[fpp]

Their example dedicated host adds up to $2'226 per month - had a quick calc on the retail HW cost for a machine like this - should not be more than $6.5k with 2 * E5-2670 v3 12 cores.

What I understand so far - it is physically bundling a fixed amount of virtual machines to a physical host - in the example "dedicated host" 22 * m4.large.

Bundling your virtual machine to one or a series of physical hosts / on the same network segment is a service you can have from quite a few hosting providers (if you ask).

If you opt for a solution like this, it is also most likely that you will run an enterprise scale solution and you will do so for quite some time - at least 6 months upwards.

Keeping that in mind together with a lifetime of at least 2 years for such HW, you will be paying 8 times the HW cost for a 2y lifetime for a management layer (storage / connectivity you pay per GB with EC2).

I guess everybody will have to see how this fits into their business model for non volatile / predictable resource demand or a set of when physical iron might be a better choice (colo or rent).

[cstejerean]

You are looking at their on-demand rates, which means no commitment. You can do this for a month or even a few days. If you know you will need infra for 1 year or more you can use reserved rates. Right now those are not yet publicly available for Dedicated Instances, although the post mentions you can contact them if you want early access. With reserved rates the price should be 70% less for a 3 year commitment (speculating based on the post). A huge difference.

[vidarh]

But I can still for most things get lower prices on a month by month basis than the price a 3 year commitment to Amazon gets you. And that's before paying their outright extortionate bandwidth prices.

[nitrogen]

If you have to hire an extra person to manage the new hardware, then you aren't saving money.

[vidarh]

In my experience, moving people off EC2 cuts down on the ops time they need, it doesn't increase it.

For one of my clients that I manage multiple racks in two different locations for with 150+ VMs, "managing the hardware" comes out to about 1-2 days a year in aggregate to bring new hardware in and wire it up (most of that is travel) + 20-30 minutes to investigate the very few issues we can't diagnose and fix via IPMI. I pop a server in, attaches power and ethernet, checks that the IPMI is reachable and that it sees the PXE server, and beyond that "managing the hardware" comes to yanking the occasional dead harddrive and inserting a new one, and ever now and again to confirm a server is dead.

Meanwhile with EC2 I see most of the same non-hardware issues (e.g. kernel panic, applications occasionally spinning out of control and taking a server down) that are just as trivial to handle via IPMI as via the EC2 console, but we also have to engineer around things like the lack of solid, stable, directly attached RAID arrays, which we don't need to worry about with the bare metal servers.

And no, EBS does not count - the number of times volumes have gotten stuck in attached state on a failed instance terrifies me. It also can't in any way match directly attached SSD RAID setups for performance which is another reason why it ends up taking more ops time: You end up with setups that simply take more vms to compensate for platform limitations.

I absolutely think EC2 is great for things like large batch jobs etc. where your requirements vary wildly, but most people don't even have enough daily variance for that to get anywhere near compensating for the cost of EC2 (and nothing stops you from deploying hybrid approaches - in fact I'm working on hybrid approaches mixing bare metal servers with EC2 to handle batch jobs and load spikes now)

[jbverschoor]

wake up

[brianwawok]

What if the license of the software you want to run is 100k per physical host? Then being able to run 2 or 4 instances on the same physical host makes the $2226 cost pretty insignificant.

[dsr_]

If you have software that costs that much, you will want to run it on hardware optimized for that software. (Does it want lots of GPU cores? I/O? Raw computrons? Does it prefer more cores or more GHz/core?) Unless Amazon happens to have exactly what you want available, you'll be better off putting it in a lab or datacenter.

[brianwawok]

Maybe, maybe not. Just because software cost a lot does not mean it is super high performance. Some is awful php strung together hacks, but if it does what a customer wants - it may be worth 100k to them.

[vosper]

Except, of course, that for anything important you'll want redundancy and failover in the face of hardware failure, so you'll need two of those $6.5k servers.

[idlewords]

The same (kind of specious) argument applies to the AWS case.

[vosper]

Maybe - I have a number of services that can tolerate a small amount of downtime if they fail, during which I would spin up a replacement AWS server. 99% of the time I'm only paying for the one machine that's running. These would all need dedicated hardware failovers if they weren't hosted in AWS (the same system does have hardware components, and they either have redundant failovers that are mostly idle, or for clusters we run at 66% capacity to allow for failure. Either way, it's often not true that one hardware instance can be substituted for one AWS instance, unless you don't care about long downtime when the hardware fails).