Slashdot Mirror
Intel Shows Data Centers Can Get By (Mostly) With Little AC
Ted Samson IW writes "InfoWorld reports on an experiment in air economization, aka 'free cooling,' conducted by Intel. For 10 months, the chipmaker had 500 production servers, working at 90 percent utilization, cooled almost exclusively by outside air at a facility in New Mexico. Only when the temperature exceeded 90 degrees Fahrenheit did they crank on some artificial air conditioning. Intel did very little to address air-born contaminants and dust, and nothing at all to deal with fluctuating humidity. The result: a slightly higher failure rate — around 0.6 percent more — among the air-cooled servers compared to those in the company's main datacenter — and a potential savings of $2.87 million per year in a 10MW datacenter using free cooling over traditional cooling."
How about reducing the need for AC POWER as well by cutting down on the number of AC TO DC PSU's.
When will the editors get "around around" to reading these submissions before approving them?
I do wonder how things could be improved with a decently sized stack... the higher an exit chimney, the more draw you'll get from the temperature differential. If your computer rooms are near the base of a decent sized office building, and you have a 20 story stack, I'd expect you could get away without any intake or exhaust fans.
Anyone here that can confirm or deny this?
Makes sense to me. The most efficent places to store data centers is in the northern US or Canada where you have sub-zero temperatures from November - March and ranging between 0-15 in April/May and Sept/Oct and the rest of the year 20-30+ (Celcius of course) With these lower temperatures they could run a data center entirely off outside air from September - May each year. Put a heppa filter in between to scrub out dirt and dust and vola, o'natural cooling solutions
I leave my systems on the deck.
... in Anchorage you have all the free cooling you want!
lets look at this from another perspective: Some datacenters allow for others to used slots inside their datacenters. would a small company running off a single server inside one of these datacenters be aright with the increased risk of possible damage to thier servers?
I asked the president of an engineering firm that I work for about this. He ships racks of boxes, each holding DSP boards on backplanes, each backplane has it's own PSU.
When I asked him why he doesn't just have one or two -big- power supplies in the unit, he said that he tried that, but the cost of the non-standard PSU was higher than all the ATX PSUs put together, and then some, and replacing the units when they eventually fail would be tricky, as opposed to just stocking more ATX PSUs.
I agree that it's a good idea, but until there's enough volume of large multi-output PSUs shipping, the cost of manufacture makes the product unworkable (unless you think big-picture and want to spend more up front for power savings over the whole unit's life).
Generally, the people who use the hardware aren't the ones building it, and buyers usually go for the lowest bid.
"Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
Isn't it always above 90 degrees there? (Except at night, of course.)
I thought the story was going to be about Alternating Current, but instead it was Air Conditioning.
Written by another AC
The savings should be more than enough to pay for replacement hardware, and even for upgrades. And stepping back and looking at the big picture tells me that there is at least one brilliant person at Intel--whoever though of doing this study is a genius!
--MarkusQ
The paradigm for data center cooling has been based so far on the mainframe model - great big equipment that needs meticulous care. But with the advent of commodity equipment, it's easier to just throw the damned thing away. Dust and humidity control are pretty trivial - 35% filters are fine, and as long as the interior is non-condensing, humidity can be whatever.
"As God is my witness, I thought turkeys could fly." A. Carlson
Using today's beefy servers, wouldn't the room be over 90 degrees all the time?
Well, it makes sense. Normal PCs run on essentially ambient air, and live for years even under heavy loads (games put a lot of load on systems) despite all the dust and cruft. Servers aren't that different in their hardware, so it makes sense they'd behave similarly. And there's a lot that can be done cheaply to reduce the problems that were seen. Dust, for instance. You can filter and scrub dust from the incoming air a lot cheaper than running a full-on AC system. In fact the DX system used on the one side of the test probably scrubbed the incoming air itself, which would explain the lower failure rate there. Reduce the dust, you reduce the build-up of the thermal-insulating layer on the equipment and keep cooling effectiveness from degrading. Humidity control can also be done cheaper than full-on AC, and wouldn't have to be complete. I don't think you'd need to hold humidity steady within tight parameters, just keep the maximum from going above say 50% and the minimum from going below 5%. Again I'll bet the DX system did just that automatically. I'd bet you could remove the sources of probably 80% of the extra failures on the free-cooling side while keeping 90% of the cost savings in the process.
The standard replacement cycle is about three years, so until they try that, this doesn't mean a lot. Also, what was the density of the data center? I still love the story of a datacenter with some DSLAMs that cooled left to right which were put next to each other in about 12 racks and the rightmost one caught fire once a week...
Also, I don't know the climate there, but in the regular climate here where it goes between -10 and +35 celsius (that's between 14 and 95 fahrenheit) and there's a good dose of humidity, the failure rate might be somewhat bigger...
...doesn't fluctuate that much, and is nearly always very low. I'd be very curious to see how a similar experiment goes in a place like Florida, that's at least as hot and much more humid.
There's no failure quite as dissatisfying as a complete and total solution to the wrong problem.
If they're paying ten cents a kilowatt-hour, that 10MW data center is paying about $9M/yr for power.
Cooling systems move about 15 times the power than what they draw. So the savings for a 10MW datacenter would be around $600K. Wonder how they came up with $2.9M ?
This is just speculation, but isn't much of new mexico rather arid? So this study is not actually useful for people who need to build data centers in more humid places then new mexico which I think includes most of the places there are actually people.
But if you are going to allow for an arbitrarily re-locatable data center, what does it matter that it can handle 90 degree whether when you can move it somewhere cold enough that you can have a humidity controlled room that gets passive cooling from the exterior.
I'd say that they will have to wait longer to get failures. Try to have a server running in that enviroment for 5 years and then we will see. I would not do it without having some good filters. But for a test it is a interesting experiment.
For datacenters in colder climates, you can already get cooling systems that cools the water using air only when the temperature is below a certain temperature(just forgot the number). When it gets above that level the water gets cooled like you normally do.
At work our old AC system was old and needed to be replaced and the new one does that. The outside temperature is so low that the water will be cooled with just air for half the year.
It was more expensive to install since it needed more and bigger cooling units(I belive they also talked about bigger slower fans that used less power) when just using air but it pays itself in a few years.
Another interesting experiment would be to use the heat again. I dont know if the water temperature is high enough so that you could use heat exchangers, perhaps as the first step on heating ingoing cold water.
from a few weeks ago?
http://slashdot.org/comments.pl?sid=947231&cid=24787415
The fluctuating humidity probably wouldn't be a problem in New Mexico either. The rest of us might have a problem.
that 'air conditioning' 'air cooling'.
Sure it's great to have the air cool and all... but I thought that dehumidification was important too?
Sometimes the best solution is to stop wasting time looking for an easy solution.
Can anyone think of a reason not to build these things underground?
The typical ambient temperature 6ft down is 60f or 16c. With proper ventilation (think solar-powered fans) and using the walls as heat-pipes, I'm sure you could keep the temperature down with little to no energy cost.
Add some of the Dyson vacuum inspired vortex thingy's to the intake to help filter out the dust and you wouldn't have to waste as much money on filters either.
Or what if you run the incoming air through a swamp cooler? wouldn't the running water cut down on the incoming dust significantly?
Life moves pretty fast; if you don't stop and look around once in a while, you could miss it. -FB
I work at the University of Montana and we talked a bit about direct venting our server rooms. Right now the big push is for ground water cooling. All new buildings on campus must use ground water cooling. Unfortunately, this is starting to hit the wall.
A fellow sysadmin across campus was having a new server room designed, the tons of cooling for his system just got down rated because the groundwater has been warming up with all the new ground source cooling wells.
"You never know when some crazed rodent with cold feet might be running loose in your pants."
-Calvin
The Russians can see your servers from their houses.
A company I used to work for (SeaChange International) would ship systems that, in some cases, were large enough to be considered their own datacenter. Some customers would order -48 volt DC power supplies. They'd do their own wiring at the site, having one big AC-DC converter to handle the entire system. They were certainly more expensive than the ATX supplies.
SIG: HUP
But I bet in parts of Canada you could do this with no added A/C.
In Soviet Russia, Data Center cool you.
Awesome new business idea for someone out there. Now you need to pay $30 before buying a used computer to see if it was in any "air economizers" before the jerks sold it. Nobody wants a computer that's been beat to crap for 3-5 years.
No comprende? Let me type that a little slower for you...
Exactly - the 65 degree server room is a waste of money. The only use for it is so the server guy can be comfortable while taking his nap.
Ah HA!
So that's the reason for all this "Global Warming". Intel was using the atmosphere as a heat sink. Should have known.
I mentioned tinker-toys once in a post - now I'm modded down for life.
To reduce AC needs, why not build the datacentre in say St John's NFLD. Never gets too hot there. Of course there is a tad more humidity.
Mark
------- Mark
Part of the problem is people are looking for very complicated solutions for very simple problems.
In retrofitting a standalone building, all you really need to do is reduce the amount of heat a building gains from the sun by improving it's R value and use sensible ducting to draw air through the building. I've seen some super energy efficient designs where each floor is vented, so that the building is itself a chimney, with cool air coming from vents from covered areas near the base, and enough size provided at the top to pull enough from the bottom, which is also easily aided by fans.
In building an entirely new datacenter, it would make sense to bury the server rooms, and cover the concrete structure with earth and solar panels. Combined with a flywheel load balancer, you could have an "off the grid" datacenter with the grid for backup. During the daylight hours, especially in the south, the panels can provide a good deal of the A/C and power necessary. At night the flywheel can continue powering the data center for a while, and turn fans without compressors to cool the equipment with night air.
This can all be done with existing technology. The trick is to convince people that green investment will lead to a return in the long run. I haven't personally looked at average rate increases in electricity, but the difference between efficient and additional construction expenses versus long term energy price fluctuations probably looks very good.
They're already real cool heads
and they're making real cool bread
I've often wondered about that myself. It seems absurd to have so many little AC to DC PSU's in a data center. Why not just have 1, directly integrated into a backup power supply? What is there in a datacenter that doesn't run on 12V/5V/3.3V DC? It would seem way more efficient, and less costly to me. Not only that, but those PSU's are producing heat too, which only exacerbates the cooling issue (fans for each PSU). Also, it would seem to me an evaporative cooling system instead of AC would be just as effective, especially somewhere like NM.
Prediction: The real iPhone killer is going to be sex robots from Japan. Think about it.
Um... you do realize that AC moves the heat (plus some) into the outside air, it doesn't destroy it, right?
Obviously, the solution is orbital data centers using microwave power links and laser data links. No doubt Google is working on this.
if the "air economizer" where just a tiny
bit more "strong", maybe bubbling the incoming air
in some water would clean it.
you know like blowing bubbles into a coke with a
straw?
Antarctica would be kind of a neat place for a data center. You have all of the cold air you need and there is enough wind for power. Just have to find a way to keep it stable amidst moving ice.
The article said they got up to 90% humidity at times. Remember, they didn't have any humidity controls at all, and it does rain in New Mexico resulting in short durations of high humidity.
I would say that fluctuations in humidity were tested quite well - long term effects of constant humidity, not so much.
The original article says humidity fluctuated between 4 and "more than 90%" over the course of the study. If you've never been to New Mexico you've missed out... they get some wicked thunderstorms.
Neil
Put the data center in Canada where we can use it to heat our igloos. Then when it goes down everyone can sing Blame Canada.
You are joking, right?
AC units aren't some kind of magic cold machines, they are heat pumps. The heat is going to get dumped outside in either case, it's just a question of whether you'll be dumping heat from the servers or heat from the servers + heat from the AC units.
All cooling systems ultimately rely on dumping heat outside(whether into air, water, or whatever), the trick is to spend as little energy on cooling as you can possibly get away with.
We have a monsoon season here, in mid summer. Gets pretty humid at times.
- None can love freedom heartily, but good men; the rest love not freedom, but license. -- John Milton
You insensitive clod!
MG
Isn't it more efficient to do the DC conversion as close to the last second as possible? Once the juice is DC it becomes much less efficient to move it around, no?
The heat's making its way to the atmosphere anyways... AC generates additional heat from the losses required to cool the air down. So direct air cooling actually is more environmentally friendly (from both a power consumption and heat dumping perspective) than using AC.
Does anyone else remember that study Google did on hard disk reliability a while ago that indicated no strong relation between temperature and failure rate? (I think there was also little relation between heavy use and failure - if it was going to fail in the test period, it was going to fail regardless of load.)
As for chips... keep them from burning. Keep fans from dying of heat (what?) and it should be ok...
Of course I'd much rather have a cool datacenter just to err on the safe side, but I can see the hardware withstanding it if things are out of dangerous ranges.
I've often wondered about that myself. It seems absurd to have so many little AC to DC PSU's in a data center. Why not just have 1, directly integrated into a backup power supply?
4 words "Single point of failure"
You're messin' with my Zen Thing, man.....
Heavy equipment uses something like that, (helps when wherever you are working it gets real dusty...) the intake air is spun-via a belt sometimes or just the force of the vacuum with a finned filter canister- and all the larger chunks in the air get flung to the outside away from the particulate filter itself. It works pretty good, when you open one up, the outside cannister, you can see all the dirt and stuff that the filter didn't even have to filter, you just dump them out once in awhile. Sort of hard to describe, you might be able to find a picture/schematic on the internets if you are really interested how it works. It is much better than the passive stuff they have on passenger cars.
Sun is also running a comparable experiment with Belgacom and allows you to log in to a live interface to view stats on in- and outlet temperatures and more at http://wikis.sun.com/display/freeaircooling/Free+Air+Cooling+Proof+of+Concept For more details and analysis see http://www.datacenterknowledge.com/archives/2008/09/18/intel-servers-do-fine-with-outside-air/ or http://securityandthe.net/2008/09/18/intel-sees-the-future-of-datacenters-and-it-does-not-include-airconditioning/
DC Knowledge also has a nice video of this experiment at http://www.datacenterknowledge.com/archives/2008/09/18/video-intels-air-side-economization-test/
Have more then one of them
Data Center Knowledge has a video in which the Intel engineers who conducted the study talk in detail about the setup and the results.
There is another really smart thing you can do too. When it is hot inside and not hot outside yu can open a window. That seems obvious but how many office building have openable windows? For some reason Architects like to cool office space with AC even if there is "free" cool air out doors.
This is even easier with computers. The servers would be happy to run at 95F and much of the time even in the American SW the outside air is cooler than 95F.
I've been saying this for many years. I think the reason for resistance is that no one gets a take home pay bonus based on how much power is saved.
Do you realise that AC requires electricity to make it work, and that
1. That electricity ends up as extra heat
2. The coal/gas/oil used to generate it releases CO2 into the atmosphere which causes global warming
I've noticed that often 'old-school' telco data centers often seem to be much more sparing with the AC running 70F-85F vs. the 'high-tech' data centers who tend to run 'freeze your ass off' data centers. Something has always told me they had something (whether it was just being cheap or not).
Also, google put out that report a few years ago (google: "Failure Trends in a Large Disk Drive Population") and it basically proved that too cold (59F-86F) actually causes more problems early in the drives lives than too hot. Optimum temperature is something around 86F-104F for both early and late in life.
Obviously ambient temperatures effect the drives core temps, but it shows that you can run them hotter than typical data center dogma would have you believe.
Its ironic that an industry that is so 'logical' in nature doesn't use science to determine the ideal temperature. "Cold" to humans doesn't necessarily mean anything to a computer. I wish we had more large studies for this sort of stuff, we could probably save a lot of energy.
Yes, I was joking, though I was hoping for a funny rather than a troll mod.
"Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
At first I thought, "Noooo, Edison's dirty tricks have won out again! Damn you for maligning Tesla with your dog electrocution." Air Conditioning. That's better.
That is done in many of the NEBS style colos, where -48VDC is always available in your rack, from a central supply. As mentioned earlier, most customers have AC gear, and don't think to order 48V PS for them.
Lots of interesting comments on this thread. The whole issue of heat and humidity levels in the data center was the subject of a heated debate last fall at Data Center World. Mark Monroe from Sun suggested raising the set point from 68 to 72 degrees and got all kinds of pushback from the audience.
A key concern about higher set points is that nudging the thermostat higher can save money, but may leave less time to recover from a cooling failure. That would certainly be relevant if you're using free cooling when it's 90 degrees outside.
RichM
Data Center Knowledge
Having very large PSUs is a pain in the ass. Failures tend to be catastrophic and dangerous. They're more expensive to build and maintain. (think basic economy of scale problems) They also may not be any more efficient than distributed conversion. You also tend to distribute much lower voltages with DC than you do with AC. (240vac vs 48vdc) This gives very high amperages which requires much thicker wiring. Copper is EXPENSIVE right now, this makes it a big factor in the cap-ex of building a new DC.
This is why a lot of work is going into improving the efficiency of commodity power supplies. Groups like 80plus.org are doing great things.
Also some other links:
http://www.treehugger.com/files/2007/07/secret_efficien.php
http://services.google.com/blog_resources/PSU_white_paper.pdf
4 words "But guard that basket!"
In 1979 at CMU, I did a homework project where I analyzed the cost savings of using outside air for cooling CMU's computing center. And no, I did not keep my paper for 29 years so don't ask me what the cost savings were. And if I remember correctly, I only got a B on the paper. I guess I was ahead of my time.
is a very interesting read
The 0.6 percentage point increase was relative to the average at other data centers. The air-conditioned reference trailer actually did better than their average. But comparing the failure rate in the air-conditioned trailer to the non-air-conditioned failure showed that the servers failed roughly twice as often in the hot trailer.
It's an interesting start and more work should be done. Even just raising the temperature 10 degrees in an existing facility should reduce AC power consumption tremendously. It would be interesting to see a life-cycle (typically 2-3 year) study in a more temperate climate.
~~~~~~~
"You are not remembered for doing what is expected of you." - Atul Chitnis
...data centers are designed by CRAC addicts =)
I didn't see the outside air temp during this test.Sure it ran for 10 months, but 10 months out of the year Arizona is a gorgeous hospitable place. It's the other two (July-August) that are inhospitable. When the air temp outdoors is 120 degrees how are you cooling it to sub 90s?
I'd like to see how long term humidity would work out for that type of tech. At my job we're seeing high failures from water based flux, our engineers loath the crap but we oursource board making and it's 'cheaper'. We can use no-clean for some of our stuff but we've also had problems with no-clean reacting to airborne gasses and chemicals. ASIG
Have you ever BEEN to Abq?
You have two actually.
That's why a lot of places use aluminium. And the practice isn't new. CP&L (now Progress Energy) wired the feed for a data center (150KW) with aluminium "wire" (if you wanna call something 1" in diameter a wire.) And that was 15+ years ago.
Well of course intel wants you to burn your machines up early. They get to sell you the replacement.
---- Booth was a patriot ----
4 words "Single point of failure"
You mean like the power circuit that you are already connected to? That single point of failure has long ago been handled. Where the costs can be justified, run more than one power circuit, backup generators and UPS, etc. That's no different.
I'm personally more interested in the wasteful DC to AC and back conversion when considering small scale solar. Why in the world is the default option to run a wasteful inverter just to plug an AC to DC converter in to that? Almost everything I looked at for portable solar to power a laptop or netbook worked like that. A lot of netbooks could be run on a 10W solar panel with battery backup, or more reliably of course with more solar capacity.
A company I used to work for (SeaChange International) would ship systems that, in some cases, were large enough to be considered their own datacenter. Some customers would order -48 volt DC power supplies. They'd do their own wiring at the site, having one big AC-DC converter to handle the entire system. They were certainly more expensive than the ATX supplies.
-48V DC is nothing special in many telco applications. Sun equipment (which has been historically popular with telcos (they have lots of NEBS-certified hardware)) has DC power supplies as a standard option on a good portion of their servers.
Of course many other manufacturers also offer DC P/S options (and NEBS).
http://www.epanorama.net/wwwboard/messages/1142.html
the voltage drop on such low voltage high amperage wires would mean that your hardware would receive voltages wildly out of spec.
Also the transients would be wicked.
And you'd better *really* not drop your screwdriver.
MP3 Search Engine
The lower the DC voltage, the higher the current and line loss. And running 3-4 different voltages throughout the place leads to confusion and much higher costs (4 voltages == 4x the wire.) -48VDC systems have been common for decades... in the telco world. They just haven't been common for computer datacenters.
If you have a rack of servers, then you obviously have a reason to have separate machines with separate parts. If you want to start integrating things, there's no reason not to go all the way and get a mainframe. I don't see how it would be advantageous to mix and match.
Employees in the data center had windows & they were allowed to open the windows.
Slashdot shows websites can get by with lots of ACs
I'm so excited I just made water in my pantaloons!
That'll cut down on the rectification stage of the power supply, however you still need to generate various supply voltages for the electronics. So you're stuck with the losses in DC-DC conversion.
Meanwhile, with DC you now have thicker metal (that means expensive) power distribution cables to handle the current and you've got DC losses through the conductor.
Or you could just use 240V AC and enjoy the savings.
If you want to go straight DC, you need to use the economies of scale, not replace AC power supplies with some alternate power scheme that still uses AC on the rack and DC into the server.
Instead, use large, very efficient AC-DC transformers and wire the rack DC.
If you convert AC to DC in bulk with more expensive but highly efficient equipment you will save significant money on the power conversion PLUS you can put that transformer outside in its own enclosure with a big metal heat exchanger for a case.
DC can be stepped down very easily and efficiently so various voltages are available from the transformer or from a seperate step-down box that doesnt create much heat because it is pretty efficient.
Now, you dont have to worry about the heat from the power supply and dont have to cool for it. You gain savings in efficiency and less AC use.
also, the transformer can very easily be cooled but an extremely simple ground loop and small pump can handle that for a few bucks per month.
I worked in a data center, it was 95degs inside because we couldn't generate enough heat to keep the roof top chilled water from freezing. So they turned off the chilled water. It was 8 degs outside on a Colorado winter day. We asked facilities if we could break out a window to keep our servers from cooking, but they wouldn't. almost a 90degs delta. the only thing keeping us from the outside was a pane of glass. Rocket Scientists they were not...
Can we dispense with these comments that question a new technology if the implementation doesn't take into account common sense?
I wouldn't build a below ground data center in New Orleans or a solar power plant in Seattle or a hydroelectric dam in the Sahara. If you're within a flood plain, who builds underground, besides every single skyscraper in NYC?
So, it could be done - if your engineering takes into account common sense, that is.
EVERYTHING _M_U_S_T_ be air-conditioned at all times. From what we heard from France during their last heat wave a few years ago, air-conditioning isn't universal in the First World. Therefore, it must sound strange that air-conditioning is a inviolate moral imperative in all offices in the US. My wife has a sweater with her at work at all times even if it is July or August. Same for me. 100% wool. When it is 95 outside and 68 inside, I want nothing more than to hibernate -- like seriously drift off to sleep. I've worn gloves with the fingers cut out in July at my keyboard. I've sneaked in an incandescent lamp to warm my hands (please, sir, just a lump of coal?). I've gotten on my chair and stuffed paper towels in air ducts.
If management can't see that they are air-conditioning some of their people into productivity loss, not to mention pain, how much more likely are they to reduce air-conditioning on their precious equipment? No, doesn't matter whether one experiment shows it would save big money. The person who suggests reducing air-conditioning in the U.S. will be about as popular at his business as if he had suggested commissioning a portrait of Karl Marx on the lunch room wall. This just isn't a technical issue.
No. The reason AC was more convenient to move around is the ability to step it up and down with transformers. But in fact line losses are higher for a given voltage with AC than DC, for various reasons (e.g. peak voltage is higher, some of the power radiates). Nowadays, converting DC to DC is about as easy (it goes through a high frequency AC step on the way, however). A switching power supply actually converts AC (60Hz) to DC to AC (tens of kilohertz) to DC.
100% humidity is rain. I would expect almost everywhere to see 100% humidity at times. Where I live it rarely goes below 50% humidity. We need more of an average to make any sense of it rather than the extremes.
How about reducing the need for AC POWER as well by cutting down on the number of AC TO DC PSU's.
Intel are backing that idea
http://www.theinquirer.net/en/inquirer/news/2006/09/26/intels-rattner-hails-you-tube-as-the-future
Can you do more? Sure, but you need to look at the whole power cycle, from the mains in to the building to the use in the individual computers. About 1/3 of the power that comes in the door ends up doing work, you have many AC -> AC, AC -> DC and DC -> AC transitions, each losing a bit here and there. Those bits end up byting you in the nibble, puns intended.
Intel then brought up one of the older single rail 90% efficient PSU and pointed it out that it was obsolete. Instead of all the transitions, you go to a direct high voltage DC power system. The savings went from 3800 or so watts to power a rack to about 3300W, or about a 15% power savings with that one change. I think someone took a trip to Rackable and noticed what they were doing.
They demo'd a high voltage DC server rack at Comdex.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
I'm sure everybody read the story in USA Today how Canadian provinces, which unlike US states, have some say over immigration. As a result, Alberta has been headhunting skilled foreign workers whose permanent status in the US has been taking too long. I'd find a link to the article, but I'm too tired right now. Well anyway, given the cold climate there and the potentially huge influx of skilled foreign workers, this could be the perfect storm that would allow places like Alberta that already have what I imagine to be copious bandwidth, to become a new data center capital. Add in efficient outside cooling as mentioned earlier and companies would flock there. And think.. slightly less restrictive laws to deal with since they wouldn't be in the US.
Could this be a new trend???
In Arizona, you don't cool computer, computer cools YOU!
http://blog.ltc.arizona.edu/ltcannouncements/archives/2008/07/green_ice_disco.html
Central chilled water runs through the supercomputer and cools the room too.
100% relative humidity is when the dewpoint is reached and water condenses out of the air (aka fog). The popular idea that 100% rel humidity = rain is not accurate.
Or they could just setup a tarp with netting to keep rain and other forms of live out, excluding humans of course.
Oh yeah, one more thing. Host it in Antarctica. All datacenters should be moved to Antarctica. We don't use it for anything other than scientific research anyways. Damn global warming, we should capitalize on the cold parts of this planet.
Aluminum wiring is a FIRE hazard and was BANNED in all new
houses in the US due to it.
You might be able to get away with it outdoors, but it is
most likely a bad idea based on the indoor results.
http://www.physicsforums.com/showpost.php?s=7d306106c574b8acd101e052ab90be42&p=615606&postcount=6
http://books.google.com/books?id=2edigWaeGPUC&pg=PA175&lpg=PA175&dq=aluminum+wiring+ban&source=web&ots=l0eE26iMkt&sig=rVIgBVl0gXGlJicEHA_qW8s4zY0&hl=en&sa=X&oi=book_result&resnum=4&ct=result
Alot of areas you cannot even get insurance for the building
with aluminum wiring in it.
http://en.wikipedia.org/wiki/Aluminum_wiring#Hazard_insurance
google "32 trillion offshore needs IRS attention"
It would seem way more efficient, and less costly to me.
Priced out copper lately? Those 4/0 AWG wires you'll need to pull to handle a few googleracks aren't that cheap, and think of how many you have to pull...
Think of that long dc cable as a big-ass resistor. Apply I=P/E and P=I^2*R to see that your cables start losing a lot of power themselves the lower the voltage goes. Add inductance, the complexities of trying to regulate the voltage at 1000 different points,... you just really don't wanna go there.
Keep your regulator close to your equipment. It'll appreciate you.
/. -- the Free Republic of technology.
For a list of interesting places to locate a data center, see data centers in strange places/
Statesman
That's because aluminum significantly contracts and expands with temperature changes. When it does so in a residential setting, it will cause shorts and sparks and such in outlets and switches. The 1" wire (probably more like a crossbar) was probably specifically designed for electrical use, and had appropriate connectors and so on so that it was NOT a danger (as noted in the physicsforums post you linked to. Given the price of copper any more, the special work needed for aluminum is possibly worth it.
My blog. Good stuff (when I remember to update it). Read it.
You're only half right. If you actually read any of the articles you linked to you'd know that.
Aluminum wire by itself is no hazard at all. It just doesn't do well when you connect it copper or other galvanically dissimilar materials that can cause corrosion. And there are some issues with dissimilar thermal expansion rates, but that's largely dependent on the terminal size and type.
You're right that the standard 14-10 AWG wiring used in homes is typically not aluminum, and that the wiring of that size that was aluminum and installed in the the 60s and 70s needs to be treated specially.
But aluminum was and still is commonly used in large-gauge wiring, starting around 8 AWG -- the ~2 AWG feed for many homes *is* aluminum. And it's entirely possible to safely wiring aluminum, even of smaller gauges, even of older alloy types, so long as you understand the limitations and use CO/ALR-rated devices.
Relative humidity can go above 100% as well in certain situations it is called Supersaturation.
An Education is the Font of All Liberty
That, and they become a single point of failure.
Having seen a few commodity power supplies fail in the most spectacular manner possible makes me shudder to think that companies are willingly switching to massive power supplies just to save a few bucks.
Stating on Slashdot that I like cheese since 1997.
And where, exactly, were we discussing wiring for a house? For a datacenter, NOT a house, at -48VDC, the hazards are low. A cold welded copper or aluminium lug avoids the problem of bi-metal corrosion. And if you've ever seen the wiring in a telco datacenter, you'd know it's jacketed with a fire resistant material and rated for 2x the current it's intended (read: fused) to carry. (and it's never hidden inside walls where you cannot see building problems.)
Btw, I've seen the power distribution systems in *brand new* building using aluminium bus bars. Yes, being a poorer conductor, they are a fair bit larger than their copper cousins, but it's still a lot cheaper.
I use a datacenter to protect my servers from dust and powerloss, not from heat
'Chimneys' above the rack or over the hot aisle are ok to allow somewhere for the hot air to go naturally.
Dig the foundation down 15 feet so hardware is officially below the surface.
You mean like the transmission lines into the facility are a single point of failure? Just make it highly modular and keep a spare.
Yeah, I like to see how it works here in SE Louisiana where we have extreme humidity, basically a swamp.
Won't Bow.....Don't Know How
I work for a company that puts computers in the most hostile enviroment in the world: Bars.. we install boxes running the Audio and video software for all types of bars.. Now.. if we are lucky, they get a designated location in an audio rack somewhere along side the amps of the dj which get air cooled. Most of the time however, the get dumped somewhere under the counter, together with the rest of stuff a bar owns.. standing there, humming, sucking in the hot air the cooling of the tap, amplifiers or other electronics throw out, next to an over for heating a pizza etc.. They got all sorts of substances leaking in (water, beer, coke, orange juice and the occasional tomato sauce..). we even have the occasional real bug: fried cockraoch.. But still.. when looking at the figures ( using only a class hardware.. white boxes have a higer failure rate), they actually do well... most boxes have 2 failures every 4 years.. 90% of the time, this is because of heating issues or too much beer (for the computer OR the bartender)... I've known multiple occassions where computers kept running even though you could not touch them barehanded anymore due to heat... In the end.. spending millions of dollars on cooling something that CAN handle higer temps and might cause slighty more failure, means the millions you save should easily pay some extra stuff for failover to cath those, slighty higher, failures...
Yeah, I like to see how it works here in SE Louisiana where we have extreme humidity, basically a swamp.
Probably like everything else. Extremely slow and lazy. ( I couldn't help myself )
You'll have that sometimes...
Computers run hot enough to get rid of moisture and one assumes that these data centers run around the clock.
But dust can be lethal to computers and in particular to power supplies and CPU fans. I clean my PCs guts at least twice a year and what comes out is amazing. Fans are great at collecting dust and they don't pump much air when coated with dust either.
Running a data center in a low humidity location for 10 months doesn't reflect real-world data center life, making this study basically worthless. Heat reduces the life of electronics. Run the experiment in somewhere of ~average~ humidity, for the typical lifespan of a data center and then compare the results. We keep our servers between five and ten years depending on the application. The cost savings will be dramatically impacted if we have to buy new servers twice as often. If people are to adopt this, they need to know how well it will work well in varying conditions. FWIW, I used to work for a major chipset company. We'd test all our hardware from 0C to 60C ambient temperature. Too cold can cause problems just as too hot can. Humidity can also contribute to corrosion, regardless of condensation, which also causes problems. What hardware is used also makes a difference - PSU's and drives often have a harder time taking the higher temps. Also, inconsistent temperatures (warmer in the day, cooler at night) can contribute to broken contacts due to the tiny amounts of expansion/contraction that would occur every day.
It is good to see that the machines will function properly at the 90 degree range, though living in the Mid-Atlantic, humidity is an issue. We have experienced heat alarms in our labs due to failed AC units, however, the air in the labs wasn't moving. Perhaps some system of venting and intake would help reduce the ambient temperature. Another possibility would be to add green roofs to free standing data centers. Instead of big cubes with flat roofs sucking up the sun's rays, a green roof would cut that heat absorption by about 20% and reducing the surrounding temperature. There was a great article titled "Data Centers Need Green Roofs" at http://cleanerairforcities.blogspot.com/2008/07/data-centers-need-green-roofs.html gives some great examples.
Little air conditioning? Alternating current? Anonymous Coward? How about being a bit more specific?
What's that, you say? RTFS? You must be new here...
That aside, saying the relative humidity peaked at 90 isn't saying much. The west coast is going to see a *hell* of a lot more humidity than New Mexico will. Giving us the peak value is useless when your point is that the humidity didn't bother the system.
Comment removed based on user account deletion
If you actually read any of the articles you linked to you'd know that.
Wow, that is some real tongue in butt cheek there buddy.
By the way any dissimilar metal with a difference in potential
does what ?
That's right Homer Simpson, it corrodes.
I think if you thought about all the receptacles and the fact
that apprentice electricians do most of the residential wiring
in the US and not fully licensed journeymen, then you'd realize
the potential for slop is overwhelming.
If you take it a step further and realize that alot is
being done by illegals who are supervised by an apprentice,
who then gets final inspection from a Journeymen who runs
through the house and talks to the 1 apprentice and then
he is off to the races to the next Mc Mansion speed wire job.
Why do you think they won't insure the houses ?
Why do you think they banned it in most states ?
Some tinfoil hat conspiracy against Aluminum ?
Cause the insurance companies own copper mines ?
You are an idiot.
google "32 trillion offshore needs IRS attention"
That, and they become a single point of failure.
You should design your system with dual power supplies anyway, unless you're doing some kind of clustering.
Finally! A year of moderation! Ready for 2019?
Cheap does not always equal good.
google "32 trillion offshore needs IRS attention"