From Rackspace OnMetal: The Right Way To Scale:
OnMetal servers are single-tenant, bare-metal servers provisioned via the same OpenStack API as our cloud. They can be spun up as quickly as VMs to offer the agility of multi-tenant environments with the performance of single-tenant hardware.
Going from an EC2 style “spin up a VM via API call” to a “spin up a whole server via API call” seems like the next logical step. There are more challenges when it comes to managing this at a whole server level instead of VMs, but with new challenges come new opportunities.
One important note, there is reportedly no VM layer on these servers. It isn’t just a single-tenant VM, but an actual bare-metal server.
6 replies on “OnMetal”
I’m still waiting for the multi-host single VM server. I wonder if we will ever see this kind of beast, but that surely would be interesting!
How multi-host are you thinking? VMWare has a HA cluster version that will automatically move a VM to a new server in the event of a hard crash.
Well, I’m looking for something that uses the capacity of all the hosts all the time (not just for HA purposes), basically, something that would scale up when we had more hosts, without changing the VM runtime.
Something in the category of Heroku?
Hi, Can you automatically scale the OnMetal servers on an hourly basis. I.E. “”Auto Scaling allows you to scale your Amazon EC2 capacity up or down automatically according to conditions you define. With Auto Scaling, you can ensure that the number of Amazon EC2 instances you’re using increases seamlessly during demand spikes to maintain performance, and decreases automatically during demand lulls to minimize costs.”” Can you do this with OnMetal? Thanks.
No idea if that is something they have built in or not, but it would still be doable either way.