[cat199]

> less expensive than the colocated hardware and the three additional people required to provide support and ensure service levels

i often hear people comparing cloud vs colo but not including more traditional dedicated hardware rental - seems to me this should be pretty similar, maintenance wise to cloud since H/W is handled by the vendor (just need to monitor hardware faults in addition to OS/app layer & notify DC on issues)

[lazide]

The difference is that in cloud you get live migration (generally) that works. So if whatever machine you are on dies, you don’t have an expensive and disruptive rebuild/restore cycle to deal with.

Since this can take a day+ even once you get new hardware, and architecting most software stacks so you have the redundancy and ability to migrate services around without downtime is hard, and hence expensive if you don’t have the expertise (AND randomly available time), running on dedicated rented hardware really shouldn’t be compared to cloud.

It’s a fundamentally different type of experience for the vast majority of people.

[manbart]

Solutions like VMware vCenter work well for live migrating, cluster balancing, HA priority etc. it’s not exactly a cheap product though.

[nfsdnd]

When did any cloud provider other than Google get live migration?

[dilyevsky]

GCP definitely live migrates and it’s well documented. Azure and OCI do too but details are a bit less clear. AWS does not afaik