Archivo de la categoría: Networking

Amazon, Amazon AWS, Amazon Web Services, AWS, Cloud & IT Management, Cloud computing, Data center, Disaster Recovery/Business Continuity, Hardware, James Hamilton, Networking

Wired Profiles a New Breed of Internet Hero, the Data Center Guru

febrero 19, 2013 Richard

The whole idea of cloud computing is that mere mortals can stop worrying about hardware and focus on delivering applications. But cloud services like Amazon’s AWS, and the amazingly complex hardware and software that underpins all that power and flexibility, do not happen by chance. This Wired article about James Hamilton paints of a picture of a new breed of folks the Internet has come to rely on:

…with this enormous success comes a whole new set of computing problems, and James Hamilton is one of the key thinkers charged with solving such problems, striving to rethink the data center for the age of cloud computing. Much like two other cloud computing giants — Google and Microsoft — Amazon says very little about the particulars of its data center work, viewing this as the most important of trade secrets, but Hamilton is held in such high regard, he’s one of the few Amazon employees permitted to blog about his big ideas, and the fifty-something Canadian has developed a reputation across the industry as a guru of distributing systems — the kind of massive online operations that Amazon builds to support thousands of companies across the globe.

Read the article.

CDN, Cloud & IT Management, Content delivery network, Content Management, EMEA, hybrid cloud, Le Nouvel Observateur, Multimedia & Internet, Networking, Nouvel Observateur, Openmix, User Story

Le Nouvel Observateur Digital Uses Openmix Hybrid CDN Strategy for News Cycle Load Balancing

diciembre 21, 2012 Richard

Sudden traffic load bursts following the news is business as usual for an online news provider. When the news is hot, interruptions and heavy slow-downs are common things on various websites; which can mean loss of audience and consequently loss of revenues, forcing technical teams to constantly anticipate any possible incident.

The third most read news & politics media in France, as per a September 2012 Nielsen study, with almost 8 million unique visitors every month, Le Nouvel Observateur recently chose the Cedexis “Openmix” load balancing solution to roll out and manage its own hybrid CDN — a mix of their infrastructure at origin and their own cache servers spread among various webhosting providers with third parties CDNs.

Rolled out during the second quarter of 2012, Le Nouvel Observateur’s hybrid CDN strategy now includes two content origins, backed by Varnish cache servers, located at two French hosting providers whose performance had been previously measured with Cedexis Radar as being optimum for serving their French audience. A global CDN is also used, mostly to deliver content to their international audience.

Details can be found in a case study published by Cedexis.

Business transaction management, Deep Packet Inspection, Ipanema, Ipanema Technologies, Networking

Ipanema Technologies Updates Its Autonomic Networking System

diciembre 11, 2012 Richard

Ipanema Technologies today released v7.1 of its Autonomic Networking System (ANS). This new release includes enhancements that improve application visibility, control, and performance, giving large enterprises, particularly those in the cloud, the ability to manage increased data volumes.

With ANS v7.1 using a new software architecture and faster Deep Packet Inspection (DPI), Ipanema triples its high-end device performance (ip|e1800ax) reaching up to 20,000 new connections per second. This results in a throughput of 2Gbps alongside a classification system recognizing over 300 applications out of the box. Intelligent device clustering guarantees business application performance up to 10GBPS. As a result, companies are better placed to cope with the significant year-on-year traffic growth they are now experiencing.

Other additional ANS v7.1 enhancements include:

Cloud application performance report. The new Cloud
Application Monitoring (CAM) report allows enterprises to understand
and control the cloud applications usage and performance from the user
perspective in the branch offices.
Virtual appliances (virtual|engine) that can be deployed as an
alternative to hardware appliances in virtualized data centers and
branch offices. ANS v7.1 enables hybrid deployments of physical and
virtual devices that work together to measure control and optimize all
application traffic across the enterprise.

For more information, visit: www.ipanematech.com

WAN Governance (blog) | Ipanema Users Group (LinkedIn) | Follow Ipanema (Twitter)

LAN, Network Infrastructure, Networking, WLAN

Optimizing Controller-Based Wireless LANs with Good Old-Fashioned Autonomous Concepts. Well – Kinda.

noviembre 6, 2012 Nate Schnable

Get your attention yet? This isn’t fresh news by any stretch, but there are some good concepts to observe when deploying today’s controller-based WLANs. We have known for years the benefits of the typical controller-based wireless networks. The intelligence that the controller has of the access points (APs) and the ability to dynamically change channels and power outputs is obviously fantastic. Depends on the manufacturer as to what they call it – Radio Resource Management or Adaptive Radio Management etc. Either way, it’s one of the main reasons to go to a controller-based solution.

On top of this we also can get Layer 3 roaming capabilities. A typical controller-based solution has each individual access point create a tunnel back to the controller. In a lot of cases this gives you the ability to roam between L3 subnets. Consider a scenario where you have a corporate campus – there very well could be a voice and a data VLAN per closet. If the access point didn’t tunnel back to a controller we would potentially drop sessions (unless you extended a wireless VLAN across campus which has its own implications) when you went from one AP on one subnet to another AP on a disparate one. Often, this may not be an issue with some standard TCP applications – but if we are talking about time-sensitive applications such as voice this could be disastrous. If we have a tunnel from each AP to the controller, we can now set up Layer 3 roaming capabilities without having to create a sprawling wireless VLAN. Voice connections stay up and all is good – right?

So what happens if we have a situation – let’s call it a remote office without a controller – where you want to keep local traffic local, but tunnel the rest of the traffic back to a controller at the Data Center. If we stick to the newer model, all traffic gets directed to the controller via the tunnel. Kind of seems pointless for me at a remote branch sending a print job back to the Data Center and then back to the remote office to the printer next to me right? Many companies now are allowing their controller-based solutions to “hairpin” local traffic to keep it local rather than waste valuable bandwidth. This hybrid or HREAP type approach does in fact give us the ability to glean the benefits of both the centralized intelligence of the controller, but also can minimize the bandwidth burden that these tunnels take up. If it’s meant for the Data Center so be it; if it’s meant to remain local we can do that too. If the remote office is large enough to warrant its own local controller then that is a different conversation – until next time.

We’ll be holding educational events in Boston, NYC, and Atlanta over the month of November. Should be a lot of good info and a great networking opportunity. Click for registration details.

Internet Protocol Address Management, Internet Technology, IP address, Networking

6Connect Launches Cloud-Based Network Automation Suite for Next-Gen IP Networks

octubre 22, 2012 Richard

6connect, Inc. today announced at Interop in New York City, their new automated, cloud control suite architected from the ground-up for a new era of IPv6 migration, rampant device and IP address proliferation, and widespread adoption of virtualization and cloud computing.

Delivered locally or through the cloud, the 6connect ProVision™ Suite offers Service Providers and Enterprises a future-ready, unified SaaS platform for provisioning and managing networks in today’s integrated IPv4 and IPv6 world. ProVision provides dramatic time and cost efficiencies over old spreadsheet-dependent and costly appliance solutions for IPAM, DNS, DHCP and asset management. The Service Provider Edition also incorporates peering management and SWIP automation.

“With the number of connected devices and virtual machines growing exponentially and regional internet registries for Europe and Asia already out of IPv4 space, network architectures are undergoing fundamental change,” said Bill Bien, CEO of 6connect. “Legacy DDI and automation solutions are no longer efficient. We’ve designed ProVision as a disruptive, next-generation platform for automated management control of complex IP address zones, virtual machines, mobile devices, and all types of corporate assets.”

The ProVision Suite comes with RESTful APIs that integrate through connector apps with existing business software, such as CRM, ERP and BPM. It provides easy access to portals and templates that provide better control and faster access to fully automated tools.

6connect’s cloud-based provisioning software is already used by leading service providers and enterprises around the world. With the launch of ProVision, 6connect now provides a single, integrated and vendor neutral platform for network discovery, planning, provisioning and management of IP resources and devices.

“6connect has helped us become much more efficient,” said Alex Latzko, Senior Architect, Lightower Fiber Networks. “We no longer use multiple incompatible systems, it’s unified now.”

With the Internet running out of IPv4 space, service providers and enterprise network operators need to manage the remaining inventory more closely than ever before, while they migrate to IPv6. 6connect makes managing these changes easy, scalable, and secure. With ProVision Suite, RIR (regional internet registry) and LIR (local internet registry) resource allocations are also integrated with the platform.

Data center, InfiniBand, Mellanox, Mellanox Technologies, Networking, Scalability, SDN

Mellanox Introduces SwitchX-2 Software Defined Networking VPI Switch

octubre 15, 2012 Richard

Mellanox Technologies today announced SwitchX-2, the next generation of its switch silicon optimized for Software Defined Networking (SDN). SwitchX-2 includes advanced capabilities of remote configurable routing tables, lossless and congestion free networks, efficient control planes, and SDN-optimized software interfaces. SwitchX-2 enables IT managers to program and centralize their server and storage interconnect management and dramatically reduce their operational expenses by completely virtualizing their data center network. According to IDC*, the broader SDN/OpenFlow market is expected to see rapid growth, reaching $2 billion by 2016, a significant portion of which will be network infrastructure.

SwitchX-2 is based on Mellanox’s leading Virtual Protocol Interconnect® (VPI) technology which allows for simultaneous connection to InfiniBand or Ethernet with integrated gateways to legacy data center and storage systems. Utilizing industry-first, RDMA-based 56Gb/s Ethernet and InfiniBand, SwitchX-2 is the world’s fastest, most scalable SDN switch with unmatched 4Tb/s switching capacity (50 percent higher than closest competition), the industry’s lowest power consumption, extremely low 170ns latency, hardware-based L2/L3 congestion management for highest efficiency and hardware-based data error correction for highest reliability. SwitchX-2’s advanced feature set enables the creation of larger flat SDN networks with lower cost and higher performance.

“Software Defined Networking is rapidly emerging as a key architectural element for next generation cloud, Web 2.0 and scalable data centers. As a building block for SDN-enabled network infrastructure, switches with high throughput, low latency and low power consumption are expected to be instrumental in realizing the goal of reducing operational expense while enabling data center scalability and flexibility,” said Rohit Mehra, vice president, Enterprise and Datacenter Networks, IDC. “Technologies such as Mellanox SwitchX-2, when built into next-generation data centers, will enable IT to benefit from the promise of Software Defined Networking by delivering improved throughput, latency and power, along with enhanced programmability, automation and control.”

“Mellanox’s SwitchX-2 VPI switch leads the industry with the highest throughout capacity, low latency with nearly zero jitter, as well as advanced SDN interfaces for control and management,” said David Barzilai, vice president of marketing at Mellanox Technologies. “SDN technology has been a critical component of the InfiniBand scalable architecture and has been proven worldwide in data centers and clusters of tens-of-thousands of servers. Now, with SwitchX-2, Mellanox provides the most efficient SDN solution for both InfiniBand and Ethernet data centers. Mellanox’s fast, RDMA-based interconnect technology leads the competition in terms of performance, SDN technology and return-on-investment advantages it brings to IT and application managers.”

Amazon, Candia, Midokura, Networking, Nicira, Start Up, Virtualization, VMware, Wired

NoSQL Pioneer Pino de Candia Taking Aim at Virtual Networking

septiembre 28, 2012 Richard

Wired has a good article today on some of the geniuses and startups in the Virtual Networking space, and how they might “remake the internet.”

Together with Dan Dumitriu — another Amazon vet steeped in the science of massive computing systems — de Candia is one of the key engineers behind a company called Midokura. Much like the oft-discussed Silicon Valley startup Nicira, Midokura deals in virtual networks — computer networks that exist only as software.

Over the past decade, VMware, Microsoft, and others have helped move the world’s computing applications onto virtual servers — machines that exist only as software — and now, a new of wave of companies is fashioning software for building complex virtual networks that tie all those virtual servers together. That’s a hard concept to grasp, but basically, these companies are moving the brains of the network out of hardware and into software.

Read the article.