From Zero to One Hundred in the Arctic Slope
In November 2017, the Internet Society hosted the inaugural Indigenous Connectivity Summit in Santa Fe, New Mexico. The event brought together community network operators, Internet service providers, community members, researchers, policy makers, and Indigenous leadership. One of the participants shared her story.
“‘Mom, did you have YouTube?’” Patuk Glenn, recalls her six year old son asking. Glenn, who lives in Utqiaġvik – a city in Alaska north of the Arctic Circle – laughs as she remembers one of his first words: “loading,” thanks to the sluggish Internet speeds on the Arctic Slope. But things are changing, and soon. Fiber optic cable is going live in Glenn’s community and she has travelled to the Indigenous Connectivity Summit looking for lessons from other Indigenous communities. “We’re going from zero to one hundred overnight,” says Glenn. “How can we best prepare our people?”
It’s not just a question of digital literacy. Glenn’s looking for information on cybersecurity and entrepreneurship – as high-speed Internet opens avenues for economic development and for community members to share their own content with the rest of the world. Like many summit participants, Glenn sees connectivity as a pathway to enable education: not only unlocking online courses, but Continue reading
Twinax – Cheap, Cheerful and Annoyingly Chubby
What’s not to love about twinax? Formerly the exclusive domain of IBM systems, twinax has seen itself reborn in the last few years in the form of the Direct Attach Cable (DAC) used to connect systems at speeds of 10Gbps and 40Gbps (by way of bundling four twinax pairs in a single cable).
Direct Attach Cables
Before diving into the pros and cons of DAC, it’s important to understand the different varieties that are available. A DAC is a cable which has SFP+ format connectors hard-wired on each end; plug each end into an SFP+ socket and, vendor support notwithstanding, the link should come up. A direct attach cable is frequently and erroneously referred to as a “DAC cable”, so if the words “PIN number” give you the jitters, working anywhere with DACs is likely to drive you to drink.
Passive Copper DAC (Twinax)
The most common kind of DAC is the passive DAC. The SFP+ connector on a passive DAC, give or take some electrical protection circuitry, is pretty much a direct connection from the copper in the twinax to the copper contacts which connect to the host device:
Sending a 10G signal over a single copper pair requires Continue reading
From Microsegmentation to DevOps Nirvana: Here Are the Top Analysis Posts of 2017
Our analysis posts provide a deeper dive on what certain trends mean to the industry. In 2017 these articles coveraged a wide swath of topics from the best tools for deploying containers to how network virtualization will help companies track compliance issues.
Top Webinars of 2017: From Streamlining the Data Center to Analyzing Network Traffic
In 2017 many organizations and companies offered up their time and experience to teach us all something new. A number of topics were covered, from deciphering network traffic to simplifying the data center.
The Biggest Personnel Changes of 2017
Hans Vestberg resurfaces; Meg Whitman resigns; and other movers and shakers of 2017.
The Brocade Sale Concludes a Year-Long Shopping Frenzy
It all culminated with a dramatic decision by Broadcom.
Network Performance Monitoring Tools: CA vs. Micro Focus
Users review CA Spectrum and Micro Focus Network Node Manager.
(Micro)benchmarking Linux kernel functions
Usually, the performance of a Linux subsystem is measured through an external (local or remote) process stressing it. Depending on the input point used, a large portion of code may be involved. To benchmark a single function, one solution is to write a kernel module.
Minimal kernel module
Let’s suppose we want to benchmark the IPv4 route lookup function,
fib_lookup(). The following kernel function executes 1,000 lookups
for 8.8.8.8 and returns the average value.1 It uses the
get_cycles() function to compute the execution “time.”
/* Execute a benchmark on fib_lookup() and put result into the provided buffer `buf`. */ static int do_bench(char *buf) { unsigned long long t1, t2; unsigned long long total = 0; unsigned long i; unsigned count = 1000; int err = 0; struct fib_result res; struct flowi4 fl4; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = in_aton("8.8.8.8"); for (i = 0; i < count; i++) { t1 = get_cycles(); err |= Continue reading
Bloomberg Using Kubernetes to Test Kubernetes Deployments
PowerfulSeal test platform likened to Netflix's Chaos Monkey.
Our commitment to open networking
On Monday we released our latest version of Cumulus Linux, 3.5. It includes symmetric VxLAN routing, Voice VLAN and 10 new hardware platforms. This includes General Availability (GA) of our two supported chassis, the four slot Backpack and eight slot OMP800. We announced Early Access (EA) support for both chassis in our previous release, Cumulus Linux 3.4.
At Cumulus, moving fast to fix problems and get features in the hands of our customers is core to our culture. In today’s webscale networks, it’s hard for even the largest of organizations to operate on classic 18+ month buying cycles. Some folks want the ability to use new technology as soon as possible.
The EA process gives customers the ability to use working software or hardware and provide direct feedback on the final product. That feedback improves all aspects of the product, from purchasing, delivery, default configurations or operations.
When we announced EA for our chassis systems, we had many Fortune 500 customers express interest. For some, the EA process allowed them to start the purchasing process knowing that it would take months until a final purchase order was ready. For others, they were able to put working, stable Continue reading
Programming Unbound
I’m doing some research on Facebook’s Open/R routing platform for a future blog post. I’m starting to understand the nuances a bit compared to OSPF or IS-IS, but during my reading I got stopped cold by one particular passage:
Many traditional routing protocols were designed in the past, with a strong focus on optimizing for hardware-limited embedded systems such as CPUs and RAM. In addition, protocols were designed as purpose-built solutions to solve the particular problem of routing for connectivity, rather than as a flexible software platform to build new applications in the network.
Uh oh. I’ve seen language like this before related to other software projects. And quite frankly, it worries me to death. Because it means that people aren’t learning their lessons.
New and Improved
Any time I see an article about how a project was rewritten from the ground up to “take advantage of new changes in protocols and resources”, it usually signals to me that some grad student decided to rewrite the whole thing in Java because they didn’t understand C. It sounds a bit cynical, but it’s not often wrong.
Want proof? Check out Linus Torvalds and his opinion about rewriting the Linux kernel in Continue reading
Reflections on the Internet’s Past
Earlier this year, as part of the Internet Society’s 25th anniversary celebration, we asked you to share your memories of the early Internet. As we look forward to the new year, it’s fun to read through the stories and look back at where we started.
One of the earliest memories was from Stanford University.
I got my first Arpanet email account in 1978.
[By 1985] All the graduate students and professors had accounts, and there was a campus Ethernet, Macs were being integrated into the network via AppleTalk (print and file sharing services)… Also, beyond email we had ftp servers that served shareware and USENET to help with sysadmin problems. Much of the networking software and hardware was developed on campus, including the AppleTalk gateways (Kinetics) and routers (early Cisco protoypes).
There was also this dose of funny reality from nearly ten thousand kilometers away, in Moscow:
I had remote data connection more than 26 years ago, in 1991. We had so called dial up modem connection via telephone PSTN pre-analogue PBX- the step-by-step switch.
It was toooooo extremely long.
Another member shared this memory from INET ’93 San Francisco:
…among the papers and presentations one which drew the largest crowd was Continue reading
Episode 18 – Whitebox Networking
In Episode 18 of Network Collective, Pete Lumbis of Cumulus Networks and Kevin Myers of IP Architechs join us to talk about the pros and cons of running whitebox or commodity hardware in your network. There’s no denying that the price point on commodity hardware is attractive but we discuss all you should consider when you’re looking to transition away from a major network hardware vendor.
Show Notes
What is whitebox networking?
- Has a variety of definitions depending on the person answering
- Associated with ONIE and Oss like Cumulus Linux, BigSwitch, IPI
- Commodity hardware not mainstream vendor with OS that may or may not be from the same vendor
- To some, hardware has more to do with hardware
- Commodity hardware has to do with using chipset, board, or even layout that someone else created
- Component of disaggregation to consider
- Britebox is the larger vendors offering disaggregation options
- Whietbox equipment isn’t about homemade devices soldered together in our garages
Why whitebox networking?
- The original impetus for whitebox was often around cost, and sometimes it still is
- Current reasons are to have more options like customized operating systems
- Whitebox utilizes the equipment to move to an x86 model that compute Continue reading
Top 5 blogs of 2017: LinuxKit, A Toolkit for building Secure, Lean and Portable Linux Subsystems
In case you’ve missed it, this week we’re highlighting the top five most popular Docker blogs in 2017. Coming in the third place is the announcement of LinuxKit, a toolkit for building secure, lean and portable Linux Subsystems.
LinuxKit includes the tooling to allow building custom Linux subsystems that only include exactly the components the runtime platform requires. All system services are containers that can be replaced, and everything that is not required can be removed. All components can be substituted with ones that match specific needs. It is a kit, very much in the Docker philosophy of batteries included but swappable. LinuxKit is an open source project available at https://github.com/linuxkit/linuxkit.
To achieve our goals of a secure, lean and portable OS,we built it from containers, for containers. Security is a top-level objective and aligns with NIST stating, in their draft Application Container Security Guide: “Use container-specific OSes instead of general-purpose ones to reduce attack surfaces. When using a container-specific OS, attack surfaces are typically much smaller than they would be with a general-purpose OS, so there are fewer opportunities to attack and compromise a container-specific OS.”
The leanness directly helps with security by removing parts not Continue reading
From SD-WAN to the Network Edge: Here Are the Top Sponsored Posts of 2017
Here is a list of our Top 5 sponsored posts of 2017