Open Stack

From: Donny Davis [mailto:donny at fortnebula.com] 
Sent: Wednesday, August 05, 2020 8:23 AM

> If you have any other questions I am happy to help where I can - I have been working with all nvme stuff for the last couple years and have gotten something into prod for about 1 year with it (maybe a little longer). 
> From what I can tell, getting max performance from nvme for an instance is a non-trivial task because it's just so much faster than the rest of the stack and careful considerations must be taken to get the most out of it. 
> I am curious to see where you take this Eric

Thanks for the response!  We also use Ceph with NVMe SSDs, with many NVMe namespaces with one OSD per namespace, to fully utilize the SSDs.  You are right - they are so fast that they are literally faster than any application can use.  They are great for multi-tenant environments, though, where it's usually better to have more hardware than people can utilize.

My first test is to try using the Libvirt "images_type=lvm" method to see how well it works.  I will report back...

Eric