Hot Aisle Or Cold Aisle For Containment?

1sockchuck writes "Separating the hot and cold air in a data center is one of the keys to improving energy efficiency. But containment systems don't have to be fancy or expensive, as Google showed in a presentation Thursday, which discussed the use of clear vinyl curtains in isolating hot and cold aisles. Containment systems have been in use at least since 2004, but there's an ongoing debate about whether it is best to contain the hot aisle or cold aisle. Leading vendors are split as well, as APC advances hot aisle containment while Emerson/Liebert champions a cold aisle approach. What say Slashdot readers? Do you use containment in your data center? If so, do you contain the hot aisle or cold aisle?"

Comments

Can you try both methods?

[e9th]

Depending on how your facility is ducted, it might not cost much to try both options and measure the results. Even if you have to spend a few thousand doing so, the long term savings from choosing the best method for your site would probably be well worth the cost of testing.

Re:Can you try both methods?

[twisteddk]

Well, as most companies that have to build a new datacenter will tell you. It's cheaper to generate heat than cold. So I'd go for cold containment. Generally speaking most companies do AIM to put their new datacenters as close to the north pole as possible simply because it's cheaper to use outside air that's natually cold. That puts countries like Canada, Greenland, Denmark, Norway, Sweden and Finland in high demand for datacenters (end technicians to staff them). If the US didn't have rediculous data laws, Alska might also be ideal.

In our new datacenter we're even using the excess heating from the servers to heat the offices ontop of the giant basements below. This sort of setup is ideal for outside temperatures that generally range below the normal cooling needs of a server (or several). But in any event there's still a huge bill to pay for moving the air back and forth, so containment is definately still an issue, as is the size of the pipes when you have say... 10MW of electricity going into your servers and quite a lot of that energy coming back out as heat ;)

Re:Can you try both methods?

[starfishsystems]

You can build a switched network to connect the remote data center to the point of presence where you want it to join the backbone.

Though this does nothing to mitigate time-of-flight latency, it nicely eliminates the latency and jitter issues due to routing. It's what we did at Westgrid to connect our computing clusters to storage facilities many hundreds of kilometers away.

I suggest hot aisle containment

[mysidia]

Contain and exhaust your heated air, vent it up outside

That way it doesn't mix with the cold air much.

If you just contain your cold air, then you have a situation where the hot air is staying in the room, and that heat will be absorbed over a larger surface area, by all the things in your server room (including the Air handling units).

Re:I suggest hot aisle containment

[nacturation]

You can still vent the hot air elsewhere, but the problem with hot air only containment is that then the entire room is effectively one large cold aisle, contained within the walls and the limiting factor is how well insulated the walls are. If that logic holds, it's better to limit the size of the cold aisle as you can add a lot more really good insulation where appropriate to limit unwanted heat absorption.

Re:I suggest hot aisle containment

[Bigjeff5]

I suggest containing the cold air.

If you contain the hot air you must cool a much larger area, which is very inefficient and makes anybody who must work in the server room less comfortable when compared to allowing waste heat to warm the main areas. More comfortable, less energy wasted cooling the cold aisle, and less energy wasted venting the hot aisle.

A vinyl partition is plenty of separation, and if you want to upgrade, use two vinyl partitions separated by an air gap. That's the same basic setup that the ski resort in Dubai uses, except they use two roofs instead of two vinyl partitions, of course. Air is a fantastic insulator when it is not allowed to mix.

Temperature lost through seepage from solid objects is going to be minimal, at best, unless they are made of large sections of aluminum or copper. Frankly, I've never seen a server room with large panels of aluminum or copper, so I don't see that being an issue.

See why there is a debate?

contain the heat

[Tumbleweed]

When you contain the heat, you then have the ability to move it around and use it for cogeneration, thus vastly increasing your overall efficiency.

Both

[funkboy]

The answer will be specific to each implementation.

But in general, it should be pretty obvious to anyone that understands basic thermodynamics: get the "cold" into the servers without mixing it with the ambient or letting it touch any hot metal, and get the heat out of the servers without mixing it with the ambient or letting it heat up any other metal.

It should be pretty obvious that air is not really the best way to do this; air goes all over the place, and is not a very good thermal conductor (relatively speaking).

There are entire 10k+ machine datacenters in France that use only liquid cooling circuits, right up to the servers. Energy costs for running the external condensers are a small fraction of what it would cost to do the same thing with air. Of course, it helps if you only have your own machines in such an environment, but if APC, Emerson, etc were serious about efficient cooling then they'd partner with HP, Dell, etc. to make standardized systems that would allow this...

Both might actually be best

[Roger W Moore]

It's cheaper to generate heat than cold. So I'd go for cold containment.

Actually containing both might be best since then you will have a "room temp" air gap between the two and air is a fantastic insulator. IF you do not contain the hot then the heat will diffuse and the air on the other side of the vinyl curtain will be warmer than room temp. This will warm your incoming cool air. The effect may not be particularly noticeable but it would be an interesting test to see if there is a noticeable improvement to doing both.