I don't know how Starwind vSAN can be run but if it's on a hypervisor it's severely limited by I/O congestion through the kernel. NVMe drives is causing problems that was of no concern whatsoever with spinners. Both KVM and Xen has made a lot of work to limit their I/O latency and use polling techniques now but it's still a problem. That's why you really need SR-IOV on NVMe drives so any VM can bypass the hypervisor and just have it's own kernel to slow things down. Anton: There are no problems with polling these days You normally spawn a SPDK-enabled VM (Linux is unbeatable here as most of the new gen I/O development happens there) and pass thru RDMA-capable network hardware (virtual function with SR-IOV or whole card with PCIe pass-thru, this is really irrelevant...) and NMVe drives and... magic starts happening This is how our NVMe-oF target works on ESXi & Hyper-V (KVM & Xen have no benefits here architecturally, this is where you're either wrong or I failed to get your arguments). It's possible to port SPDK into Windows user-mode but lack of NVMe and NIC polling drivers takes away all the fun: to move the same amount of data we normally use ~4x more CPU horsepower on "Pure Windows" Vs. "Linux-SPDK-VM-on-Windows" models. Microsoft is trying to bring SPDK to Windows kernel (so does VMware from what I know), but it needs a lot of work from NIC and NVMe engineers and... nobody wants to contribute. Really. Just my $0.02

@marcinozga said in Linux users with iPhones / iPads: @NashBrydges That's most likely direct connection. Plex uses UPnP and NAT-PMP to open ports on router, otherwise you simply cannot connect directly. If you stream through relay, that's where limitation is in place. I have UPNP + NAT-PMP enabled. I'll disable them and test things out when I have a chance.

Placeholder

Posted.

This video was in the list from before. Good review though.

@connorsoliver said in An Overview of RAID - CompTIA A+ 220-901 220-902 Video Training by Prof. Messer: Is using a RAID 1 configuration faster as well? Or is its main purpose so if you lose one of the drives you have a backup? Primary purpose is definitely data protection. But RAID 1 provides a 200% read performance benefit over using a single drive. Write performance is the same as a single drive.

@connorsoliver said in An Overview of Storage Devices - CompTIA A+ 220-901 220-902 Video Training by Prof. Messer: What did he mean when he said there's only a limited number or writes on a USB flash drive. So this is a small mistake on the A+ material. They are making assumptions about the storage media based on the communications protocol. But it's based on very common things. A standard USB flash drive using a flash memory technology that "wears out" as you write to it, but essentially never wears out as you read it. So the way that a USB stick is "meant to be used" is that you store things on it and read it a lot. You can change it, but it isn't meant for constant writes. So under "normal" use, USB sticks last a long time. But it you write to it constantly (like when using it as swap) you will cause the memory chip(s) to die quickly.

@dafyre said in How would you build a File server with 170TB of Usable Storage?: Systems like Ceph and Gluster don't necessarily need RAID since they can work with different disks in the same node. They definitely don't need RAID. That's their point.

I've used it a couple of times, but since I started using the DC series of drives it's pointless. Only for their consumer class drives. It's great for firmware and secure erase if you have a compatible drive.

@scottalanmiller said in Dell MD1220 RAID 5 Rebuild Question: @Jimmy9008 said in Dell MD1220 RAID 5 Rebuild Question: @scottalanmiller said in Dell MD1220 RAID 5 Rebuild Question: @travisdh1 said in Dell MD1220 RAID 5 Rebuild Question: That makes a little more sense. They've negotiated a deal with Microsoft from the sounds of it. No, way, way more likely they just figured out how hard it is to get caught. I totally doubt anything like that is going on here. I have been told our annual budget for licensing which we pay is in the region of £600,000. Either way, not my problem Wow. But, sounds like only that high because they don't know what they are using, lol. The only way to get licensing truly down is to know what you use. Someone is both ignoring what is used, but also encouraging unlimited use. Both things set MS up to just keep making it more and more expensive. It's a trick, sounds easy, but makes one lazy licensing person encourage not keeping licensing lean - basically giving Microsoft the power to charge anything that they want down the road. Yeah, not your problem, but definitely a symptom of management issues and a lack of clear thinking. If they are truly paying their bills, my guess is a licensing "specialist" who has created their own job and knows if MS isn't used heavily, their job would go away, so is doing stuff to encourage you to lock in MS so that that specialist can't be eliminated. Basically creating their own job. Yeah, I don't disagree with anything you said. It's just not my issue. I still get to buy shiny new toys

@Emad-R said in Linux NFS SSD caching: AID 10 on Linux File Server machine, how can I speed up this NFS storage by an intelligent cache, for example I wish to add another 250 GB SSD to act as cache, how will tha Yeah the RAID 10 is on HDD, due to cost effectiveness. Will check LVM since its baked in.

@RojoLoco said in OSX Mojave - System Storage - Time Machine Disabled: @DustinB3403 said in OSX Mojave - System Storage - Time Machine Disabled: That seems unnecessary as this shouldn't be so difficult, nor should it ever occur. ...because everything apple does is perfect and never, ever malfunctions in any way, right? Yeah. . . no I get the stance. What makes no sense is there is no way for me to find where this bulk is coming from.

@CCWTech said in Restoring Google Drive Folders Instead of Individual Files: Unfortunately what they did ended up orphaning the files. https://support.google.com/a/answer/6008339?hl=en Ouch

@dafyre said in Its is okay to sync/delete often from Cloud Storage?: @scottalanmiller said in Its is okay to sync/delete often from Cloud Storage?: I don't believe that there is any charge for Wasabi deletions. From what I can tell, Wasabi only charges for storage. There are no egress or deletion fees. Correct, same here. Unless you have the old accounts where they did charge for egress.

@scottalanmiller said in Should I bother to learn Windows Storage Spaces and what about Glances export?: @PhlipElder said in Should I bother to learn Windows Storage Spaces and what about Glances export?: @scottalanmiller said in Should I bother to learn Windows Storage Spaces and what about Glances export?: @PhlipElder said in Should I bother to learn Windows Storage Spaces and what about Glances export?: HCI or disaggregate with Hyper-V and SOFS S2D are they way we're deploying now. So, the whole conversation is essentially moot. Not really HCI as described with the DataOn. That's just a software RAID version of the non-HC model. HC has always meant physical convergence. I believe I referred to the DataON setup as "Converged" or sometimes "Asymmetric" not Hyper-Converged which is what Storage Spaces Direct is when running with both Storage Spaces and Hyper-V on the nodes. I see. Asymmetric is a decent term. What about it is converged, though? It seems "unconverged", if you will. Other than the software RAID running on the storage nodes. "Converged" in this case refers to both Hyper-V and Storage Spaces running on the nodes to provide virtual machine and storage cluster based arbitration.

@DustinB3403 said in Nextcloud Backup System Idea: Practicing process also requires that you practice developing process and having holes punched into said idea. Yep. And you've validated some holes I've considered, but didn't explicitly write in my posts.

@Emad-R IOPS varies wildly by how it is tested. The question for your Windows tests would be... how was it tested? We know how the Linux was tested, it tells us. Knowing how the Windows was tested is the real need at this point.

@jaredbusch Right. The datastores are at the hypervisor level. The vmdks would be on respective datastores and then in the VM, they would be also be shown as separate disks.