Leaf and spine traffic engineering using segment routing and SDN


The short 3 minute video is a live demonstration showing how software defined networking (SDN) can be used to orchestrate the measurement and control capabilities of commodity data center switches to automatically load balance traffic on a 4 leaf, 4 spine, 10 Gigabit leaf and spine network.
The diagram shows the physical layout of the demonstration rack. The four logical racks with their servers and leaf switches are combined in a single physical rack, along with the spine switches, and SDN controllers. All the links in the data plane are 10G and sFlow has been enabled on every switch and link with the following settings, packet sampling rate 1-in-8192 and counter polling interval 20 seconds. The switches have been configured to send the sFlow data to sFlow-RT analytics software running on Controller 1.

The switches are also configured to enable OpenFlow 1.3 and connect to multiple controllers in the redundant ONOS SDN controller cluster running on Controller 1 and Controller 2.
The charts from The Nature of Datacenter Traffic: Measurements & Analysis show data center traffic measurements published by Microsoft. Most traffic flows are short duration. However, combined they consume less bandwidth than a much smaller number of Continue reading

Migrating to the cloud? Start with a readiness assessment

This vendor-written tech primer has been edited by Network World to eliminate product promotion, but readers should note it will likely favor the submitter’s approach.

After careful consideration you’ve decided it’s time to migrate a major on-premise software solution to the cloud. But how do you create and execute a plan to make sure your migration stays on time, on budget, and delivers on your expectations? Effective planning is critical, and it should start with a thorough assessment of your infrastructure by an experienced vendor who understands your specific objectives.

Usually available as a service engagement from a hosting vendor or, better yet, from the software vendor whose solution is being migrated to the cloud, this cloud readiness assessment is part checklist and part roadmap. It audits the entire environment so you can plan and execute an efficient and effective migration.

To read this article in full or to leave a comment, please click here

Datanauts 001 – Hyper Convergence with Scott D. Lowe

A brand new podcast -- Datanauts -- has launched! Here's the summary of episode 1. The latest form factor, hyper-converged infrastructure, seems to be storming through the data center market like a thundering donkey with a rainbow laser cannon. Join the Datanauts as they pick apart the pros and cons of hyper-converged, ramble on about architecture and design challenges, and shine a piercing light into a dark and murky corner of the next generation data center!

The post Datanauts 001 – Hyper Convergence with Scott D. Lowe appeared first on Packet Pushers.

Datanauts 001 – Hyper Convergence with Scott D. Lowe

A brand new podcast -- Datanauts -- has launched! Here's the summary of episode 1. The latest form factor, hyper-converged infrastructure, seems to be storming through the data center market like a thundering donkey with a rainbow laser cannon. Join the Datanauts as they pick apart the pros and cons of hyper-converged, ramble on about architecture and design challenges, and shine a piercing light into a dark and murky corner of the next generation data center!

The post Datanauts 001 – Hyper Convergence with Scott D. Lowe appeared first on Packet Pushers.

Global Collateral Damage of TMnet leak

12322b_All_Sources-4

The Washington Post recently published a great piece about the development and current weaknesses of the Border Gateway Protocol (BGP, which is used to route all Internet traffic). This morning Telekom Malaysia (a.k.a TMnet) helped to illustrate the points made in the article by leaking almost half of the global routing table via Level 3 at 08:44 UTC.

Some of the most affected companies were those peering with Telekom Malaysia.  The following graphics illustrate the impact to routes from Amazon and Cloudflare.

54.255.128.0_17_1434096000 190.93.249.0_24_1434096000

Google’s extensive peering likely insulated it from some of the effects of having its routes leaked.  However, it didn’t escape the incident completely unscathed.  Here is an example of a normal traceroute to Google’s data center in Council Bluffs, Iowa from Prague, which goes via Frankfurt and London before crossing the Atlantic Ocean.

trace from Prague to Google, Council Bluffs, IA at 02:45 Jun 11, 2015
1  *
2  212.162.8.253    ge-6-14.car2.Prague1.Level3.net     16.583
3  4.69.154.135     ae-3-80.edge3.Frankfurt1.Level3.net 22.934
4  4.68.70.186      Level 3 (Frankfurt, DE)             23.101
5  209.85.241.110   Google (Frankfurt, DE)              23.796
6  209.85.250.143   Google (Frankfurt, DE)              24.086
7  72.14.235.17     Google (London, GB)                 32.709
8  209.85.247.145   Google (New York City)             103.091
9  216.239.46.217   Google (Council Bluffs)            133.098
10 209.85.250.4     Google (Council Bluffs)            133.245
11 216.239.43.217   Google (Council Bluffs)            133. Continue reading

iPexpert’s Newest “CCIE Wall of Fame” Additions 6/12/2015

Please join us in congratulating the following iPexpert students who have passed their CCIE lab!

This Week’s CCIE Success Stories

  • Ali Syed, CCIE #48998 (Data Center)
  • Panayiotis Chiras, CCIE #48880 (Wireless)
  • Evgeniy Petrunko, CCIE #48938 (Data Center)

We Want to Hear From You!

Have you passed your CCIE lab exam and used any of iPexpert’s self-study products, or attended a CCIE Bootcamp? If so, we’d like to add you to our CCIE Wall of Fame!

Datanauts 001 – Hyper Convergence with Scott D. Lowe

A brand new podcast -- Datanauts -- has launched! Here's the summary of episode 1. The latest form factor, hyper-converged infrastructure, seems to be storming through the data center market like a thundering donkey with a rainbow laser cannon. Join the Datanauts as they pick apart the pros and cons of hyper-converged, ramble on about architecture and design challenges, and shine a piercing light into a dark and murky corner of the next generation data center!

Author information

Ethan Banks

Co-host at Packet Pushers

Ethan Banks, CCIE #20655, has been managing networks for higher ed, government, financials and high tech since 1995. Ethan co-hosts the Packet Pushers Podcast, which has seen over 3M downloads and reaches over 10K listeners. With whatever time is left, Ethan writes for fun & profit, studies for certifications, and enjoys science fiction. @ecbanks
TwitterGoogle+LinkedIn

The post Datanauts 001 – Hyper Convergence with Scott D. Lowe appeared first on Packet Pushers Podcast and was written by Ethan Banks.

Four things to watch for as net neutrality rules go into effect

The U.S. Federal Communications Commission’s net neutrality rules went into effect Friday, after an appeals court denied multiple requests to delay them while the agency faces 10 lawsuits challenging the regulations.The rules prohibit broadband providers from selectively blocking or slowing Internet traffic and from charging website owners and providers of Web-based services for prioritized traffic. The rules also reclassify broadband from a lightly regulated information service to a more heavily regulated telecom-style service, although the FCC voted to exempt broadband providers from many of those common-carrier rules.Here are four things to watch for as the rules go into effect and the lawsuits go forward:To read this article in full or to leave a comment, please click here

PlexxiPulse—Partnering with CloudGov Technologies

This week we announced our partnership with CloudGov Technologies, a third platform IT Solutions provider servicing the government and commercial markets. This partnership helps federal agencies address the increasing need for scalable, agile and distributed data center networks built for third platform computing workloads. As a result of this partnership, a large U.S. government agency recently deployed our solutions to automate the provisioning and deployment of more than 30,000 virtual desktops with minimal administration. The deployment significantly improves application user experience and performance by optimizing the flow of east-west traffic across its virtualized data center.

Interested in learning more? Drop us a line at [email protected] to schedule a demo or stop by booth #7071 at the AFCEA Defensive Cyber Operations Symposium from June 16-18 in Baltimore. We will be showcasing our third platform solution alongside CloudGov Technologies.

Below please find a few of our top picks for our favorite news articles of the week. Enjoy!

Fortune: 5 things that keep tech execs up at night
By Barb Darrow
Pity the poor soul at your company who is in charge of technology decisions. Whether that person is the CIO, the director of engineering, vice president of IT, or Continue reading

Mini-PC round-up: A look at 6 new Windows 8.1 offerings

A look at 6 new Windows 8.1 mini-PCsImage by ThinkstockThe idea of a desktop PC traditionally invokes images of a tower or all-in-one that lives at your desk in your home or office. But as tech gets smaller and more mobile, so have desktop PCs. With a mini PC, you can have all the computing capabilities of a traditional desktop in a small, compact and portable package.Here are 6 mini PCs running Windows 8.1 that will let you take your desktop experience mobile.HP Stream Mini DesktopImage by ThinkstockTo read this article in full or to leave a comment, please click here

Amazon boosts cloud offerings with souped-up virtual servers

Amazon Web Services has launched new, more powerful general-purpose and data-warehouse virtual servers as it works to stay ahead of the competition by offering users a wider array of cloud-service options.Amazon has had a busy week, expanding its portfolio on Tuesday and Thursday with new virtual servers, or "instances," for its public cloud.The M4 family is Amazon's latest generation of EC2 (Elastic Compute Cloud) general purpose instances. There are five sizes to choose among, each with up to 40 virtual CPUs and 172GB of system memory, Amazon said on Thursday.MORE ON NETWORK WORLD: How to build a private cloud The top size costs users from US$2.52 per hour when they pay on an on-demand basis. The smallest size costs $0.126 per hour and has 2 virtual CPUs and 8.6GB of system memory.To read this article in full or to leave a comment, please click here

IDG Contributor Network: 5 ways to fight mainframe malaise

As a mainframer, I belong to a number of organizations and groups that focus on this technology. And when I read message boards, Web sites, magazines, and blogs about big iron one theme always comes through loud and clear: my peers are overwhelmingly negative about their jobs.

In fact, some recent polls highlighting employee job dissatisfaction paint a fairly grim picture. A recent Gallup Poll is here. The Washington Post poll is here. And a Forbes poll is here.

To read this article in full or to leave a comment, please click here

A good start, but developers want more access to the Apple Watch

A software update to the Apple Watch’s OS gave third-party developers access to the device’s sensors this week, fulfilling a request they’ve had since Apple unveiled the wearable.With watchOS 2, which Apple showed on Monday at its annual developer’s conference, developers can create more-capable apps that directly tap into the watch’s components, like its microphone and heart rate sensor, instead of relying on an accompanying iPhone to handle app processing.While developers welcomed this news, some think Apple could go even further in making the watch a better platform for their apps.To read this article in full or to leave a comment, please click here

Report: Blackberry’s next devices could run Android

Beleaguered smartphone manufacturer Blackberry could go Android with its next device, abandoning development of its own platform in the interest of getting a more robust ecosystem of apps into the hands of its few remaining users, according to a report from Reuters.Citing anonymous sources, the news agency said that the idea is to transform Blackberry into a software and services company, centered on BES 12, a mobility management system designed to work across Android, iOS, and Windows Phone devices, in addition to Blackberry’s own. (Read the full Reuters report here.)To read this article in full or to leave a comment, please click here

Worth Reading 06:12

According to the Data Center Journal:

What’s the problem with IT resumes? They’re useless.

The real problem with IT resumes, though, is we want to see a long list of technologies, because we want to find the specific technology we want to implement (or are implementing) — rather than a good engineer. The hiring process is a fishing expedition rather than a search for solid talent and personality fit. If we want to fix this problem we can. The question is — do we want to?

Bruce Schneier has some wise thoughts on airport security this week —

We don’t need perfect airport security. We just need security that’s good enough to dissuade someone from building a plot around evading it. If you’re caught with a gun or a bomb, the TSA will detain you and call the FBI. Under those circumstances, even a medium chance of getting caught is enough to dissuade a sane terrorist

Replace “airport” with “network,” and you get the drift of where network security is going, I think. Of course, there’s the reality that you can’t stop insane attackers… Worth remembering. The same point can be made for network uptime, by the way. Perfection is Continue reading

1 … 3,364 3,365 3,366 3,367 3,368 … 3,765