Skip navigation
Help

Frankfurt

warning: Creating default object from empty value in /var/www/vhosts/sayforward.com/subdomains/recorder/httpdocs/modules/taxonomy/taxonomy.pages.inc on line 33.

CloudFlare's CDN is based on Anycast, a standard defined in the Border Gateway Protocol—the routing protocol that's at the center of how the Internet directs traffic. Anycast is part of how BGP supports the multi-homing of IP addresses, in which multiple routers connect a network to the Internet; through the broadcasts of IP addresses available through a router, other routers determine the shortest path for network traffic to take to reach that destination.

Using Anycast means that CloudFlare makes the servers it fronts appear to be in many places, while only using one IP address. "If you do a traceroute to Metallica.com (a CloudFlare customer), depending on where you are in the world, you would hit a different data center," Prince said. "But you're getting back the same IP address."

That means that as CloudFlare adds more data centers, and those data centers advertise the IP addresses of the websites that are fronted by the service, the Internet's core routers automatically re-map the routes to the IP addresses of the sites. There's no need to do anything special with the Domain Name Service to handle load-balancing of network traffic to sites other than point the hostname for a site at CloudFlare's IP address. It also means that when a specific data center needs to be taken down for an upgrade or maintenance (or gets knocked offline for some other reason), the routes can be adjusted on the fly.

That makes it much harder for distributed denial of service attacks to go after servers behind CloudFlare's CDN network; if they're geographically widespread, the traffic they generate gets spread across all of CloudFlare's data centers—as long as the network connections at each site aren't overcome.

0
Your rating: None

GCirc01E-025

Update: In my eagerness to announce these workshops I made a scheduling error, incorrectly thinking the dates would be March 15+16 rather than 16+17. As a result I need to move one of the workshops to the weekend before, and since the Intro workshop should happen before the Advanced the new dates will be:

  • Saturday March 9: Introduction to Processing and Generative Art
  • Saturday March 16: Generative Art, Advanced Topics

Sorry for the confusion! On the plus side the Intro workshop might now be a smaller group which should make it nice and intimate.

I haven’t done any workshops in New York since November, so I have decided to offer my Intro and Advanced Generative Art workshops back-to-back the weekend of March 16+17 on consecutive weekends, Saturday March 9 and Saturday March 17.

The venue will be my apartment in comfortable Park Slope, Brooklyn. As usual I have 8 spots available for each workshop, they do tend to reach capacity so get in touch sooner rather than later. Reservation is by email and your spot is confirmed once I receive payment via PayPal.

The workshops will be taught using the most recent Processing 2.0 beta version (2.0b8 as of this moment), and as usual I will be using my own Modelbuilder library as a toolkit for solving the tasks we look. Familiarizing yourself with Processing 2.0 and Modelbuilder would be good preparation.

Make sure to download Modelbuilder-0019 and Control-P5 2.0.4, then run through the provided examples. Check OpenProcessing.org for more Modelbuilder examples.

Note about dataviz: I know there is a lot of interest in data vizualization and I do get asked about that frequently in workshops. I can’t promise to cover data in detail since it’s a pretty big topic.

If you’re specifically looking for data techniques I would recommend looking at the excellent workshops series taught by my friend Jer Thorp. He currently offers two such workshops, titled “Processing and Data Visualization” and “Archive, Text, & Character(s)”.

0
Your rating: None

The inside of Equinix's co-location facility in San Jose—the home of CloudFlare's primary data center.

Photo: Peter McCollough/Wired.com

On August 22, CloudFlare, a content delivery network, turned on a brand new data center in Seoul, Korea—the last of ten new facilities started across four continents in a span of thirty days. The Seoul data center brought CloudFlare's number of data centers up to 23, nearly doubling the company's global reach—a significant feat in itself for a company of just 32 employees.

But there was something else relatively significant about the Seoul data center and the other 9 facilities set up this summer: despite the fact that the company owned every router and every server in their racks, and each had been configured with great care to handle the demands of CloudFlare's CDN and security services, no one from CloudFlare had ever set foot in them. All that came from CloudFlare directly was a six-page manual instructing facility managers and local suppliers on how to rack and plug in the boxes shipped to them.

"We have nobody stationed in Stockholm or Seoul or Sydney, or a lot of the places that we put these new data centers," CloudFlare CEO Matthew Prince told Ars. "In fact, no CloudFlare employees have stepped foot in half of the facilities where we've launched." The totally remote-controlled data center approach used by the company is one of the reasons that CloudFlare can afford to provide its services for free to most of its customers—and still make a 75 percent profit margin.

Read 24 remaining paragraphs | Comments

0
Your rating: None

Yes, we’ve all laughed at Ted Steven’s “series of tubes” line—including Jon Stewart. But as Andrew Blum writes in his new book, Tubes: A Journey to the Center of the Internet, the Internet may be more tube-like than most people realize.

Sure, if you’re an Ars reader, chances are that you have at least a basic understanding of how the Internet works. That is to say, of course, the computer you’re on right now talks to your ISP, which in turn talks to a central hub, which in turn connects to other networks, over fiber optic cables, and so forth. All in tiny fractions of seconds, all the way to its destination. You probably understand the basic principle of packet switching, that the route of data can change, and indeed, that this is its primary innovation.

But even the most geeky network engineers among us may not know that the very first original TCP/IP router, the “IMP,” was nearly tossed out of its original University of California, Los Angeles home. Or how oddly appropriate it was for an early porn site from the late 1990s, Danni.com [NSFW], to have a photo shoot at an important Internet exchange, called MAE-West. Or, who the current power couple of the North American Network Operators’ Group is.

Read more | Comments

0
Your rating: None