Beta

×

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

Thank you!

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

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

Is a Wireless Data Center Possible?

samzenpus posted about 2 years ago | from the we-don't-need-no-stinking-wires dept.

Microsoft 172

Nerval's Lobster writes "A team of researchers from Microsoft and Cornell University has concluded that, in some cases, a totally wireless data center makes logistical sense. In a new paper, a team of researchers from Cornell and Microsoft concluded that a data-center operator could replace hundreds of feet of cable with 60-GHz wireless connections—assuming that the servers themselves are redesigned in cylindrical racks, shaped like prisms, with blade servers addressing both intra- and inter-rack connections. The so-called 'Cayley' data centers, so named because of the network connectivity subgraphs are modeled using Cayley graphs, could be cheaper than traditional wired data centers if the cost of a 60-GHz transceiver drops under $90 apiece, and would likely consume about one-tenth to one-twelfth the power of a wired data center."

cancel ×

172 comments

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

There are still wires (4, Insightful)

laron (102608) | about 2 years ago | (#41661765)

Unless they plan to use microwave beams for power.

Re:There are still wires (3, Interesting)

michaelmalak (91262) | about 2 years ago | (#41661811)

Wake up Tesla

Re:There are still wires (4, Funny)

tjonnyc999 (1423763) | about 2 years ago | (#41662153)

...the Matrix has you.

ok, no wires then... (3, Interesting)

fyngyrz (762201) | about 2 years ago | (#41662953)

Within a data center, you could use $1.00 LED emitters and receivers with integral lenses for short runs, precision (but still cheap) alignment fixtures and $0.10 mirrors. For long runs, LED laser emitters. You'd still beat $90/point by a huge margin. And as a plus, you'd have some extremely high speed connections. Power consumption... I dunno, you'd have to do an analysis. One thing that seems obvious is that for any line not sending data, the LED should be off the vast majority of the time.

Re:There are still wires (5, Funny)

Anonymous Coward | about 2 years ago | (#41661839)

Let's just set up some servers in a room, blast 'em with every form of radiation known to man, and see what happens! Sounds like a fun weekend project.

Re:There are still wires (5, Funny)

Talderas (1212466) | about 2 years ago | (#41662061)

I'll be honest here. We're just kind of throwing science at the wall and seeing what sticks.

Re:There are still wires (0)

Anonymous Coward | about 2 years ago | (#41662211)

Isn't that the definition of science?

Re:There are still wires (0)

Anonymous Coward | about 2 years ago | (#41662321)

Volunteer for testing today!

Re:There are still wires (1)

MollyB (162595) | about 2 years ago | (#41662109)

No one's noticed the link to TFA is /. itself, "Business" something or other?
Aren't we s'posed to be complaining about that?

Re:There are still wires (2)

rubikscubejunkie (2664793) | about 2 years ago | (#41661975)

bigger question....how are the union guys going to bill for running wireless?

Re:There are still wires (1)

Githaron (2462596) | about 2 years ago | (#41662245)

The modern day version of The Emperor's New Clothes [wikipedia.org] .

Re:There are still wires (1)

Anonymous Coward | about 2 years ago | (#41662023)

Man, I never thought of that. Those guys at Best Buy ripped me off. They said it was a wireless router but I still need to plug it in! WTF?!?!?! Wires everywhere!!

Re:There are still wires (5, Funny)

Bill Dimm (463823) | about 2 years ago | (#41662147)

Those guys at Best Buy ripped me off. They said it was a wireless router but I still need to plug it in! WTF?!?!?!

Best Buy didn't make it clear that there were wires involved? What is the name of the sales associate who failed to offer you a Monster power cable for your router? He must be fired!

Dubius claims (0)

Anonymous Coward | about 2 years ago | (#41661773)

While I could see this being practical in some ways, I have trouble with claims like this:

"one-tenth to one-twelfth the power of a wired data center."

Are we re-defining physics now?

Re:Dubius claims (5, Funny)

maxwell demon (590494) | about 2 years ago | (#41661897)

They obviously mean computing power. Because the networking is so bad that all processes are blocked on I/O most of the time. :-)

Re:Dubius claims (1)

Tastecicles (1153671) | about 2 years ago | (#41663069)

Yeah, I had a bit of trouble with that as well.

Here's why.

I have a pair of 4U servers, each containing a 1000W PSU (for hard drives and fans) and a 450W (for the mainboard and everything else). That's shy of 3kW on servers which wouldn't fill a rack a quarter the way. The switch (24-port unmanaged) consumes 40W. That's about 1% of the total power requirement of the entire system. If I switched out for say a Linksys E3000 (7W) and the associated wireless interface cards (I'd have to go with USB since all my expansion slots are occupied with SATA controllers, so call it 5W a pop), I would save a staggering 23W (nowhere even close to 90% of the total power requirement of the system) and all of nine feet of copper, on top of creating a data security nightmare.

90% Power Savings??? (4, Interesting)

CajunArson (465943) | about 2 years ago | (#41661793)

Or Rlly? So a traditional datacenter is sinking > 90% of its power into the wired network connections? Not the actual servers themselves? Not the cooling? The wired network connections? I'm not buying those power saving estimates.

Re:90% Power Savings??? (5, Insightful)

Anonymous Coward | about 2 years ago | (#41661851)

Not exactly. 90% less for networking.

Re:90% Power Savings??? (1)

Tastecicles (1153671) | about 2 years ago | (#41663125)

not even close. Server NICs are generally integrated, wireless requires a dongle or card. That's extra power for each server. Even if you cut your switch power requirement by 75% there's still the problem of the extra power required by the interface cards, which at the very least will cancel out any power savings (which will be negligible anyway)

Re:90% Power Savings??? (0, Funny)

Anonymous Coward | about 2 years ago | (#41661873)

It's M$, so the extra power savings comes from the servers running on pure EVIL......

Re:90% Power Savings??? (0)

Anonymous Coward | about 2 years ago | (#41662091)

1999 called...

Re:90% Power Savings??? (5, Funny)

maxwell demon (590494) | about 2 years ago | (#41662125)

1999 called...

Oh my god! Did you warn them?

Re:90% Power Savings??? (3, Informative)

sconeu (64226) | about 2 years ago | (#41662787)

Source [xkcd.com]

Re:90% Power Savings??? (0)

Anonymous Coward | about 2 years ago | (#41662327)

Can you have them tell me to buy Google and Apple stock?

Re:90% Power Savings??? (0)

Anonymous Coward | about 2 years ago | (#41662959)

Is M$ some sort of weird way for complete morons to be able to write MS?

Re:90% Power Savings??? (1)

Anonymous Coward | about 2 years ago | (#41661877)

Switches, routers, firewalls, and the UPSs to drive them, use a surprising amount of power and generate a lot of heat that often goes unconsidered.

Re:90% Power Savings??? (1, Troll)

rot26 (240034) | about 2 years ago | (#41662119)

I don't think "switches","routers","firewalls","UPSs","drive","them","use","surprising","amount","power","generate","lot","heat","often", or "unconsidered" mean what you think they mean.

Re:90% Power Savings??? (1)

Anonymous Coward | about 2 years ago | (#41662729)

And they still will once we go wireless. What's your point? Maybe we can put it at the top of your science fair project.

Re:90% Power Savings??? (5, Insightful)

Anonymous Coward | about 2 years ago | (#41661917)

DNRTFA, but I imagine that the figure is quoted off of the networking equipment alone, without regard to any other aspect of the datacenter. I.e.: your actual network equipment footprint would shrink 20-30 fold, and that renders the power savings -- and while that is far from a majority of the power utilization of a traditional, large-scale datacenter, it is not an insignificant number in either physical space or power consumption.

That said, I doubt this is feasible without rethinking the datacenter design from the ground up. Simply rearranging the racks to minimize interference is not going to be enough.

Re:90% Power Savings??? (0)

Anonymous Coward | about 2 years ago | (#41662183)

Me netiher. Moving around a data center it's obvious what's eating power. You can feel it.

Re:90% Power Savings??? (1)

trashcoder (1839814) | about 2 years ago | (#41663231)

Maybe you should read the article. "The maximum power consumption of a 60GHz transceiver is less than 0.3 watts [43]. If all 20K transceivers on 10K servers are operating at their peak power, the collective power consumption becomes 6 kilowatts. TOR, AS, and a subunit of CS typically consume 176 watts, 350 watts, and 611 watts, respectively [9–11]. In total, wired switches typically consumes 58 kilowatts to 72 kilowatts depending on the oversubscription rate for datacenter with 10K servers. Thus, a Cayley datacenter can consume less than 1/12 to 1/10 of power to switch packets compared to a CDC. Besides the lower price and power, lower maintenance costs stemming from the absence of wires and substantially increased tolerance to failure can be a strong point for wireless datacenters. In summary, we argue that 60GHz could revolutionize datacenter construction and maintenance."

Mixed Signals (0)

Anonymous Coward | about 2 years ago | (#41661835)

They "could" be cheaper, but they use an order of magnitude less power? Doesn't that mean they ARE cheaper already, just there's an upfront cost to building them this way (which would be recollected through lower electricity bills over time).

Taking Bets (0)

Anonymous Coward | about 2 years ago | (#41661871)

I'm going to wager a big FAT no on this one.

Wireless is unreliable. I can't have my entire data center go down because the airport got a new RADAR system or some other electromagnetic interference extends a lobe into my data center.

Re:Taking Bets (1)

houstonbofh (602064) | about 2 years ago | (#41662949)

As someone who makes a living installing and supporting wireless data communications, and has done so since 97, this is totally laughable. Not to mention insecure as hell. And did I mention unpredictable performance? And how did they measure latency on a draft spec that is still a horse race between 4 draft specs? Looks like someone has a new buzzword for when "cloud" starts to wain.

Less power? (2)

anarcobra (1551067) | about 2 years ago | (#41661875)

Can someone explain how a wireless approach could use less power than a wired approach?
I understand that if you compare a crappy wired implementation to highly optimized wireless implementation the wireless might win out,
but then it would be cheaper to optimize the wired one.

Re:Less power? (1)

Anonymous Coward | about 2 years ago | (#41662243)

You don't need as much power because air has lower resistance (well, mostly capacitive resistance) than wires.

BUT

Wires are vastly superior - they are waveguides. And if you need faster speeds than via the 80GHz transceiver, why not just jump straight up into the 1e15Hz range and use short fiber optic (waveguide) connections??

Basically, they are saying, fuck the switched network business. Let's go back to coaxial-style network (ie. everything is shared) so we can save a tiny little power. And pray to god no equipment malfunctions and throws the entire rack out due to interference. Heck, old style level 1 hubs were superior networks than wireless!

Re:Less power? (2)

AK Marc (707885) | about 2 years ago | (#41662283)

Switches are inherently hub and spoke (even the last of the rings were physically hub and spoke). So you have to have the hubs (networking switches, but literal hubs). With wireless, you could mesh and reduce hubs.

Now, if we were to get switches better optimized for power (most seem to be going the wrong way, with even datacenter-class switches being PoE capable, requiring lots of extra power), then there wouldn't be a savings. Get switches that turn off ports and cores based on load and connections. Eliminate status lights. Negotiate receive power and decrease power based on line characteristics. But innovation stops when "good enough" is hit. And we are "good enough" so long as power is below $1 per kWh.

Re:Less power? (1)

fa2k (881632) | about 2 years ago | (#41662861)

You could get rid of some switches. Because 60 GHz doesn't penetrate through metal well, you can have your own little private network inside the rack cylinder without a switch. Each pair of computers could communicate on a separate frequancy, so you'd get the equivalent of a switched network (one coudl do full duplex to, by using more frequencies). The wireless approach would be more resiliant to failure too. You could use N! wires between the N computers instead, possibly using even less power.

For inter-rack communication, you'd get a mesh configuration where each computer naturally has a direct connection with some other racks, as the 60 GHz is approximately line-of-sight. You could probably install a switch instead of each wireless frequency used, to get better bandwidth and slightly worse resiliancy, and maybe higher power usage. I think that's the conclusion, that you can implement this with a reasonable number of wires, but you're more prone to failure because the switches can die. Or you can implement it with a ridiculous number of wires, one for each pair of servers that would communicate wirelessly, and you'd get an even better performance. Assuming you can buy NICs with 8 or more ports, of course.

Re:Less power? (1)

fa2k (881632) | about 2 years ago | (#41662891)

You could use N! wires between the N computers instead, possibly using even less power.

OK I promise not to use maths on slashdot ever again. It's not N!, it's N + (N-1) + ... + 2 + 1. It probably can be written more easily somehow.

Re:Less power? (1)

DragonWriter (970822) | about 2 years ago | (#41663099)

OK I promise not to use maths on slashdot ever again. It's not N!, it's N + (N-1) + ... + 2 + 1. It probably can be written more easily somehow.

N*(N+1)/2.

Re:Less power? (1)

YoopDaDum (1998474) | about 2 years ago | (#41663225)

N*(N+1)/2

Write the same sum but in the other direction just below the previous one, and sum both lines term by term. Notice you have N times N+1, and that's for twice the sum. So one half for a single line. A visual way to let a kid old enough to know multiplication tables to find it for small cases is to draw the sum as dots on a piece of grid paper as a rectangular triangle. Then double the triangle (symmetry on the long edge) and you get a rectangle where the number of dots can be computed with a simple multiplication.

Good luck with that. (0)

trancemission (823050) | about 2 years ago | (#41661891)

Even TFA is short on details, how fast is 60mhz? Last I looked the speed of light was quite fast....fibre is tried and tested.....

Re:Good luck with that. (0)

Anonymous Coward | about 2 years ago | (#41661967)

"how fast is 60mhz?"

It depends. Depends on the baud rate and how much bits per baud are being transmitted.

Re:Good luck with that. (2)

maxwell demon (590494) | about 2 years ago | (#41661985)

60 mHz means about 1 cycle every 16.7 seconds.

Just wait . . . (4, Funny)

smooth wombat (796938) | about 2 years ago | (#41661895)

until the wackadoodles who claim they get headaches from radio signals find out they're living next to a place which runs such an environment.

I can't wait to see the signs they use to protest as they stand outside in the blazing sun:

Stop killing us with radio waves!

Radio waves kill!

Save a life. Turn off your radio.

Re:Just wait . . . (0)

Anonymous Coward | about 2 years ago | (#41661951)

Save a life. Turn off your radio.

I totally agree! Turning off your receiver will totally block the radio transmissions!

Re:Just wait . . . (1)

maxwell demon (590494) | about 2 years ago | (#41662079)

Indeed, you have to do the opposite: Turn all radios on all the time, so that they can consume all those evil radio waves before they reach you. :-)

Re:Just wait . . . (1)

AK Marc (707885) | about 2 years ago | (#41662315)

Cheap receivers radiate more than the signal they are receiving. How else do you think radar detector detectors work?

Re:Just wait . . . (0)

Anonymous Coward | about 2 years ago | (#41662411)

Electromagnetic reflectivity?

Re:Just wait . . . (1)

BeanThere (28381) | about 2 years ago | (#41663451)

You don't understand how it works. Your radio causes vibrations and oscillations in the same magnetic harmonic frequencies as the transmission. These vibrations upset the natural rest state oscillation harmonics present in All Living Things, these negative and deathly vibrations cause cancer. Life Crystals oscillating in the same Resonant Frequencies absorb these energies and give off life-giving restorative vibrations.

LOL (1)

Nexion (1064) | about 2 years ago | (#41662425)

I'm getting cancer faster just thinking about it.

I doubt it (5, Insightful)

SuperMooCow (2739821) | about 2 years ago | (#41661903)

You can't have nearly infinite bandwidth in a finite frequency spectrum, but you can keep adding a shitload of wires if needed.

Given the problems people have when multiple wi-fi routers are too close together like in an apartment building, I am doubtful that it would work well in a server environment, not matter which frequencies are used.

Re:I doubt it (0)

Anonymous Coward | about 2 years ago | (#41661989)

The cylindrical hacks may be used to block the wifi signal to go outside of the hack. Therefore, the signal does not "leak" and the interference with other hacks would be minimum.

Re:I doubt it (1)

RabidReindeer (2625839) | about 2 years ago | (#41662483)

What I don't understand is what wireless brings to the table. The way it read to me, it was more a matter of having local "sewing circles" that were networked.

I liked the "sewing circle" concept, but why wireless? These are short distances. If you don't like short network cables, why not just use LED transceivers, instead? No wires to plug in when you jack compute modules in and out, (in theory) simpler circuitry, and as long as the cabinets are light-tight, no leakage issues. You could even put a big light up on top of the cabinet to be the transceiver for cabinet-to-cabinet networking.

Re:I doubt it (1)

mlts (1038732) | about 2 years ago | (#41662725)

Ages ago (early 1990s), there used to be a system like that for Macs. Aim one transceiver at an area (such as a wall or ceiling), aim another one at the same area, and they would notify you with a LED when the connection was working.

Just have little directional device from each host, have them all point at one area, and be done with it. If two devices just want to communicate with each other, find another piece of paper to aim them at.

Re:I doubt it (0)

Anonymous Coward | about 2 years ago | (#41662567)

What is a 'hack'?

Re:I doubt it (1)

timeOday (582209) | about 2 years ago | (#41662345)

You can't have nearly infinite bandwidth in a finite frequency spectrum, but you can keep adding a shitload of wires if needed.

On the contrary, any number of optical signals can pass right through each other, whereas cables (electric or fiber-optic) cannot do that. In other words, it's all a matter of how directional the signals are, and how powerful they are.

Re:I doubt it (1)

GigsVT (208848) | about 2 years ago | (#41662517)

Never heard of interference?

Cost justifications (4, Interesting)

hawguy (1600213) | about 2 years ago | (#41661943)

When the 60Ghz transceiver (which doesn't exist yet commercially) drops to $90 each, won't 10Gig ethernet drop down to $9/port, skewing their cost justifiication results? They mention using 4 - 15gbit transceivers... what's the aggregate bandwidth of a 60Ghz network? If the aggregate bandwidth is 15gbit, that's not going to handle a rack full of servers.

Re:Cost justifications (1)

helix2301 (1105613) | about 2 years ago | (#41662931)

I agree I do not think that cost will pay off electric to run the transceivers I mean a 7ft cat 5 is so cheap why would you spend the money if you have 3 ports on server 2 nic and ilo cost is a lot less for 3 cat 5 cables.

Re:Cost justifications (1)

TubeSteak (669689) | about 2 years ago | (#41663315)

When the 60Ghz transceiver (which doesn't exist yet commercially)

60 GHz exists right now for point to point communications.
You can get it on newer computers by looking for "Intel wireless display" aka WiDi
You can use it commercially with multi-gigabit speeds at ranges up to 1.5km (about a mile assuming good weather).

They mention using 4 - 15gbit transceivers... what's the aggregate bandwidth of a 60Ghz network? If the aggregate bandwidth is 15gbit, that's not going to handle a rack full of servers.

Talking about aggregate bandwidth for 60GHz is meaningless.
The only number you have to worry about is the maximum bandwidth of a single transceiver, because, unlike most current wireless offerings,
60 GHz frequencies are so directional that you can run multiple tx/rx systems on the same frequency as long as they're not pointed directly at each other.
And if you're using polarized antennas, you can run multiple signals on the same frequency, without any interference.

That said, unlike most current unlicensed frequencies, the 60 GHz spectrum is enormous.
The unlicensed 2.4 GHz has 84.5 MHz of bandwidth.
The unlicensed 5.8 GHz has 125 MHz of bandwidth.
The unlicensed 60 GHz has 7 GHz of bandwidth from 57GHz to 64GHz.

/I wonder how many library of congresses/second that works out to.

Interference (0)

Dainsanefh (2009638) | about 2 years ago | (#41661983)

Just make a jammer and that will render the whole data center paralyzed.

wireless is like the old layer 1 hubs (4, Insightful)

alen (225700) | about 2 years ago | (#41661987)

the traffic is sent into the air and its up to each receiver to filter the noise and ignore data not meant for it. lots of interference.

its OK for starbucks or for home use but not by much. i have at least 10 wifi networks around me that constantly interfere with mine. i used to get regular disconnects from x-box live that went away when i tried to connect my x-box to my router with Cat5 cable. same with video streaming.

this is why large events have crappy data speeds. everyone is broadcasting into the same air space and interfering with each other.

Re:wireless is like the old layer 1 hubs (0)

Anonymous Coward | about 2 years ago | (#41662121)

Not to mention we're always reading about how cellular networks are hitting problems because of a finite resource and many smart phone users trying to connect. You can saturate any link.

I can't even get a stable wifi signal in my house for two computers actively gaming on Diablo III or Starcraft II. Powerline or wired runs work. I don't understand the fantasy world where WIFI works some folks go on about. I buy apple equipment at home, not cheap stuff. It's only used for WIFI.

Similarly, we have massive problems at work with cisco business equipment. No, I didn't setup the work network, but I've used wifi spectrum graphs to see there are many wifi networks in the area. My work borders a residential area with a school and a few large buildings with wifi networks. My home is in a new subdivision with 8 other wifi networks near by. Changing channels has had little effect. There are just too many wifi networks. I think the article was trying to say the configuration of the racks would minimize interference, but it just seems weak. There's also the point of failures in the wifi base stations. It might be more reliable than wired runs in a carefully controlled environment, but it's still not going to be as fast. There's also security concerns about running packets over the air. Unless every server is on a VPN, I don't see how this is a good idea.

Re:wireless is like the old layer 1 hubs (2)

maxwell demon (590494) | about 2 years ago | (#41662179)

I buy apple equipment at home, not cheap stuff.

Maybe that's your problem. <gd&r>

Re:wireless is like the old layer 1 hubs (1)

niado (1650369) | about 2 years ago | (#41662285)

wireless is like the old layer 1 hubs the traffic is sent into the air and its up to each receiver to filter the noise and ignore data not meant for it. lots of interference.

Um, well, not exactly. They are similar in that they operate at half-duplex, but WAP's operate at L2 and L3 in addition to L1 (Wifi uses CSMA/CA [wikipedia.org] , vs. the CSMA/CD [wikipedia.org] used by switches). Interference can be an issue, but only in an uncontrolled or poorly-designed environment (Pro tip: don't put 2.4ghz wireless phones in your wireless data center).

Great! (2)

Alex Belits (437) | about 2 years ago | (#41662027)

I am so happy that Microsoft is doing that kind of loony shit.

Re:Great! (1)

Nutria (679911) | about 2 years ago | (#41662545)

Contrary to the popular belief, there indeed is no God.

Don't act like religionists and make absolute statements when you have no evidence for them. (They're the ones who are making positive statements and so must present the proof.)

Re:Great! (2)

Alex Belits (437) | about 2 years ago | (#41663141)

This is how science works. Statements about existence of anything, made without no evidence to support them are supposed to be treated as false unless and until such evidence is provided. With given evidence, it's much more likely that I am a four-headed lizard who lives in a volcano, than that any kind of deity exists, or ever existed.

Slashdot now stealing content (4, Interesting)

Animats (122034) | about 2 years ago | (#41662157)

So Slashdot is now ripping off other sites, copying their content to Slashdot-hosted pages, adding ads, and breaking links. [slashdot.org] The original article [cornell.edu] says "Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ANCSâ(TM)12, October 29â"30, 2012, Austin, Texas, USA. Copyright 2012 ACM 978-1-4503-1685-9/12/10 ...$15.00."

In the actual paper, the power consumption bullshit part reads "Power consumption: The maximum power consumption of a 60GHz transceiver is less than 0.3 watts [43]. If all 20K transceivers on 10K servers are operating at their peak power, the collective power consumption becomes 6 kilowatts. TOR, AS, and a subunit of CS typically consume 176 watts, 350 watts, and 611 watts, respectively [9â"11]. In total, wired switches typically consumes 58 kilowatts to 72 kilowatts depending on the oversubscription rate for datacenter with 10K servers. Thus, a Cayley datacenter can consume less than 1/12 to 1/10 of power to switch packets compared to a CDC. That's comparing transceiver drive power with a whole store and forward switching fabric.

It's also not clear how their "Y-switch" thing, which doesn't store anything, handles busy reception points. At some point, in a forwarding network, you either have to store packets or drop them. Or set up end to end channels first.

Re:Slashdot now stealing content (1)

aglider (2435074) | about 2 years ago | (#41662351)

Catcha!

Re:Slashdot now stealing content (1)

AZURERAZOR (472031) | about 2 years ago | (#41663111)

Not sure that a link with a brief synopsis constitutes a copy... IANAL, but that seems like a stretch.

Re:Slashdot now stealing content (1)

Culture20 (968837) | about 2 years ago | (#41663307)

Do you know for certain that /. did not get prior specific permission and/or pay a fee? Maybe Dice got permission and/or paid the fee?

Cancer? (5, Funny)

Anonymous Coward | about 2 years ago | (#41662185)

Hopefully they will also pass out those cancer detecting bras to all of the staff members as well.

No way! (3, Funny)

aglider (2435074) | about 2 years ago | (#41662207)

The overall amount of radiating energy involved would make a datacenter technician ... medium well.

Good Luck Troubleshooting.. (0)

Anonymous Coward | about 2 years ago | (#41662249)

seriously anybody that does this is just crazy

Less secure? (2)

kheldan (1460303) | about 2 years ago | (#41662257)

Even with careful planning and management, wouldn't a completely wirelessly-networked datacenter be more of a target to hacking? Even with a high level of encryption, which would add to network overhead?

Re:Less secure? (0)

Anonymous Coward | about 2 years ago | (#41662605)

You can shield (i.e, Faraday cage) the room the servers are in, but you'd still be prone to attacks from the inside.

Re:Less secure? (1)

camperdave (969942) | about 2 years ago | (#41662631)

The datacentre would be inside a faraday cage, so no signals would be getting in, or out, except through the external (presumably fiberoptic) data links

Re:Less secure? (1)

na1led (1030470) | about 2 years ago | (#41663045)

I'm sure the network side of things would be secure, but I'd be worried about invisible radio wave attacks that could come from anywhere. A satellite, or parked van could essentially kill the whole network if they focused enough wattage at the data center. Not to mention other interferences like solar-flares.

Two to three mistakes in half a sebtence (0)

aglider (2435074) | about 2 years ago | (#41662331)

A team of researchers from Microsoft...

Microsoft designing new datacenter technologies? What if the results are similar to Windows 95 or Vista?
Microsoft doing research? Weren't they just "ruling" the market?
"Team" means a group of individuals joining the efforts in order to achieve a goal otherwise unreachable by each single person. I am not sure whether Microsoft can accommodate such a thing.

Re:Two to three mistakes in half a sebtence (1)

maxwell demon (590494) | about 2 years ago | (#41662553)

"Team" means a group of individuals joining the efforts in order to achieve a goal otherwise unreachable by each single person.

No. "Team" means a group of individuals working together. Not more, not less. They usually do so to achieve a goal, but that's not part of the definition. And it's definitely no given that a single member of the team couldn't achieve the goal.

Quantum communication (1)

aglider (2435074) | about 2 years ago | (#41662383)

Will be the solution. If only we dared to wait for the technology.

so-called (1)

mfwitten (1906728) | about 2 years ago | (#41662399)

so-called [princeton.edu] : (adj) alleged, supposed (doubtful or suspect) "these so-called experts are no help"

Umm...Wireless security has a cost. (1)

Green Salad (705185) | about 2 years ago | (#41662427)

I wonder how robustly Microsoft plans to address security at a wireless data center. In many data centers, wireless devices, even encrypted ones, were simply forbidden and twisted pair was inside physically locked metal conduit. Most security schemes for wireless transmission will involve more overhead on CPU, memory, transmission and therefore, energy, air conditioning, floor space, etc., not to mention a staff division related to spectrum monitoring & analysis.

On the other hand, if the data center is merely for storing consumer's account information...[ rimshot ]

Re:Umm...Wireless security has a cost. (1)

confusedwiseman (917951) | about 2 years ago | (#41662707)

Just make the data center a Faraday cage for security. No encryption needed! It would also keep the interference out!

ARTICLE COURTESY OF FOX NEWS (1)

partyguerrilla (1597357) | about 2 years ago | (#41662441)

...Is this real life?

Re:ARTICLE COURTESY OF FOX NEWS (0)

Anonymous Coward | about 2 years ago | (#41663149)

...Is this real life?

Is this just Fantasy?

Unmanned data centers, I assume? (1)

SuricouRaven (1897204) | about 2 years ago | (#41662459)

60GHZ would barely get through a wet tissue. You could track the location of the technicians by watching the server-down warnings move around.

Burritos (3, Funny)

djhertz (322457) | about 2 years ago | (#41662607)

It'll be cool when somebody microwaves a burrito in the lunch room and random servers drop connection. 3.. 2.. 1.. ding! Hm, server connections are back.

duh. (0)

Anonymous Coward | about 2 years ago | (#41662711)

Did some work on this in the late '90s-early 00's, based on UWB tech, before 9/11 paranoia, petty greed, et al. shit all over my finances. Chip maker clammed up about datasheets, etc., too, for some reason. The nice thing about wireless interconnects, though, is you can have a much broader range of network topologies. Very useful for massively parallel architectures.

   

Re:duh. (1)

kasperd (592156) | about 2 years ago | (#41663359)

The nice thing about wireless interconnects, though, is you can have a much broader range of network topologies.

Not really, no. Want two nodes connected in your network topology, just pull a wire or fibre between them. Requires lots of wires, but it is going to be better than wireless on throughput, latency, and reliability. Wireless is useful for devices that are constantly moved around. For anything stationary, pulling a wire is a better long term solution. And I assume servers in most data centers are considered stationary.

I know people who'd love to see wireless data centers become a reality (assuming they don't have to debug new problems). But I consider it to be a pipe dream. Wireless will never catch up with wired networks, because any wireless technology could be turned into something more reliable by using some sort of wires to ensure the signal gets where you want it, and not everywhere else.

Optical? (1)

edelbrp (62429) | about 2 years ago | (#41662721)

I was always a bit dubious of the infrared based wireless networking (like IrDA) for an office environment, but what about optical wireless in a data center? Seems like that would solve the potential security issues and you could isolate racks (or parts of racks) on their own wireless network and then do the traditional wired scheme to join those nodes together so that you weren't stretching the bandwidth too thin?

This is obviously the way things are going anyway (1)

jeffmeden (135043) | about 2 years ago | (#41662777)

These days, with VMs (and hence software switches) carrying the actual workload, and hastily programmed core switches broken down into a hundred VLANs, why are we hanging on to the ancient notion of "wires"? Clearly a wireless method for every server to be able to talk to every other server is the next logical evolution. Just sprinkle a little software on top to make sure that the servers only see/process what they are supposed to, and surely it will all work great!

Re:This is obviously the way things are going anyw (1)

adri (173121) | about 2 years ago | (#41663195)

Problem - 60GHz is currently very near-space wifi. It's also what, a couple of gigabit worth of bandwidth. Also, I haven't seen any studies yet looking at 60GHz saturation and lots of multi-path reflection. It's a cool technology but it does read like someone's trying to sell the tech, rather than really being suitable for it.

Bulll.... (0)

Anonymous Coward | about 2 years ago | (#41662907)

$ hiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiitt

WTF Is This Drivel (1)

Revotron (1115029) | about 2 years ago | (#41662965)

Hey, I have this awesome idea, let's take out all those expensive copper wires and make our data center wireless. It'll save so much money! But first we'll have to redesign racks to be cylindrical and servers will need to be keystone-shaped. Also, because of the new rack design, you won't have access to rear ports. If something in the center of the rack comes undone or stops working, you need to open the entire rack. And each rack will have to be a faraday cage so the signal doesn't leak out and collide with other racks. And each rack has to share the bandwidth. And servers will lose their connection every time a mouse farts. And you'll also have to devise a new cooling method because hot/cold-aisle won't work with a bunch of cylinders.

Just think of the simplicity and savings!

Wireless Security (0)

Anonymous Coward | about 2 years ago | (#41663445)

Would this be a security problem? You could stand outside a data center (or use a direction antenna from a further distance) and sniff internal network traffic.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?
or Connect with...

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>