Given a Docker image you can spin up a container in lots of places. For example on my Mac under Boot2Docker, at Orchard, or on Digital Ocean. I don’t have any bare metal at hand, so these all involve the slight tax of virtual machine.
I ran the same experiment on these three. The experiment launches 18 containers, serially. The jobs they varied; but they are not very large.
180 seconds Boot2Docker 189 seconds Orchard 149 seconds Digital Ocean
These numbers are almost certainly meaningless! I don’t even know what might be slowing things down: CPU, I/O, Swap, etc.
Interestingly if I launch all 18 containers in parallel I get similar results +/-10%. The numbers vary only a few percent if I run these experiments repeatedly. I warmed up the machines a bit by running a few jobs first.
Yeah. Adding Google App Engine and EC2 would be interesting.
While Orchard charges $10/month v.s. Digital Ocean’s $5 their billing granularity is better. You purchase 10 minutes, and then a minute at a time, v.s. Digital Ocean which bills an hour at a time. Orchard is a little more convenient to use v.s. Digital Ocean. A bit-o-scripting could fix that.
I’m using this for batch jobs. Hence I have an itch: a batch Q manager for container runs. That would, presumably assure that machines are spun up and down to balance cost and throughput.
Queue of Containers