Network Capacity Planning: Is Your Network Positioned for Growth?


Authored by:  Sandy McGregor, Director of Sales & Marketing for APConnections, Inc.
Sandy has a Masters in Management Information Systems and over 17 years experience in the Applications Development Life Cycle.  In the past, she has been a Project Manager for large-scale data center projects, as well as a Director heading up architecture, development and operations teams.  In Sandy’s current role at APConnections, she is responsible for tracking industry trends.

As you may have guessed, mobile users are gobbling up network bandwidth in 2010!  Based on research conducted in the first half of 2010, Allot Communications has released The Allot MobileTrends Report , H1 2010 showing dramatic growth in mobile data bandwidth usage in 2010- up 68% in Q1 and Q2.

I am sure that you are seeing the impacts of all this usage on your networks.  The good news is all this usage is good for your business, as a network provider,  if you are positioned to grow to meet the needs of all this growth!  Whether you sell network usage to customers (as a ISP or WISP) or “sell” it internally (colleges and corporations), growth means that the infrastructure you provide becomes more and more critical to your business.

Here are some areas that we found of particular interest in the article, and their implications on your network, from our perspective…

1) Video Streaming grew by 92% to 35% of mobile use

It should be no surprise that video steaming applications take up a 35% share of mobile bandwidth, and grew by 92%.  At this growth rate, which we believe will continue and grow even faster in the future, your network capacity will need to grow as well.  Luckily, bandwidth prices are continuing to come down in all geographies.

No matter how much you partition your network using a bandwidth shaping strategy, the fact is that video streaming takes up a lot of bandwidth.  Add to that the fact that more and more users are using video, and you have a full pipe before you know it!  While you can look at ways to cache video, we believe that you have no choice but to add bandwidth to your network.

2) Users are downloading like crazy!

When your customers are not watching videos, they are downloading, either via P2P or HTTP, which combined represented 31 percent of mobile bandwidth, with an aggregate growth rate of 80 percent.  Although additional network capacity can help somewhat here, large downloads or multiple P2P users can still quickly clog your network.

You need to first determine if you want to allow P2P traffic on your network.  If you decide to support P2P usage, you may want to think how you will identify which users are doing P2P and if you will charge a premium for this service. Also, be aware that encrypted P2P traffic is on the rise, which makes it difficult to figure out what traffic is truly P2P.

Large file downloads need to be supported.  Your goal here should be to figure out how to enable downloading for your customers without slowing down other users and bringing the rest of your network to a halt.

In our opinion, P2P and downloading is an area where you should look at bandwidth shaping solutions.  These technologies use various methods to prioritize and control traffic, such as application shaping (Allot, BlueCoat, Cymphonix) or behavior-based shaping (NetEqualizer).

These tools, or various routers (such as Mikrotik), should also enable you to set rate limits on your user base, so that no one user can take up too much of your network capacity.  Ideally, rate limits should be flexible, so that you can set a fixed amount by user, group of users (subnet, VLAN), or share a fixed amount across user groups.

3) VoIP and IM are really popular too

The second fastest growing traffic types were VoIP and Instant Messaging (IM).  Note that if your customers are not yet using VoIP, they will be soon.  The cost model for VoIP just makes it so compelling for many users, and having one set of wires if an office configuration is attractive as well (who likes the tangle of wires dangling from their desk anyways?).

We believe that your network needs to be able to handle VoIP without call break-up or delay.  For a latency-sensitive application like VoIP, bandwidth shaping (aka traffic control, aka bandwidth management) is key.  Regardless of your network capacity, if your VoIP traffic is not given priority, call break up will occur.  We believe that this is another area where bandwidth shaping solutions can help you.

IM on the other hand, can handle a little latency (depending on how fast your customers type & send messages).  To a point, customers will tolerate a delay in IM – but probably 1-2 seconds max.  After that,they will blame your network, and if delays persist, will look to move to another network provider.

In summary, to position your network for growth:

1) Buy More Bandwidth – It is a never-ending cycle, but at least the cost of bandwidth is coming down!

2) Implement Rate Limits – Stop any one user from taking up your whole network.

3) Add Bandwidth Shaping – Maximize what you already have.  Think efficiency here.  To determine the payback period on an investment in the NetEqualizer, try our new ROI tool.  You can put together similar calculations for other vendors.

Note:  The Allot MobileTrends Report data was collected from Jan. 1 to June 30 from leading mobile operators worldwide with a combined user base of 190 million subscribers.

NetEqualizer Field Guide to Network Capacity Planning


I recently reviewed an article that covered bandwidth allocations for various Internet applications. Although the information was accurate, it was very high level and did not cover the many variances that affect bandwidth consumption. Below, I’ll break many of these variances down, discussing not only how much bandwidth different applications consume, but the ranges of bandwidth consumption, including ping times and gaming, as well as how our own network optimization technology measures bandwidth consumption.

E-mail

Some bandwidth planning guides make simple assumptions and provide a single number for E-mail capacity planning, oftentimes overstating the average consumption. However, this usually doesn’t provide an accurate assessment. Let’s consider a couple of different types of E-mail.

E-mail — Text

Most E-mail text messages are at most a paragraph or two of text. On the scale of bandwidth consumption, this is negligible.

However, it is important to note that when we talk about the bandwidth consumption of different kinds of applications, there is an element of time to consider — How long will this application be running for? So, for example, you might send two kilobytes of E-mail over a link and it may roll out at the rate of one megabit. A 300-word, text-only E-mail can and will consume one megabit of bandwidth. The catch is that it generally lasts just a fraction of second at this rate. So, how would you capacity plan for heavy sustained E-mail usage on your network?

When computing bandwidth rates for classification with a commercial bandwidth controller such as a NetEqualizer, the industry practice is to average the bandwidth consumption for several seconds, and then calculate the rate in units of kilobytes per second (Kbs).

For example, when a two kilobyte file (a very small E-mail, for example) is sent over a link for a fraction of a second, you could say that this E-mail consumed two megabits of bandwidth. For the capacity planner, this would be a little misleading since the duration of the transaction was so short. If you take this transaction average over a couple of seconds, the transfer rate would be just one kbs, which for practical purposes, is equivalent to zero.

E-mail with Picture Attachments

A normal text E-mail of a few thousand bytes can quickly become 10 megabits of data with a few picture attachments. Although it may not look all the big on your screen, this type of E-mail can suck up some serious bandwidth when being transmitted. In fact, left unmolested, this type of transfer will take as much bandwidth as is available in transit. On a T1 circuit, a 10-megabit E-mail attachment may bring the line to a standstill for as long as six seconds or more. If you were talking on a Skype call while somebody at the same time shoots a picture E-mail to a friend, your Skype call is most likely going to break up for five seconds or so. It is for this reason that many network operators on shared networks deploy some form of bandwidth contorl or QoS as most would agree an E-mail attachment should not take priority over a live phone call.

E-mail with PDf Attachment

As a rule, PDF files are not as large as picture attachments when it comes to E-mail traffic. An average PDF file runs in the range of 200 thousand bytes whereas today’s higher resolution digital cameras create pictures of a few million bytes, or roughly 10 times larger. On a T1 circuit, the average bandwidth of the PDF file over a few seconds will be around 100kbs, which leaves plenty of room for other activities. The exception would be the 20-page manual which would be crashing your entire T1 for a few seconds just as the large picture attachments referred to above would do.

Gaming/World of Warcraft

There are quite a few blogs that talk about how well World of Warcraft runs on DSL, cable, etc., but most are missing the point about this game and games in general and their actual bandwidth requirements. Most gamers know that ping times are important, but what exactly is the correlation between network speed and ping time?

The problem with just measuring speed is that most speed tests start a stream of packets from a server of some kind to your home computer, perhaps a 20-megabit test file. The test starts (and a timer is started) and the file is sent. When the last byte arrives, a timer is stopped. The amount of data sent over the elapsed seconds yields the speed of the link. So far so good, but a fast speed in this type of test does not mean you have a fast ping time. Here is why.

Most people know that if you are talking to an astronaut on the moon there is a delay of several seconds with each transmission. So, even though the speed of the link is the speed of light for practical purposes, the data arrives several seconds later. Well, the same is true for the Internet. The data may be arriving at a rate of 10 megabits, but the time it takes in transit could be as high as 1 second. Hence, your ping time (your mouse click to fire your gun) does not show up at the controlling server until a full second has elapsed. In a quick draw gun battle, this could be fatal.

So, what affects ping times?

The most common cause would be a saturated network. This is when your network transmission rates of all data on your Internet link exceed the links rated capacity. Some links like a T1 just start dropping packets when full as there is no orderly line to send out waiting packets. In many cases, data that arrive to go out of your router when the link is filled just get tossed. This would be like killing off excess people waiting at a ticket window or something. Not very pleasant.

If your router is smart, it will try to buffer the excess packets and they will arrive late. Also, if the only thing running on your network is World of Warcraft, you can actually get by with 120kbs in many cases since the amount of data actually sent of over the network is not that large. Again, the ping time is more important and a 120kbs link unencumbered should have ping times faster than a human reflex.

There may also be some inherent delay in your Internet link beyond your control. For example, all satellite links, no matter how fast the data speed, have a minimum delay of around 300 milliseconds. Most urban operators do not need to use satellite links, but they all have some delay. Network delay will vary depending on the equipment your provider has in their network, and also how and where they connect up to other providers as well as the amount of hops your data will take. To test your current ping time, you can run a ping command from a standard Windows machine

Citrix

Applications vary widely in the amount of bandwidth consumed. Most mission critical applications using Citrix are fairly lightweight.

YouTube Video — Standard Video

A sustained YouTube video will consume about 500kbs on average over the video’s 10-minute duration. Most video players try to store the video up locally as fast as they can take it. This is important to know because if you are sizing a T1 to be shared by voice phones, theoretically,  if a user was watching a YouTube video, you would have 1 -megabit left over for the voice traffic. Right? Well, in reality, your video player will most likely take the full T1, or close to it, if it can while buffering YouTube.

YouTube — HD Video

On average, YouTube HD consumes close to 1 megabit.

See these other Youtube articles for more specifics about YouTube consumption

Netflix – Movies On Demand

Netflix is moving aggressively to a model where customers download movies over the Internet, versus having a DVD sent to them in the mail.  In a recent study, it was shown that 20% of bandwidth usage during peak in the U.S. is due to Netflix downloads. An average a two hour movie takes about 1.8 gigabits, if you want high-definition movies then its about 3 gigabits for two hours.   Other estimates are as high as 3-5 gigabits per movie.

On a T1 circuit, the average bandwidth of a high-definition Netflix movie (conversatively 3 gigabits/2 hours) over one second will be around 400kbs, which consumes more than 25% of the total circuit.

Skype/VoIP Calls

The amount of bandwidth you need to plan for a VoIP network is a hot topic. The bottom line is that VoIP calls range from 8kbs to 64kbs. Normally, the higher the quality the transmission, the higher the bit rate. For example, at 64kbs you can also transmit with the quality that one might experience on an older style AM radio. At 8kbs, you can understand a voice if the speaker is clear and pronunciates  their words clearly.  However, it is not likely you could understand somebody speaking quickly or slurring their words slightly.

Real-Time Music, Streaming Audio and Internet Radio

Streaming audio ranges from about 64kbs to 128kbs for higher fidelity.

File Transfer Protocol (FTP)/Microsoft Servicepack Downloads

Updates such as Microsoft service packs use file transfer protocol. Generally, this protocol will use as much bandwidth as it can find. There are several limiting factors for the actual speed an FTP will attain, though.

  1. The speed of your link — If the factors below (2 and 3) do not come into effect, an FTP transfer will take your entire link and crowd out VoIP calls and video.
  2. The speed of the senders server — There is no guarantee that the  sending serving is able to deliver data at the speed of your high speed link. Back in the days of dial-up 28.8kbs modems, this was never a factor. But, with some home internet links approaching 10 megabits, don’t be surprised if the sending server cannot keep up. During peak times, the sending server may be processing many requests at one time, and hence, even though it’s coming from a commercial site, it could actually be slower than your home network.
  3. The speed of the local receiving machine — Yes, even the computer you are receiving the file on has an upper limit. If you are on a high speed university network, the line speed of the network can easily exceed your computers ability to take up data.

While every network will ultimately be different, this field guide should provide you with an idea of the bandwidth demands your network will experience. After all, it’s much better to plan ahead rather than risking a bandwidth overload that causes your entire network to come to a hault.

Related Article a must read for anybody upgrading their Internet Pipe is our article on Contention Ratios

Created by APconnections, the NetEqualizer is a plug-and-play bandwidth control and WAN/Internet optimization appliance that is flexible and scalable. When the network is congested, NetEqualizer’s unique “behavior shaping” technology dynamically and automatically gives priority to latency sensitive applications, such as VoIP and email. Click here for a full price list.

Other products that classify bandwidth

White Paper: A Simple Guide to Network Capacity Planning


After many years of consulting and supporting the networking world with WAN optimization devices, we have sensed a lingering fear among Network Administrators who wonder if their capacity is within the normal range.

So the question remains:

How much bandwidth can you survive with before you impact morale or productivity?

The formal term we use to describe the number of users sharing a network link to the Internet is  contention ratio. This term  is defined as  the size of an Internet trunk divided by the number of users. We normally think of Internet trunks in units of megabits. For example, 10 users sharing a one megabit trunk would have a 10-to- 1 contention ratio. If sharing the bandwidth on the trunk equally and simultaneously, each user could sustain a constant feed of 100kbs, which is exactly 1/10 of the overall bandwidth.

From a business standpoint, it is whatever a customer will put up with and pay for without canceling their service. This definition may seem ethically suspect, but whether in the bygone days of telecommunications phone service or contemporary Internet bandwidth business, there are long-standing precedents for overselling. What do you think a circuit busy signal is caused by? Or a dropped cell phone call?

So, without pulling any punches, what exactly will a customer tolerate before pulling the plug?

Here are some basic observations about consumers and acceptable contention ratios:

  • Rural customers in the US and Canada: Contention ratios of 50 to 1 are common
  • International customers in remote areas of the world: Contention ratios of 80 to 1 are common
  • Internet providers in urban areas: Contention ratios of 15 to 1 are to be expected
  • Generic Business ratio 50 to 1 , and sometimes higher

Update Jan 2015, quite a bit has happened since these original numbers were published. Internet prices have plummeted, here is my updated observation.

Rural customers in the US and Canada: Contention ratios of 10 to 1 are common
International customers in remote areas of the world: Contention ratios of 20 to 1 are common
Internet providers in urban areas: Contention ratios of 2 to 1 are to be expected
Generic Business ratio 5 to 1 , and sometimes higher

As a rule Businesses can general get away with slightly higher contention ratios.  Most business use does not create the same load as recreational use, such as YouTube and File Sharing. Obviously, many businesses will suffer the effects of recreational use and perhaps haphazardly turn their heads on enforcement of such use. The above ratio of 50 to 1 is a general guideline of what a business should be able to work with, assuming they are willing to police their network usage and enforce policy.

The numbers above are a good, rough starting point, but things are not as simple as they look. There is a statistical twist as bandwidth amounts get higher.

Contention ratios can actually increase as the overall Internet trunk size gets larger. For example, if 50 people can share one megabit without mutiny, it should follow that 100 people can share two megabits without mutiny as the ratio has not changed. It is still 50 to 1.

However, from observations of hundreds of ISPs, we can easily conclude that perhaps 110 people can share two megabits with the same tolerance as 50 people sharing one megabit. What this means is that the larger the ISP, the more bandwidth at a fixed cost per megabit, and thus the larger the contention ratios you can get away with.

Is this really true? And if so, what are its implications for your business?

This is simply an empirical observation, backed up by talking to literally thousands of ISPs over the course of four years and noticing how their oversubscription ratios increase with the size of their trunk.

A conservative estimate is that, starting with the baseline ratio listed above, you can safely add 10 percent more subscribers above and beyond the original contention ratio for each megabit of trunk they share.

Thus, to provide an illustration, 50 people sharing one megabit can safely be increased to 110 people sharing two megabits, and at four megabits you can easily handle 280 customers. With this understanding, getting more from your bandwidth becomes that much easier.

I also ran across this thread in a discussion group for Resnet Adminstrators around the country.

From Resnet Listserv

Brandon  Enright at University of California San Diego breaks it down as follows:
Right now we’re at .2 Mbps per student.  We could go as low as .1 right
now without much of any impact.  Things would start to get really ugly
for us at .05 Mpbs / student.

So at 10k students I think our lower-bound is 500 Mbps.

I can’t disclose what we’re paying for bandwidth but even if we fully
saturated 2Gbps for the 95% percentile calculation it would come out to
be less than $5 per student per month.  Those seem like reasonable
enough costs to let the students run wild.
Brandon

Editors note: I am not sure why a public institution can’t  exactly disclose what they are paying for bandwidth ( Brian does give a good hint), as this would be useful to the world for comparison; however many Universities get lower than commercial rates through state infrastructure not available to private operators.

Related Article ISP contention ratios.

By Art Reisman

Art Reisman CTO www.netequalizer.com

Editor’s note: Art Reisman is the CTO of APconnections. APconnections designs and manufactures the popular NetEqualizer bandwidth shaper.

%d bloggers like this: