Slashdot Mirror
Google Reveals "Secret" Server Designs
Hugh Pickens writes "Most companies buy servers from the likes of Dell, Hewlett-Packard, IBM or Sun Microsystems, but Google, which has hundreds of thousands of servers and considers running them part of its core expertise, designs and builds its own. For the first time, Google revealed the hardware at the core of its Internet might at a conference this week about data center efficiency. Google's big surprise: each server has its own 12-volt battery to supply power if there's a problem with the main source of electricity. 'This is much cheaper than huge centralized UPS,' says Google server designer Ben Jai. 'Therefore no wasted capacity.' Efficiency is a major financial factor. Large UPSs can reach 92 to 95 percent efficiency, meaning that a large amount of power is squandered. The server-mounted batteries do better, Jai said: 'We were able to measure our actual usage to greater than 99.9 percent efficiency.' Google has patents on the built-in battery design, 'but I think we'd be willing to license them to vendors,' says Urs Hoelzle, Google's vice president of operations. Google has an obsessive focus on energy efficiency. 'Early on, there was an emphasis on the dollar per (search) query,' says Hoelzle. 'We were forced to focus. Revenue per query is very low.'"
I think Google may be selling themselves short. Once you start building standardized data centers in shipping containers with singular hookups between the container and the outside world, you've stopped building individual rack-mounted machines. Instead, you've begun building a much larger machine with thousands of networked components. In effect, Google is building the mainframes of the 21st century. No longer are we talking about dozens of mainboards hooked up via multi-gigabit backplanes. We're talking about complete computing elements wired up via a self-contained, high speed network with a combined computing power that far exceeds anything currently identified as a mainframe.
The industry needs to stop thinking of these systems as portable data centers, and start recognizing them for what they are: Incredibly advanced machines with massive, distributed computing power. And since high-end computing has been headed toward multiprocessing for some time now, the market is ripe for these sorts of solutions. It's not a "cloud". It's the new mainframe.
Javascript + Nintendo DSi = DSiCade
From 2007, the modular data center patent (where the bottommost image of the article comes from). There's no lack of patents revealing piece by piece how their power management setup works.
Ah, the catch--22 of the patent--being forced to reveal your hand in order to protect it while underpaid workers at Baidu figure out how to integrate your ideas into their hardware.
My work here is dung.
Get that man a beer.
I'm no guru of servers, but from my own limited experience in installing servers at the small to midsized company I work at, space is always a looming issue. And shrinking the size of the UPS you need can only save money and space in the long run; which any IT manager will tell you is a huge benefit and a great selling point.
Nothing to do but wait for a finished product at this point though.
Posting with out proof reading since 2001.
We all know the searches are actually being done by a large amount of people in suspended animation, being fed the corpses of the previous people.
The thing about each server having its own battery is a cruel joke.
The in-computer onboard UPS is not a new idea. I don't see how they could have gotten any patents on it since I used it have one of these (my day might still). The device I saw had a gel cell mounted on an 8-bit ISA card, full length. It had +5/12v pass through connectors for powering the drives and it powered the computer through the main bus. There was more logic to it, as it had some monitoring capabilities too.
What's next, patenting a hard drive on a plugin board? Been there, it was called the Hard Card and put a 20mb HDD in an 8 bit full length ISA slot, a truly neat idea for upgrading old XT computers back in the day. You could make them work with AT computers too by putting a regular disk controller, without a drive connected, on the bus too and the BIOS would see the XT controller and boot from it.
Google claims they did the math and found it was cheaper with commodity hardware. I advise everyone else to do the same and run the calculations for themselves to determine the optimal hardware for their particular load. With out the specifics of their situation, its difficult to criticize in an intelligent fashion, other than a more generalized statement expressing surprise at their configuration.
Well.. maybe. Or Maybe not. But Definitely not sort of.
When the weather gets warmer, Google notices is that it's harder to keep servers cool.
Brilliant journalistic work there.
I've a few questions, if the data centre is built in the desert don't you have a number of issues?
* Latency, if you have all your data centre's located in essentially a single part of the USA (lets ignore the rest of the world for this.. regardless that there are no deserts in Europe for example) won't that increase latency quite a bit to the more further away places that want the search results?
* Bandwidth/redundancy, if you have all your eggs in one basket as it were aren't you going to have to pay extra to have lots of extra fibre laid down to be able to handle all that extra traffic? What about natural disasters, if you have all your data centres in a single location then surely you run the risk of things going pear shaped if it burns down, suffers earthquakes, aliens destroy the building etc.
* Cooling, because it's in the desert isn't a lot of the electricity that is generated going to be cooling not only the building because of the outside heat, but also the heat generated by the servers? Surely it makes more logical sense to build in a colder climate say further north and use hydroelectricity? (if you're talking of using exclusively non active polluting (and non radioactive) natural electricity solutions)
Googles secret is that all there computers have battery.
I think, it is called a laptop.
Greater than 99.9% efficiency? They likely made a mistake in their measurements.
Maybe they measured 99.92% efficiency.
That is greater than 99.9% efficiency and they aren't breaking any laws of thermodynamics.
...why desktops didn't have a built in battery deal that lived in an expansion bay. If you could even keep RAM alive for extended periods even with the machine shut down that would be spiffy as an option, let alone as a little general UPS.
look at the date the article was published.
"It would be wrong to refuse to face the fact that everything is fundamentally sick and sad."
This is a questionable number. The best DC-DC conversion is around 95% so they aren't including voltage conversions from the battery to what the system is actually using.
Many data centres expressly forbid UPSes or batteries bigger than a CMOS battery in installed systems - because when the fire department hits the Big Red Button, the power is meant to go OFF. IMMEDIATELY.
So while this is a nice idea, applying it outside Google may produce interesting negotiation problems ...
http://rocknerd.co.uk
I'm working on a solution. If only I can contact Oracle.
This is composed purely of commodity parts. The power supply is the same thing you'd buy for your desktop, those are SATA disks (not SAS), and that looks like a desktop motherboard (see the profile view where all the ports on the "back" are lined up in the same manner they would need for a standard desktop enclosure).
Only the battery is custom (or even non-consumer grade), and you can note that since the power goes through the PSU first, that's DC power. DC is significantly better than AC, since the PSU then has to convert AC-to-DC (which wastes power and generates needless heat). While you can get DC battery supplies for server-grade systems, these are not server-grade systems. Built-in DC battery backup therefore affords them the ability to keep the motherboards cheaper. Very smart.
Also, if you recall from a few months ago, Google has applied pressure on its suppliers (I'm not sure why Dell comes to mind...) to develop servers that can tolerate a significantly higher operating temperature (IIRC, they wanted at 20 degree (Fahrenheit?) boost). I wouldn't be surprised if the higher temperature cuts down on operating expenses more than smarter battery placement.
Use my userscript to add story images to Slashdot. There's no going back.
A desert does not describe the temperature of a region but the (lack of) rainfall/moisture.
http://desertgardens.suite101.com/article.cfm/definition_of_a_desert (link found using Google).
And besides, put the containers underground and I'm pretty sure that "hot" you refer to becomes a non-issue as well.
Or maybe they think bigger...
They're deploying containers of servers. Maybe when a container gets a to a certain age or a certain failure rate, they replace/refurbish the entire container.
I doubt they care if some of their nodes go down in a power outage as long as some percentage of them stay up.
Hundreds of thousands of servers == thousands of dead batteries each month, since those batteries don't last more than a few years.
I would imagine that the battery replacement schedule mimics the server obsolescence perfectly.
LOL, when the battery catches fire, time to replace the server.
I'm a little surprised by the keyboard and mouse port and the two USB ports. If it uses USB, why not just use that for the keyboard and mouse? And why the second USB port? I suspect the second port doesn't consume extra energy directly, but it causes air resistance where they'd like to clear path to drag air across the RAM and CPUs.
And why the slots which will never get used? In quantities like Google buys, you'd think those would be left off.
Maybe they don't make any demands on Gigabyte (the manufacturer) and just buy a commodity board? When they're buying this many, you'd think Gigabyte would be happy to make a simpler board for them. On a trivial search, I don't see the ga-9ivdp for sale anywhere, but maybe it's just old.
Google is basically re-implementing the efficiency that already exists in a laptop.
You have a laptop with >1000 processors, consisting of several times that many cores, with its own built-in gigabit ethernet running on built-in gigabit switches?
I'd hate to sit next to you on an airplane!
Javascript + Nintendo DSi = DSiCade
A google mainframe would be stupid.
If you take the price of a mainframe, and compare that to what google can get for the same money using their current solution, their current solution offers at least 10 times as much cpu performance, and much much more aggregate io(Both hard disk and memory) bandwidth.
There are only 2 reasons to use mainframes now.
1: Development cost. Building software that can scale on commodity hardware is expensive and difficult. It require top notch software developers and project managers. It make sense for Google to do it, because they use so much hardware(>100000 computers at last count).
2: Legacy support.
They'd still have a computer there that is staggeringly efficient, especially since a computer's output energy is entirely heat - information is not energy, computers are all 0% efficient. Still, this isn't what they meant and the 99.9% figure probably comes from battery in/out figures.
It's ok, appearently he stores it in his middle finger.
Date Center Knowledge has videos of the secret server and a tour of one of the container data centers.
Probably because they own these datacenters and can do what they want with them. The EM emissions are probably contained by the fact that the servers are all in a giant metal box. UL is optional, and if they don't want to go through it they don't have to. It's not like they're selling these servers to anyone.
I read the internet for the articles.
How did this get marked informative?
I mean it's certainly true that Deserts are defined by lack of rainfall but since the GP said
"Build your data center in the desert and build 150 MW industrial solar thermal system to power it."
I think it's fair to assume they were talking about the stereotypical sunny and hot desert.
Secondly the reason it's cool underground is because soil is generally a very good insulator. I would suggest that it's a really bad idea to put things that are going to get hot inside a huge lump of insulating material.
I could design this PSU configuration, and I do electronics only as a hobby.
First, your main PSU delivers 12V in this scheme. Then this is stepped down to 5V and 3.3V for mainboard use, a design that is already employed by some Enermax PSUs, for example. For the 12V line, remember that +/-10% lower is acceptable. The lead-acid battery delivers up to 14V, so you need a step-down converter to 12V. In fact, you can design a switching regulator that steps the input voltage down to 13.2V (12V+10%), if it is larger, and just passes it through for 13.2V...10.8V with very, very low losses. A similar design can be done for 5% tolerances. Modern switching FETs go down to 4mR per transistor and you can do the transition from switching mode to pass-through mode very easily, e.g. with a small microcontroller that can then also do numerous monitoring and safety things. I had actually considerd such a design (purely analog though) for a lower-power, 12V external supply system myself some years ago, but a single UPS was so cheap that I did not went through with it.
I do not mean to belittle the what the Google folks do, though. The real ingeniuity is relaizing you can do it this way on a datacenter scale when nobody else does it. The engineering is then not too demanding, at least for folks that know what they are doing.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
Have you ever even seen Mainframe pricing? No really have you?
It will cost you at least 10000$ to match the power of a single quad core intel/amd cpu.
And you do not want to run a mainframe(Or other computer that have a cpu bound task) for a decade. I think my current desktop computer have more power then avg mainframe
from a decade ago, and when I buy a new development workstation in then next decade, it will most likely have more cpu power then a 1 million $ mainframe you could buy today.
Just to set things in perspective: I am pretty sure, that google have more cpu power, more ram, more hd space and more aggregate io, then all mainframes in USA combined.
A 12v battery. I never knew DC was more efficient than AC! WOW GOOGLE IS SO COOL!
I'm not sure if you are being sarcastic. A 12v battery in the power supply is more efficient than taking DC -> AC -> DC. That is what a UPS does, each conversion introduces loss. Having the battery in the power supply means there is no conversion so less power loss.
Actually, they're not.
Laptops run slower than their PC counterparts.
Laptop drives run slower than their PC counterparts.
Laptops run hotter under load than their PC counterparts.
If you look carefully at the picture, they've found a 12v motherboard, tied a 12v battery directly into it, and used otherwise commodity parts. That's been the mantra for Google for as long as I can remember. Oddly enough, that was my mantra when I built up a big network. Lots and lots (and lots and lots) of cheap servers are better than a handful of really expensive ones. That saved our cumulative posteriors on more than one occasion.
I've spoken with some people who have personal knowledge of Google's equipment. They were setting up with RAID 01 or 10. I suspect with the two drive configuration, they're only setting up with RAID 0 now, and the redundancy is across multiple servers. I can confirm that they are using this open tray system for it's superior cooling.
I had considered open trays like this, except there's one huge downfall. You would have to be amazingly careful of what happens near the rack. If you are screwing something in, and the screw or screwdriver falls, that can become very bad very quickly. Did you see any fuses or breakers from the battery to the power supply?
Short of making the area around the rack a metal-free zone (no screws, screwdrivers, rings, keys, watches, etc), you'd seriously run the risk of shorting something out. I know I've been working up in the higher areas of a rack, and dropped screws. You listen to it rattle it's way down across several machines until it finally hits the floor. Since I use closed servers cases, it's never a problem. Maybe they don't have a big problem with it at Google, but I'd be terrified of it. Anyone who says they've spent any substantial time working in and around racks, and haven't ever dropped anything, are lying. I do love the idea for free airflow and better cooling, but ... well ... I like to keep magic smoke in it's place. :)
The one-battery-per-server is a nice idea though. I may look into that for future builds. Most PC's have 5v and 12v output. That power supply only indicated a 12v output, and didn't have any wires that indicated anything different.
Serious? Seriousness is well above my pay grade.
The problem I have with running a motherboard directly from a 12V battery is that most batteries are 12V nominal; actual voltage varies quite a bit (10.5-13.8 for a Pb-Acid). So the question is how well do the 12V components cope with the lower/high voltage? Most of the logic should be OK; that's all 5/3.3/1.xV. I'm guessing the only stuff that really uses 12V anymore is actually disk drive circuitry(not technically on the MB).
I have a suspicion that you really don't want to be running a hard drive off a voltage supply that varies by up to 25%. They must have solved this somehow (step up + step down converter? But that is not efficient) but I really see no point in using 12V motherboards unless everything else can reliably run off the battery first. The home consumer may as well stick with getting 5V from the PSU and letting that dissipate the heat from the step down conversion until we're all using 5V disk drives. In which case, we can probably move to lower voltages (and lower voltage batteries); ~8V seems about right to get a stable 5V.
I have determined that my sig is indeterminate.
"If you take the price of a mainframe, and compare that to what google can get for the same money using their current solution, their current solution offers at least 10 times as much cpu performance, and much much more aggregate io(Both hard disk and memory) bandwidth."
no it doesn't.
Plus they are cheaper to maintain, require less power per cycle, require less square feet to house.
Yeah, I actually know about these things.
The Kruger Dunning explains most post on
Modern high speed chips (which draw the bulk of the power in a typical PC) run thier core logic at much lower voltages. Typically somewhere between 1V and 2V though I think some may have gone below a volt now. Theese very low voltages have to be produced very close to the chip that uses them to avoid huge losses.
This means that modern PC motherboards take most of thier power at 12V anyway. The 5V and 3.3V lines really only serve to power the low speed chips and some of the interfaces between chips.
Given that I doubt there would be too much efficiancy loss from making a 12V only board. You could probablly even design it to hapilly deal with an input that was only approximately 12V without losing too much (since most of that 12V power is going to the input of switchers anyway).
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
When I worked for a University, we bought a few of the largest IBM pSeries machines (power4 at the time). These were powerhouse machines 5 years ago. Each one had a dedicated 24" oversized rack cabinet, and then we had a couple racks just for disk. The 4 machines, and about 40T of Fibre channel disk (or was it DASD), I think it was a total of 128 core and 256GB of ram. I think we paid about a million for that setup.
As was mentioned elsewhere on the webs, the machine shown off by Google was based on Nocona CPUs.. those are atleast 4 years old now. Not likely what they're buying new now.
I bet you could get a base z10 for a few hundred thousand, but a fully loaded one? With a disk array of 750 drives? I bet 4 racks of disk from IBM would cost most of that 950k budget.