, I’m in the process of upgrading my Unraid server setup and would appreciate some advice from the community. Currently, I’m running Unraid on an old Dell Optiplex 7070, which has served me well, but I want to enhance my capabilities for local LLM inference. I have committed to a new build with the following key specifications: Relevant Info on Server Build CPU + Motherboard: AMD 9 Ryzen 7900 + ProArt Creator X870E WiFi Memory: Corsair Vengeance RGB 64 GB (2 x 32 GB) DDR5-6000 CL30 Video Cards: 1. MSI RTX 3090 Ti Suprim X 24G 2. ROG-STRIX-RTX3090-O24G-WHITE Power Supply: Corsair HX1500i Fully Modular Ultra My initial plan was to run LLMs using Ollama and Open WebUI in Docker containers. However, since I won't be utilizing all of the GPU resources at all times, I’m considering setting up a VM that can pass through one of the GPUs for gaming (primarily World of Warcraft), as well as photo and video editing. I have a couple of specific concerns: GPU Binding: I understand that when a GPU is passed through to a VM, it can be bound to that VM. Is it possible to unbind and free up the GPU effectively when the VM is shut down? Idle GPU Power Draw: If the VM is halted and the GPU is unbound, will I still face issues with idle power draw from the GPU? Anti-Cheat Issues with VMs: I read about there being anti-cheat issues when running games in VMs. Additionally, I’ve read that Proxmox may offer better VM management capabilities. Would it be more beneficial to run Proxmox with an Unraid VM alongside a Windows VM, rather than using Unraid directly with a Windows VM? I would greatly appreciate any insights, advice, or recommendations based on your experiences. Anyone else in a similar situation and what approach have you taken? Thank you!

Thanks so much for the response, @JorgeB. If I understand correctly, the first approach in which I directly assign the new HDD at Disk 1 of the array and move the existing SSD (that was previously Disk 1 of the array) to the Cache pool seems to be the most straight forward route. The only issue would be since the SDD with the data is now in the cache pool, the unbalance plugin may not be able to move the data out of the cache pool. If so, I could then use the mover script (or the mover tuning plugin) to move the shares / data from the cache pool SSD into the new HDD in the array.

Hi all, I am running an Unraid 7 setup on a Dell Optiplex with a 1 TB SSD in my array. I do not have any parity drives and have a couple of Docker containers up and running. I have installed a 12 TB HDD which is currently being precleared. I want to assign/mount my HDD as Disk 1 in the array (where my SSD is currently assigned to) and to assign the SSD to a new Cache pool. What is the best way to do this? My thoughts are that once the HDD has finished preclearing, to: 1. Stop the array 2. Use the New Config tool to clear the previous disk assigns 3. Assign the HDD as Disk 1 of the array and assign the SSD in the new Cache disk pool. 4. Start up the array and use the Unbalance plugin to move the longer term data storage shares to the array / Disk 1. 5. Finish Will the above approach work? Alternatively, I was thinking that after the HDD finishes preclearing, I could: 1. Stop the array 2. Assign the HDD as Disk 2 of the array. 3. Start the array. 4. Use the Unbalance plugin to move the relevant files / shares from the SSD to the HDD. 5. Stop the array. 6. Run New Config tool refresh the disk mountings. 7. Reassign the HDD to disk 1 of the array and assign the SDD to a new cache pool. 8. Restart the array. 9. Finish Clearly the alternative approach is more complicated, but I just want to know the way to do this without upsetting my current docker containers and settings. Thanks for taking time to look at this and I would be very grateful for your inputs on whether the above works!

Hi! I'm new to unRAID and would like to get started with a modest build that has above average performance and an upgrade path. Budget: Not pinching pennies but trying not to be a fool parting with his monies. Ideally under USD 1,500. Capacity / Drives: For now, looking to have about 10-20 TB although I fully expect this to slowly grow. I'm a hobbyist photographer that loves to shoot in RAW. Expandability: I want to have an upgrade path for the build, both storage wise and performance wise. Additional apps / Purpose: I am thinking of running Plex, the *arrs, VM Docker for Home Assistant, a Minecraft server, and to use it for Apple Time Machine backups. Plan for Hard drives: I'm not sure what this means... but I'm planning to have a couple of 7,200 rpm hard disks with 1 parity drive for now and will probably want 2 parity drives later on for data security. Happy to add more hard drives as my needs grow. Spare parts: What are these...? Just joking, I use Macs (although I have built my own PC before I became a Mac user); therefore, I don't have any spare parts. I've done some lurking on the forum (probably not enough) and have come up with what I think is a decent build which I would be grateful for opinions on: PCPartPicker Part List: https://pcpartpicker.com/list/YZ2ZDZ CPU: Intel Core i5-13600K 3.5 GHz 14-Core Processor ($297.99 @ Amazon) CPU Cooler: *Noctua NH-D15 chromax.black 82.52 CFM CPU Cooler ($119.95 @ Amazon) Motherboard: Gigabyte Z790 AORUS ELITE AX ATX LGA1700 Motherboard ($229.99 @ Newegg) Memory: Corsair Vengeance 32 GB (2 x 16 GB) DDR5-5600 CL36 Memory ($117.99 @ Amazon) Storage: Inland Performance Plus 1 TB M.2-2280 PCIe 4.0 X4 NVME Solid State Drive ($84.99 @ Amazon) Storage: Seagate Exos X14 12 TB 3.5" 7200 RPM Internal Hard Drive ($193.99 @ Amazon) Storage: Seagate Exos X14 12 TB 3.5" 7200 RPM Internal Hard Drive ($193.99 @ Amazon) Case: *Fractal Design Meshify C ATX Mid Tower Case ($99.99 @ B&H) Power Supply: Thermaltake Toughpower GF1 PE 850 W 80+ Gold Certified Fully Modular ATX Power Supply ($109.99 @ Amazon) Wired Network Adapter: Intel X540-T2 2 x 10 Gb/s Ethernet PCIe x8 Network Adapter ($69.98 @ Amazon) Total: $1518.85 Generated by PCPartPicker 2024-03-03 09:37 EST-0500 Is this build way overkill or a decent starting point for a home lab? I love experimenting and tech so I would rather spec for more processing power although I would like the system to be reasonably power efficient. I also want a 10 Gbe NIC for faster file transfer speeds. Thank you for reading!