Google's Secret Plans For All That Dark Fiber?

beat.net writes "Robert X. Cringely details the plan for all the dark fiber Google has been buying up: "The probable answer lies in one of Google's underground parking garages in Mountain View. There, in a secret area off-limits even to regular GoogleFolk, is a shipping container. But it isn't just any shipping container. This shipping container is a prototype data center. Google hired a pair of very bright industrial designers to figure out how to cram the greatest number of CPUs, the most storage, memory and power support into a 20- or 40-foot box. We're talking about 5000 Opteron processors and 3.5 petabytes of disk storage that can be dropped-off overnight by a tractor-trailer rig. The idea is to plant one of these puppies anywhere Google owns access to fiber, basically turning the entire Internet into a giant processing and storage grid. While Google could put these containers anywhere, it makes the most sense to place them at Internet peering points, of which there are about 300 worldwide.""

Google is Skynet?

"Maybe Google will end up becoming the first sentient AI, if storing and finding association patterns between data is the essence of conscious thinking. The amount of information that Google has at its disposal is staggering, and poised to continue its growth with the introduction of Google Mail. What makes Google more than an extra-big database is the software that sits under that database, and its ability to continue scaling up. Jason Kottke has a great post on the big-picture trajectory of Google's technical efforts, and hits an essential point by noting that Google's focus has always been about what people are doing - searching, talking, shopping, and soon, emailing. Google's focus is human activity and the relationships between trillions of interactions. When I think about that , and then think about how much the daily use of the web has come to rely on Google, my joke about the system becoming sentient, by intent or by accident, seems a little less funny. " source : http://www.holycola.net/archives/000423.html [holycola.net]

Re:Google is Skynet?

That was my thought, too. I'm all in favor of Google as the search engine but the capability that a network of these things would give to a single corporation which owns them outright makes me more than a little uneasy. For no particular reason other than the sheer "dayum. Is there anything you can't do if you have that at your disposal?"

The Alternative Re:Google is Skynet?

The alternative is everybody running their own stations in a massive wireless mesh network.

Re:The Alternative Re:Google is Skynet?

I second this. I am just waiting for the moment when the technology becomes available. Its the way the internet was really intended to be run. Screw ISPs. The internet needs decentralised wireless peering.

Re:The Alternative Re:Google is Skynet?

There are too many dead zones between major cities .

Great distances of rural farmland .

http://www.locustworld.com/ [locustworld.com] is a awesome idea, and they have done some
great things, but there are many places off the coast where distances
between cities is greater than the range of WiFi unless u use the ballon trick .

But long shots in the midwest are going to have to route via
conventional telecom unless we setup telecommunications WiFi ballons .

www.21stcenturyairships.com

Someone has to pay for them ... At least they are cheaper than satellites and fly
high enough to avoid all wind .

Ex-MislTech

Re:Google is Skynet?

Don't forget Crzmblski's Limit.

Re:Google is Skynet?

Don't forget Crzmblski's Limit.

I hadn't heard of Crzmblski's Limit, so naturally I went to Google to find out what it was ... to my surprise, Google has already removed all references to it. So it must be fantastically important, so important that Google must hide it from the world... now I'm *really* scared.

Re:Google is Skynet?

I think it has something to do with the readability of variable names in Hungarian Notation... The memorability of the name decreases as the square of the variable's importance.

The limit's definition is posted on everything2

Here's the link http://www.everything2.com/index.pl?node_id=176552 3&lastnode_id=1765513 [everything2.com]

Re:Is this a joke?

It's a reference from Keith Laumer's novel "The Great Time Machine Hoax". Don't know if I spelled it quite right.

Crmblznski's Limit -- Definition

Taken from http://www.incendiary.ws/node/194 [incendiary.ws]

Crmblznski's Limit, sometimes spelled Crizmblski's Limit, has its origins in Keith Laumer's novel "The Great Time Machine Hoax" [1].

The basic theorem is that there is a finite limit to the complexity of any given machine, which specifically precludes the operation of "a machine with sufficiently extensive memory banks, adequately cross-connected and supplied with a vast store of data, [that by its very essence] would be capable of performing prodigious intellectual feats simply by discovering and exploring relationships among apparently unrelated facts." The Limit is an irrational number, much like Pi, in that the total complexity of machine is wholy dependent upon both hardware and software designs.

Re:Google is Skynet? So is Wikipedia now Google?

Many of the things I used to go to Google for, I go to Wikipedia instead. Now there is a category for which I go to Wikipedia for and a category I go to Google for. Actually they were distinct before, but the category of things I go to Wikipedia for, I fancied Web Directories might be useful for except that they weren't very robust and got out of date.

Re:Google is Skynet?

yep, I just entered the posting area to post a comment "skynet anyone?" but your posting confirmed that this was not such an obscure idea.

    all the buzzwords like "dark fiber" "secret underground garages" and "dropped off overnight" and even "peering points" make this sound like a recipe for a very red future.

Re:Google is Skynet?

Skynet? No I rather think it sounds and looks more like WOPR.

How about a nice game of chess?

Re:5,000 opterons? That'd make a fine...

By unplugging it.

Imagine

a Beowulf cluster of these puppies...

...Oh, we don't really need to Google seem to be building one.

Obviously...

...the puppy's on fire.

How are they going to cool these things?

Re:Obviously...

With dark energy... duh!

Nice work of fiction

Has anyone given any thought to how many of these peering points have excess power capacity for 5000 Opterons? Hmmmmm?

Re:Nice work of fiction

I'm sure google has. It's not like you can't have another truck towing a generator following the truck towing the portable datacenter.

I used to work at a datacenter and we had a generator small enough that you could fit 12 of them in a shipping container, and the genny was enough to run a 500 machine datacenter for three days without refueling. The portable datacenter may well have a generator included.

Re:Nice work of fiction

Actually, I'm curious how Cringeley thinks Google can get the hardware at the prices he quotes in the article. I'm sure he's given it some thought, but unless they're getting hardware at below-cost prices, I don't see how it can be done. The CPUs cost about $50 each to make, so that's $250k for chips. Then you need a few petabytes of disk. I don't know what the manufacturing cost is for disks, but I'd guess about $50 there too. Say $50 for a 500GB drive. That's a few thousand drives to reach the several petabytes, and there goes the rest of his half-million dollars. You still need motherboards, RAM, power supplies, chassis, racks, switches, etc.

I'm not saying he's wrong, but I'd be curious to hear where I've gone astray in my figuring.

Not to mention, of course, the enormous electrical requirements this thing would have, as you've commented. If we round the CPU's power consumption up to account for all the support machinery, and figure 100W per CPU, this neat little semi-load is going to want half a megawatt, plus cooling. Just the disk array will chew through 50kW or so. Even from a power plant's perspective, that's a pretty hefty chunk of juice.

Re:Lots of heat, lots of power

Even with liquid cooling it's a hard problem. For one thing you need 5000 little hoses, and beefy pumps to get the water through there at a reasonable speed. Opterons are specced to run up to about 85C (depends slightly on model / family). Suppose you've got incoming water at 10C, and heat it up all the way to 85C. That's 75C difference, or 313.5J/g of water you're taking away. That works out to 5.75 million grams of water per hour, or just under 6000 liters per hour. You can't just dump it into a lake or river or you'll completely nuke the resident ecosystem. It's a manageable number from the point of view of getting it through the machines, but it's still an awful lot of energy to get rid of.

The sort of temperature-differential energy recovery you speak of is technically possible but isn't efficient enough to substantially reduce the cluster's power requirements, and thus its need to vent waste heat.

Re:Nice work of fiction

At peak performance, one Opteron will draw (conservatively) 1 Amp, and use (more conservatively) 100 Watts. Double it to include the disks, etc, and we're probably still conservative at 200 W * 5000 CPUs = 1 Megawatt, which basically all gets converted to heat, all in a box that size. Surface area of the box?
    40 * 40 * 40 feet -> 104 Watts/sqft out...

Your numbers are off...

A 40 ft shipping container has a surface area of something more like:

(40 * 8) * 4 + (8 * 8) * 2 ==

1408 sq. ft.

which, for 1 megawatt, is more like 710 watts/ sq. ft.

additionally...

Even assuming the power and heat requirements of cramming that many opterons into that small a space could be dealt with, there's another, larger problem:

It's not fucking 1997 any more.

"Peering points" -- big, open-access traffic exchange handoffs like the old MAE-East [wikipedia.org] and MAE-West used to be a big deal back in the late 90s, when OC-12 circuits were still rare and hideously expensive beasts, and Gigabit Ethernet was still a gleam in some 3Com engineer's eye.

In 2005, they simply don't matter. The big players (level3, MCI/Verizon, Qwest, SBC, etc) all exchange traffic over private fiber interconnects, and everyone else buys transit from the big guys directly or ponies up for a switch port at Equinox, PAIX/Switch&Data or some other 'carrier neutral' colocation center. Dropping a datacenter-in-a-box onto MAE-east or any of its surviving ilk would buy Google precisely nothing.

(And nevermind the fact that google is documented to own thousands upon thousands of unused square feet of datacenter space already: they went on a very well-thought-out buying spree in 2000-2001 when all the dot-com datacenter companies were going out of business, and are very well provisioned for the forseeable future as a result.)

Now, a much more interesting application of the "Google node in a shipping container" idea can be summed up in one simple word: China. Why wait for the local market to develop the infrastructure you need when you can just drop a box down and then run fiber to it? I'm still dubious though...

Re:Nice work of fiction

That's it! The opterons produce heat, which boils water which runs the turbines to generate electricity to power the opterons! My god man! It's the Google perpetual motion machine!

Stealing

That's a nice idea but that thing must need some serious amount of power to run. Add the massive cooling system needed to keep the box runnning without melting. If they intend to just "drop" it anywhere... they have to think about security. You don't want some geek with a saw to steal your 3.5 PB array! Omni

Re:Stealing

Problem solved (portable nuclear reactor) [newscientist.com].

Re:Stealing

Security?! I'd be more afraid for the geek's security, than the cube's.

Knowing Google, I would think that these shipping container computer things would be covered with sensing devices. It's probably scanning the face, gait, apparent weight, and shoe size of anyone that gets near it, and googling for their name, their address, their family and children, employer, and all other relations. As it prepares to activate the lightning sprocket, it's probably composing emails, editing video footage, and notifying the newspapers of an impending obituary.

I'd sooner touch the Ark of the Covenant of the Lord your God, than touch one of these here Google Skynet Singularity Machines.

When will sinister phase two begin?

Sounds like Google may be ready to go starbucks [theonion.com].

HEY!

If most Google employees don't know about the storage container, how does THIS guy know about it???

Re:HEY!

He probably googled it.

5000 Opterons

While Google could put these containers anywhere, it makes the most sense to place them at Internet peering points

5000 Opterons? It makes sense to put those near power plants / ice bergs. That's at least 500 kW of heat dissipation.

Mommy Mommy...

...I know what I want for Christmas this year.

aren't they all?

>Google hired a pair of very bright industrial designers

I haven't yet met one that didn't think they were very bright. Industrial Designers invent stuff that takes 'ordinary' engineers years to throw away and build something else that will fly. No danger of anything happening here folks :o)

Missing something here...

I don't understand how a few boxes full of Opterons automatically means taking over the Internet.

In my opinion, Google has penetrated the American market with its services as much as it can. It is probably looking to other places in the world to prop up its cash flow. You know, like a business, rather than a collection of world-domination-bent nerds?

Cooling 5000 Opterons?

If an Opteron produces say, on average, 50W heat output (I know this isn't accurate, but just as an example), 5000 Opterons would produce 250kW of heat. That would require an air conditioning unit larger than the building used to house the container.

Re:Cooling 5000 Opterons?

why does everyone have to stick to the old school tried and true method of computer room cooling, in which you HAVE TO cool down the hot air. how about this... suck outside air from one end of the container, filter it, cool it if needed, and then exhaust it out the other end. It makes absolutely no sense to cool hot air when you might have an unlimited supply just outside your door. In many climates your total cooling bill is going to be a small fraction of what it was in the old school scenario.

Re:Cooling 5000 Opterons?

Humidity control.

Re:Cooling 5000 Opterons?

1W = the amount of power required to heat 1g of water 1 degree celsius in 1 second (1 J/sec).
1 cup of coffee: 0.2 litres (200g) heated from 10 to 100 degrees celsius (90 degrees) = 18 KJ.
250 KW: 14 cups of coffee per second.

The answer to "where do we put these puppies"?
Next to Starbucks.

Re:Cooling 5000 Opterons?

If an Opteron produces say, on average, 50W heat output (I know this isn't accurate, but just as an example), 5000 Opterons would produce 250kW of heat. That would require an air conditioning unit larger than the building used to house the container.

Hardly -- a kWh is 3413 BTUs and 12,000 BTUs is a refrigerating ton. So they would need about 71 tons of cooling (the name of the unit is derived from the cooling capacity of a ton of ice per day). They make chillers into the hundreds of tons of capacity.

Here is some information on a 75 ton chiller [hvacportablesystems.com]. That's smaller than the shipping container it would be cooling -- a normal shipping container is 40 feet long and about 8 foot square cross-section.

In fact, if there's any truth to this story at all, I bet they fit all the computer gear in the first 22 feet of the container and the chiller in the last 18 feet.

Re:Great

Uh, excuse me? Google IS a huge company. Don't fool yourself into thinking this is David vs. Goliath. This is one Goliath fighting for another Goliath's territory.

Don't think that if somehow Google makes MS a lesser force that suddenly the sun is going to come out from the clouds and everyone is going to live happily ever after... Too many people on slashdot already have this attitude and it's an unfortunate one, at best.

Re:Great

Some people seem to think that being a huge necessarily makes a company evil, or the enemy. But I don't dislike Microsoft because they are a big company. I dislike them because they do dirty tricks to hold technology back; to ensure that their goddamn awful technology succeeds over more promising technology. Google hasn't as yet done that. They've got to where they are now through the excellence of their technology. And they will get my respect for as long as they are like that, no matter how large they get.

Re:Why?

Network latency. You get a faster response from a server in your own locale than on the other side of the world. And if you're doing network applications that are intended to compete with traditional local applications, then you need low latency.

Nothing to worry about folks...

>>We're talking about 5000 Opteron processors and 3.5 petabytes of disk storage

They're just getting ready to run Windows Vista when it comes out.

Same applies to Skype

Makes sense for google to decentralise their server farms and be able to provide direct access to their services - one of the biggest risks to their continuted success would have to be the breakdown of the "open" internet, though peering failures or closing off (or imposing higher tolls on) private networks.

Skype is in the same situation - they've been able to support so many users simply because their bandwidth is only used to setup the initial connection between the two parties, after that it's the telcos who are supporting and providing the infrastructure for the service that threatens them most. Now that Skype can make real money from its pay services, look for them to do something simliar to Google, to ensure the availability of their service.

Salt

This is the man who brought us the mathematically impossible [bawug.org] 6.5 mile 802.11 link with a passive repeater [pbs.org]. The repeater that he never showed to anybody [oreillynet.com]. He also shows us an idealistic world of a community cable and telephone company [pbs.org] that nobody's ever seemed to find evidence of.

Saying that, when it comes to technology at least, he is speculative is something of an understatement. Take what he says with an extremely large grain of salt.

Re:article doesn't explain network

> what's the point of putting network latency between all those shipping containers?

To remove the network latency between them and you.

They're not being used "for computing" in the sense you're envisioning. For one thing, 5000 Opterons is enough to tackle pretty much any problem you'd care to throw at it, so there's no need to talk to anyone else. For another thing, they wouldn't be doing big computations, they'd be doing massive numbers of small ones. Think Gmail. 3.5PB is enough to store an awful lot of email, and a few thousand Opterons can run rather a lot of simultaneous HTTP connections from people accessing the mail. Add in a fast network link (for talking to all those many people accessing the mail, and for replicating everything offsite), and you're set.

Cringeley's penchant for sensationalism aside, it's pretty clear that Google's got the expertise and the mindset to deal with problems that start with "if we had 10,000 fast CPUs, 10,000 hard disks, and 10,000 GB of RAM...". Google's rapidly expanding, and has been ever since they started. Back when Google fit in a closet, a new server constituted a big expansion. I'm not surprised that these days their unit of expansion is a tractor trailer with a few dozen racks in it. And if you've got something that packages up that nicely, it only makes sense to pepper the globe with capacity.

Re:article doesn't explain network

Running with your numbers, look at this. Quoting you:

With 500GB drives, it would take 7340.032 drives to attain 3.5PB... with NO redundancy.

For the Deskstar7k500 [techreport.com] [Please note that this isn't the "DeathStar" anymore, it was just when they put five instead of the industry-standard four platters into the DeskStar that they started dropping like flies, and I suppose the DeathStar reputation no longer stands. I've never owned one.]

The specifications [bigbruin.com] [see footnote for a few other sites] state

Height (mm) 25.4
Width (mm) 101.6
Depth (mm) 146

146 mm) x (101.6 mm) x (25.4 mm) x 7 340 = 2.76551705 m^3 [google.com],
and, running with the article's numbers, let's see how much of 20 feet cubed that is... (article: the most storage, memory and power support into a 20...foot box -- note that a BOX of course is less cubic area than a 20-foot cube)....

((146 mm) x (101.6 mm) x (25.4 mm) x 7 340) / (20 (feet^3)) = 4.88316565 [google.com]...

WHAT? it's not a fraction, but larger by a factor of 4+??? Just for the hard-drives? Even when we assumed a CUBE???

Man, I want some of the shit that guy's smoking. I was expecting to debunk with just the hard-drives taking an impossibly large percentage of the proposed 20-foot "box". But....man. Cringely must not have done even a basic sanity check. (And remember, I'm pretty sure he didn't have a 20 foot high, 20 foot wide box in mind, or he would have said cube. To a writer, a "20-foot box" sounds like an elongated storage container [uniteam.org], e.g. 8x8x20 feet.... BTW that's the first hit for 20 foot storage container [google.com], I can only assume a writer would have such a thing in mind...)

English and math, people, English AND math.

Footnote:
Other sources for specifications:

1. First. [hitachigst.com]
2. Second. [hitachigst.com]
3. Third. [xtremeresources.com]
4. Fourth. [storagereview.com]
5. Fifth. [pricegrabber.com]

So when does this become self-aware?

Now all we have to do is wait for some Google employee to play a Sony CD on this and these will become spam relays.

Perfect.

Hardware limits

Google's growth was in part made possible by heaps of commodity hardware. Hardware that was originally meant for standard lusers, cheap and unreliable. They built their systems for it and tolerate that. They change lots of haddrives in their datacenters and god knows what else.

What I'm trying to say is that for each of those googlecubes they need staff that regularly changes whatever hardware fails. With 3.5 Petabytes of storage and 5K processors it means that something will fail every single day that beast is powered. All that crammed inside 20/40 feet space (WTF does that mean?) means that heat will kill even more hardware.

So, yeah it should be possible, but not very likely.

Re:Hardware limits

With 3.5 petabyte storage and 5K processors, plus some smart software, taking offline one CPU or two harddrives will have hardly any impact. And when performance of given container drops by 3% (that is 150 nodes have already failed and are offline) they send someone to replace them. Or even not then, just a single truck running around the country replacing broken nodes during each visit.
Just like painting the Golden Gate bridge. There's a small crew of painters assigned to that work. It takes them 4 years to paint the whole bridge, but when they finish at one end, the other already requires repainting, so they start over. The bridge is never 100% "brand new" painted, but it remains in acceptable state at all times.

"Google Desktop" delivered via FreeNX?

With 300 data centers hosted at the important Internet peering points, and only 2-3 hops away from each user, Google will be easily able to offer a personal "Google Desktop" to each person, driven by FreeNX remote GUI technology (remember, NX can make X11, VNC and RDP run a multiple speeds with fractions of the bandwidth needed as compared to the protocols run natively).

Google will manage everything for its users: software upgrades, backups, search and organisation of personal data and files. Just like ISPs 20 years ago offered a monthly rate of 20 $US to connect to the internet (giving away a 2400 b/sec modem for a reduced price), Google could ask for a 20 $US fee (and give away a Google Thin Client embedded into a georgeous 17'' LCD screen that includes a EJ45 jack) to take care of people's computers.

I for one would sign in immediately.

So, Cringely is wrong. No need for AJAX office. It will all work with traditional GUI desktop programs, over an NX link that does not consume more than 40 kBits/sec for office productivity work.

So, Cringely is also right. The operating system doesn't matter to Google.

Not $500,000

Actually this article came in on my rss reader yesterday, I did some quick back on the envelope counting, and I'm not sure you can get a container for $500.000. I read before that Google used to have racks with wheels under them, completely full with 1U servers and fully cabled. They only had to plug in power and network and they were all set. When the datacenter went bankrupt, they just wheeled the racks off to another location. So assuming that they are only using the containers for shipping:

One 20Ft container is:

* Length (20Ft)
* Width (8Ft)
* Height (8.5Ft)

That means you can get about 12 * 19" racks in, using 4 rows, about 64U high. That means a total of 3072 servers, using dual socket, dual core opterons, that's 12288 cores. Each server with 8 memory sockets + 4 disks, that's 24,576GB of RAM (1G sticks) and 6,144,000GB of Storage (500G disks). With some guestimate figures on current prices, I'd say one of those container would be worth about $12,500,000.

But then again, from a quick Google, they have about $3 billion in cash, and that's a lot of containers....

PS: I'm european using metrics mostly, so they're might be a small conversion problem here and there ;)

When Google owns all our data access...

...will we still love them? I get a feeling Microsoft's monopoly will look like a minor bother compared to Google's omnipresence one day. Google, the Evil Empire?

Sounds like Cringely saw a Petabox

The Internet Archive's Petabox [archive.org]. is a petabyte of storage in a shipping container. Each rack holds 100 terabytes, and power consumption is 6 KW per rack. Capricorn [capricorn-tech.com] builds them for the Internet Archive.

Sounds like Google is trying that out.

There's nothing that exotic about this. The military builds racks of electronics into shipping containers all the time. It's mostly a cable management and maintenance access problem. You have to be able to do everything from the front of the rack, which requires some design work but isn't rocket science.

Shipping Containers can be problematic

Back in 1991 I worked for a wireless company that tried using data containers for quickly deployed cellular switch and cell sites. The idea would be to prebuild these at a central location and then drop them at areas where they needed to go up.

The idea was good, except for a couple of problems.

These shipping containers are nothing but a giant metal box. Grounding can become an issue, so can accidnentally having the box be one of of the poles for a DC based power system. If you are near an active AM tower, the box becomes a giant antenna and it's virtually impossible to filter out the AM signal internally.

Last, and certainly not least, these shipping containers are vulnerable to rust and other problems due to exposure to the elements. That can take several years (5 or so) if the box is in perfect shape at the start, but if they are using used boxes then it can take less than 2 years for rust holes to be a problem.

Plus, physical security isn't all that good unless the walls are beefed up.

I'm hoping these are not "standard" shipping containers, just something that looks like them.

This grand experiment with shipping containers for cellular applications was an attempt to make it cheaper to deploy equipment to new locations. And, shipping containers (especially used) were a _LOT_ cheaper than fibrebond or other prefab buildings for that purpose. Of course, the fibrebond building had a lifespan a lot longer than 2 to 5 years. So, you get what you pay for.

This is pure bullshit

What's this really about?

It's about that Google want to be able to move Google computers around in any datacenter asap. We know that google uses a grid of single computers, that all compute the search results as fast as possible. All these computers create a space-problem (physical space) at any datacenter that Google owns. Also, shipping these computers around costs money. I bet google store this "secret package" just to be able to send it around anywhere where there suddenly is a problem with the network.. We all know how much money google loose if they are experiencing downtime...

Cringley is wrong. Google is going ISP

Why then buy all the fiber ? There are areas of the country that aren't attractive to telcos/cable co.s.

I hope they succeed along with their WIFI access.

Good job boys.

One more point if anyone at Google is listening. How about a tax on chip companies to use this highspeed access. It would be nice if they could help support it since they are the ones who benefit.

Can't buy latency...

Cringley may be a fool, but he's almost right on this one. There's a saying in networking that you can't buy latency. The speed of light is just too low for Google's AJAX applications to take over the world - for many apps you can never get the latency low enough if you use only a few datacenters. So, the shipping container is irrelevant to the important part of this story. The key is that for Google to succeed in making online services as effective as desktop applications, they have to get the latency down. And there's only one way to do that, which is to move the servers close to the customers. To do that, they need a lot of data centers, and they need a lot of bandwidth between them, because when you connect they need to move your data to the nearest data center to you. So, they really do need to have a way to provide data centers quickly and easily to places all over the world. But Cringely doesn't seem to have realized why this is the only way Google can succeed in the long run. It appears you can buy latency after all if you spend enough. - Fzz