Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Microsoft's underwater data centre resurfaces after two years

bbc.co.uk

Post reply on HN
Print view View original

221–230 of 386 posts

Re: Microsoft's underwater data centre resurfaces after two years

#221

Post by StillBored »

In none of the articles do I see the power consumption of the pod..

But it looks packed with a lot of servers, and the surface area is quite minimal given there don't appear to be any cooling fins/etc.

So, that many servers are definitely many KW of power, and its all being conducted away via what appears to be a fairly minimal surface area. So the problem probably isn't the exterior so much as the interior which appears to mostly be a air->paint interface.

So, whats the cooling mechanism here, or are the servers that low power?

Re: Microsoft's underwater data centre resurfaces after two years

#222

Post by sandworm101 »

mips_avatar wrote: post #3

It seems an additional hurdle is anti-fouling. Those barnacles and algae act as an insulator, making the cold-water cooling advantage less and less of an advantage.

>> Those barnacles and algae act as an insulator

Maybe not. Barnacles probably conduct heat at a similar rate to water. And they create a rougher surface with greater contact area to the surrounding water. And some of them actively filter water, push it around. Perhaps having a layer of barnacles woudl increase cooling.

Re: Microsoft's underwater data centre resurfaces after two years

#223

Post by jandrese »

cmarschner wrote: post #212

I wonder how you would deal with theft and espionage for an underwater data center. The fact that no humans are around could be detrimental.

It's hard to imagine anybody getting in there while it's underwater without nation-state level resources. We're talking about a sub with a huge moon pool that you park on top of it, or a specialized cover that fits over the hatch or something. You also have to deal with the pure nitrogen atmosphere inside of the data center. All in all it seems a lot harder than bribing the guards at a regular data center to look the other way while you mess around with some servers.

Re: Microsoft's underwater data centre resurfaces after two years

#224

Post by reaperducer »

tbabb wrote: post #33
reaperducer wrote: post #22

Earlier quoted context omitted.

the impact was pretty minimal We used to say that about plastics in the ocean. And landfills. And light pollution. And noise pollution. And space junk. And on and on and on. Heck, not that many decades ago there were responsible people who thought that air pollution was no big deal because there's plenty of air, and it's just fine if California allows rich car collectors to keep buying leaded gasoline long after othe…

This reads like you have not done any calculation to determine whether the entire ocean can be heated by any plausible number of datacenters or not.

What does it matter if the entire ocean is heated? Power plants aren't allowed to dump unlimited quantities of hot water into the ocean. Why is it OK for a data center?

Re: Microsoft's underwater data centre resurfaces after two years

#225

Post by jandrese »

maxander wrote: post #190
24gttghh wrote: post #179

5 years planned with no maintenance (e.g. no storage disk failures to replace). I wonder how many spare drives were slapped in that tube to make that feasible?

I would bet they just used SSDs and made sure that the workload they were giving these servers wouldn’t tend to hit the rewrite limit over that time period. (Even then, I’d bet the expected writes-per-time was the source of the “five year” figure.)

Probably a decent number of warm spares in the mix as well.

Re: Microsoft's underwater data centre resurfaces after two years

#226

Post by 24gttghh »

jandrese wrote: post #225
maxander wrote: post #190

Earlier quoted context omitted.

I would bet they just used SSDs and made sure that the workload they were giving these servers wouldn’t tend to hit the rewrite limit over that time period. (Even then, I’d bet the expected writes-per-time was the source of the “five year” figure.)

Probably a decent number of warm spares in the mix as well.

Yeah. I can't see just using the MTBF for the drives and not having any spares. Shit happens.

Re: Microsoft's underwater data centre resurfaces after two years

#228

Post by aaron695 »

For anyone with a brain this is a dumb idea.

And of course we get an unquestioning BBC article.

If you dump it in landfill or a random corn field this still holds

"We think it has to do with this nitrogen atmosphere that reduces corrosion and is cool, and people not banging things around"

But it was underwater and that made it magical! Which I honestly think it did. It's still a garbage practical idea though.

Re: Microsoft's underwater data centre resurfaces after two years

#230

Post by quickthrowman »

StillBored wrote: post #221

In none of the articles do I see the power consumption of the pod.. But it looks packed with a lot of servers, and the surface area is quite minimal given there don't appear to be any cooling fins/etc. So, that many servers are definitely many KW of power, and its all being conducted away via what appears to be a fairly minimal surface area. So the problem probably isn't the exterior so much as the interior which app…

I was wondering the same thing, since it’s submerged I’m assuming they use seawater running through chillers to cool down the servers?
Post reply on HN