Mellanox, Ixia and Cumulus: Part 3

Last–but not least–in the technology triumvirate presenting a joint session at Networking Field Day 17 was Cumulus Networks. This post looks at the benefits of Cumulus Linux as a NOS on the Mellanox Spectrum Ethernet switch platform.

Cumulus/Mellanox/Ixia Logos

Cumulus Networks

I’ve not yet managed to deploy Cumulus Linux in anger, but it’s on a fairly short list of Network Operating Systems (NOS) which I would like to evaluate in earnest, because every time I hear about it, I conclude that it’s a great solution. In fact, I’m having difficulty typing this post because I have to stop frequently to wipe the drool from my face.

Cumulus Linux supports around 70 switches from 8 manufacturers at this time, and perhaps obviously, that includes the Mellanox Spectrum switches that were presented during this session. This is the beauty of disaggregation of course; it’s possible to make a hardware selection, then select the software to run on it. Mellanox made a fairly strong case for why the Spectrum-based hardware is better than others, so now Cumulus has to argue for why they would be the best NOS to run on the Mellanox hardware.

Cumulus Linux, as the name suggests, is based on Debian linux. Continue reading

Plotting the interface flap – That’s some analysis

Hi,

What started to be a exploration project is now turning out to be pretty useful for me in day to day analysis. Back in days when I worked in support, there was nothing to predict or really worry about historical events for any future work, just grep for logs and you are done with the last flap and analysis.

Customers / Networks now look for more data, while there are systems which do the telemetry and prediction, from an analysis point of view, as an engineer I want to know if the device or a circuit over an interface is stable over a period of time or even if it flaps what is the likely time and day it flaps in a week for a smoother migration.

Requirement : Plot a simple graph analyzing the interface flaps over a period of one week for a  specific interface and decide the actions next from the log messages.[in this case i used a junos device]

Well grepping the logs is not something new for a seasoned engineer but having visual data will prove to be useful for a cutover or migration.

There are systems which can do this work on Continue reading

Weekend Reading 041318: GDPR, and the ever deepening pile of security vulnerabilities

I think we are all hoping that when ICANN meets with the DPAs (Digital Protection Authorities) a clear path forward will be illuminated. We are all hoping that the DPAs will provide definitive guidance regarding ICANN’s interim model and that some special allowance will be made so that registrars and registries are provided with additional time to implement a GDPR-compliant WHOIS solution. —Matt Serlin @CircleID

Security researchers at Embedi have disclosed a critical vulnerability in Cisco IOS Software and Cisco IOS XE Software that could allow an unauthenticated, remote attacker to execute arbitrary code, take full control over the vulnerable network equipment and intercept traffic. —Swati Khandelwal @The Hacker News

With the growing presence and sophistication of online threats like viruses, ransomware, and phishing scams, it’s increasingly important to have the right protection and tools to help protect your devices, personal information, and files from being compromised. Microsoft already provides robust security for Office services, including link checking and attachment scanning for known viruses and phishing threats, encryption in transit and at rest, as well as powerful antivirus protection with Windows Defender. Today, we’re announcing new advanced protection capabilities coming to Office 365 Home and Office 365 Personal subscribers to Continue reading

NEON is the new black: fast JPEG optimization on ARM server

NEON is the new black: fast JPEG optimization on ARM server

As engineers at Cloudflare quickly adapt our software stack to run on ARM, a few parts of our software stack have not been performing as well on ARM processors as they currently do on our Xeon® Silver 4116 CPUs. For the most part this is a matter of Intel specific optimizations some of which utilize SIMD or other special instructions.

One such example is the venerable jpegtran, one of the workhorses behind our Polish image optimization service.

A while ago I optimized our version of jpegtran for Intel processors. So when I ran a comparison on my test image, I was expecting that the Xeon would outperform ARM:

vlad@xeon:~$ time  ./jpegtran -outfile /dev/null -progressive -optimise -copy none test.jpg

real    0m2.305s
user    0m2.059s
sys     0m0.252s

vlad@arm:~$ time ./jpegtran -outfile /dev/null -progressive -optimise -copy none test.jpg

real    0m8.654s
user    0m8.433s
sys     0m0.225s

Ideally we want to have the ARM performing at or above 50% of the Xeon performance per core. This would make sure we have no performance regressions, and net performance gain, since the ARM CPUs have double the core count as our current 2 socket setup.

In this case, however, I Continue reading

On Old Configs and Automation

I used to work with a guy that would configure servers for us and always include an extra SCSI card in the order. When I asked him about it one day, he told me, “I left it out once and it delayed the project. So now I just put them on every order.” Even after I explained that we didn’t need it over and over again, he assured me one day we might.

Later, when I started configuring networking gear I would always set a telnet password for every VTY line going into the switch. One day, a junior network admin asked me why I configured all 15 instead of just the first 5 like they learn in the Cisco guides. I shrugged my shoulders and just said, “That’s how I’ve always done it.”

The Old Ways

There’s no more dangerous phrase than “That’s the way it’s always been.”

Time and time again we find ourselves falling back on the old rule of thumb or an old working configuration that we’ve made work for us. It’s comfortable for the human mind to work from a point of reference toward new things. We find ourselves doing it all Continue reading

Stuff The Internet Says On Scalability For April 13th, 2018

Hey, it's HighScalability time:

 

Bathroom tile? Grandma's needlepoint? Nope. It's a diagram of the dark web. Looks surprisingly like a tumor.

If you like this sort of Stuff then please support me on Patreon. And I'd appreciate if you would recommend my new book—Explain the Cloud Like I'm 10—to anyone who needs to understand the cloud (who doesn't?). I think they'll learn a lot, even if they're already familiar with the basics. 

  • $23 billion: Amazon spend on R&D in 2017; $0.04: cost to unhash your email address; $35: build your own LIDAR; 66%: links to popular sites on Twitter come from bots; 60.73%: companies report JavaScript as primary language; 11,000+: object dataset provide real objects with associated depth information; 150 years: age of the idea of privacy; 30%~ AV1's better video compression; 100s of years: rare-earth materials found underneath Japanese waters; 67%: better image compression using Generative Adversarial Networks; 1000 bit/sec: data exfiltrated from air-gapped computers through power lines using conducted emissions; 

  • Quotable Quotes:

Finding what you’re looking for on Linux

It isn’t hard to find what you’re looking for on a Linux system — a file or a command — but there are a lot of ways to go looking.7 commands to find Linux files find The most obvious is undoubtedly the find command, and find has become easier to use than it was years ago. It used to require a starting location for your search, but these days, you can also use find with just a file name or regular expression if you’re willing to confine your search to the local directory.$ find e* empty examples.desktop In this way, it works much like the ls command and isn't doing much of a search.To read this article in full, please click here

Show 385: Getting Inside Cisco Tetration (Sponsored)

If you d heard of Cisco Tetration when it was first announced, you might have a vague memory of it being this huge rack of hardware at an eye-watering price that did some sort of analytics for massive data centers.

Tetration has evolved into a platform that meets needs for organizations of many sizes. Tetration also has a bunch of genuinely interesting use cases, as Cisco has become increasingly clever about what they can do with all of that data Tetration gathers.

For example, you can auto-implement a whitelist policy for application workloads. You can detect when your apps are deviating from their normal traffic patterns. You can detect software vulnerabilities. And depending on where you run Tetration, you can still get deep network performance insights, what I think of as the original Tetration value proposition.

Today on this sponsored episode, we delve into what Tetration does, explore use cases, and dive into how it fits into compute environments. Our guests from Cisco are Jason Gmitter, Principal Systems Engineer; and Yogesh Kaushik, Senior Director of Product Management for Tetration.

Show Links

Cisco Tetration – Cisco Systems

Cisco Tetration Workload Protection Extended with new Options: SaaS and Virtual Appliance – Cisco Continue reading

Enable self-healing applications with Ansible and Dynatrace

Ansible_and_Dynatrace

The size, complexity and high rate of change in today’s IT environments can be overwhelming. Enabling the performance and availability of these modern microservice environments is a constant challenge for IT organizations. 

One trend contributing to this rate of change is the adoption of IT automation for provisioning, configuration management and ongoing operations. For this blog, we want to highlight the repeatable and consistent outcomes allowed by IT automation, and explore what is possible when Ansible automation is extended to the application monitoring platform Dynatrace.

Thanks to Jürgen Etzlstorfer for giving us an overview of the Ansible and Dynatrace integration.

---

Monitoring Today

Considering the size, complexity and high rate of change in today's IT environments, traditional methods of monitoring application performance and availability are often necessary and commonplace in most operations teams. Application performance monitoring (APM) platforms are used to detect bottlenecks and problems that can impact the experience of your customers.

Monitoring alone, however, isn’t always enough to help keep your applications running at peak performance. When issues are detected, APM platforms are designed to alert the operator of the problem and its root-cause. The Ops team can then agree on a corrective action, and implement this Continue reading

Is Networking Complex/Hard ?

Its not complicated (natch). Its distributed. And we don’t have visibility to know. Distributed Systems What makes networking hard ? A network is a distributed system where state must be shared between devices that are unreliably connected. Its a fallacy that a network will ever be reliable or predictable. Skills Network technologies and their fundamentals […]

Building Bigger, Faster GPU Clusters Using NVSwitches

Nvidia launched its second-generation DGX system in March. In order to build the 2 petaflops half-precision DGX-2, Nvidia had to first design and build a new NVLink 2.0 switch chip, named NVSwitch. While Nvidia is only shipping NVSwitch as an integral component of its DGX-2 systems today, Nvidia has not precluded selling NVSwitch chips to data center equipment manufacturers.

This article will answer many of the questions we asked in our first look at the NVSwitch chip, using DGX-2 as an example architecture.

Nvidia’s NVSwitch is a two-billion transistor non-blocking switch design incorporating 18 complete NVLink 2.0 ports …

Building Bigger, Faster GPU Clusters Using NVSwitches was written by Timothy Prickett Morgan at The Next Platform.

Software opens up new career opportunities for network professionals

The topic of network engineer re-skilling has been front and center for the past few years. Some network professionals have embraced the concept and are leading the network industry in a whole new direction. Others, though, are more resistant and show about as much enthusiasm for this new world as my wife does when I ask her to watch a Star Trek marathon with me.Network professionals need to become software-fluent Part of the resistance to re-skilling is that change is scary and often hard. Many network engineers have been working a certain way for years, possibly decades, and now they are asking, "Do I need to throw those skills away and learn new ones?" To those people, I say an emphatic YES! It’s absolutely critical to learn new skills today, or you could find yourself quickly looking for a job.To read this article in full, please click here

1 … 1,691 1,692 1,693 1,694 1,695 … 3,886