[hobs]

Imagining they completely solve the problem of sea water, leaks, etc, it still is amazing to think that you would want to do your server maint by pulling a data center out of the ocean on a boat and replacing hard drives and the like.

The only way this makes sense to me is if there is the ability to create something akin to the cargo container as a building block of a data center, where you can have arbitrary compute and storage plug into a greater complex.

[BinaryIdiot]

Sounds like that's exactly what they want to do: they would only pull them out of the water every 5 years to do computer replacements / maintenance. If some components fail then who cares. They wouldn't do a full rebuild for 20 years.

[winfred]

I worked in large data centers before and I just don't see how this can be done practically. Data centers require quite a bit of physical maintenance.

Every computer design has some element that will render a large part of the design inoperable in case of failure. Either it is a SAN head (even if you have two, the fail over can malfunction), or a switch setup.

Then there are things like failures of simultaneously purchased components (hard drives purchased at the same time, that are worked the same load will roughly fail at the time).

[andrewvc]

Cloud datacenters are not complex heterogeneous mixes of components. There's no SAN head. It's one thing multiplied + some networking gear. Even if a top of rack switch fails they're still not going to yank the box yet because the TCO will be lowered by too much maintenance at this scale. They wait for their maint interval and fix everything at once (or just upgrade the hardware).

[acveilleux]

Think of a farm of small data center pods with cloud apps. When failure in a pod exceed useful threshold, apps are migrated out to other pods and the pod is retrieved, serviced and returned to its place.

A custom made barge with dynamic positioning gear and a grabbing/coupling system to detach the pod from the subsea grid, lift it, and then re-attach it would make the servicing relatively efficient.

I could see the roundtrip time for a full hardware replacement of a pod being under an hour, conceivably under 10-15 minutes.

[kbenson]

> The only way this makes sense to me is if there is the ability to create something akin to the cargo container as a building block of a data center

Which is something Google already did[1].

1: https://en.wikipedia.org/wiki/Google_Modular_Data_Center

[cm2187]

And if it is just cooling, why aren't datacenters built on the coast pumping sea water for cooling?

[anonymfus]

High cost of the land on the coasts?

[cm2187]

And I guess you wouldn't even need to use sea water as a primary cooler, just as a secondary cooler. I.e. the primary cooler flows through your datacenter and the secondary cooler cools that primary cooler. So fewer pipes are exposed to sea salt.

[creshal]

So, same procedure as power plants.

[cm2187]

Yeah. Instead of trying to protect the environment from what's inside (radioactivity), you are trying to protect what's inside from the environment (sea salt)!