Fans of HBO’s hit series True Blood are getting glamorous this month, thanks to Los Angeles based interactive agencies Haus, BBDO, and the PEER 1 Hosting GPU cloud.
In case you’re unfamiliar, True Blood is a hugely popular HBO series that will be entering it’s fifth season in 2012. With over nine million fans on Facebook, social media engagement has been vital to the show’s success.
Set in small town Louisiana, the show features all sorts of supernaturals such as telepaths, shape-shifters and you guessed it – vampires. One of the reoccurring aspects of the show is the vampires’ ability to “glamour” someone, or put them into a hypnotic, trance-like state. Haus and BBDO wanted to create an app that would give fans the ability to glamour their friends, keeping them engaged while they eagerly await the launch of the fifth season next spring.
How it Works
The Glamour Your Friends app is simple: fans upload a photo of themselves via their webcam, hard drive or Facebook photos. The app then turns them into a Glamouring vampire, complete with fangs and a sultry southern drawl. Fans can customize the audio and location specific to the recipient, and then they can share their creations with each other on Facebook and Twitter.
Glamour Your Friends uses software licensed from Motion Portraitto create a 3D avatar. Facial recognition is used to place bitmap data that the user uploads onto a 3D mesh. The Flash client communicates with Motion Portrait’s software through web and Flash APIs. To ensure the demand of such a large and devoted fan base could be met, HAUS worked with PEER 1 Hosting to create a load-balanced GPU hosting solution.
Nasuni recently published their Cloud Storage Benchmark Study Report which had only six of the leading 16 cloud storage providers pass their rigorous test for performance, stability and scalability. PEER 1 Hosting, along with Microsoft Azure and Amazon S3 made the final six.
The company’s research began in April 2009, and evaluated cloud storage providers in a specific use case – how providers perform for mid-sized organizations that want to take advantage of the cloud for primary storage, data protection and disaster recovery. The five testing stages used for the study were API Integration, Unit Testing, Performance Testing, Stability Testing, and Scalability Testing.
SuperComputing is one of the longest running technology conferences in America, getting it’s start back in 1988 in Orlando. Every year the conference brings together mathematicians, computer scientists, quantz and data nerds of all types for a week of technical talks and sessions focussing on the latest trends and ideas in super computing.
Attending the show? Don’t forget to stop by booth #6102 for a demo of our affordable, high performance GPU cloud.
Today, marks a major milestone at PEER 1 Hosting. We have officially unveiled our new public cloud hosting service, Zunicore.
Zunicore is a professional-grade cloud service that allows users to benefit from customizable resource pools versus preset virtual machines, hands-free autoscaling, and transparent pricing. FairPlay Pricing™ guarantees that customers pay only for what they use and are never locked into a long-term contract. The complexities of managing the cloud have driven many businesses away from the public cloud. Now, with Zunicore’s simple dashboard that show the user the resources being used, the amount of resource remaining, and options to increase or decrease resources, it is easier for companies to migrate to the cloud. The core features of our new public cloud include:
User-controlled Environment: Customizable resource pools that allow users to increase or decrease the size of their pool, or add virtual machines based on their business needs. This type of control also provides Overdraft Protection against the users hosting cost.
Data Reliability: Unlike other cloud environments that utilize local hard drives for storage at an additional cost, Zunicore offers persistent storage area network (SAN) storage, which is more reliable, less susceptible to data loss and offers higher performance – all at no extra cost.
Scalability: Hands-free autoscaling allows users to specify by how little or much they want to scale their resources, based on user-defined thresholds such as technical resources, cost, or both.
Minimized Downtime Risk: Several features help limit Zunicore’s risk of downtime: availability in PEER 1 Hosting’s three geographically dispersed datacenters on two continents, AnyCast DNS across PEER 1 Hosting’s FastFiber Network™, persistent SAN and a Zero Downtime Network service level agreement (SLA).
Early users can sign up for a free 30-day trial. If you are at Cloud Expo all this week in Santa Clara, CA stop by the Zunicore booth (#622).
“The sharing of content among consumer circles will dominate the consumer cloud,” noted Greg Rusu, General Manager of Zunicore, PEER 1 Hosting’s newest division focused on cloud computing.
“Early attempts at sharing frameworks, followed by the emergence of social networks, and the current growth of streaming services all point to the massive unmet demand among consumers for interacting with media and social networks – cloud computing offers an elegant aggregation of secured collaboration and publishing.”
Click here to read the rest of this exclusive Q&A between Greg and Jeremy Geelan, Conference Chair of Cloud Expo.
The transition from physical to virtualized infrastructure introduces a new set of challenges for system administrators everywhere, especially when the v-machines live in a cloud somewhere. Last week our very own Chris DiGanci spoke to NetworkComputing about how some of these challenges can be addressed by leveraging the advanced virtualied monitoring capabilities of VKernel 3.5.
Some of the biggest problems for any IT shop taking on a massive virtualization project are almost always going to be related to resource management. Managing virtual hardware requires a different approach than managing physical hardware, so allocation (either over or under), unregulated VM sprawl, and the creeping cost of thinking about virtualization with a physical hardware mentality are common problems. It takes a pretty big shift in thinking to go from “I need dual CPUs, 16GB of Ram and at least 120GB of disk space” to “My application or system is going to run ideally with one vCPU, 2.1GB of RAM and a thin provisioned footprint of 6GB that can grow up to 22GB”.
Nowadays, it’s about process workload and being able to scale to meet the needs of your customer. The only way you’re going to be able to do that is to effectively balance your systems to the appropriate clusters and have the ability to right size your virtuals so you get the most value for your investment. You can’t make informed decisions about capacity without the right tools in place to monitor for trends, consumption, burst and cost.
Vkernel has been a tremendous asset in helping us to determine server bottlenecks, to plan for future growth, to right size our existing environments, and to identify where we need to balance out systems or add resources. So far, we’ve been mostly able to reduce the consumption of most systems and have found a considerable amount of over allocation. In the not distant future, we’re going to be able to give the business a holistic view into the real cost-benefit and consumption of the virtual infrastructure.
One of the biggest advantages of VKernel is the chargeback system. It gives us incredibly granular control of how we can monitor usage of the various virtualized services. Systems can be assigned into tiers based on the type of service, such as SAN space, fast spindles, replicated LUNs, internal storage, SSDs, etc. Fixed costs can then be assigned by datacenter (power per kw, cooling cost, networking) with the appropriate measurable billing metric (per GHz, per gig of ram, per gig of disk space, etc.). The system also enables us to do snapshots of costs or trend costs-per-product. With this data in hand, we can determine the real cost of any product we have out there, and make adjustments if necessary. Using this data as ‘showback’ also helps departments reduce their spend and makes them a little more conscious of their cost to the infrastructure.
Your first thought when someone mentions clouds may resemble puffy white cotton balls. But if you are a business owner, you should be changing your train of thought to opportunity because that is exactly what cloud computing offers to small businesses.
Modern hosting, and, more specifically, cloud computing, means having your computing infrastructure, platforms, and applications hosted in a location other than your facility. It offers the ability to access storage or computing or processing power on demand through web-based cloud platforms. It benefits small businesses in many ways, including reduced investments in software and hardware, because companies can pay for computing needs on an as-needed basis. [1]
While some people may be hesitant to embrace modern hosting solutions, it’s clear that small businesses are flocking to the cloud. A recent study conducted by Microsoft revealed that 39 percent of small and mid-sized businesses expect to pay for at least one cloud service in the next three years, and that 43 percent of computer workloads in the United States will shift to paid cloud services. [2]
What Types of Clouds Are There?
Forget the things you learned in science class about stratus and cirrocumulus clouds. Today, the cloud is about IaaS, PaaS, and SaaS; which respectively stand for Infrastructure as a Service, Platform as a Service, and Software (or application) as a Service. [3]
Software as a Service typically involves accessing software applications via a web browser and includes functions such as accounting and invoicing (think Quickbooks Online), human resource management, content management, and other functions. This typically covers the needs of most small businesses that are not in the IT field. [3] [4]
Platform as a Service is the deployment of a computing platform or solution stack on the cloud. Often, it offers the increased ability for development and team collaboration. In simpler terms, PaaS is used to support multiple users simultaneously. PaaS also offers developers greater flexibility by allowing them to work in any programming language, any database, and any operating system. [5]
Infrastructure as a Service typically involves a platform virtualization environment. Clients buy resources such as servers, software, data-center space, and networked equipment as a fully outsourced service that is often billed based on resources consumed.
The Bottom Line
The bottom line for small businesses depends on increasing revenues and cutting expenses. If used properly, modern hosting platforms can contribute directly to the bottom line through savings. The old model involved buying servers, routers, and storage equipment. It meant expensive software that ran in the hundreds, if not thousands, of dollars, plus the cost of updates.
With cloud computing, small businesses can limit the risk and financial impact by renting these applications. Online application stores allow small business owners to discover professional applications and services for areas such as customer resource management, marketing, accounting, and collaboration. [4]
Scaling is arguably the most attractive feature of cloud-based computing for small business. As Microsoft’s research revealed, growing companies want a scalable environment that meets expanding needs with a pay-as-you go pricing model and one that also eliminates the need for major investments in IT. [2]
This chart shows a model for “on-demand” computing infrastructure. Note that the infrastructure costs rise only as actual demand increases and are not based on anticipated demand.
A company engaging cloud-based computing services pays only for what it needs. What this means is that costs increase only as business grows. This allows for tremendous flexibility for businesses using a new application. The business can start with fewer users, features, or support, and upgrade as needs increase.
Furthermore, the cloud is a great option where frequent spikes or surges in computing demands are a normal part of business. Cloud computing services have the ability to quickly increase resources as demand increases, and then scale the resources back as demand recedes. Often, this change in available resources can be automated by creating trigger actions. [4]
Convenience and Flexibility
In many ways, the cloud “understands” that business has gone global, mobile, and is a 24/7 pursuit. Applications on the web can be accessed from any computer and from many mobile devices. The cloud helps small businesses mobilize their employees, thereby reducing operating costs. [6]
Additionally, many small businesses will find it easier and more convenient to access data stored on the cloud or with application providers. Employees, vendors, and others will be able to access the data stored on the cloud. For example, a CPA would be able to access a company’s cloud-based accounting records, therefore eliminating the need to transfer paper files back and forth. [3]
Cloud computing also makes it easier for small businesses to engage in conferences and business meetings without expensive travel costs. By launching web-based, cloud-powered conferencing platforms, users can give online presentations and conduct meetings and trainings to anyone with a computer, and small business owners can connect quickly and affordably without the need for travel to other locations. [3]
Additionally, the cloud offers reliability. A business owner will no longer need to worry about a server crash losing important documents and files. [7] Documents created in and accessed through the cloud are also saved in the cloud, providing for continuous access and prevention of accidental erasure of files. [6]
Working Together
The cloud makes collaboration with vendors and experts easier. It also makes teaming with remote employees a realistic alternative to pulling everyone into a central office. A small business may grow to develop its own applications through PaaS and then host those applications through IaaS on the cloud. [3]
Furthermore, simplified document storage makes it easier for employees to upload, store, and share important documents, videos, and files. [6]
Security Concerns
A responsible business should always be concerned with online security. When a story about wrongful access to information breaks, it generally makes headlines and can have a negative impact on a company’s reputation. However, the cloud is a safe computing platform, and in most small businesses a reputable cloud vendor will offer a much higher level of security than what can be achieved in-house. [3]
This chart shows the different layers of cloud security in one cloud platform. The different layers require passwords for access.
Similarly, when an application goes down or is temporarily offline, the headlines and Twitter broadcast this immediately to the world. However, this is unlikely to occur with a reputable vendor, as there are frequent redundancies in place – redundancies a small business can’t generally afford to build on its own. A thorough review of the vendor’s Service Agreement will inform a business owner about important factors such as back up plans, redundancies, and how emergencies are handled. [3]
Hybrid Hosting
Using cloud computing offers small businesses many benefits and advantages that they would not be able to afford otherwise, but there are situations when a company is better served by having a dedicated server running an application. For example, if a company needs to guarantee that its sensitive data will be secure, the data should be kept on a server used exclusively for that data. Furthermore, a business website that generates heavy traffic may perform more efficiently if it has its own server. [8]
For these situations, hybrid hosting is a viable alternative to using only cloud computing. Hybrid hosting involves using a combination of cloud computing plus dedicated servers. It has the same advantages as cloud computing – scalability, affordability, increased availability of services, etc. – but instead of having a business share a server with other companies, the Internet service provider (ISP) dedicates an entire server to the company’s network. The ISP is responsible for the maintenance and security of the server, and the company is reassured that its data is as secure as possible. When the company needs to add services or scale up, hybrid hosting can accommodate this. [9]
Why Wait?
The cloud is a great equalizer. It allows small and mid-sized businesses to innovate, grow, and compete with their much larger counterparts. They can expand and contract computing power as needed based on demand, and access platforms and infrastructure that were previously unaffordable to them.
Keeping up to date on emerging technology, as well as maintaining current technology, is an expensive and time-consuming task. It is an area in which many small businesses struggle, which takes a toll on their bottom line. However, cloud computing services level the playing field by removing the costs of technology investment and maintenance, giving small businesses the flexibility they need to grow.
Computers at home or at work need software in order for us to use them the way we would like. Many of us want to make documents, work with photos, and create presentations with our computers. In addition, companies use computers to manage all aspects of the business, from accounting to customer service. For years, the only way to do this was to purchase the necessary software – often at a relatively high cost – and install it on the computers’ hard drives or on a company’s internal servers. With the rise of cloud computing, however, this is changing rapidly, and the days of hosting software on each individual computer or server may be numbered.
Cloud Computing – What is it?
Cloud computing is using web-based software hosted on a dedicated server elsewhere instead of buying a copy for each individual computer. Traditionally, each computer had its own operating system and its own software, but this is changing as software moves “into the cloud.” The variety of services available in the cloud is increasing. According to Gartner Group, cloud revenue could grow from $56 billion in 2009 to $150 billion in 2013 – that’s a jump of 63%! [1]
Cloud Computing Providers
Google Docs is one example of a cloud computing service. Google provides a word processor, spreadsheet program, presentation software, and a form builder as part of its Docs suite. All of these are web-based, so users can share the documents easily, without the need to email them or transfer them to another users’ computer with a physical storage device (e.g., a thumb drive). Google Docs, which is free, replaces most of the functions of a traditional software bundle like Microsoft Office. Users can save themselves several hundred dollars per computer if they opt to use it instead of paying for Office. In an effort to compete with Google, in 2010, Microsoft released its own free, web-based service as well, to mixed reviews. [2] [3]
Cloud-based Providers Based in the Cloud
Located in the cloud itself, 37Signals provides cloud-based collaboration and project management software to companies. As the number of customers using their software grew, 37Signals had a choice: it could either build their own servers, making sure the company had enough computing power and backup capability to keep up with demand, or it could outsource network administration. Executives decided that it was easier and cheaper to rent space on Amazon’s S3 network. Pleased with their decision, they let Amazon manage the networking and are able to focus their own efforts on creating applications to help customers be more productive. [4]
Dropbox is a cloud service that allows users to store and sync files online. Users can store photos, videos, and other types of files so they can access them from anywhere in the world and don’t have to worry about always having a storage device with them. In the past, transferring data from an old computer to a new one was a hassle. People would first have to transfer a file to a storage device, then later transfer it to their new computer. A service like Dropbox allows users to leave the data in the cloud so that it doesn’t affect them when they change devices. Another plus is that users no longer need to update contacts or reload all of their settings each time they replace their computer. Like 37Signals, Dropbox also runs in the cloud, using Amazon’s S3 as its technology platform. [5]
Benefits for Companies
Cloud computing allows companies to match computing power more closely with the demands of the business. When a company is first started, it needs relatively few services, but with growth needs can change rapidly. With cloud computing, a company can add computing power quickly without buying new hardware. It can incrementally grow the IT system at the same pace as the business. According to Mark Benioff, author of “Behind the Cloud: The Untold Story of How Salesforce.com Went from Idea to Billion-Dollar Company – and Revolutionized an Industry”, for businesses, “there’s no longer a need to buy servers and software.” [6]
Competition is growing among cloud-based service providers. Benioff, who helped found Salesforce.com, a cloud-based provider of business services, says that the company “used to be alone, but now there is a robust marketplace of cloud applications and cloud platforms. There are many clouds to choose from – everything from financials to the classic productivity apps we all use every day.” Benioff claims that by using the cloud, companies can achieve the results they want “five times faster at half the cost,” compared to traditional server/software models.
Examples of Companies that use the Cloud
The cloud’s benefits have led a number of very successful companies to jump on the bandwagon. TheNew York Times, Nasdaq, ESPN, and Major League Baseball all use the cloud as a platform for their websites. [7]
Cloud computing can lead to some interesting collaboration between companies who might not otherwise work together. Netflix, for example, runs many of its services on Amazon’s networks. Amazon is a competitor in the streaming movie business, but it also is one of the major providers of “cloud computing” services in the world. [8]
In addition to having applications online, there are also web-based operating systems that allow customers to create a virtual computer, accessible from anywhere there is an Internet connection. Services such as iCloud, GlideOS, and the soon-to-be-released Chrome OS from Google will allow people to work on any device that has a web browser at any time. [9]
Governments Use Cloud Services to Save Money
In addition to the private sector, government entities are also finding that cloud computing can be better than building and running their own networks. The City of Panama City, Florida, for example uses Google Docs for its word processing and spreadsheet needs. [10]
The City of Los Angeles moved to cloud-based services from Google Apps in 2009, when it replaced its IT networks. The city estimated that it would save $750,000 in electricity costs alone by moving its email to Google. On top of that, there are more savings available in reduced maintenance costs. [11]
The federal government is edging toward cloud-based services, too. According to Vivek Kundra, the federal government’s chief information officer, the Agriculture Department is moving onto Microsoft’s Azure platform, which will save the government $27 million. He expects this trend to continue over the next few years, as the government plans to shut down 800 data centers by 2015. Savings like this should please politicians from all levels of the political spectrum. [12]
Universities are also switching over to the cloud, especially with their email systems. In fact, 50% of universities have already outsourced email, primarily because webmail companies can provide better technology with more services than the university can, all at a lower cost. A university can save hundreds of thousands of dollars per year by outsourcing its email. [13] [14]
There Could Be a Cloud in Your Future
For businesses, the proliferation of cloud computing services makes sense. It reduces start-up costs, speeds up innovation, and allows companies to grow more quickly at lower investment levels, letting them concentrate on what they do best without worrying about their IT infrastructure.
Cloud services have let consumers connect with friends, share photos and videos with each other, and move their media online so that they can access it from a variety of devices and places. All of the benefits of cloud computing make it likely that one day we will look back on the days of individual computers’ unique operating system and software as the dark ages of computing. In fact, it might be sooner than you think.
A colleague of mine started runningFolding@Home on a few PCs in his office last summer. When a load of powerful servers were freed up at the end of last year, I figured that since we now had a lot of spares in the data center, why not see what kind of PPD we could squeeze out of them?
For those who have never heard of it, Folding@home is a distributed computing project. People from around the world download and run a piece of software, all of which combine together to make one of the largest supercomputers in the world, which is used by scientists to simulate and study protien folding. You can read more about the project here.
Originally we started out with a little over sixty dual-5420/5520 Xeon servers (8-12GB RAM each) running one instance of the regular CPU client for each CPU core. This gave a big boost to our rankings, going from a very low number to the mid-2000s pretty quickly.
As the 5420/5520 servers were used up by new orders (and as we bought more powerful servers), I started running the SMP client (with the -bigadv option to increase the PPD) on a few Dell PowerEdge R810 servers (each with four quad-core HT-capable Xeons – a staggering 32 logical cores per server), which resulted in an enormous PPD increase.
We later had a bunch ofGPU Cloud servers sent over from another datacentre, each with two 5620 Xeons, between 12 and 48GB RAM and two nVidia Fermi GPUs (pictured). With sixteen of these servers running two GPU Folding clients and the CPU SMP client (again with the -bigadv option), we shot up the team rankings, going from the low 1000s in early January to our current position of 232nd worldwide! And we’re still climbing…
The power usage of these servers is also pretty phenomenal; each GPU servers uses a little over 2amps (at ~240VAC) when running at 100% CPU/GPU load, which equates to just under 40 amps for all sixteen. Each R810 uses about 4amps at full load (2amps per PSU) while the dual-5420/5520 servers only use approximately 1amp each.
And of course, with big power usage comes big heat output: each GPU server throws out an epic amount of hot air at over 50°C (122°F). You could heat a pretty big room with a single one of these GPU servers, as long as the occupants didn’t mind the horrendous noise the fans make at full speed.
Fred Taylor-Young works as a Data Center Operations Technician in our UK data center. This post was originally posted on his site, fr3d.org. P9D9WTFA4BMR
It’s exciting times to be in the network game, especially when it comes to the datacenter. It’s in this environment, service providers around the world have seen tremendous traffic growth and security requirements from their customers that can stress the capacity and capabilities of their current networks. No longer is it a matter of tailoring a datacenter for just web hosting; service providers need to make sure their networks can be flexible enough to accommodate the many types of customer usages (Web, VOIP, MMORPG, Video, Mobile Apps, Storage, etc.) AND deliver carrier services such as MPLS/VPLS, IDS/IPS, IPv6, and dynamic routing protocol signaling to customers (eg. BGP). To top it all off, service providers need to accommodate the new cloud strategies, as customers scramble to find server virtualization products that meet their needs for reduced costs and getting horsepower on demand. With the wide variety of cloud offerings available (and growing), the network operator has to have an infrastructure flexible enough to accommodate the complex requirements of each type of cloud product.
So what’s a network engineer to do to in the face of ever-growing challenges that their customer requirements pose? Keep adding etherchannel links within an oversubscribed network access layer, adjust complex spanning tree algorithms and hope to hell that nobody plugs in a switch in the wrong port that could potentially tear down the whole datacenter? Even with the emergence and availability of 10 Gb ports in today’s DC networks, maintaining a loop free topology becomes increasingly difficult as network access layers grow in size, and inefficient. Locking down a network so that only a very few select operators can work on it, is not an option; Try explaining to the COO that you are slowing down provisioning of customers and keeping operational departments on standby, in the interest of maintaining network stability. Safe to say you won’t win that argument;->
Fortunately, the network hardware vendors recognized these business challenges in the datacenter, and have come up with new strategies and designs that call for the minimization or complete eradication of complex spanning tree protocols inside the DC, while at the same time providing a high availability, highly flexible, easy to scale, and of course a high performing network. PEER 1 Hosting had the chance to review and assess DC strategies from some of these vendors over the last 24 months as we prepared for the new network deployment in our flagship datacenter in Toronto.
Cisco Virtual Switch System (VSS) & Nexus Platform
The Cisco VSS is a network system virtualization technology that pools multiple Cisco Catalyst 6500 Series routers into one virtual router. Access Layer switches connect to this pool of 6500’s, and run Multichassis Etherchannel protocol across multiple links, and all links are live (multipath). There is no port blocking or spanning tree involved on these links, giving high throughput capabilities. Some highlights of the VSS design are ease of management (at the routing level anyways), no need for spanning tree at least at one level, no need for HSRP/VRRP/GLBP, and flexible deployments options as switches can de positioned in various locations throughout the DC, connecting back to the 6500’s either by Gigabit or 10 Gigabit interfaces.
On the heels of VSS strategy, Cisco also came out with another virtualization design that started at the access layer instead of the distribution. The Nexus 5000/2000 Platform virtualizes the access layer by using a pair of 1U 5000 model switches that act as ‘parents’ to a maximum of 12 Nexus 2000 fabric extenders. All devices act as a single logical unit, flattening the access layer, simplifying operations and removing the need for spanning tree. The Nexus seems to be the dominant datacenter strategy for Cisco, as it addresses a lot of the ‘moving parts’ and requirements at the access layer instead of just at the distribution layer like the VSS does; operationally speaking, the access layer has been the most volatile to deal with inside any large enterprise datacenters.
Brocade TRILL
While not a Brocade specific protocol, the TRILL (Transparent Interconnection of Lots of Links) protocol has been embraced by the company for their datacenter network initiatives. Akin to VSS, TRILL introduces multipath into the Layer 2 networks, while at the same time minimizing the need for spanning tree. In a flattened layer 2 network, TRILL requires each device to run a link state protocol amongst themselves to identify optimal paths through the various links within (via ISIS or in Brocade’s case FSP). In the Brocade implementation, switches participating in the TRILL protocol will auto discover and auto-configure each other to form a single logical switch to the rest of the datacenter network as one large switch. The very recent launch of the Brocade VDX Datacenter Ethernet Fabric is being touted as significant development on their Trill strategy, and initial indications are impressive.
This tactic, coupled with their Multi Chassis trunking solution at the distribution layer (very similar to the Cisco VSS), brings a lot of simplicity and scalability to the datacenter network. And because TRILL is an IETF protocol, it should allow for interoperability with other hardware vendors, such as Cisco and HP, although I wouldn’t hold my breath for this to be realized any time soon..
Juniper Virtual Chassis & Stratus
Taking a decidedly different path, Juniper has taken a proprietary approach for the datacenter fabric, which is as a bold step for company traditionally viewed as being in the carrier space only. Starting with their virtual chassis (VC) EX4200 switch fabrics, one of the first to market in this sphere (Brocade has a FCX switch fabric in this sphere), Juniper was able to provide the first 10 member VC switch fabric with a 128 Gb/s backplane. This virtual chassis, not to be confused with stackable switches, has an ‘any to any’ port mapping within, meaning that full Ethernet packet processing is executed only once upon entering the VC and the packet is transported to the exit port without repeating that processing; a radical departure from what happens in typical tree architectures seen in most datacenter network implementations. Even in a TRILL implementation, each network element has to do it’s own packet processing as a packet passes within a TRILL boundary. To deliver the any-to-any port mapping, the EX4200 uses shortest-path, cost-aware and multicast-aware protocol, ensuring optimal use of the VC backplane resources and allowing multipath and extended reach topologies; a huge advantage when it comes to customizing a network deployment to the unique needs of each datacenter.
Aside from the flattening and simplification of the data plane, the EX4200 proprietary approach calls for a single control plane (unlike TRILL), which allows for master/backup routing engine architecture within a VC, and all members have a consistent view of the forwarding database. This provides for substantial improvement in management and availability, inherently lower latencies and excellent cross-sectional bandwidth. And of course removes the need for the dreaded spanning tree protocol from your operation.
Everything I’ve discussed has pertained to the access layer so far, but Juniper’s vision, known as the Stratus Project, is to realize the any-to-any, single control plane design to encompass the distribution and edge routers. Their ultimate goal is to have the whole datacenter network be administered as one big logical switch, allowing for simplicity, huge scale, and great flexibility.
So, Who did PEER 1 Hosting Choose?
After taking all the vendor proposals into consideration with what we wanted to achieve at our new flagship datacenter in Toronto, we went with the Juniper solution. Our DC design called for top of rack switches for individual rows, where each row needed a minimum of 10 Gb/s trunk capability, and an ability to LAG up in 10 Gb increments for massive capacity. We also needed network profiles for customers to easily move anywhere throughout the DC, for many reasons including vMotion and supporting non linear customer growth. In addition to meeting our requirement for removing spanning tree and providing huge flexibility and simplicity, the Juniper platform also has the added benefit in its operating system by providing onboard automation. As most network engineers are quasi developers and scripters at heart, we were able to start developing operational, event driven, and commit scripts on the network devices themselves to help manage the network infrastructure. We are also exploring utilizing this onboard automation to enhance the current automated provisioning process of our hosting products.
At the time of our decision, it was seen as a bold move to use Juniper, as it was not regarded as a traditional datacenter network vendor. However, we’ve been duly impressed by the rollout, and it would seem that the industry recognizes this as well: Juniper’s Enterprise product line appeared recently in the Gartner Magic Quadrant in the Enterprise Lan as a challenger to the traditional incumbents of Cisco and HP (http://www.gartner.com/technology/media-products/reprints/juniper/vol6/article4/article4.html), as well as being identified in the latest market share report from Dell’Oro Group showing Juniper advancing to the #3 spot in the Ethernet switch market. It’s been enough of a success in our new Toronto DC , that we chose to use the same strategy in upgrading our Serverbeach networks. I’ll describe that in a later post.
Chat Now
Email Us
Fans of HBO’s hit series True Blood are getting glamorous this month, thanks to Los Angeles based interactive agencies Haus, BBDO, and the PEER 1 Hosting GPU cloud.
Today, marks a major milestone at PEER 1 Hosting. We have officially unveiled our new public cloud hosting service, 
“The sharing of content among consumer circles will dominate the consumer cloud,” noted Greg Rusu, General Manager of Zunicore, PEER 1 Hosting’s newest division focused on cloud computing.
Nowadays, it’s about process workload and being able to scale to meet the needs of your customer. The only way you’re going to be able to do that is to effectively balance your systems to the appropriate clusters and have the ability to right size your virtuals so you get the most value for your investment. You can’t make informed decisions about capacity without the right tools in place to monitor for trends, consumption, burst and cost.
The cloud’s benefits have led a number of very successful companies to jump on the bandwagon. The New York Times, Nasdaq, ESPN, and Major League Baseball all use the cloud as a platform for their websites. [7]
Cloud computing can lead to some interesting collaboration between companies who might not otherwise work together. Netflix, for example, runs many of its services on Amazon’s networks. Amazon is a competitor in the streaming movie business, but it also is one of the major providers of “cloud computing” services in the world. [8]
Twitter
Badges
