@jblaze said in Latency with VDI in VMware View 7 environment: I'm new to VDIs so not entirely sure if I'm asking the right questions. The server is hosted externally by our MSP and they're trying to determine what the cause is. That it is external alone is almost certainly the problem. VDI can work remotely, but is often relatively painful. Also, be aware, while there is some extreme edge cases where you can do hosted VDI, this has traditionally not been allowed and unless your MSP has figured out some extremely new and rare licensing with Microsoft, those VDIs aren't legal.

@oksana said in How many IOPS your NVMe can do? All of them!: There’s a common opinion that the performance in general and IOPS-intensive performance like NVMf [NVMe over Fabrics] is usually lower in virtualized environments due to the hypervisor overhead. Check out this article to prove or knock down this belief! Great, now I'm impatient to see the results!

@oksana said in Accelerating your IT environment to new speeds with StarWind iSER: @travisdh1 Yes, PFC for switch and RDMA support for Ethernet So, yes, it does require a few things, but things that should be available already. Great!

So when I first install XenServer and I "tick" thin provisioning, behind the scene it's making the drive ext, so I assume if I didn't choose thin provisioning it would have made it LVM?

Veeam's free monitor is decent. The built-in stuff works great too. (perfmon)

I've been looking at this too as part of a overall project.

@MattSpeller said in Shadow Protect and Disk IOPS usage..: @scottalanmiller said in Shadow Protect and Disk IOPS usage..: @MattSpeller said in Shadow Protect and Disk IOPS usage..: @scottalanmiller said in Shadow Protect and Disk IOPS usage..: @DustinB3403 said in Shadow Protect and Disk IOPS usage..: The read usage on this system is insane for what it is normally doing. Even a tiny SW install we recommend some hefty resources and dedicated SSDs. You definitely just figured out the problem. Had you led with this we could have told you instantly what the issue was. Our rather beefy SW install runs on rust just fine. Not even a half decent rust array. Old junk. I'm surprised. Even when ours was tiny we gave it 100,000 IOPS and it remained slow. ¯\(ツ)/¯ There's only 3 of us in IT here. I suspect more concurrent users would kill it. We had probably ten or fifteen and loads of tickets. But that isn't that much of a jump, I wouldn't think.