“It’s impossible to solve significant problems using the same level of knowledge that created them!” –Albert Einstein Outages happen- it’s a simple fact of running any type of system, be it network, server, application, aviation, nuclear, etc. Urs Hölzle, a Distinguished Fellow at Google and it’s first vice president of engineering, plainly states it this […]
The hype surrounding SDN (Software-Defined Networking) and now NFV (Network Function Virtualization) is widely known. As one of the first to enter the market of innovative network solutions, I have seen new players enter (and exit) while others have re-positioned themselves to try to get a share of the pie. I’m proud to say that we have remained committed to the vision we laid out at the beginning and are delivering real products to real customers that execute on that vision.
While championing the advantages and benefits that SDN enables, in many ways we steered clear of the hype around Layer 2 solutions created to solve problems that customers don’t have. We listened to customers that craved solutions that are disruptive, but not destructive. We focused on delivering evolutionary solutions that provided new tools to the right people rather than forcing unnecessary organization and infrastructure changes; and our customers rewarded us with their investments.
Today, we are announcing our support for OpFlex, a new open, standards-based protocol that provides a unique mechanism to enable a network controller such as Cisco’s Application Policy Infrastructure Controller (APIC) to transfer abstract policies to a set of “smart” devices capable of directly rendering Continue reading
Well deserved Overall Best of Interop (in my opinion) for OpenDaylight Hydrogen release. As the IEEE and IETF fail deliver on innovation we are turning to open source for real progress & change in networking. While the Open Daylight Hydrogen release is a bit rough, it deserves the Best of Interop award for the reasons […]
The post Response: Best Of Interop 2014 Winners Unveiled appeared first on EtherealMind.
While perusing vendor datasheets, have you ever questioned the inclusion of seemingly insignificant latency specifications? Take a look at Arista's line-up, for instance. Their 7500 series chassis lists a port-to-port latency of up to 13 microseconds (that's thirteen thousandths of a millisecond) whereas their "ultra-low latency" 7150 series switches provide sub-microsecond latency.
But who cares? Both values can be roughly translated as "zero" for us wetware-powered humans. (For reference, 8,333 microseconds pass in the time it takes your shiny new 120 Hz HDTV to complete one screen refresh.) So, does anyone really care about such obscenely low latency?
For a certain few organizations involved in high-frequency stock trading, those shaved microseconds can add up to billions of dollars in profit. The New York Times recently published an article titled The Wolf Hunters of Wall Street by Michael Lewis, which reveals how banks have leveraged low network latency to manipulate stock prices in open markets. (Thanks to @priscillaoppy for the tip!)
The increments of time involved were absurdly small: In theory, the fastest travel time, from Katsuyama’s desk in Manhattan to the BATS exchange in Weehawken, N.J., was about two milliseconds, and the slowest, from Continue reading
From Juniper to Cisco to VMware, companies are spouting up new SDN solutions. Juniper’s Contrail, Cisco’s ACI, VMware’s NSX, and more are all vying to be the next generation of data center networking. What is surprising, however, is what’s at the heart of these new technologies.
Is it VXLAN, NVGRE, Openflow? Nope. It’s Fibre Channel.
Seriously.
If you think about it, it makes sense. Fibre Channel has been doing fabrics since before we ever called Ethernet fabrics, well, fabrics. And this isn’t the first time that Fibre Channel has shown up in unusual places. There’s a version of Fibre Channel that runs inside certain airplanes, including jet fighters like the F-22.
Keep the skies safe from FCoE (sponsored by the Evaluator Group)
New generation of switches have been capable of Data Center Bridging (DCB), which enables Fibre Channel over Ethernet. These chips are also capable of doing native Fibre Channel So rather than build complicated VPLS fabrics or routed networks, various data center switching companies are leveraging the inherent Fibre Channel capabilities of the merchant silicon and building Fibre Channel-based underlay networks to support an IP-based overlay.
Buffer-to-buffer (B2B) credit system and losslessness of Fibre Channel, plus the new 32/128 Continue reading
Route Analytics in the Age of SDN - Now, More than Ever.
One of the biggest problems that may delay widespread SDN adoption is not a problem of coding or engineering, but one of poetry.
Network management is about logic and reason, but our nomenclature was written by poets. Even the word “networking” calls to the image a “netting work” - like you would find on a hammock or trapeze artist's safety net. We talk about network “pipes,” and conjure throughput like liquid water flowing through Roman aqueducts or modern PVC piping. We think of the “flow” of data through those pipes, though the only “fluid” is the movement of electrons – if that.
Metaphors that are inelegant or uninformative (“Information Superhighway” for example) fail.
Which is why SDN can be hard to envision. Intellectually, we know that it is about separating the control of where data is sent and the hardware that actually sends it. But what metaphor can we conjure that makes sense to explain this concept?
This is a problem for poets.
One metaphor that was recently used in IT Business Edge was the idea of “relying Continue reading
By its action the Commission significantly increased the utility of the 100 megahertz of spectrum, and streamlined existing rules and equipment authorization procedures for devices throughout the 5 GHz band.This ruling makes the following changes to the UNII-1 band:
The Dell networking team has asked the Packet Pushers to co-host a couple of Interop sessions at their booth. Greg Ferro and Ethan Banks will be at the Dell booth on Tuesday, 1-April and Wednesday, 2-April at 3:45pm. In the Tuesday session, we’ll be discussing the new Dell Z9500. In the Wednesday session, we’ll discuss […]
The post The Packet Pushers At Dell’s Interop Booth Tuesday & Wednesday @ 3:45pm appeared first on Packet Pushers Podcast and was written by Ethan Banks.
Earlier this month, the International Cable Protection Committee, a submarine cable advisory group, held their annual plenary in Dubai. One question that they could have considered is: Why do so many submarine cables get cut in the February/March timeframe? In this blog, we’ll look back at the last three years and the submarine cable industry’s own version of March Madness.
2012
Two years ago in February 2012, we saw a rash of closely-timed submarine cable cuts, causing Internet disruptions extending into March. In one incident, three cables were simultaneously severed in the Red Sea on February 17th, and then a fourth was damaged on the 25th off the coast of Kenya. The fourth cable was the TEAMS (The East African Marine System) cable systems, which runs from Mombasa to Fujairah, UAE.
| We detailed the impact of the TEAMS cable break here, noting the resilience of many East African providers, who had purchased redundant capacity on the other two East African submarine cables: EASSy and SEACOM. The TEAMS cable would experience a second cut just weeks after it was repaired, which led TEAMS to threaten a lawsuit against the Kenya Ports Authority (KPA) over the repeated damage caused by Continue reading |
How do vendors decide to make network products ? What is the process and thinking behind what happens inside the wall of the vendor ? Today, Greg is join by Omar Sultan from Cisco to talk broadly about how vendors make big decisions
The post Show 185 – Vendor Product Management appeared first on Packet Pushers Podcast and was written by Greg Ferro.
Some time ago I wrote that FCoE would have problems on 10GBaseT due to relatively high error rates of 10GBaseT deployment. New information suggests that this problem is solved under certain circumstances.
The post FCoE, 10GBaseT and BER – problem managed appeared first on EtherealMind.
That’s right listeners, you’re not in Kansas anymore! It’s time to follow that Yellow Brick Road to another episode of Healthy Paranoia. Today, we’ll be discussing phone phreaking, hacking and fraud, oh my! So we’re off to see Wizard, the Wonderful Wizard of VoIP security, Patrick McNeil. Joining me over the rainbow for this trip […]
The post Healthy Paranoia Show 23: Phone Phreaking, Hacking and Fraud, Oh My! appeared first on Packet Pushers Podcast and was written by Mrs. Y.
Internet censorship in Turkey took a new and ominous turn yesterday. In order to better seal off access to social media sites like YouTube and Twitter, the incumbent TurkTelecom began hijacking the IP address space of public DNS resolvers like those of Google. This allows TurkTelecom servers to masquerade as Google DNS servers, returning whatever answers they want. Under normal circumstances, such queries would have been destined for servers outside the country, which is how Turkish users were circumventing the ban on YouTube imposed earlier this week. However, now local users of these global DNS services are surreptitiously redirected to alternate providers within TurkTelekom. You can see this route redirection for yourself, here and here.
Recap
Turkey’s 25th and current Prime Minister, Recep Tayyip Erdoğan, has publicly and repeatedly expressed his dislike of social media, instructing various sites to be blocked. The current attempt to curtail this important medium began on March 21st via DNS poisoning of Twitter by Turkish ISPs, probably trying to implement the government-mandated ban in a minimally invasive way.
Twitter blocked in Turkey via local DNS poisoning, global DNS providers not impacted: http://t.co/qFEBPXAho8 pic.twitter.com/JDL8SNv62G
— Renesys Corporation (@renesys) March 21, 2014
But Continue reading
At BGPmon we see numerous BGP hijacks every single day, some are interesting because of the size and scale of the hijack or as we’ve seen today because of the targeted hijacked prefixes.
It all started last weekend when the Turkish president ordered the censorship of twitter.com. This started with a block of twitter by returning false twitter IP addresses by Turk Telekom DNS servers. Soon users in Turkey discovered that changing DNS providers to Google DNS or OpenDNS was a good method of bypassing the censorship.
But as of around 9am UTC today (Saturday March 29) this changed when Turk Telekom started to hijack the IP address for popular free and open DNS providers such as Google’s 8.8.8.8, OpenDNS’ 208.67.222.222 and Level3’s 4.2.2.2.
BGP hijack
Using the Turk Telekom looking glass we can see that AS9121 (Turk Telekom) has specific /32 routes for these IP addresses. Since this is the most specific route possible for an IPv4 address, this route will always be selected and the result is that traffic for this IP address is sent to this new bogus route.
Turk Telekom route server displaying the Continue reading
Do you feel like you are in data center acronym soup these days? I sure feel it, and I think sometimes tech-speak can help mask the real driver for change. In the data center, we are striving for a new model. The idea of real time resource allocation and reallocation, the ideal organism that responds perfectly to every request and oh, did I mention resiliency in the whole stack for instant recovery from any fault. Wow, that would be great! I think we have a ways to go. For now, the latest craze is to add the word virtualization to each topic.
Why is that? I think it is because virtualization has helped us learn that you can decouple the hardware and software and create layers of abstraction that lead to better systems. And here “better” could be lower power / cooling and space utilization, or it could the idea that a virtual machine (VM) can be your 18 wheeler, or container ship, and move the application
or data anywhere you want, to help in that resource allocation / re allocation or resiliency story I mentioned above.
Now if we look on the network side, Continue reading
This is the write-up of a recent event we experienced on our network. This will be combination of a journal of symptoms, troubleshooting steps taken, and a brief overview of the environment and platforms involved. This isn’t a forensic analysis of the cause or of different behaviors in various environments. Rather, it’s meant to be […]
Collection of useful, relevant or just fun places on the Internets for 28th March 2014 and a bit commentary about what I’ve found interesting about them: Brocade – Brocade Extends Ethernet Fabric Leadership – Brocade hasn’t given up on the Campus. This announcement from February talks about their switch platform, most interesting is that […]
The post Internets of Interest for 28th March 2014 appeared first on EtherealMind.
