Slashdot Mirror
Why We Don't Need Gigabit Networks (Yet)
AmyVernon writes "Most computers today can't support gigabit connections and current Wi-Fi networks can't offer those speeds either. The first trial of Sonic.Net's gigabit network was a speed test on a generic laptop that showed off 420 Mbps down; the laptop couldn't handle a full gig. Plus, few applications need those speeds. It's hard to justify such a huge investment in a network that will have few subscribers and few applications that need it. Of course, that can change, and then these networks will be vital. This story has a good analysis of where things stand and what has to change."
Gigabit networks are important when working with almost any kind of file copy. I am not sure the last time someone tried to backup even just 100GB of data (Think backups) over a 100 megabit network. Copies like that can take for ever a fully saturate 100 megabit network and slow down traffic for everyone. While copies over gigabit rarely use the entire pipe its good to know that there is still bandwidth left over for other tasks.
How DARE you say we don't need faster networks! This article should be purged from the interwebs and timothy should be strung up by his gonads for even considering posting it!
I am not sure how "one does not need a gbit connection". Even a small file server in 2006 could output more than 70MB/sec (practical test on large files).
I have 2 computers, a ps3, and a wii connected to the net. even if I am doing something simple like streaming a movie from one computer to the ps3 to watch on my tv while someone else is playing a game online, downloading something or the other, or just generally using the web to watch anything in HD, I could easily find a use for that bandwidth.
I think the gist of the article is that we don't need gigabit connections from an isp to the home. While that's debatable, that's not the same as saying that gigbit networks within a home or office are not necessary.
Well.. maybe. Or Maybe not. But Definitely not sort of.
My sentiments exactly. If you build a (vastly) faster internet, the hardware will be ready for it long before you actually have it to the customers doors. And yes. we do need it. Why? because the vast shift towards streaming all media content is going to murder the shit out of the current system. If a customer can download an entire HD movie in seconds, that frees up the network in general, instead of slowly moving the file over the course of an hour. The streaming model can die the death it deserves at that point.
I've decided to Diversify my Holdings. I've divided my cash between my left and right pockets, instead of all in one.
What do you mean "speed test", we've had gigabit broadband for some time in Sweden. It costs about 900 SEK/€100/$140, you can order it here: https://order.bredband2.com/index/products/cOrderType/broadband/iCitynetID/768537
Not available in all cities of course, but still. Not much news with gigabit broadband.
And that WiFi and most peoples computers, let alone routers are unable to push those speeds is not newsworthy either. At least not at /. ...
The reason this post is stupid is that infrastructure is long term. When you go to the trouble of sending out a crew to dig up and put fiber in the ground your putting in an infrastructure asset that should have a 15-30 year lifespan. The fact that can average machine can't saturate it today means we're being forward thinking.
... and 640K computers.
Build a faster network and someone will invent more devices to connect to the network to shove around data that they don't need.
Schroedinger's Brexit: The UK is both in and out of the EU at the same time!
The problem is that TFA was not correctly edited.
1. She's talking about gig connections from your home to your ISP.
2. She's mixing wired and wireless.
3. She mixes gig and 100Mb/s.
4. $40 for 100Mb / $70 for gig is NOT a lot of money.
5. She's wrong. Computers today CAN handle a gig connection.
6. So what if the cheap router/firewall/whatever you have cannot handle a gig connection (it can probably handle a 100Mb/s connection)? That's the easiest piece for the consumer to replace.
7. The apps that would use it TODAY are things like streaming media. Getting the WHOLE movie or song or whatever 100x faster means fewer delays from the consumer's point of view (perception).
If I could get gig speeds here in Seattle for under $100 I would certainly do it.
not everyone keeps/needs a server at home.
The misconception that people would have no use for a home server has led to prevalence of highly asymmetric Internet connections suited more to a spectator culture than to a participatory culture. Have you heard of the FreedomBox?
Plus, few applications need those speeds.
That, I can agree with. How many high def uncompressed live video feeds can a household watch?
For example, ATSC "over the air HDTV" is only 20 megabits/sec, so I could watch 50 HDTV channels simultaneously...
"Science flies us to the moon. Religion flies us into buildings." - Victor Stenger
FTA:
"So we’re stuck at a point where a gigabit — or even 100 Mbps – sounds awesome, but it’s not exactly worth the prices most companies want (or need to charge). This is why Google’s and Sonic.Net’s plans to expand moderately priced 100 Mbps and gigabit networks will be so important."
The summary to this article is misleading. It led me to write a mini-rant about the usefulness of gigabit LANs. In fact, the article's talking about gigabit WAN connections at the home. Their denouncement has the tinge of that old Microsoft exec quote about the internet being a fad and no one needing very much ram.
FTA:
“If every consumer has 100 Mbps, we’d have some better applications,” Jasper said. ” At 100 Mbps, high-def video conferencing becomes a reality and you don’t need local storage anymore. You don’t even need local computing.”
You went from talking about gigabit WANs (at the corporate level), to the use of fast ethernet WAN at home. Somehow, there's a use-case at the home that isn't there at the corporation.
And this made /. frontpage, why? Can I get a +5 comment simply by using the words "100 mbps, gigabit, ethernet, 802.11[n-z], important, high-def, local, storage, computing" ?
PS: I don't reply to ACs.
is not for one computer to saturate it, but for 10 machines to get decent throughput simultaneously.
As the island of our knowledge grows, so does the shore of our ignorance.
"640k ought to be enough for anyone." "There is a world-wide market for about fifteen computers."
Time and time again people have been deeply mistaken about anything having to do with the future of computing. The first time I saw a VGA display I was so smitten that I thought "this is the best it can be". Well I was wrong and so were a lot of other people who thought that there would never be a need for something more advanced than what technology has to offer today.
We expand technology by pushing against the current limits, finding things that cannot be done as the technology exists today and figuring out how to get it done and then proposing that solution as a standard. Meanwhile someone else has found a different solution and they too have submitted it as the standard. Then the wrestling begins perhaps one solution is accepted or maybe the solutions are married or an entirely different standard is found or maybe everything is rejected and they become proprietary products.
I'm 55 years old with lots of gray hair yet I still hold out hope that before I die I will be able to play, just once, in a holodeck, maybe with someone overseas. That could require something more than gig lines.
Shared networks work best if they are unsaturated. Having a very fast network is a simple way to achieve that without having to sweat bullets over how to enforce fairness in the sharing algorithms.
Getting the WHOLE movie or song or whatever 100x faster means fewer delays from the consumer's point of view (perception).
From the consumer's point of view, what's the point of downloading faster than one can listen? I can see only two reasons: 1. to skip around in the file, which could be handled with out-of-order downloading techniques such as HTTP range requests; or 2. when a handheld media playert will soon be moved out of reach of a fixed Internet connection (the download at home and watch in back seat/bus/train/plane scenario).
So, just because a single "generic laptop" was sold with a crap GigE card then no one should be able to get such a connection?
It looks like a desperate attempt to bullshit their clients into believing that they want what they really want but the ISPs don't want to provide, and instead what they really want is what the ISPs is already providing. It's the "640kb is enough for everyone" shtick, but bullshittier.
Slashdot, fix your code or at least hire someone who is competent at it to do it for you.
When you wake up to the obvious facts of 1999, let me know, and I'll give you an invite to the 21st century. Cuz I'm k3vvL and rollz like dat.
Shoes for Industry. Shoes for the Dead.
So useing 1 system and a laptop for that is a poor test.
Why not test a desktop system? A system with a SDD?
Test with 2 systems on the same link at the same time?
There's no point in having gigabit networks, network cards can't handle that traffic.
There's no point in having network cards handle that much data, networks don't have that kind of capacity.
Why the hell do you think you're entitled to say what we need and what we don't need?
Idle, anyone?
The streaming model can die the death it deserves at that point.
Streaming is still the only model I can see for live events such as news talk shows, sports, scripted sports (e.g. WWE PPV), concerts, and the like where viewing begins before the whole video has even been recorded.
Time to recycle those old Novell Netware licenses !
The Cloud - because you don't care if your apps and data are up in the air.
"I think there is a world market for maybe five computers." - Thomas Watson, chairman of IBM, 1943
Most of the systems out there already download faster than you can watch / listen to the content.
But they still have issues where there are delays and the play-back has to pause and "buffer" more content.
Simply put, the longer the download process is (all the way down to receiving the packets a microsecond before playing them) the more likely it is that something will cause packets to be lost or delayed and the system will have to interrupt the customer and "buffer" more data.
With higher speeds, if you can download a 2 hour movie in 10 minutes you won't see any Internet-based delays for an hour and fifty minutes. Which makes for a better "customer experience".
100 Mbps and 1,000 Mbps costs the same. Both require FTTH and the expensive part is the fiber. The equipment to run gigabit on that fiber is almost the same cost as 100 Mbps equipment.
Gigabit internet is also not expensive. It turns out that most people do not use huge amounts of bandwidth just because it is possible. They will take advantage of faster download and upload speeds. They will do offsite backups. But since that backup now is 10 times faster it takes 10 times shorter. When you are done, someone else can use the bandwidth. With enough people it evens out.
I live at an apartment complex with a shared gigabit fiber. We have about 1000 active subscribers on that fiber. The average bandwidth used is approximately 100 Mbps and peak is about 300 Mbps (measured in 5 minute intervals). We never get near the full gigabit even though it is available. This does not mean it is useless. It is very useful to be able to download that ISO and not have to wait.
There are lots of use cases and more will come by each day. The major blocker right now is not that my computer is too slow, but that the servers out there usually are not able to deliver at those speeds. That will change when more people are able to take advantage of greater speeds.
Our apartment complex was able to buy a bulk gigabit fiber and share the cost. If you want to buy gigabit, even if FTTH is available in your area, they will rape you hundreds of dollars a month. Do not let this fool into thinking this is the real cost of gigabit internet. This is just what they can get away with because there is almost no competition on high speed internet. There is an issue if someone tries to run a commercial high bandwidth service on your gigabit offering. But for most customers offering gigabit is not one cent more expensive than offering slower speeds.
There are about 200 people who use my department's network at any given time during the day, and maybe 50 at night. All the desktops have their filesystems mounted on NFS, and people routinely upload or download large datasets. Gigabit networking is not even fast enough for what we do (yet somehow we have trouble getting that much installed).
Palm trees and 8
And other bloated tech.. and we will never need it.
---- Booth was a patriot ----
GigE comes on nearly every new computer. Consumer GigE routers and switches are marginally more expensive than their 10/100 equivalents. Most home media appliances are GigE. Nearly any home NAS you can buy has GigE. Most Cat5e cable can handle GigE speeds. Why would you bother buying 10/100 equipment? Even if your ISP isn't yet capable of it, there is plenty of application for it in the home, and it's conceivable that consumer-grade services provided by US ISPs will break the 100Mb barrier in the next five years, which isn't an unreasonable life expectancy of any of the aforementioned equipment. Say nothing of the benefits of GigE in small business and enterprise.
Flatulent, unwashed, blind and deaf elephant in the room is more like it. Not to mention a dumb article.
If God had intended man to fly, he would have given him wings.
Seven puppies were harmed during the making of this post.
From where I sit on a consumer cable connection it isn't about max speed, it's about being able to carry the current customer load and no caps.
So if a Gigabit network would solve or at least alleviate those issues then it is justified, the corps can't seem to figure out a way to charge you more for giving you what they initially promised to start with, so apparently it isn't justified from their point of view.
"If any question why we died, Tell them because our fathers lied."
With faster networks you can download an entire HD movie is much less times than it takes to watch it. By clearing the intertubes of so many low speed connections it makes it easier to route information through it. Faster networks makes so many things that are difficult now trivial. Try providing decent network access to a small apartment building or teleworking with largish datasets. 640 kbps is all anyone should ever need.
As a Virgin Media customer, I need gigabit internets as the upstream will be ( if the ratio is similar to my current service ) 60Mbit.
They whose government reduces their essential liberties for temporary security, receive neither liberty nor security.
Living sustainably on a healthy planet?
...you don't need something is usually looking to take something away or prevent you from acquiring it.
When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
I remember reading a PC Magazine review back in early 87 or so, talking about the recently released Intel 386 processor.
(paraphrasing) "No one needs that kind of speed at home. This is strictly for business servers."
Speed it up, and they will come.
Eh.. nothing wrong with the streaming model, as far as network bandwidth goes, and there are advantages for things that lots of people are trying to get: under the streaming model, you can use multicast a little better. For instance, if something just needs to be downloaded, you can multicast it in a continuous loop and clients can assemble the pieces in the right order at their end, waiting until they have enough to finish.
Or you can have multiple streams staggered (for say, video), so that people can join in at almost any time and get on a stream.
The other advantage of streaming is that if, say, a client is downloading video and the user decides halfway through to stop watching, you don't have to send any more bits.
Can you be Even More Awesome?!
This is like saying back in the dialup days "who needs speeds faster than a T1? It's not like the text is going to get read any faster"
Going to faster throughput makes other things possible that previously weren't.
I don't see the Koreans or the Swedes giving up their fast-as-shit-through-a-goose internet connections because "they don't need it."
--
BMO
This is the most pathetic excuse for an article ever posted by Slashdot. It's complete bunk.
Gigabit NICs are standard equipment. Just because a single machine can't saturate the link due to other IO bottlenecks doesn't make the technology premature or useless. It just means you've got a really, really crappy laptop.
I do not fail; I succeed at finding out what does not work.
This ignores the two principal problems... Latency, and MTU.
Gigabit ethernet connections can use 9KB MTU, My 100Mbps link between Montreal and California can only get 12Mbps. Owing to the 75ms latency.
This is why CDN's (like Amazon, Microsoft, Akamai, etc) are necessary until the endpoints have these high speed connections.
If ISPs offer these at reasonable prices, they will probably add a data cap--like Comcast's 250 GB data cap--much like the new 4th Generation mobile networks, which have a 2GB, 5GB, or 10 GB data cap.
'when for today’s applications, a cable modem offering 12-14 Mbps down will do just fine?'
So we can get better applications. So Netflix can stream without butchering the content like it currently does. Because you really have to worry about multiple users and aggregation. You can really see this with GoToMeeting and WebEx: I don't care what their service claims are, every time we have more than a couple people on a meeting the voice and video are crap.
How about the up being much more constrained than the down? That's not a problem for streaming video in, but is for other applications.
'You don't need more than 12-14 Mbps down because that's all we have today' is a blisteringly dumb argument.
I'm not actually sure theres been any computers for a better part of the last 7 or so years sold without Gigabit Ethernet. Routers and Switches are another story mind you. And it just so happens that IPv6 is a repeat story of that.
"It's very interesting, but I cannot foresee any practical application"
etc etc blah blah blah.
... broadband and on and on.
My organization is on the verge of needing to move our equipment to 10gig soon, because the 1gig network is starting to become a serious bottleneck...
Gee... what third world country or year is the OP posting from??? My workstation, built in 2007, supports GigE and is capable of speeds nearing the theoretical limit, just as it can on a 100Mbps link. I also have several of my servers connected on the same GigE VLAN. As for 10Gig... my old employer had racks and racks of servers which we tested and found to be able to use a significant portion of a 10Gig link. Of course, these systems were using NICs which were at the time (about 2 years ago) running about $700 ea., and connected to switches running about $20K each... but when you build a super computing cluster (to which we had a dedicated 10Gbps connection to the NLR)... you don't skimp on your infrastructure.
Helping build UN*X and the Internet since 1981.
The article is really talking about WANs/ISPs, not networks in general. I don't blame the submitter, though, because even though you can glork from context that this is what it's talking about, the author kept generally referring to "networks" (with a few exceptions).
My first guess is that this isn't an error, but rather someone pushing the religion of "the cloud," where it's presumed peoples' own computer don't do anything but download stuff from outside their home. Talking about last-mile networks and LANs as though they are the same thing, would fit that agenda.
Once you get away from that and back to the real world, though, the idea there are no applications for gigabit networks is a laugh. The lowly "cp" command is one application that comes to mind... I can tell you right now that 802.11n is easily three orders of magnitude higher than the limit of human perception, where I sometimes think "Hurry up" (not that I expect much from wireless -- did I ever mention that I hate my home's LAN? Stupid solid walls!).
I have heard this argument so many times before, but it is just stupid to say: You can only use 400MBit, so better keep your 100MBit instead of getting that full GBit, as you would not be able to use it fully. It might not be 10 times faster, but it still is 4 times faster, which might well be worth the price to some.
Speed is not important, latency is. And even more so are the current problems with buffers.
Here is a presentation on the subject:
http://www.youtube.com/watch?v=qbIozKVz73g
Here is the website which deals with the problem and is trying to fix any problems in Linux (drivers and TCP/IP stack):
http://www.bufferbloat.net/
New things are always on the horizon
Obviously, you plug the Gigabit Ethernet into a router and serve multiple computers with Wi-Fi and Ethernet. Then you can run Netflix all day in the living room and still have fast access from other systems.
And all Macs have had Gigabit Ethernet since the turn of the century, with the exception of older MacBook Air models that don't have Thunderbolt. That is a lot of data heavy users, video people and so on.
And any machine with Thunderbolt or PCI-Express has a faster connection than Gigabit, so the idea that Gigabit is too big for today's computers is not right.
For once can we not get the damn network in place and let everything else fall in line later? It'll make the transition much nicer than waiting until everything else is in place and waiting for the network bottle neck to go away.
I wholeheartedly agree. The whole point of Gigabit is that one computer can't saturate it. You don't want any one transfer saturating a network.
While a full gigabit on my notebook would be a hog, not just a waste, something more than 100 mbps wouldn't be bad at all, and there aren't many standards in between 1 gbps and 100 mbps.
And, most important, even though one notebook doesn't need a full gigabit, I want the whole pipe coming to my house. Because I want to use my notebook while someone else is using theirs and we're both streaming HD video while the TV is streaming HD video and we're doing all this HTML5ish interactive crap in other windows.
When the choice is "gigabit" that's *only* 420MB of 10/100 that's maybe 70...
YEAH! I'll go for the 420MB connection saying it is gigabit.
When I'm pushing gigs of files over my network I want it to happen as quickly as possible so the network resource isn't choked for hours at a time.
But NOOO!
WE DON'T NEED NO STEENKIN' GIGABIT!
*Cue everything in the omniverse with both a face and a palm facepalming at the same exact instant.*
Chas - The one, the only.
THANK GOD!!!
What I find most telling about the article is that they tested the connection using a single consumer grade article.
I'm techy enough to be on /., but I don't spend too much time at home living in a high-tech wonderland. However, on the network at home we have the following devices:
5 iPhones (view 2 wireless APs)
4 laptops
1 desktop
2 XBoxes with live
Wii
Roku box
AppleTV
All those devices stream media from the internet, play games on the internet, etc. That one single laptop can't handle the connection is fine, but as a household between myself, my wife, and kids, we do cumulatively use a lot of media. Have kept our unlimited data plans for the iPhone, my son has peaked at 8Gb in one month of data usage over 3G. That's on a single phone.
Between video chat, games, working remotely and streaming a desktop session, netflix, hulu, amazon video, etc there is a huge amount of bandwidth required at home. I find that Verizon FiOS does a great job. I can't stand the company, but the product is top notch.
Yes, I'd love more bandwidth at home, just treating a home network connection as a single device is rediculous. I want everything in the house to be networked, and controllable.
Or put it another way, i can get over 4x the throughput, and future proof my network by going gigabit. It's a no-brainer. Particularly if i want to connect to something over iscsi.
I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
My old notebook - a Tecra A8 - had a GigE ethernet connection. Many times when I wanted to move a few gig of data, I would skip the Wifi and connect directly to the ethernet. Linux never had a problem reaching high transfer speeds.
It finally came time to upgrade to a new laptop, and to my horror I discovered that many of the manufacturers aren't including GigE any more, because they seem to think Wireless N is enough. Under ideal conditions, I still have to wait a lot longer to transfer large files onto my new laptop than I did with my old.
My whole computing life I've been used to watching things get faster/smaller/cheaper, etc... this is probably the first time I've had to suffer a downgrade because of an upgrade.
Um, probably not. He's rolling out fiber in my town of 7000. But it's also his business to know whether it's really going to be saturated so they can do the right network on the backend. Sonic.net is a pretty kick-ass ISP. They instituted outbound SMTP blocking. But they noticed I'm running my own SMTP server and sent me an email saying they weren't blocking SMTP to/from me, but I could enable/disable it just by visiting my member account page. Also, they just rolled out free fax numbers (gateway to PDF/email) and outbound faxing for everyone.
Awesome furniture, accessories and cabinetry in Santa Rosa, CA: http://humanity-home.com/
Of course the summary leaves out the part of the conversation where bandwidth is also a measure of well, bandwidth. Just because one single individual device can only get ~500MB does not mean that GbE is worthless. What if there are two laptops sharing that connection? It will be tapped out. Put another one on there and all of a sudden a one gig pipe is not big enough.
How stupid are people, really?
Wrong, wrong, wrong. If you don't want at least a gigabit Internet connection and a 10gig LAN, you're probably a grandma reading this on an iPad.
"When information is power, privacy is freedom" - Jah-Wren Ryel
It's nice to see that kind of speed being sold to the public. Really. And I would be one of those who would pay for it (never mind the benefit, just being able to have it is enough for me -- but that's beside the point). However, once you really look into it, it would be better to have the following: a) Decreased latency. This also goes for the need to be able to cope with everyone maxing out their connections and the amount of packets dropped due to overflow (too many packets too fast) be around 0.00.............1% b) Increased Upload Speeds. This is one that bugs me the most. While downloading works great (you only need to tell the other end "got it"), when you have to send information, or there are too many people using internet, even if you have the awesome speed of 1Gbit DOWN, you won't enjoy it. Fix those two points, and THEN we can talk about increasing what you offer to customers. Oh yeah, don't forget the hardware to deal with it.
I don't care if I'm wrong. I only care about everyone obtaining something from the discussion.
it's also his business to know whether it's really going to be saturated so they can do the right network on the backend.
Naw, that's Jasper's Engineers' business to know. As CEO, it's Jasper's business to swim around in a pile of money like Scrooge McDuck.
All I know is, working at home, if I -could- get a 1Gb connection here where I live, even at the $300 a month Chattanooga is charging, I would do so in a heartbeat.
If you have sufficient bandwidth
Except one is unlikely to have sufficient bandwidth. Home users MUST NOT exceed either of two data rates: the advertised "burst" rate, measured in megabits per second, or the average rate buried in fine print, measured in gigabytes per month. Both must be improved, and from what I've seen, home users in the United States will continue to have insufficient bandwidth for the foreseeable future.
The current mentality of hoarding everything on LAN connected disk is simply due to the fact that we have insufficient reliable bandwidth available.
That and it's a lot harder for a publisher to "recall" a work stored on the end user's machine. Cases of this happening (such as Nineteen Eighty-Four on Amazon Kindle) are newsworthy.
I have a computer, my wife has a computer. My daughter has a computer. If they all slurp .4 gig per sec, that's more than a gig.
Yes, the chances are we won't all be needing as much as we can possibly get at the same time, but .1g because we can only do .4g? Who's the brainiac arguing for this?
A. Computers keep getting faster, and all three machines will be able to slurp 1g in just a few years. Telcos should wait until it's a painful need before acting? (Oh, wait, that's been the model since telcos got into the ISP business: do nothing, get kickbacks from the government for doing it, screw the poor and lie. Skip this point.)
B. When we do need it at the same time, we're annoyed. Better to have more capacity than too little.
C. It seems like the alternative to 1g is not 400m, it's 100m. So we should pick
I used to think this this limit existed - for home use, I hit a wall at full HD video streaming - you'ld only use ~30Mb. Some mention torrent packages - but the actual utilization of this package would still hit the same limit, making the download process redundant. However, if distributed computing (REAL cloud computing - so memory, processors, applications and data are essentially 'out there') becomes real, 1Gbps would get very slow very fast. For now, just give me a game that utilizes realtime streaming of application binaries, and high quality assets over the Net and I'll be happy. Other than games, I'm at a loss as to what these monstrous home applications could be. Anyone?
But yeah, I'm a 'wait and see' on Thunderbolt.
As long as we have these pesky bandwidth caps, there is no need or point for gigabit to the net.
Sig for hire.
It looks like you didn't comprehend the article one bit if you read it at all. Jasper was only quoted a couple times and his only point was that there is a cat and mouse game of networks not wanting to grow without apps that force them to and app developers not wanting to write apps that need high bandwidth because it's not available to most people.
The author, Stacey Higginbotham, is the one that has a completely flawed argument about gigabit costing too much. She opens up by saying in the first paragraph that gigabit costs $300/m and 100mbit costs $120/m but then in the fourth paragraph she states that Sonic.net (Jasper's ISP) offers them for $70/m and $40/m respectively which also includes VoIP. AT&T was charging us twice as much for a 3mbit/384kbit line and local POTS than Sonic.net charges for a 5.5mbit/1mbit line (we're ~10k feet from the office, if we were closer then it would be 20mbit/1mbit) with nationwide long distance POTS. Sonic.net is a great ISP with wonderful tech support and all my friends have switched to it. They've all gotten similar speed increases and cost reductions.
Cable will do 250Mbps just fine. DSL currently maxes out around 50Mbps, so it does require fiber.
An ordinary PCI interface cannot handle GB rates. You need at least a PCIe x1.
There is a conspicuous lack of affordable PCIe wired interfaces available. Directly onboard chips are feasable. But only if properly designed. A laptop may have other limiting factors.
The laptop couldn't handle a 52Mb/s Hard disk equiv?
That's pretty slow.
How can laptop be expected to use 280MB/s flash drives, when they
can't even handle 52MB/s? (One would presume the same I/O offload
on network chips as we have on disk drives being available if the speed were there. -- so to claim it's about the HW, is really STUPID!
My desktop can easily handle 600-800MB/s in a hard disk -- so...for bits/sec, I could benefit, AT LEAST up to 5-6Gbps... likely more...
My home network is crying out for 10Gbps already!...get a home server -- put a few T's on it, and see how fast that Xfers over a 1Gbit network...Not real fast. 125MBps is max I've measured and that was on writes. (where I can have multiple writes outstanding so RTT doesn't hurt as much).
So I'd guess that someone is trying to come up with reasons why they should spend money in infrastructure -- better to throw on caps and claim they don't have sufficient bandwidth for those higher BW users....
I suppose most of you have not read the article... The article deals with 1Gbit Internet Broadband, not 1Gbit LAN.
While it may in fact be true that most of the current installed base of computers don't have gigabit ports, this is changing. Most new motherboards have had gigabit ports on them for several years now.
The statement is not accurate. Any modern computer can handle full gigabit speed with ease over ethernet cable. If there's a limiting factor, it's in the peripheral network equipment.
What the article is missing, is that you can manage reasonably well at 10 or 20mbit. But jumping to 100Mbit as I have done means a huge improvement on a few applications. Things you'd "just not do" because they would take too much time.
Similarly the network companies are aching to be able to sell you stuff that the network can't handle today. A video rental store just around the corner can rent you a movie when you're "in the mood for a movie at home". But you have to go out and walk/drive to the shop. Wouldn't they sell more if you could rent the movie from your couch? Sure! And you can do that already. But then it takes planning. How many people plan badly?
And another thing. Just looking at the traffic numbers, you can extrapolate when > 20Mbit is necessary. Telcos have to start planning for that and actually invest for that way ahead of time. So it's good that telecom companies are looking ahead and investing ahead of time. In the mean while some advanced users will be happy to be connected to the internet at gigabit speeds TODAY.
Common situations where you'll easily saturate a number of these circuits: -If I want to address an iSCSI NAS from across town practically without shelling out enterprise dollars(to be read 10's of thousands), and I do...I could use a Gigabit connection. - When you have 20, 50 100 Wi-fi cards,each only access at ~54Kb/s, you need tech to deal with the higher aggregate number of transactions while managing large packets and there's a great deal of data flowing. Common situations where you will not: -Posting to Slashdot while downloading porn.... I feel I'm entitled to unimaginable bandwidth, and I'm so disappointed...I mean, I don't want it to travel to me from somewhere, I want to step into it and go there.... but that's just how I roll.....but I need much bandwidth...so I'm just rolling slow....
Holy shit... as a developer of broadcast television infrastructure equipment which is used throughout the world, though predominantly in Europe, I thought I was clued in quite a bit on the back-assward methods used within the industry for transmitting TV and Internet signals.
This was a total shocker for me though. I'm a huge fan of using wavelength multiplexing within fiber. Especially when the fiber in my house is a single fiber as opposed to pairs which are much harder to make look pretty in a house. However this is one of the funniest things I ever heard of.
It's taken a really long time for the industry to finally come up with a less than insanely shitty method of using coax cabling for digital media access. Oddly enough, the cable companies have more or less completely rebuild their coax backbones to make it happen... what makes it odd is that they wanted to keep the coax to avoid having to lay new cable.. haha wow that worked well.
Now, it appears that Verizon has decided to transmit the entire cable multiplex over a single wavelength, therefore allowing them to a) guarantee their bandwidth usage even if it's insanely high, b) decrease hackability of TV fiber as it is on a not so common wavelength and therefore difficult for consumers/hackers to get receivers for it. c) run less expensive multiplexers they wouldn't require conditional IP multicasting at the switches. d) decrease the cost of maintaining a huge TCP/IP network of devices as it would be possible to remove the IP layer altogether and use a more reliable ATM style layer.
This design so fantastically screws consumers into buying/leasing equipment exclusively from Verizon that it damn near guarantees Verizon a minimum of $30 a month extra per average household just in equipment rentals. And what's best is, they can claim "Sure, we support using third party hardware with our system Mr. FCC, but there's no law that says we have to help anyone make equipment that works with out network is there? But if anyone ever does... sure, we'll support them".
The only true benefit of this design to the consumer is that it would be possible to make a fiber to DVB-C converter that would theoretically make it possible for a TV to receive the signal using the digital coax connection within the TV.
I am SOOOOO glad I don't live in the states anymore... this stuff would infuriate me... it's bad enough I had to make an FPGA for brute forcing DVB-CAS in order to cut my power usage in the house by 100watts (24/7 since the shutting off the set top box from the fiber company requires a 3-5 minute startup time). Now I use an FPGA which consumes 5watts to crack the keys and shared them out with the rest of the house. Saves me a fortune. The FIOS thing would drive me nuts... oh there's the additional bitch about FIOS which is that it's DOG SLOW!!!!
History is littered with comments of this ilk, but made by people whose opinion should be considered. ./ readers you should hang your head in shame.
"I think there is a world market for maybe five computers."
"There is no reason anyone would want a computer in their home."
This commentary is made by a journo who's only job is to make lots of people go to this web site.
Game/Set/Match to journo,
ps a decade ago I had access to a network with multi-gig connectivity to the Internet as I had a job with a research organisation. It's the only network that I've work on where I actively tuned the TCP stack and optimised disks to cope with the download speeds, it was fantastic. All I can say is bring it on.
it's a lot harder for a publisher to "recall" a work stored on the end user's machine. Cases of this happening (such as Nineteen Eighty-Four on Amazon Kindle) are newsworthy.
Yes, sure, a publisher can remove access, but thats a separate issue really - they can already do that via DRM embedded into the content.
But there's a lot more bad press when the publisher terminates access to a work that users have already downloaded than when when the publisher terminates streaming access to a work. Take the case of the Kindle and the various WMA music stores that have shut down their DRM servers. It's comparatively no big deal when a work is no longer made available for streaming, but if termination of end users' license to view a downloaded work were to become a regular occurrence, it could undermine end users' faith in a particular technology.
Looking at the adoption rates of Internet solutions and any other technology you have a Field of Dreams situation of "If you build it they will come".
While laptops may not be able to take advantage of a 1Gb connection two could. 3 really could and looking at the roll out of computers that is they type of household we are looking at. Especially as more video content is delivered over the internet. At some point the cable companies will figure out a better way to deliver their content over an IP based network and that Gb connection will not seem like so much if you are trying to watch multiple HD channels in different rooms while also trying to download the latest video that your aunt Nelly shot of her dogs on her 4k camera. Letting the connection companies give the bare minimum with old and outdated technology will just result in an old infrastruture that will not be able to be upgraded.
In rural areas where the providers didn't want to spend the money on fiber backhauls they were stuck with a cap on their maximum supported speeds and just tried to ride it out by laying more copper to get them by. Unfortunately they spent that money on a technology that wouldn't scale out. Now you have many areas of the country that have broadband available but that broadband is only 512k or 786k because they can get away with it and they don't have the backhauls to provide more than that to all the customers. They also are running over some crappy old copper that gets flakey when they try to push 1mb dsl over it.
By the time its even modestly deployed it'll be 10 years after we need gigabit networks. Start building it now so we're only marginally behind the curve instead of decades.
If we didn't have bandwidth caps how would our poor broke isp/video content providers punish us for using a competing service?
Because there is only one computer per household. That computer only has one network accessing application. That application only makes one request. And! Only one response returns to that one computer while that one person waits patiently until it is finished before ever making another request.[/snark]
Having to work for a living is the root of all evil.
No, it's not that big a company. And as CEO, if he doesn't know the market his company (he was the founder) is dead.
Awesome furniture, accessories and cabinetry in Santa Rosa, CA: http://humanity-home.com/
When I was working on large farms of big iron (SGI, Sun, IBM systems) we regularly found that GigE over copper couldn't do much better than 400-500 Mbit/s. These were enterprise-class NICs, not cheap-o home gear. Switching to fiber got us much much closer to theoretical max.
When is fiber going to finally be available/affordable for the home market? I think that will make the biggest difference...
Actually some pretty modest hardware will generate very high thruput if tuned properly. The network stack default parameters we use today are remnants of what we did in the the 90s, when 16MB RAM was big, 4Mbit token ring was used, and 100k for a network buffer was a lot.
To increase thruput there are several things which can be done. The first is to increase the window size so that data can flow until the ACK packets get back. The second is to increase the packet size (aka jumbo packets, or MTU). After that you need to allocate enough buffer space to keep the pipe full on the transmit end and prevent buffer overflow on the receiving end. The OS needs to prioritize interrupt handling so the incoming data get handled, it doesn't need a lot of CPU, but it needs it NOW.
Finally, realize that the disk subsystem may become a bottleneck at Gbit speeds, sustained transfer to/from disk may take more than the minimal bargain drive. You don't need super hardware to use that Gbit, but you do need some optimal use of the hardware you have.
Ok, so for two computers directly connected over a gigabit connection trying to transfer a file - yes, it is correct - you cannot max out a gigabit using most computers - the hard drive interface becomes the main limitation, and you'll typically max out around 500 Mbit/second. That's not to say an application that only generates network traffic - that does not need to put it on the hard drive - could not max it out, it very well can since the limitation is the I/O for the hard drive, and not the computer in general (CPU or RAM). This is true even of vintage year 2000 hardware.
However, when talking about multiple computers the systems interleave, and then it can be very easy to max out a gigabit connection even with just two or three computers on the network.
That said, many homes have multiple computers once you start counting: laptops, desktops, iPods, iPhones, Android devices, DVRs, BlueRay, Gaming Systems (e.g. Wii, PlayStation, XBox), and the list goes on.
So yes, Multi-gigabit networks to the home from an ISP are very very relevant and necessary.
Truth is like the sun. You can shut it out for a time, but it ain't goin' away. - Elvis Presley (source: imdb.com)
How can you hit 420 Mbps and still diss Gigabit ? 420 Mbps is greater than 100 Mbps, and we don't have a standard for 0.42 Gigabit networks. Chances are, the throughput was limited by disk I/O or even motherboard bandwidth to the port, as laptops often have to sacrifice performance in favour of size and power conservation.
If I had a gigabit pipe to the internet today, I probably would use about 30% more bandwidth than I currently do - which is already quite a bit - but I would enjoy the experience a lot more since I'd spend much less time waiting for transfers to complete. I could mount remote filesystems over the wire without suffering through long pauses due to FS overhead. I wouldn't need such a beefy laptop to do my work, because I could comfortably remote into my desktop powerhouse at home. I could fling media projects around without having to wait a half-hour per file, fostering real-time collaboration with my teammates.
So we may not need gigabit networks yet, but we'd be fools to turn them down. If the computer industry had been built around needs, we would not have personal computers today, because at the time, nobody needed an Apple II. We wanted them, because they were cool, and then we discovered new uses for the tech.
-Billco, Fnarg.com
Here in Norway, our configuration isn't too much different with regards to the distribution of the signals. The primary difference is that instead of using coax over fiber as you've explained, instead, the signals are multiplexed by using VLANs. This makes it so that the pretty much any common ethernet switch (by common, I mean common infrastructure grade) can be used for distributing the signals. Therefore there's no additional need for being able to broadcast a non-ethernet signal over the fiber.
:)
The drawback as I see it in comparison is that all the television channels belong to individual multicasts and therefore unless you have something similar to the ONT which will join all the multiplexes and buffer and remultiplexes them and then modulates all the new multiplexes as DVB-C. If the provider were to provide MPTS streams on a separate multicast, then this could theoretically be handled by a relatively inexpensive unit... something in the cost level of a cable modem... well possibly even less as demodulating QAM is more expensive than modulating given the substantially less complex clock circuitry.
There are a few companies which have attempted to make DVB-IP to DVB-C gateways, but their systems were not as advanced. What they did was to produce a centralized set top box which would then contain 3 individual DVB-C modulators that would rebroadcast a single channel each. Then using RF based remote controls, the viewer would change their channel at the set top box itself.
Altibox (the biggest fiber provider in Norway) for the moment will do everything possible to guarantee the set top box rental fees since after 4-6 months, those boxes are generating huge revenues for the company. They also want to guarantee that every time you look at the TV guide, you're being bombarded by advertisements for VoD.
I am pretty impressed in the end by the FIOS design after all... I'm not 100% convinced it's the right design, but until things like ethernet switches and jack are more common in a household... meaning that when a house is built, conduits are installed in the walls and a patch panel is present in a centralized location, it might be the best solution possible.
Thanks for the information