Microsoft, Google Battle Over Energy Efficiency
1sockchuck writes "Microsoft and Google have opened a new front in their battle for global domination: data center energy efficiency. Just weeks after Google published data on the extreme efficiency of its previously secret data centers, Microsoft says it has achieved similar results with shipping containers (despite Google's patent) packed with up to 2,500 servers. The geeky benchmark for the battle is Power Usage Effectiveness (PUE), a green data-center metric advanced by The Green Grid. Microsoft says its containers tested at a PUE of 1.22, while Google reported an average PUE of 1.21 for its data centers, which apparently are also now using containers."
If they care so much about being "green", are they using recycled containers ?
1% APY, No fees, Online Bank https://captl1.co/2uIErYq Don't let your $$$ sit in a no-interest acct.
OK so if you have a PUE of 1.2 then five-sixths of the input energy is used to power the computer equipment. But that doesn't say how energy efficient the machines themselves are. You could be running 150W Pentium 4 Extreme Edition processors, or whatever, and still get a higher 'efficiency' than someone using Atom processors giving the same computational speed with lower power usage.
In the old days I would have suggested that Microsoft was limited to x86 processors and so they would necessarily have higher power usage than Google, who would be free to use more power-efficient architectures like ARM or PowerPC. But I get the feeling this isn't true nowadays. In servers and high-end desktops, do Intel x86 chips now offer the best bang per watt?
-- Ed Avis ed@membled.com
Given Live! search popularity, it is easy to be ahead of Google in this regard. They could as well turn the whole thing off and become rich.
839*929
Microsoft, which is currently putting the finishing touches on a huge new data center near Chicago. The bottom floor of the $550 million facility will house at least 150 data center containers packed with servers.
So they put servers in containers, then put the containers in a warehouse? What good does the container do at that point? You're just compartmentalizing the warehouse, with really unwieldy compartments (I'll bet you can't move the containers once installed, so you're stuck with the form factor chosen at installation). Why not install modular walls instead (if it's the compartmentalization that yields the extra efficiency)?
This is like two fat people drinking diet coke with their supersized double cheeseburger meal.
PUE is a rubbish metric for this. The definition is nothing more than "power at utility meter" / "power used directly by IT kit". There's no account of WHAT that power is doing. Is it running one PC or a thousand? Is it hitting Gigaflops or nanoflops? You could put a laptop without a battery into a datacentre and get a PUE better than someone who has a thousand rackmounts all running at full speed. All PUE measures is the efficiency of the power conversion gear and associated equipment (e.g. UPS, etc.). In fact, UPS is an interesting measure too because the PUE of kit with a UPS would be greatly hindered in PUE stakes even against otherwise identical equipment.
Now, "Total Teraflops / Power at utility meter" - that's a more accurate metric to be comparing. And I'd guess that there Google's containers would wipe the floor with MS's (unless, of course, some trickery is being done in the TFlops measurement - you would have to carefully define what's needed). And even then, throwing a bucket load of low-power ARM processors running Linux into every square inch possible would probably thrash even Google in those stakes (unless they already do that?).
If you're going to have a contest over a metric, at least understand the metric and its shortcomings before you start claiming that X is better than Y.
Would be more interesting if it were a fight to the death.
Even if an employee died, they could claim that it was one less person breathing out carbon dioxide. Win-win.
Task Mangler
Is there some unwritten rule that you can't use 'and' in a headline?
Since it is mostly irrelevant where a data center physically is, and cooling via electrical power is going to result in a comparable draw to generating the computing cycles in a warm climate, I suspect the greenest thing Google/Microsoft could do would be to site their data centers in the coldest northern climates feasible (rather than, say, California). It makes generated waste heat potentially useful as well, rather than just pumping it straight back out into the atmosphere.
(Thinking about it, Iceland would be ideal for a big datacenter. Cold climate and lots of cheap renewable energy via geothermal.)
"I bless every day that I continue to live, for every day is pure profit."
I recently had a back-and-forth over on the Windows 7 development blog regarding Microsoft's comments on encouraging their users to put their computers in standby mode rather than shutting down the entire computer. Apparently the startup time from standby is worth the extra power saved over hibernating. Some other people on the blog said that computers use "only" 1 watt now in standby. I said sure, that's great. Now multiply that by the hundreds of thousands of computers in homes around america. If only a fraction of those computers were in standby mode at any moment rather than hibernation, they would be using tens of thousands of watts of energy that would otherwise be responsibly saved. So I've a hard time imagining that MS is really pushing for any sort of true "green" balance.
Here's to help you what a PUE is.
Just send your Data-Center to the province of Quebec (Canada). We have Hydro electricity aplenty. Heck, if you go North enough, you won't even need an AC in the server room.
I like Sun's SWaP metric because its value is based on a business operation that you can define.
And as the article mentions, datacentres in a shipping container are like, sooo 2006 .
Slap a bit of paint on them; good as new!
A couple of months ago there was a story about a university using shipping containers for student housing.
Total Teraflops - that's a floating-point measurement. Not much floating point done in a database search - apart from the google rating and calculating the search speed pre haps.
You do know that a patent doesn't prevent you from building and using a patented device? You just can't sell them. In fact, making the information available was the reason for patents.
The reason we subjugate ourselves to law is to better procure justice. If law does not accomplish this purpose then it m
It is a written rule of journalists, they economize the amount of letters in a headline. It makes sense with printed press, but at the web they should follow some different gidelines.
Rethinking email
some metric devised by an international nonprofit which microsoft happens to be a
director level member and google does not.
disney and enterprise rent-a-car are also members??
what ever happened to kilowatt hours?
Good people go to bed earlier.
"Microsoft and Google have opened a new front in their battle for global domination: data center energy efficiency".
We should just have one. Big. Googlesoft.
It seems to be a grouping of power-hogs who want to claim to be environmentally friendly. Don't get me wrong, I'm not saying that it won't do some good, but until it get a few organizations like GreenPeace as members, and asks them to audit its standards, then nobody should take it too seriously.
The Green Grid: Members List
Reduce, reuse, cycle
The website linked to basically regurgitates material from a Google website about their data centres and a blog entry by a Microsoft data centre employee.
The original links are more informative than the rehash.
Classical Liberalism: All your base are belong to you.
Or have they redefined "hibernation"? Hibernation used to mean "you save all the system state to disk, and cut power". You should be able to use the big toggle switch on the back and drop AC completely.
You shouldn't need to keep a "trickle" going unless you want to use something like "wake on lan".
MS are getting a PUE of 1.22 in their new container datacentre. Google are getting an average of 1.21 across all their datacentres, and 1.13 at their best datacentre, which it is speculated may use containers. So MS have the dubious achievement of their best datacentre being slightly less efficient than Google's overall average. Whoop!
Somewhat related to the article; Today I looked at the google frontpage, I saw a link under the search box to some energy-efficiency stuff, I thought I'd check the hippie stuff out, but the link took me to www.google.com/hauntedhouse08/
I refreshed the frontpage, and mysteriously the link had disappeared.
Remember, you heard it here first.
Will whoever pue'd 'is pants kindly go and change? Thanks.
The PC electronics only burns 1-2 watts in standby, but the large and idle power supply will burn another 8 or so.
Or at least that's the way my imac is. I got a watt meter and it's 70w at full power, 40w in low-power mode, 10w in standby and 10w when off. It only goes to zero when you unplug it.
My laptop is the same: the charger burns 7w even when you don't plug it in to the laptop.
Actually I think containers are a great idea as you can attach some solar panels on the roof and sides to maximize the solar consumption. I don't know if I have enough computers for it, but definitely I could see containers being used more and more for mobility as well in disaster situations, I know I want one!
I see a reference to Kang, so I assume this is Kodos the executioner. What is the ray gun you are talking about. Kodos was best known for killing a large portion of the population of his colony to save the remainder from starvation only to have the resupply ships show up a day later, thus being tried and convicted instead of applauded for a brave decision. Is there another Kodos that involves a ray gun?
Not if you think of the container as your "PC".
When X% of the computers in the container are not working, you unplug it, pull it out and replace it with a container where 100% of the computers are working, and send the faulty one for servicing.
If they do that though, that means the real life PUE won't be as great. Since a fair number of containers would have nonworking machines in them.
What kind of bogomips are they getting?
Flops is a totally BS metric, too ... no respectable microarchitecture paper has reported FLOPS or MIPS for more than a decade now. Energy per transaction would be more useful, but that depends greatly on what you're doing.
That isn't answered by TFA, and I don't see how packing a few racks of servers in a large metal box would help make a datacenter more efficient.
To save power over phase-change (i.e. freon-style) cooling (and yes, I do realize evaporation is a phase-change, I didn't pick the name).
So they save on electricity and instead use a lot more water. Is this a big advance? Is the energy cost of getting that water there counted in the efficiency rating?
If Google really wants to reduce the energy used (and not just their electrical bills), they need to look at these kinds of things.
http://lkml.org/lkml/2005/8/20/95
"Microsoft, Google Battle Over Energy Efficiency"
And! Microsoft and Google! Say your goddamn conjunctions!
I'd like to have a Beowulf cluster of these shipping containers...
Or better yet, imagine a container ship filled with them--how many MIPS is that, anyway?
(Dyson sphere--here we come!)
P.S. Never underestimate the bandwidth of a Panamax freighter filled with Flash chips...
"Not an actor, but he plays one on TV."
What's funny about this is that the Microsoft employee is touting getting one new container in testing down to what Google's current running average is. If you think about what an average means (that there are some higher and some lower than the average) then MS's accomplishemnt doesn't mean much. The article sort of mentions this noting that Google has one at 1.13 and that its numbers are for working installations, not just testing numbers like MS.
On the other hand I fully agree with the other comments that PUE is only a small part of the equation. It's the amount of useful work per electrical watt expended that is much more important. But at least when the focus is on lower power data centers, the rest of the problem is being worked on too.
One day in the near future at Microsoft's new data center... "Okay boss! We've stuck all our servers in the shipping containers! Everything's going great!" "Good work. Let's go to Taco Bell and feast on tacos to celebrate!"
At taco bell... "Mmmm boss this is taco-licious!" "You deserve it kid! You got all those servers into those containers right quick!"
Meanwhile, back at the data center... Beep! Beep! Beep! The night air is pierced by the sound of a large truck reversing. Soon, the truck which arrived empty, leaves in a cloud of diesel smoke with a shipping container full of servers on the back. "Hey Sergei, it was nice of Microsoft to put all their servers into a shipping container to make them easier to steal!" "Yes Pamela, those suckers at Microsoft must have thought long and hard about this."
CERN advisory: Systems administrators are warned of a truck-related denial of service attack. Thieves load a container full of servers onto a truck and drive away.
I'm voting for Kibo.
In cold countries, anyone who has thermostatically controlled heating may end up saving NOTHING even if they turn the device right off.
The heat NOT generated by the now OFF devices will be generated by the central heating when the thermostat kicks in sooner.
Successful campaigns for low energy light bulbs and other low energy devices mean that it often isn't worth the time it takes to say "turn it off", there's much worse waste to target.
Sam
blog.sam.liddicott.com
Too much Star Trek, too little Simpsons. Try again, AC.
It is pitch black. You are likely to be eaten by a grue.