SDN Performance Takes a Leaf of Faith

By: John Shepler

If the cloud has done anything, it has turned a magnifying glass on once mundane WAN connections. Back in the day, it was OK for file transfers to take a bit too long or the Internet to be a little dicey. After all, the really critical operations were confined to the company LAN and in-house data center. No more. Once your services are hosted in the cloud, WAN performance becomes just as critical as LAN performance.

The New WAN Problem
There’s only one problem. YOU don’t own the WAN like you do your LAN wiring. You are at the mercy of wireless, cable, DSL, fiber and copper wireline service providers. Any issues in their networks have an immediate impact on your business.

How Do You Protect Yourself?
The answer is increasingly SDN or Software Defined Network solutions. SDN covers a lot of technology, but one very popular implementation for business is the integration of multiple, diverse WAN connections. You have several connections to the cloud, but they are coordinated by SDN.

Nature Knows How
Bigleaf Networks calls their process for doing this “Natural Networking.” They create a redundancy of connections with fault tolerance similar to how leaves protect themselves in nature. Here’s how Bigleaf explains their system:


Pretty clever, right? The SDN performance optimization that Bigleaf provides can also save you money. Without traffic management, many businesses wouldn’t even consider “best effort” broadband services like wireless, cable, DSL or low cost fiber options. The cost of outages and variations in performance was too great. The only acceptable WAN solutions were multiple dedicated private line services set up with automatic instant failover. These lines can get pretty expensive and you still have the headache of having to manage this system yourself.

Don't Do It Yourself
Bigleaf makes optimizing multiple Internet connections painless. They provide the managed router that tunnels traffic to their gateway clusters in the cloud. It’s all plug-and-play for you. For the ultimate in reliability, they even have an option to install redundant routers and switches at your site to match the redundancy of their cloud cluster.

Are you frustrated with the performance of your business broadband connection for cloud services? It’s time to take a closer look at what Software Defined Networks can do to improve both quality and reliability of your WAN services. Bigleaf technology is now offered by Telarus, along with services from over 50 data, voice and cloud providers. Discuss your issues and needs with an expert consultant now at no charge.

The Cloud Needs Low Latency

By: John Shepler

It makes so much economic sense. Instead of getting a bank loan and making a major capital investment in your own server farm and data center, you simply contract with a cloud service provider and pay only for what you use when you use it. No more having to predict how business will be next year or even next quarter. You can roll with the punches with on-demand cloud services.

It Seems So Easy
The solution is deceptively simple. Clean out your current data center or don’t build one in the first place. Rent what you need from one of a myriad of cloud service providers. All you need is a simple link from your facilities to theirs and nobody on the network will know the difference. After all, how can they tell whether the servers are down the hall or across the country? Few users do anything but run the applications anyway.

The Hesitating Network
There’s an old saying that goes something like this: “On the network, the printer on the other side of the country is as close as the one in the next office.”

That’s an ideal. In reality it can either seem just that close or really a thousand miles away. The server three states over works the same as the one in the basement used to. Somehow, though, it’s developed a hesitation. You have to wait for the system to respond now. Worse, yet, that hesitation seems to vary. You really don’t know how the system is going to perform from one day to the next.

The Infinite Cloud That Isn’t
One used to be able to blame system performance lags on lack of resources. When everyone is running big jobs at the same time things slow down a bit. If you were clever, you tried to get your work done at odd hours before the thundering herd got to work or when they went to lunch. Let somebody else deal with the congestion. It’s the equivalent of drive-time traffic and no more fun.

That was one thing the cloud was supposed to fix. A major benefit of cloud data centers is that they have massive resources. Any given tenant can expand or contract the number of servers and the amount of storage they are using in real time. You aren’t supposed to run out of capacity ever. Yet, it seems like the cloud has less capability than you had before. How can that be possible?

The WAN Gotcha
One big thing that is often forgotten is that the printer in the next office and the one across the country have to be connected by something. That something is your WAN network connection. When all of your network resources were sitting on the LAN, the point was moot. There was plenty of capacity and the links were short enough that network performance just wasn’t an issue. You might say that the network became “transparent.”

Now, your network includes both the sporty LAN and metro and wide area connections that can be anything but sporty. In fact, they can be downright sluggish. That’s because there’s a difference between your local networks and the ones that run by telecom carriers. Local networks can be fairly easily engineered to have enough performance to appear transparent. That’s both harder and more expensive to do over long distances.

What’s Holding Back the WAN?
There are a few technical characteristics that spell the difference between transparent and not so transparent connections. These include bandwidth, latency, jitter and packet loss. You want to maximize the first and minimize the other three.

It’s tempting to jump to the conclusion that sluggish network performance is a result of too little capacity. When you start to use most of the available bandwidth most of the time, you can have periods of congestion where there are just too many packets to send down the line at the same time. Easy solution? Increase bandwidth. A double, triple or 10x bandwidth increase should solve the problem immediately… or will it?

One issue that no bandwidth increase can fix is latency. This is a time delay for packets to traverse the network. We think of electrical transmission being instantaneous from source to destination. At the local level, that’s a really good assumption. Once you leave the premises, though, even the speed of light may not be fast enough.

Minimizing Latency
Clearly, one way to minimize the time delay of transmission is to minimize the distance involved. Even at light speed, you can only go 186 miles in a millisecond. That’s 10 mSec for 1,860 miles. In fact, even that isn’t really possible. In real world glass fiber, you may be looking at more like 15 to 20 milliseconds one way or at least 40 milliseconds round trip. If you happen to be using a geosynchronous satellite link for part of the trip, that expands to a quarter to half a second.

Most applications aren’t going to be impacted by a 40+ millisecond delay, although half a second is definitely going to be noticeable and perhaps difficult to live with. This argues for using a terrestrial fiber link to the cloud (which is actually on the ground) and using the shortest path possible. A point to point dedicated private line is most likely the highest performance you can achieve. You may be able to get equivalent or nearly equivalent performance through a privately run MPLS network at a lower cost.

How About The Internet
Oh, yes, the Internet. It sounds like the ideal resource. It goes everywhere and connects everyone. The cost is amortized over so many users that the Internet is going to be your low cost solution. Security is certainly an issue, but encryption can create tunnels that give you a virtually private network that emulates a truly private network.

That emulation may fall short, not for security reasons, but in performance. The Internet is not engineered to minimize latency or jitter. It’s architecture is designed for resilience. If you lose a connection between servers, the network will automatically reconfigure to heal itself and keep the traffic moving. Unfortunately, that means your packets may take different paths on different trips. They may also encounter bottlenecks if particular nodes get overloaded.

Does this mean you can’t use the Internet to connect to the cloud? For maximum performance or highly sensitive interactive and real-time applications, you’ll do better with private lines. Otherwise, you might be satisfied with a private/public hybrid called DIA or Dedicated Internet Access. You still share the high performance backbone of the Internet core, but you connect via a private line that minimizes latency, jitter and packet loss during that critical first mile.

Finding a Better Cloud Connection
There is a range of cloud connectivity options available for most business locations. You should look at the cost/performance tradeoffs involved with each of these and then choose the link you need to make your connection to the cloud as transparent as you need.

Is Your Network Capacity Drying Up?

By: John Shepler

It can sneak up on you without warning. One day, the network is running smoothly. Next day it’s all congested. How did that happen? More importantly, what can you do about it?


Network capacity, especially MAN and WAN network capacity, can dry up quickly as applications become more demanding. Video is a major bandwidth hog. Backups to remote data centers can also chew up a lot of your capacity. Worst of all is The Cloud. You might think that your troubles are over when you outsource your applications to cloud service providers. What is often forgotten is that all that user bandwidth supplied by your LAN must now be supplied by the WAN. Not just any bandwidth, mind you. It needs to be low latency bandwidth or you’ll still have troubles.

Why low latency? You know that latency is critical for sensitive real time apps like VoIP telephony or high definition video conferencing. But how about those business applications that moved from the local data center to the cloud? Latency is easy to control locally. It can be an issue on long distance connections, especially if you elected to use the Internet as your cloud connection service. Latency shows up as hesitation in cloud response. A little can be annoying. A lot can be a major productivity killer.

Fortunately, high bandwidth low latency connectivity is easier than ever to fit into your IT budget. Prices have plummeted in recent years on everything from old school T1 lines on up to the SONET/SDH and fiber optic Ethernet. Even MPLS networks for connecting multiple business locations may cost less than you think.

If you haven’t gone out for competitive price quotes in a few years, you’re in for a pleasant surprise. You may find that you can double your MAN or WAN bandwidth for the same telecom budget that you have now. By upgrading from TDM based SONET fiber optic services to Ethernet over Fiber, you may well be able to afford a lot more capacity than you have now. The cost per Mbps or Gbps is much more attractive for Carrier Ethernet, especially if you get your service from a competitive provider who can provide both core network and last mile connections on their own network.

Could you use a bandwidth upgrade soon? Perhaps even right now? Get fast bandwidth quotes customer tailored to your particular needs now.

New Enterprise Ready Colocation in San Francisco

Many large enterprises are coming to the conclusion that running their own data centers just doesn’t make the kind of sense it did in decades past. It costs a small fortune to build and operate a facility with the necessary size, security, environmental control, backup power, and 24/7/365 staffing to meet the technical demands of a major business. Not so long ago, you didn’t have much choice but to do it yourself to get the kind of facility that could support your demanding requirements. Now you do have a choice with the advent of enterprise ready colocation.

A shining example of a facility designed with enterprise colocation in mind is the Level 3 data center at 200 Paul Avenue in San Francisco. Level 3 has invested the capital to expand their data center so you don’t have to. That’s one of the primary benefits to colocation. It works especially well for companies that have reached the limits of growth in their own data centers but shudder at the thought of building an additional facility. By incrementally expanding into the Level 3 data center, you can get the enterprise level support you need but pay only for the resources you use.

What are some of the features and benefits of 200 Paul Avenue colocation? You’ll find 8,000 square feet of high density cabinet and suite space with 8-12 KW power cabinets and support for 200 watts per square foot power density. The juice is there no matter what your power requirements are. That primary power is backed up by fully a redundant uninterruptible power supply.

You won’t have to worry about keeping your equipment secure. Level 3 is set up with multi-layer security that includes 24/7 closed circuit video and alarm monitoring and dual authentication security.

HVAC is another major investment when it comes to data centers. The Level 3 facility is set up with industry standard heating, ventilation and air conditioning. Pull all the power you need. The cooling air is available to whisk that rejected server heat out of the rack and out of the building.

Beyond the bricks and mortar, a major reason to consider colocation is connectivity. By moving into 200 Paul Avenue, you have zero latency direct connectivity to Level 3’s global network. How much bandwidth can you get? How much do you need? Many companies would love to hear a major carrier say that about their current location. However, the reality is that copper and fiber assets are limited in all but the most densely metro areas. Even there, full conduits and right of way issues may prevent you from upgrading to the connections you really want. Or, you could get hit with a big construction bill to bring in new fiber.

That won’t happen in the colo facility because the network POPs (Points of Presence) are already there and waiting. This includes a wide variety of bandwidth options plus carrier neutrality so that you can stay with the service provider you already have. Looking for new service? You won’t find a greater range of service providers to pick from than you have access to in the colocation facility.

You may be scratching your head, wondering how colocation can be gaining such popularity when all you hear is about companies moving to “the cloud.” Cloud computing and other cloud service are, indeed, expanding at a high rate of speed. However, some companies already have proprietary processes on systems of their own architecture design that are fine tuned to their unique needs. Re-engineering to use multi-tenant cloud facilities isn’t all that attractive and comes with more than a few security concerns. By the way, if the cloud is right for your business, Level 3 offers public, private or hybrid cloud services to match your requirements.

Have you developed a need for additional data center space or simply want to do some cost//benefit tradeoffs to see if running your own facilities still makes the most sense? If so, get prices and options for enterprise ready colocation and cloud services to help in your decision making process.




Note: Photo of downtown San Francisco courtesy of Wikimedia Commons.

AboveNet Offers Gigabit Ethernet For Enterprises

Gigabit Ethernet (GigE) has pretty much taken over the LAN in large and even medium size enterprises. But what about the WAN? Are you still hobbled by the slowdown that occurs when you are sending files beyond your network edge? Isn’t it time to consider Gigabit Ethernet for the WAN as well as the LAN?

Running a Gigabit LAN and using something like DS3 bandwidth or even OC3 fiber optic service for your MAN or WAN service is like connecting a drinking straw to a fire hose. The flow can’t help but slow to a trickle when it goes through that edge router. There once were good reasons why very modest WAN connection speeds were just fine. Today, there’s much less of a case to be made for order of magnitude or larger differences in LAN and WAN speeds.

What’s happened to demand higher connection speeds today? Computer networks were once strictly internal to a company. In fact, anything connected to the network from the outside aroused suspicion. If you wanted to transfer data somewhere, you used a reel of tape or a cassette. Slowly, data communication networks arose starting with dial-up modems and Frame Relay networks. Then came the Internet. It been a speed race ever since.

Now nearly every company has a dedicated broadband connection to the Internet and perhaps one or more VPNs (Virtual Private Networks) to connect with employees working for home or on the go. Companies with more than one site often have private line or MPLS network connections to tie everyone together. With the amount of data flying around, tapes and removable disk packs are yesterday’s means of data transfer. Today it is high speed network links.

Not only has computer technology changed, but so have business practices. Now nearly everything has some form of automation involved. Business productivity is leveraged upon real-time computer systems and electronic storage. Nobody at headquarters wants you to create a report and send it overnight mail anymore. They want a video conference presentation featuring you delivering the report live. Oh, and they want it right after lunch.

Beyond mere connectivity for transmitting files electronically instead of faxing or mailing paper, companies and their computing systems are becoming estranged. The data center used to be right down the hall or in the basement. Now it’s on the other side of the country and is owned by somebody else. More and more companies are buying their computing and even their telephone service through a cloud service provider. The LAN no longer connects you to the server racks. Now you have to go through a WAN connection. Does it make sense that the bandwidth that used to be good enough for a few overnight file transfers can’t begin to support real time business applications running in the cloud?

The idea of Gigabit Ethernet connections used to be a fantasy. Now it’s becoming a given. You need the high bandwidth connections to support the amount of data moving between organizational locations and back and forth with the cloud. If you are supporting financial trading, high performance SaaS, video conferencing or enterprise VoIP, you need not just high bandwidth but also low latency and jitter with minimal packet loss. In some cases, you may also require links to overseas locations with the same network characteristics.

Where do you go to get Gigabit level connectivity? AboveNet is a premier supplier of domestic and international fiber optic services. They are recommending moving to Ethernet rather than the legacy SONET fiber services. Why? SONET/SDH services are a legacy telephone company technology. They were designed to support trunking massive numbers of telephone conversations from office to office. These protocols can be made to work with computer networks but they are not directly compatible.

What is? Ethernet! The Ethernet that runs on your LAN can now traverse your WAN to the Internet or to another LAN on the other side of the country or across the Atlantic. This makes for a simpler and more efficient overall network setup. It also enables services such as layer 2 Ethernet LAN Service that bridges two distant LANs as if they were in the same building. Ethernet scales much faster and more granularly than SONET, allowing you to buy just the bandwidth you need now with the option to quickly scale up when the need arises. Best of all, Ethernet has a cost advantage over SONET/SDH. You get more bandwidth for the same money or pay less for the same service level.

If you are feeling the pinch from too small WAN connections, this would be an excellent time to check your current options for Ethernet, Fast Ethernet and Gigabit Ethernet services from AboveNet and other fiber optic carriers. You can get instant pricing for bandwidths up to 1 Gbps and rapid quotes with helpful consultation for all other services you may be interested in for your company.

Cloud Service Providers Colocate With Customers

There’s a new migration on. No, not the migration from local data centers to the cloud. It’s a migration of cloud service providers to colocate with their customers.

Why? It’s the rude awakening that companies suffer when they find that applications running way out there don’t have the same zip as the ones running on servers down the hall. That can be fixed, of course. It requires engineering your connections to the cloud so that they have sufficient amounts of bandwidth and very low latency, jitter and packet loss. But why go that that expense when you can just cozy up to your service provider with little more than a long patch cord connecting you?

That’s what Telx thinks. They’re throwing open their doors and working to lure cloud service providers to take up residence in one or more of their high performance colocation centers. It’s an acknowledgement that the speed of computing has gotten to the point where interconnections are the weak link. The venerable T1 line or DS3 connection that worked so well when all you needed to do was surf the Web, exchange email or generate sales leads quickly chokes when you start adding virtual servers by the dozens or hundreds.

There are a couple of big crunches that strain the cloud service model. One is business processes that are now automated and support hundreds or thousands of employees. The other is high performance e-commerce, with enormous catalogs and thousands of simultaneous shoppers who have little patience for sluggish servers and none at all for errors in their shopping experience.

The cloud is becoming a victim of its own success. Cloud service providers have mastered the technology of being able to ramp up or down the number of servers online in a matter of seconds. Storage is a bottomless well that data fills as needed. Public-facing bandwidth is easily handled with multiple Gigabit and 10 Gigabit Internet connections with enough margin to serve all customers. While cloud companies have gotten used to this scale of resources, most businesses have not. They don’t have the private line connectivity to take full advantage of near-infinite, near-instantaneous computing resources.

More savvy companies have mastered the connectivity issues, but who’s going to turn down the opportunity to get more performance for less money? The notion of being on the same floor of the same building with your service provider and ditching the telecom line in favor of a local fiber or wire connection has a lot of appeal. The issues of bandwidth, latency, jitter, and packet loss simply disappear.

A lot of medium and larger companies already have equipment in colocation centers, such as Telx. The economic tradeoff between running your own environmentally controlled facilities with backup power, fire suppression and round the clock monitoring and simply renting space in a larger facility with its economies of scale makes colocation attractive. On top of that is the fact that you have easier access to competitive carrier services with more attractive pricing than you can get locally. Now, add to these advantages the opportunity to connect to a cloud service provider in-house and you are looking at really attractive cost vs performance figures.

The new Telx Cloud Connectivity Centers with cloud-optimized infrastructure to support cloud service providers in each of their 15 data centers is an idea who’s time has come. Enterprise users and cloud companies are like opposite magnetic poles trying to get as close to each other as possible. Colocation is the obvious answer.

Can your business benefit from colocation as a service provider or service user? Get pricing and technical specs for the IT resources you need and compare with what you are doing now.



Note: Photo of clouds and building courtesy of Wikimedia Commons.