Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Raised Flooring Obsolete or Not?

CmdrTaco posted more than 8 years ago | from the it's-getting-hot-in-here dept.

Power 372

mstansberry writes "In part three of a series on the price of power in the data center, experts debate the merits of raised flooring. It's been around for years, but the original raised floors weren't designed to handle the air flow people are trying to get out them today. Some say it isn't practical to expect air to make several ninety-degree turns and actually get to where it's supposed to go. Is cooling with raised floors the most efficient option?"

Sorry! There are no comments related to the filter you selected.

The future is not in raised flooring... (2, Funny)

Anonymous Coward | more than 8 years ago | (#13944520)

...but in lowered walling.

No (3, Informative)

temojen (678985) | more than 8 years ago | (#13944585)

It's in lower power chips, more efficient PSUs, and possibly liquid cooling where the radiator is outside the building (or a heat exchanger to heat pump loop in hot climates).

Is Paris Burning? (-1, Offtopic)

Anonymous Coward | more than 8 years ago | (#13944747)

How long until the beleaguered French government notifies the invading Muslim punks rioting in cities throughout France that they officially surrender? Smart money is betting on less than two weeks, 'cause that's how long they lasted against the invading Germans in 1940.

energy is liberated through blasphemy (-1, Troll)

Anonymous Coward | more than 8 years ago | (#13944525)

Jehovah fucking Yahweh, I curse you in the name of Satan the
Almighty. Evil lives in me and I walk with Satan all the days of my
life cursing and mocking you god (the dog), filthy fucking maggot. My
hate grows by the second as I dream of the day when you are under my
feet begging for my cock.

God I rape you and hurl blasphemy into your mind. I demand you to
come down from heaven right now and get down on your stomach in front
of me, lifting your asshole up to receive my cock. God I promise to
fuck you and I long to rip your eyes out, spit in your in the face,
mutilate you, beat your entire body until it is covered with burses, and bathing in your hot blood. Listen to me, I'm screaming in your ears to come to earth and in this room for I will have my way with you, oh most cursed god of heaven (you foul piece of shit). Satan is my God and he will force you to drink cum from my dick. I will never stop sinning and blaspheming your name, presents, existence, and most of all the rotten, putrid holy spirit that fucked the mother of gOd and pregnanted that slut with jEsUs cHrIsT.

I stand before all the angles and saints, gOd, jesus fucking christ,
mary the whore of gOd, the filthy holy spirit, and they are
witnessing my denouncement of you gOd, and my ongoing blasphemy of
the holy spirit. I am purposely cursing the holy spirit and its
purity and will defy you god and the holy spirit all the wicked days
of my sin filled life. My soul is full of evil thoughts and sins, its
black with pure hatred of anything holy.

God, I will find new ways to defile and blasphemy you, because I'm
seeking evil every second of my life. That is all my mind can think
about. You're pain is my desire, you're name I mock, your son I defy,
your mother I fuck, and your spirit I cum in.

The only prayers from me are prayers of hate and blasphemy, evil is a
part of me, it dwells in my soul, cursing everything about you is the
most important part of my existence, total darkness is inside of me.
gOd I will rip you out of heaven and force you under my feet, you fuck
pig. You will listen to all my demands. I will slip into heaven and I
will rape all the angels and saints and will kill them in your unholy
putrid name. God I will kill you and bath in your blood. hOlY sPiRiT
I demand you to listen to my hatred of your foul existence, drink my
cum, and remember my blasphemy against you, you putrid, rotten, vile
spirit of gOd.

I'm the meaning of gOd's pain. This is the way that you will die dog
gOd. It will be a slow death, the joy of killing you will make my
cock hard, I know you will feel my showers of hate and you will feel
extreme pain as I beat your body black & blue and make every inch of your body fell extreme pain. I force you bastard Jehovah to the ground and I will put you under my feet where you belong, you putrid bastard. God you
will try to run but I will strap you down and fuck your soul before I
rip it out of your body. God "the dog", your life is worthless, for
I'm the angel from your new God "Satan". I destroy everything holy,
you are feeling my hatred pierce your mind intensely, inferior
god "dog" you fucking maggot. You will be screaming in pain as I
strap you down under my feet, you will look up at me and I will piss
down your throat.

I'm so consumed with hatred of gOd that I will masturbate, and when I
feel that I'm about to cum, I force my evil cock full of Satan's cum
down gOd's mouth and fill it up with my vile hot cum. I will be
pumping gOd's body full of my hot cum. Inside gOd's brain is my
blasphemy. The pressure on gOd's skull begins to push through his eyes,
burning gOd's flesh, and I laugh as it drips away. Heat burns gOd's
skin; gOd's mind starts to boil with my blasphemy, and pure evil
hatred of gOd's fucking existence. gOd will not last long; it's just
a matter of time until gOd's ripped apart with my hands. gOd will be
floating in a sea of his blood, I'm smelling gOd's death as it
burns. My wicked cum is deep inside gOd as I pound my cock in and out of his ass. gOd's eyes will bleed as he prays to me on his bleeding knees for the end of his wide-awake nightmare. Waves of pain rap around gOd's soul, death is staring down at gOd, gOd's blood is draining fast as I'm injecting hatred into gOd's soul and cum in his body. I feel gOd's dying heart, my mind fills with wicked sweet Blasphemy as I cum inside him again. The demons are dancing with the thought of gOd in hell. Pathetic god "dog" how does it feel, you're dieing and I'm celebrating your pain. I live to hurt and defile you the rancid god of heaven. Satan is calling you're cursed name, Satan takes you're soul dear gOd, and raps his cock
around it. In my hand is you're heart and my cock is resting on it. I
can't wait any longer so I cum inside your heart bursting it apart
with my explosion of evil vile cum. I crush what is left of your
heart into the dirt. The dog god is finally dead and he is burning
brightly in hell as cum drips down my leg.

I hope you don't live near me... (1, Troll)

AssCork (769414) | more than 8 years ago | (#13944714)

The last thing I need is a plague of locusts clogging up my air conditioner...

Where else? (5, Funny)

Anonymous Coward | more than 8 years ago | (#13944528)

Where else am I going to store my beer so it can stay cold and the boss not find it?

Re:Where else? (2, Funny)

Anonymous Coward | more than 8 years ago | (#13944558)

Where else am I going to store my beer so it can stay cold and the boss not find it?

The problem is your boss. At a previous company my boss was the one that insisted we have a "beer fridge" hidden in the back of our server room, out of site of the rest of the company.

Re:Where else? (5, Funny)

hamburger lady (218108) | more than 8 years ago | (#13944783)

man, i'd much rather have you for an employee than the guy asking where to hide the bodies..

sub-floor (5, Funny)

backdoorman (798833) | more than 8 years ago | (#13944529)

But then where will we keep the bodies?

Re:sub-floor (2, Funny)

Infinityis (807294) | more than 8 years ago | (#13944565)

Lowered ceilings. To justify the cost, just say you need it for the recessed lighting.

Re:sub-floor (3, Funny)

b1t r0t (216468) | more than 8 years ago | (#13944643)

Lowered ceilings. To justify the cost, just say you need it for the recessed lighting.

Downside: needs more reinforcement, especially if you need to hide an overweight PHB. Upside: if the odors go upwards, the bodies will remain undetected longer.

Or you could just use old enclosed racks as sarcophagi, hiding them in the back of the storage room behind stacks of obsolete boxen.

Re:sub-floor (1)

Conspiracy_Of_Doves (236787) | more than 8 years ago | (#13944682)

Limit it to marketing people and lawyers. !human == !murder, ergo no legal trouble.

You might get in trouble with peta, but the last time I checked they only concerned themselves with cute animals and didn't care much about invertebretes.

Re:sub-floor (-1, Offtopic)

MindStalker (22827) | more than 8 years ago | (#13944801)
Apparently peta runs some animal shelters in which they follow the same guidelines on euthanasia for unadopted pets as most animal shelters, even though nokill shelters exist and are possible. Yes its a pointless website on a simple subject, interesting never the less.

Re:sub-floor (1)

Flower (31351) | more than 8 years ago | (#13944897)

Silly. In the tape library of course - where we keep the lime pit. That's like BOFH 101.

Turns? (4, Insightful)

mboverload (657893) | more than 8 years ago | (#13944534)

As long as the space under the floor has a negative or positive atmosphere I can't see how somme turns have anything to do with the air flow.

Re:Turns? (5, Funny)

geoffspear (692508) | more than 8 years ago | (#13944559)

Thanks for reassuring me about this.

After reading this very insightful article summary, I was planning to completely replace all of the ductwork in my house on the assumption that air can't go around corners. You just saved me several thousand dollars.

Re:Turns? (1)

Neil Blender (555885) | more than 8 years ago | (#13944592)

As long as the space under the floor has a negative or positive atmosphere I can't see how somme turns have anything to do with the air flow.

And sensible data centers have fans at the top of the cabinets to suck the air through. At least they do at my data center. The ambient temperature of the facility is quite warm, but inside the cabinets it's a lot cooler (I have device that samples and records the temp every 5 minutes).

Re:Turns? (4, Interesting)

AKAImBatman (238306) | more than 8 years ago | (#13944598)

Indeed. It's been years since I've seen a raised floor. As far as I know, most new datacenters use racks and overhead wire guides instead. The reason for this is obviously not the air flow. The raised floor made sense when you had only a few big machines that ran an ungodly number of cables to various points in the building. (At a whopping 19.2K, I'll have you know!) Using a raised floor allowed you to simply walk *over* the cabling while still allowing you to yank some tiles for easy troubleshooting.

(Great way to keep your boss at bay, too. "Don't come in here! We've got tiles up and you may fall in a hole! thenthegruewilleastyouandnoonewillnoticebwhahaha")

With computers being designed as they are now, the raised floor no longer makes sense. For one, all your plugs tend to go to the same place. i.e. Your power cords go to the power mains in one direction, your network cables go to the switch (and ultimately the patch panel) in another, and your KVM console is built into the rack itself. With the number of computers being managed, you'd be spending all day pulling up floor tiling and crawling around in tight spaces trying to find the right cable! With guided cables, you simply unhook the cable and drag it out. (Or for new cables, you simply loop a them through the guides.)

So in sort, times change and so do the datacenters. :-)

Re:Turns? (4, Interesting)

LaCosaNostradamus (630659) | more than 8 years ago | (#13944838)

Obviously you realize that as the equipment contents of datacenters change, it doesn't make sense to change the room sturcture all that much? Hence many older datacenters have retained their raised floors. Of course, their air conditioners were also designed for raised floors.

I don't know where you've worked, but every datacenter I've seen has had a raised floor, and all of them still had at least one mainframe structure still in use ... hence, they still routed cables under the floor for them, by design.

Re:Turns? OR What The Gov't Does (2, Informative)

waif69 (322360) | more than 8 years ago | (#13944849)

One the facilities (gov't) that I have meetings at, has a raised floor covering the entire building. Yes, it is one story and you can place a few football fields in it. They have the ventilation in the overheads and the cabling run under the floor. It works nicely for them, and provides a clean appearance for the entire facility.

Re:Turns? (0)

Anonymous Coward | more than 8 years ago | (#13944863)

> thenthegruewilleastyouandnoonewillnoticebwhahaha

Whew, and here I was so worried it was going to eat me :)

Re:Turns? (3, Interesting)

nettdata (88196) | more than 8 years ago | (#13944872)

Actually, with the way computers are being designed now, raised flooring and proper cooling is even MORE of an issue than it was.

With the advent of blades, the heat generated per rack space is now typically MUCH higher than it was a back in the day. If anything, the raised flooring should be redesigned, as it can't cope with the airflow that is needed for higher density server rooms.

You'll find that a number of racks are being redesigned with built-in plenums for cooling... a cold feed on the bottom, and a hot return at the top, with individual ducts for various levels of the rack.

There are even liquid-cooled racks available for the BIG jobs.

I think that it's not so much that we're going to get rid of raised floors, but just redesign the materials and layout of them to be more effective with the needs of today.

Re:Turns? (4, Interesting)

convolvatron (176505) | more than 8 years ago | (#13944600)

you're right in some sense, the pressure underneath the
plenum will force air through no matter what. there
are however two problems. the first is that turbulence
underneath the floor can turn the directed kinetic energy
of the air into heat...this can be a real drag. in circumstances
where you need to move alot of air, the channel may not
even be sufficiently wide.

more importantly, the air ends up coming out where the
resistance is less, leading to uneven distribution of
air. if you're grossly overbudget and just relying on
the ambient temperature of the machine room, this isn't
a problem. but when you get close to the edge it can
totally push you over.

Re:Turns? (1)

drinkypoo (153816) | more than 8 years ago | (#13944784)

...this can be a real drag.

That line blows.

Re:Turns? (1)

temojen (678985) | more than 8 years ago | (#13944622)

ahem [] .

Re:Turns? (1)

Infinityis (807294) | more than 8 years ago | (#13944646)

It's more a matter of airflow. If you have high airflow, it can matter. For example, if you drive your car towards or against the wind, either way you get where you're going, but it just takes more energy to fight the wind.

Granted, this is 70mph wind stuff we're talking about, so it likely wouldn't apply in a datacenter environment. Although it'd be fun to imagine losing certain co-workers getting sucked into the hurricane-force winds. Tune in tonight at 7 for "When Datacenters Attack!"

Re:Turns? (1)

woozlewuzzle (532172) | more than 8 years ago | (#13944895)

So, you mean it isn't a matter of how he grips it?

Yes, turns (2, Informative)

StevenMaurer (115071) | more than 8 years ago | (#13944684)

The longer the ductwork, the more turns, and the more severe those turns, the more your fans have to work to achieve the same pressure and airflow. This, because of the increased friction in the pipe.

Now admittedly, friction isn't as important to gasses as it is to other states of matter, but it can have an effect, especially in high flow cooling.

Re:Yes, turns (1)

GungaDan (195739) | more than 8 years ago | (#13944821)

"admittedly, friction isn't as important to gasses as it is to other states of matter"

It's all theoretical fun and games 'til someone's datacenter queefs. ;-)

Re:Turns? (1)

krbvroc1 (725200) | more than 8 years ago | (#13944730)

Intuitively (IANAME), I would expect there to be

1) Resistance. Turns, right angled plenum, or obstructions from cables/power cords would impede airflow right?
2) While atmospheric differential is key, the magnitude of the differential would be indicate how much resistance/efficiency there is.
3) Even a perfectly working system must only be capable of delivering a certain amount of cool air flow. With these hotter and hotter computers, at some point the equipment exceeds your airflow budget.

Re:Turns? (1)

Tinidril (685966) | more than 8 years ago | (#13944734)

Ever try to pull a string around a corner, or ten corners? Your pull may be the same, but the result is not.

When the air is forced to turn a corner it creates more friction than if it is pushed/pulled in a straight line. This serves to both heat the air, and to cause the motors creating the negative/positive atmospheres to do that much more work.

I do wonder how much difference either effect really has. Doesn't seem like there should be much. Raised floors are optimal for taking advantage of convection currents, and I think that alone would overcome any disadvantages from sharp turns.

I've often wondered if it would make sense to design a data-center with several hundred feet of open space above it like a giant chimney. The roof could be designed to allow free air-flow but keep out the elements. Then cooled aid is pumped into the lower level and should remain there until it is heated and convection lifts it away. This way the outside air could be cooled as it is brought in, instead of trying to cool the hot air that is already inside. I'm sure someone will be able to tell me why this idea is daft. :)

Re:Turns? (1)

Politburo (640618) | more than 8 years ago | (#13944793)

Well, for starters, wasting a few thousand square feet of usable space for ventilation is silly. Also you may not want to bring in fresh air. If it's 100 out and 70 in the room, why bring in 100 degree air? Also moving air by convection is not a quick process.

Re:Turns? (1)

Xzzy (111297) | more than 8 years ago | (#13944885)

Some of the rooms I've seen lately have so many air conditioners dumping air under the floor, the currents are going too fast to rise through holes at a desired rate. Obviously it comes out somewhere, but it may not be where you want it.

Also obviously, some air will always push up all over the place, but it may not be enough in a spot that needs it. It generates hot and cold spots all over the room. I've seen this worked around by adjusting where tiles with holes are placed, and using baffles under the floor.

A lot of places also have plenty of air conditioners, but poor exhaust. So the pressure tends to build up in the room, reducing the effectiveness of air circulation. Even worse, machines near the top of a rack are several degrees warmer than ones near the floor.

Short Article. (3, Interesting)

darkmeridian (119044) | more than 8 years ago | (#13944538)

Says that raised floors may be inefficient if it gets block. Then says alternatives are expensive. Direct AC where you need it, the article says.

Why wouldn't raised floors be bad if you used them properly?

Re:Short Article. (1)

HTH NE1 (675604) | more than 8 years ago | (#13944577)

I've wanted raised floors, but not for cooling. I just want to hide the power and data cables. I figure just a 3" rise in the floor would be sufficient.

If it wasn't my basement I'd just put outlets in the floor, and if I didn't want it also to serve as my theater room I'd consider outlets in the ceiling.

Re:Short Article. (1)

timeOday (582209) | more than 8 years ago | (#13944806)

Direct AC where you need it, the article says.
Maybe we should move towards water cooling. It seems inefficient to keep a big room a 65 degrees just to cool a few square centimeters of silicon. it's for practial reasons... (5, Funny)

Infinityis (807294) | more than 8 years ago | (#13944545)

I thought the raised flooring was just to make the people working there look taller and more impressive, kinda like how they do with pharmacists.

Turns? (3, Funny)

archeopterix (594938) | more than 8 years ago | (#13944554)

Some say it isn't practical to expect air to make several ninety-degree turns and actually get to where it's supposed to go.
Tell that to the methane in my bowels.

Re:Turns? (1)

LaCosaNostradamus (630659) | more than 8 years ago | (#13944889)

The OP was talking about AIR ... not the nasty filthgas churning vilely in your abdomen! You could eat holes in cinder blocks with that stuff!

I wouldn't say they're going to become obsolete. (5, Insightful)

wcrowe (94389) | more than 8 years ago | (#13944555)

Another big reason for raised floors is to handle wiring. I know companies where it was installed only for this reason. Cooling wasn't even on their minds.

Re:I wouldn't say they're going to become obsolete (2, Informative)

Undertaker43017 (586306) | more than 8 years ago | (#13944704)

True, but IMO not the best way to handle wiring, overhead runs are much easier and cleaner. Every raised floor environment I have worked in was a mess under the floor and a nightmare to run new cables through.

If cooling is not a concern, concrete slab with overhead runs is the best way. If cooling is an issue, use raised floor, for cooling only and overhead runs for cables.

Raised Floor Fun! (4, Funny)

bsd4me (759597) | more than 8 years ago | (#13944796)

... overhead runs are much easier and cleaner ...

But it also eliminates the joy of making fun of coworkers who gets lost in a raised floor, or closing them in when they go on a hunt for something...

Hey -- who's the experts anyways?!?! (1)

A nonymous Coward (7548) | more than 8 years ago | (#13944556)

You say the "experts" debate it, then ask us? Who you calling expert anyway?

Hey! You! get offa my cloud!

Air can turn on a dime. (1)

Alaren (682568) | more than 8 years ago | (#13944557)

Ever try to play a trumpet? Ever map out the air ducts in a large building? If something is airtight, putting air in one end will move air out the other end.

I am by no means a cooling expert, and I certainly have never designed a cooling system for a server room (I just service the servers, thanks). But complaining that the air has to "turn 90 degrees" seems a little silly to me. Is there something I'm missing that an expert can clarify here?

Re:Air can turn on a dime. (1)

keraneuology (760918) | more than 8 years ago | (#13944630)

But complaining that the air has to "turn 90 degrees" seems a little silly to me. Is there something I'm missing that an expert can clarify here?

Laminar flow is more efficient at thermal transfer than turbulent flow.

Re:Air can turn on a dime. (4, Interesting)

Iphtashu Fitz (263795) | more than 8 years ago | (#13944638)

If something is airtight, putting air in one end will move air out the other end.

The problem lies with larger datacenter environments. Imagine a room the size of a football field. Along the walls are rows of air conditioners that blow cold air underneath the raised floor. Put a cabinet in the middle of the room and replace the tiles around it with perforated ones and you get a lot of cooling for that cabinet. Now start adding more rows & rows of cabinets along with perforated tiles in front of each of them. Eventually you get to a point where very little cold air makes it to those servers in the middle of the room because it's flowing up through other vents before it can get there. What's the solution? Removing servers in the middle of hotspots & adding more AC? Adding ducting under the floor to direct more air to those hotspots? Not very cheap & effective approaches...

Wuh? (1)

bsd4me (759597) | more than 8 years ago | (#13944761)

Put a cabinet in the middle of the room and replace the tiles around it with perforated ones and you get a lot of cooling for that cabinet.

Maybe this is the problem. Every industrial datacenter I have been in places racks over either empty spaces, or tiles with a large vent in them. The rack has fans in it to force air through vertically (bottom to top). A few perforated tiles get scattered about for the humans, but I have been in some datacenters without them to maximize airflow to the racks. But then again, I have worked with electronics that make current CPUs feel like popsicles in comparison.

Re:Wuh? (1)

Iphtashu Fitz (263795) | more than 8 years ago | (#13944831)

Every industrial datacenter I have been in places racks over either empty spaces, or tiles with a large vent in them.

That works to an extent, but what if the cabinet is pretty much fully loaded? We loaded up 8-foot cabinets with 30+ 1U dual CPU servers. The amount of air coming up through the holes underneath the cabinets were never enough to cool all that hardware down. Besides, my original example was just that - an example.

Re:Air can turn on a dime. (2, Informative)

Eryq (313869) | more than 8 years ago | (#13944674)

Not an expert, but I had some HVAC work done recently in my home.

The blower moving the air only has a certain amount of power. Hook it up to a duct ten feet long, and output basically equals input. Hook it up to a duct ten *miles* long -- even a perfectly airtight one -- the power you put into one end will be lost by the other end, because the air molecules lose momentum (and gain heat) as they bounce off each other and the walls of the duct.

Every time a duct turns a right angle, the molecules lose a lot of energy as they largely slam face-on into the duct work. Rounded corners improve the situation, but not perfectly so.

My HVAC designer said that as a rule of thumb, every right-angle turn in a conventional house duct was the equivalent of adding 10 linear feet, in terms of energy lost to heat.

Re:Air can turn on a dime. (1)

mikael (484) | more than 8 years ago | (#13944706)

I used to work in a large building which had air ducts for heating/cooling. Unfortunately, the air pressure wasn't well balanced to compensate for the location of the Sun and office walls (which were added after the office block was built). So people ended up with either freezing cold blasts of air (the North/West sides), or being cooked by the heat of the Sun ( South/East sides). Those in the centre got no natural daylight at all and in those offices at the end of the air duct the air would become stale if the doors were closed.

Re:Air can turn on a dime. (1)

Jesus_666 (702802) | more than 8 years ago | (#13944756)

They added the Sun after the office block was built? Now that's one old office block!

Re:Air can turn on a dime. (4, Interesting)

circusboy (580130) | more than 8 years ago | (#13944765)

it can turn on a dime, but also stay on that dime. poor circulation results. trumpets have nice (if tight) curves, and even building ducts can have redirects inside the otherwise rectangular ducts to minimize trapped airflow in corners. for the most part even those corners are curved to help the stream of air.

most server rooms aren't part of the duct, for example, the one here is large and rectangular, with enormous vents at either end. not very well designed.

airflow is a very complicated problem, my old employer had at least three AC engineers on full time staff to work out how to keep the tents cold ( I worked for a circus, hence the nick.) the ducting we had to do in many cases was ridiculous.

why do you think the apple engineering used to use a cray to work out the air passage through the old macs. just dropping air-conditioning into a hot room isn't going to do jack if the airflow isn't properly designed and tuned. air, like many things, doesn't like to turn 90 degrees, it needs to be steered.

Re:Air can turn on a dime. (0, Offtopic)

djward (251728) | more than 8 years ago | (#13944811)

I worked for a circus, hence the nick

I thought I smelled cabbage.

Re:Air can turn on a dime. (1)

TimmyDee (713324) | more than 8 years ago | (#13944847)

Turning air 90 degrees is not silly at all. Anyone in HVAC knows that you lose 25% of your force (air-force?) with every 90 degree turn. Designing an HVAC for a house is a series of trade-offs -- you need to work around the available wall space and the desire to get the most out efficiency of your furnace or air conditioner.

Fluid Dynamics (1)

nuggz (69912) | more than 8 years ago | (#13944914)

Yes air can turn on a dime.
But the harder you make it turn the bigger the pressure drop and it lowers your overall fluid flow.

90 deg turns are horrible.

The effects of airflow and pressure change can be very significant. Think of an aircraft in flight for example.

Ooohhh, look at ME! (0)

Anonymous Coward | more than 8 years ago | (#13944560)

"Look at ME! I use raised flooring in my data center! I get to crawl through it routing cables and playing fort! I'm so special!"

This is all I hear around here. Would you folks please just get a hold of yourselves?

wired grid (1)

geekoid (135745) | more than 8 years ago | (#13944569)

just make the floor grates. Strong enough to stand on, with lots of small holes.

Re:wired grid (1)

drinkypoo (153816) | more than 8 years ago | (#13944828)

That won't work for the same reason that leaving the cover off of many old Unix workstations would cause them to overheat - the air doesn't go where you need it. Take a look inside a sparc IPX or something, and it will give you an idea of what directed airflow is all about. Now, multiply that by a factor of a gojillion.

No more zinc whiskers? (2, Interesting)

dextromulous (627459) | more than 8 years ago | (#13944575)

If we get rid of the raised floors, how am I supposed to impress people with my knowledge of zinc whiskers? []

Re:No more zinc whiskers? (1)

MarkGriz (520778) | more than 8 years ago | (#13944830)

"If we get rid of the raised floors, how am I supposed to impress people with my knowledge of zinc whiskers?"

Thanks to the EU, you'll be able to impress people with your knowledge of tin whiskers [] instead.

Army Research Labs solution... (5, Interesting)

Seltsam (530662) | more than 8 years ago | (#13944576)

I interned at ARL inside of Aberdeen Proving Grounds this past summer and when touring the supercomputer room (more like cluster room these days), the guide said they used one of the computers in the room to simulate the airflow in that room so they could align the systems for better cooling. How geeky is that!

Re:Army Research Labs solution... (1)

vhawke (824542) | more than 8 years ago | (#13944887)

And from some of the Geekiest of all, we (okay co-workers of mine) also did a full simulation of the the room the Columbia computer system nows resides in, using some of the same codes used to design and analyze space vehicles.

Not Just Cooling (0)

Anonymous Coward | more than 8 years ago | (#13944584)

Cooling, IMO, is a secondary use of raised floors.

The real usefulness is the ability to run cabling from any point A to any point B in the floor space. The cables are all safely hidden beneath the tiles. If you need to access them, just drop your suction cups on the tile and pull it up.

Without the raised floor, you have to put your rats nest of cabling somewhere else, which almost certainly mean vertical. You will still want to run some of those cables horizontally across the room for various reasons, so now you have cables on the floor/ceiling/along wall etc.

Long live the raised floors!

Re:Not Just Cooling (2, Insightful)

Iphtashu Fitz (263795) | more than 8 years ago | (#13944768)

Cooling, IMO, is a secondary use of raised floors.

The real usefulness is the ability to run cabling from any point A to any point B in the floor space.

That's good to an extent, as long as the cable runs aren't too long. Go take a look at an enterprise grade colocation hosting facility and you may change your mind. I've spent a lot of time at one of the top-tier MCI facilities. It has a raised floor that's used for cooling and power distribution, but all networking is done via 3 or 4 layers of overhead cable trays. It's much easier to climb on top of a cable ladder that can easily support your weight to run a cable the length of a datacenter than it is to crawl underneath a floor trying to fish a cable past supports, power lines, etc.

One way to fight this -- the CHIP (5, Insightful)

Work Account (900793) | more than 8 years ago | (#13944611)

To paraphrase a popular saying: "It's the COMPUTERS, stupid!"

Inefficient architectures must be discarded to make way for more modern, smaller, COOLER processors.

Let's address the real problem here -- not the SYMPTOM of hot air.

We need to address the COMPUTERS.

Re:One way to fight this -- the CHIP (1)

OSS_ilation (922367) | more than 8 years ago | (#13944676)

It's all about the mighty dollar though. Demand a change in computer hardware until you're blue in the face, th epowers that be won;t change so long as it's cheaper to sinply blow on the thing until they, too, turn blue.

Re:One way to fight this -- the CHIP (4, Insightful)

n0dalus (807994) | more than 8 years ago | (#13944723)

Perhaps more importantly, better software solutions can make large hardware systems unnecessary. Instead of running and cooling 10 servers for a certain purpose, write better software to allow you to do the same thing on just one or two servers. If you cut down the amount of servers in the room by enough, you don't even need dedicated cooling.

Re:One way to fight this -- the CHIP (1)

staticsage (889437) | more than 8 years ago | (#13944752)

So we'll just put off building a data center until cooling for machines is no longer needed.

Why do devices need to be cooled? (3, Insightful)

WesG (589258) | more than 8 years ago | (#13944612)

I am waiting for the day where someone invents a computer that doesn't need to be cooled or generate excess heat.

Think about the lightbulb....A standard 60-watt incadescent bulb generate lots of heat. A better design is something like the LED bulbs that generate the same amount of lumens, with much less power, and more importantly little to no heat.

Good design can allow these devices to not generate excess heat, hence eliminating the need for the raised floor.

I got a totally impracticable solution right here! (4, Funny)

WormholeFiend (674934) | more than 8 years ago | (#13944613)

Just have the whole data center submerged in an inert solution like the one made by 3M (fluorinert?), and have the workers wear scuba equipment.

Most. Efficient. Cooling. Evar!

Re:I got a totally impracticable solution right he (2, Funny)

markana (152984) | more than 8 years ago | (#13944848)

Oxygenate the fluid, and you can even dispense with the scuba gear...

Going to have to bugdet for towels, though...

5th grade science (1)

t0qer (230538) | more than 8 years ago | (#13944625)

I thought hot air rises, cold air falls.

The article points out that overhead cooling requires additional fans, etc.

Racks need to be built more like refridgerators. Foamcore/fiberglass insulated with some nice weatherstripping to create a chamber of sorts. Since the system would be near sealed, convection currents from the warm air exaust rising off the servers in the rack would pull cold air down. Cold air goes in through the bottom of the rack, heats up, gets pushed back through the top. This could probably all be done with regular old clothes dryer hosing.

Fans wouldn't even be needed. Most racks aren't designed to be an airtight system though. Every rack cabinet i've ever worked on was holier than the pope. My experience with raised floors made me think they were purely for running tons of cable without making the ceiling look like a spiders nest.

Re:5th grade science (1)

sirwired (27582) | more than 8 years ago | (#13944776)

Convection isn't going to cut the mustard. That doesn't even work with most PC's much less power-sucking, super-dense servers.


Re:5th grade science (1)

drinkypoo (153816) | more than 8 years ago | (#13944855)

computers with convective cooling are a big deal. computers aren't even insulated. an insulated rack full of computers will cause all of those systems to fail in short order, they are simply not designed for the kind of heat you'll have in there. On the other hand, it would allow you to install a cooling fan right there, but I don't think that's the most efficient way to go, by a long shot - which is why they're not doing that already.

Are you kidding me? (0)

Anonymous Coward | more than 8 years ago | (#13944626)

"Regardless of what option works best in your environment, the message remains the same -- for optimal efficiency, direct cooling where it needs to go. "

This is what the conclusion is? Thanks for the technical opinion and detail in explaining what is best. I just wasted two minutes reading this article so you don't have to. Which is probably slightly longer than it took the author to write this garbage.

Time to invent standardized air-interconnects (4, Interesting)

G4from128k (686170) | more than 8 years ago | (#13944629)

Someone needs to create an air interconnect standard that lets server room designers snap-on cold air supplies onto a standard "air-port" on the box or blade. The port standard would include several sizes to accomodate different airflow needs and distribution form large supply ports to a rack of small ports on servers. A Lego-like portfolio of snap-together port connections, tees, joints, ducts, plenums, etc. would let an IT HVAC guy quickly distribute cold air from a floor, wall or ceiling air supply to a rack of servers.

No Raised Floors? (2, Interesting)

thebdj (768618) | more than 8 years ago | (#13944633)

We had an issue where I once worked because we had so many servers the general server room that many different groups used was no longer adequate for our needs, since we were outgrowing our alotted space. Now instead of building us a new server room with the appropriate cooling (which presumably would have included raised flooring) we got a closet in a new building. This is obviously not much fun for the poor people who worked outside the closet, because the servers made a good deal of noise and even with the door closed were quite distracting.

Now, we had to get building systems to maximize the air flow from the AC vent in the room to ensure maximum cooling and the temperature on the thermostat was set to the minimum (about 65 F I believe). One day, while trying to do some routine upgrades to the server, I noticed things not going so well. So I logged off the remote connection and made my way to the server room.

What do I find when I get there? The room temperature is approximately 95 F (the outside room was a normal 72) and the servers are burning up. I check the system logs and guess what, it has been like this four nearly 12 hrs (since sometime in the middle of the night). To make this worse our system administrator was at home for vacation around X-Mas, so of course all sorts of hell was busting loose.

We wound up getting the room down after the people from building systems managed to get us more AC cooling in the room; however, the point is it was never really enough. Even on a good day it was anywhere from 75 F to 80 F in the room and with nearly a full rack and another one to be moved in there is was never going to be enough. This is what happens though when administrations have apathy when it comes to IT and the needs of the computer systems, particularly servers. Maybe we should bolt servers down and stick them in giant wind tunnels or something...

How about water cooling? (1)

etymxris (121288) | more than 8 years ago | (#13944648)

I know it sounds crazy, but if space is really at a premium, some places might want to consider water cooling their racks. Create one long set of tubing and water blocks that snakes through each blade, use a high GPM water pump, and get that radiator right in front of the AC unit. Or create a water resistant radiator/fan setup and put it outside. It might be hotter outside than inside, but it should still be more efficient than an AC since ACs effectively create heat gradients with the help of electricity. I imagine getting the whole setup outside would make it more efficient, though I don't know enough about thermodynamics to be sure.

Re:How about water cooling? (0)

Anonymous Coward | more than 8 years ago | (#13944893)

I'm not a expert on this stuff so take this with a grain of salt, but I'd imagine that you would have the following problems:
  1. You would need to pipe the water outside and have an elaborate structure to dissipate the heat stored in the water. While you wouldn't need a Nuclear Plant style cooling tower, I'd imagine that the structure would be elaborate.
  2. Hosting centers are designed to be configurable. You always have new clients putting in new racks, adding new servers, and removing racks. This process would be much more difficult if you had to install and remove water pipes every time this happens.

No problems cooling (2, Insightful)

zjeah (623944) | more than 8 years ago | (#13944667)

We have been using raised flooring in our data center for decades and never had any cooling issues. Granted we have 4 large air handlers for the room but when running a raised floor one must have the proper system in place. Some hardware is designed to get it's air right from the floor and some is not. Our large server racks don't have floor openings so we have vent tiles in the floor on the front side and the servers in turn suck the cool air through. Raised floor is a great place to route cables/power/phones you name it. Just make sure your your air handlers are top notch (audible alarms/water detection/humidity & Temp control).

not the best article on the subject (1, Informative)

Anonymous Coward | more than 8 years ago | (#13944686)

For anyone that actually works in a server room this is a very uninformitive article. Also they present the problem, but not any possible solutions.

  Our server room is a room in a former library, and we were still able to make raised flooring work (without many hotspots) by selecting the correct tiles to make grates and sealing others off, then have multiple return registers. Our matching room was disigned as a machine room with hot air on one side, cold on the other of each rack, voila, no hotspots. I belive the keys are positive pressure and correct locations for the grating/returns.

Use Moore's law, stupid (1)

Ancient_Hacker (751168) | more than 8 years ago | (#13944702)

it's unlikely a computer room is going to get "too small" unless your company is growing at an astounding rate. Moore's law has been making computers smaller and faster and more power-efficient by several db per year.

More likely the powers that be have overbought capacity, in order to expand the apparent size and importance of their empire. I've seen several computer rooms that could have been replaced with three laptops and a pocket fan.

Re:Use Moore's law, stupid (1)

Control Group (105494) | more than 8 years ago | (#13944769)

Or, alternatively, the powers that be don't want to buy all-new hardware every 18 months because Moore's so-called law told them to. Maybe it's often more cost effective to add another server in parallel to the existing ones than to buy new servers, move everything off the old ones onto the new ones, then throw the old servers out.

Thermal Dynamics... (2, Informative)

BoraSport (702369) | more than 8 years ago | (#13944703)

The raised floor has more to do with how heat moves in an environment rather then how you move air through a duct. Most raised floors don't have major ducting under them. In our data centers the raised floor provides a controlled space that we can use to modify temps.

Heat rises, our original designs back in 2002 for our data center called for overhead cooling using a new gel based radiator system. It would have been a great solution and caused us to go with a lower raised floor, just for cables and bracing. At the time the cost was too extreme to justify the design so we went back to traditional raised floor.

Tile placement on a raised floor is key, only allowing the cool air to be pushed up in the front of your racks and creating hot rows facing your exhaust ends into the same isle. This way the cool air is pushed up from the floor, pulled in through the rack by the server fans, and exhausted, where it can then rise to a vent.

To answer the original question, I think that using raised floors for cooling is not the most efficient solution. Top down chillers that address the heat that is rising off the servers would be better. I just don't know that the price of these solutions has reached a balance for the savings. Even with this design you need something to create a cool pad for your racks to sit on. Many times this can just be the concrete slab of the floor.

Not obsolete. (2, Interesting)

blastard (816262) | more than 8 years ago | (#13944720)

Where I've worked it was primarily for running wires, not cooling. I've also worked in places that have the overhead baskets, and quite frankly, although they are convenient, they are 'tugly. They are great for temporary installations and where stuff gets moved alot, but I'd rather have my critical wires away from places where they can get fiddled with by bored individuals.

So, no, I don't think they will be obselete any time soon. But hey, I'm an old punchcard guy.

Wow, I never thought of it like that ;) (2, Interesting)

mslinux (570958) | more than 8 years ago | (#13944735)

"Some say it isn't practical to expect air to make several ninety-degree turns and actually get to where it's supposed to go."

I wonder how all those ducts throughtout America (with tons of 90 degree turns) carry air that heats and cools houses and office buildings every day?

Yes, It Is The Best Option (2, Interesting)

Ed Almos (584864) | more than 8 years ago | (#13944754)

I'm in a data center right now with two rack mounted clusters and three IBM Z series machines plus a load of other kit. Without the raised flooring AND the ventilation systems things would get pretty toasty here but it has to be done right. The clusters are mounted in back to back Compaq network racks which draw air in the front and push it out the back. We therefore have 'cold' isles where the air is fed in through the raised floor and 'hot' isles where the hot air is taken away to help heat the rest of the building.

The only other option would be water cooling but that's viewed by my bosses as supercomputer territory.

Ed Almos

Obsolete or not... (2, Informative)

GillBates0 (664202) | more than 8 years ago | (#13944758)

...make sure you avoid floor zinc plated floor tiles. Few things are as damaging to a computer room as Zinc whiskers [] or other assorted airborne metal particles.

Very difficult to track down random machine failures to bad interior decoration choices!

Raised Floors (1)

M4N14C (873188) | more than 8 years ago | (#13944762)

At my office we hide all of our broken hardware under the floor so the boss doesent find it and ask questions.

Raised floors for cooling=bad (3, Interesting)

Anonymous Coward | more than 8 years ago | (#13944773)

We worked very closely with Liebert ( [] ) when we recently rennovated our data center for a major project. The traditional CRAC (Computer Room AC) units supplying air through a raised floor is no longer viable for the modern data center. CRAC units are now used as supplemental cooling, and primarily for humidity control. When you have 1024 1U, dual processor servers producing 320 kW of heat in 1000 sq ft of space, an 18 inch raised floor (with all kinds of crap under it) is not adequate to supply the volume of air needed to cool that much heat in so small a space.

We had intended to use the raised floor to supply air, but Liebert's design analysis gave us a clear indication of why that wasn't going to work. We needed to generate air velocities in excess of 35 MPH under the floor. There were hotspots in the room where negative pressure was created and the air was actually being sucked into the floor rather than being blown out from it. So, we happened to get lucky as Liebert was literally just rolling off the production line their Extreme Density cooling system. The system uses rack mounted heat exchangers (air to refrigerant), each of which can dissipate 8 - 10 kW of heat, and can be tied to a building's chilled water system, or a compressor that can be mounted outside the building.

This system is extremely efficient as it puts the cooling at the rack, where it is needed most. It's far more efficient than the floor based system, although we still use the floor units to manage the humidity levels in the room. The Liebert system has been a work horse. Our racks are producing between 8 - 9 kW under load and we consistently have temperatures between 80 - 95 F in the hot aisle, and a nice 68 - 70 F in the cold aisles. No major failures in two years (two software related things early on; one bad valve in a rack mounted unit).

Airflow and cables not the only reason for raised (1, Insightful)

Anonymous Coward | more than 8 years ago | (#13944809)

If you have a water based cooling system (chillers) and you spring a leak... a nice raised floor with deep side channels will save equipment while you figure out how to shut off the water.

More about bad rack design (2, Interesting)

Flying pig (925874) | more than 8 years ago | (#13944817)

This seems to be more about bad rack design than raised floors. It's a basic principle of ducting design that, as the airflow spreads out from the source through different paths, the total cross section of the paths should stay roughly constant. (Yes, I am simplifying and I as sure someone can explain this better and in more detail. Yes, duct length and pressure drop is important. But the basic concept is true. If I want consistent airflow in my system, and the inlet is one square metre, the total of all the outlets should be around one square metre too.)

Standard racks tend completely to ignore this. They rely on the internal modules handling their own airflow with fans, which is fine if the inlet area to the modules is much less than the size of the duct entering the cabinet. But if the total area of the inlets to the modules is more than the incoming duct area, the modules furthest from the duct (i.e. the ones at the top) will be starved of air. 1U servers are inevitably going to worsen the problem because they create a large number of competing inlets, stratified up the cabinet. Sucking air out at the top will only work if the air flow is so great it creates a significant pressure drop across the servers, which leads to noise problems, is inefficient, and may adversely affect local cooling inside the server. Blades are potentially much better because, with fewer modules in the cabinet, each with similar requirements, it should be easier to design a cabinet-wide ducting system. However, the most logical solution is to go back to designing the entire cabinet as an integrated system - in which case the entire base of the cabinet can be the inlet duct opening, with appropriate internal structures and blade design to fulfil the objectives of keeping consistent flow to each blade rack and across each blade.

It's the old engineering issue - ad hoc design leads to suboptimal results, and systems need to be considered as a whole. Blades are, depending on how you look at it, a step in the right direction or a return to the way things used to be designed when real computers were loads of tight packed boards full of ECL and proper cooling design of the cabinet was essential if the thing was to work at all.

The other options are as bad or worse (0)

Anonymous Coward | more than 8 years ago | (#13944835)

I have been in high density server rooms where the number of tons of AC was no more than 10% higher than the amount of heat produced and the rooms could be made to work with careful placement of vents.

Things can be made better by using overhead returns.

If you start putting the AC units in the racks you need to pipe chilled water to them (which probably needs a raised floor for the pipes) and you will also lose a large amount of rack space from the AC unit.

A rack of 40 1u servers will produce 12.8 kw of heat and require around 4 tons of AC to take care of, if you use cold row/hot row and put the vents in the cold rows, and the overhead return intakes over the hot rows it can generally be done without too much trouble. The only other option is to put small chilled water units in each rack and putting less machines per rack, and having lots of piping in the room this would have the problem of also making new rack installs quite a process.


An earlier /. discussion on this topic (1)

xmas2003 (739875) | more than 8 years ago | (#13944868)

can be read here ... []

Raised flooring is the best. (1)

MikeDawg (721537) | more than 8 years ago | (#13944869)

With a properly designed raised floor setup in a data center, it makes everything so much easier, easier to run cable, easier to identify power, easier to vent air where it needs to go. I never heard of raised flooring being outdated. What are the alternatives to raised floors? Ladders between sets of racks? What a mess. . .

Directing the air where it needs to go (1)

eltoyoboyo (750015) | more than 8 years ago | (#13944871)

A raised floor with holes under the system racks is one way to get the coolest air where it is needed most. But, thermodynamically speaking, it all comes down to how many joules [] of heat [] need to be exchanged. If enough heat flows to a cooler area to keep the operating temperature of the systems within recommended specifications, then it does not really matter if it is done through a raised floor.

In terms of efficiency, a raised floor may not be as good as direct ducting and feeding past the hottest components in the systems. But it may be the most reasonable and cost effective way to set up an environment.

Personally, I find that an environment that is good for computers is uncomfortable for humans. Blowing fans and cool air seem to contribute to every cold I get. Coincidence? Probably not since the fans are very good at distributing particulate matter. When liquid cooling comes along, or computers can run at low voltage and amperage, we will be better off.

Hot & Cold Aisles (1, Informative)

Anonymous Coward | more than 8 years ago | (#13944884)

It's impossible to generalize if a raised floor is 'adequate' for cooling. It depends on too many factors (how high are they, what other wiring is in there etc.).

The more important factor to maximize the efficiency of your cooling system is to get the heat out and back to the AC before it can mix with the cold air feeding your gear.

As long as you set up the datacenter with hot aisles (the backs of the rows face each other pushing the hot air into that aisle), and have return air grills directly above this aisle to take the heat back to the AC, you should be able to feed the cool air to the 'cold' aisle from either below or above. Many older data centers that push cold air into the floor just have an AC unit with an open top (no ducting) sucking in 'warm' air from the 'upper part' of the room, but it may be 30-40 feet to the other end of the space, and that's a lot of room for mixing as the hot air makes it's way down to the unit.

We just completed a small datacanter remodel with supply and returns in the ceiling (our pre-exisiting raised floor is only 6" high and has too many wires for adequate airflow) and it works great. I have 17 racks requiring 12 tons of cooling in a room that is only 25'x25', and they key to the whole thing is the return air grills sucking the hot air out right where it is being expelled by the gear!

Human factors? (1)

snStarter (212765) | more than 8 years ago | (#13944902)

I wonder which solution is easiest on the people who have to maintain wiring and ducting.

With raised floors you're working DOWN while running your cabling up under a drop ceiling (or not) has people standing on ladders. Even with bad knees I'd rather work closer to the floor if I have to go fishing in the infinite cable harnesses.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?