MLAG Deep Dive: Layer-2 Flooding

In the previous blog post of the MLAG Technology Deep Dive series, we explored the intricacies of layer-2 unicast forwarding. Now let’s focus on layer-2 BUM¹ flooding functionality of an MLAG system.

Our network topology will have two switches and five hosts, some connected to a single switch. That’s not a good idea in an MLAG environment, but even if you have a picture-perfect design with everything redundantly connected, you will have to deal with it after a single link failure.

MLAG Deep Dive: Layer-2 Flooding

Who Will Build Europe’s First Exascale Supercomputer – And With What, And Why?

Exascale supercomputing is just as important to Europe as it is to the United States and China, but each of these geopolitical regions on Earth has its own way of developing architectures, funding their development and production, and figuring out where the best HPC centers are to host such machines to maximize their effectiveness. …

Who Will Build Europe’s First Exascale Supercomputer – And With What, And Why? was written by Timothy Prickett Morgan at The Next Platform.

Cisco Nexus data-center switches promise 800Gb Ethernet but deliver 400GbE today

Cisco is prepping its high-end data-center Nexus switch family for high-speed Ethernet that will better support high-bandwidth applications such as AI and cloud-native. The vendor rolled out five new Nexus data-center switches that include improved support for 100/400Gb Ethernet networks, but its flagship box—the 9800—now includes a migration path to support 800GbE requirements. [ Get regularly scheduled insights by signing up for Network World newsletters. ] The new modular data-center switch product family with 14.4Tb/s fully encrypted bandwidth per slot. The Cisco Nexus 9800 Series features eight-slot and four-slot chassis that can scale from 57Tb/s to 115Tb/s with a combination of various first-generation line cards and fabric modules. Each line card slot can support 400GbE or 100GbE or 10/25/50GbE ports. The eight-slot option could support up to 288 400GbE ports, well above the current 9000’s 32-port capacity.To read this article in full, please click here

Cloudflare Zaraz launches new privacy features in response to French CNIL standards

Last week, the French national data protection authority (the Commission Nationale de l'informatique et des Libertés or “CNIL”), published guidelines for what it considers to be a GDPR-compliant way of loading Google Analytics and similar marketing technology tools. The CNIL published these guidelines following notices that the CNIL and other data protection authorities issued to several organizations using Google Analytics stating that such use resulted in impermissible data transfers to the United States. Today, we are excited to announce a set of features and a practical step-by-step guide for using Zaraz that we believe will help organizations continue to use Google Analytics and similar tools in a way that will help protect end user privacy and avoid sending EU personal data to the United States. And the best part? It takes less than a minute.

Enter Cloudflare Zaraz.

The new Zaraz privacy features

What we are releasing today is a new set of privacy features to help our customers enhance end user privacy. Starting today, on the Zaraz dashboard, you can apply the following configurations:

Remove URL query parameters: when toggled-on, Zaraz will remove all query parameters from a URL that is reported to a third-party server. It will turn Continue reading

Day Two Cloud 151: How To Tell If Infrastructure As Code Is Working For You

Today's Day Two Cloud podcast gets into Infrastructure as Code (IaC) and how to evaluate it so that IaC practices fit your organization, your processes, the infrastructure you're trying to support, and so on. Our guest lays out some guideposts to help you understand if IaC is working for you.

Cisco data-center switches promise 800Gb Ethernet, deliver 400GbE today

Cisco Live 2022: A Kinder, Gentler, Cloudier Monster?

Cisco Live 2022 in Las Vegas kicked off with executive keynotes, including an address from CEO Chuck Robbins. My takeaways from the keynotes from Tuesday, June 14th are: Cisco knows it has to work harder to keep customers Cisco has big cloud ambitions Meraki is one key to Cisco’s cloud & simplicity goals Cisco Has […]

The post Cisco Live 2022: A Kinder, Gentler, Cloudier Monster? appeared first on Packet Pushers.

Internal Network Security Mistakes to Avoid

Network security begins at home. Here's how to effectively secure threats from within your organization.

Red Hat Ansible Automation Platform on Microsoft Azure – Network Access – blog #2

Thank you to Hicham Mourad and Scott Harwell for co-authoring this blog.

Introduction

In this blog series, we will continue discussing the deployment of Red Hat Ansible Automation Platform on Microsoft Azure.

The first blog covered the deployment process as well as how to access a Red Hat Ansible Automation Platform on Azure deployment that was deployed using the “Public” access option.

This blog we’ll cover how to access the managed application when it’s deployed using the “Private” access option.

Connecting to Red Hat Ansible Automation Platform on Microsoft Azure

There are three ways you can access Red Hat Ansible Automation Platform on Azure if you selected “Private” access.

An Azure hosted virtual machine (VM)
Azure VPN or Direct Connect
SSH Tunnel

Let’s assume that you have already configured network peering between the Red Hat Ansible Automation Platform on Azure deployment, on the Azure network and your existing Azure Virtual Networks. Network peering is an Azure action for connecting two or more networks on Azure that route traffic to resources across those networks. See Microsoft Azure documentation for more information on network peering types.

Access Details

Regardless of whether you selected public or private Continue reading

Hedge 134: Ten Things

One of the many reasons engineers should work for a vendor, consulting company, or someone other than a single network operator at some point in their career is to develop a larger view of network operations. What are common ways of doing things? What are uncommon ways? In what ways is every network broken? Over time, if you see enough networks, you start seeing common themes and ideas. Just like history, networks might not always be the same, but the problems we all encounter often rhyme. Ken Calenza joins Tom Ammon, Eyvonne Sharp, and Russ White to discuss these common traits—ten things I know about your network.

download

10 top automation and orchestration tools

IT process automation sells itself: automating tasks is not only cheaper than paying a human to perform repetitive activities, but it’s also more efficient and predictable.While it’s possible to develop automation tools in-house with enterprise staff, that can be challenging, so ultimately, to embrace automation in a big way, it may be necessary to enlist commercial software tools. [ Get regularly scheduled insights by signing up for Network World newsletters. ] Some tasks are simpler to automate than others—managing IT systems, provisioning physical and virtual machines, managing server configuration, identifying policy drift—and many IT systems are now built with features that make it easier to move along the path toward automation without seeking commercial platforms.To read this article in full, please click here

EVPN-VXLAN Explainer 5 – Layer 3 with Asymmetrical IRB

Thus far, this series of posts have all been about Layer 2 over Layer 3 models; the customer ethernet frames encapsulated in UDP, traversing L3 networks. The routing has been confined underlay, the customer traffic has stayed within the same network.
No longer! In this post, things start getting a little more interesting, as we look at routing the customer traffic with an EVPN feature called Integrated Routing and Bridging, or IRB.

First we look at the concept of routing in VXLAN networks.
Then we have an in-depth look at asymmetrical IRB (I'll be dealing with symmetrical in the next post).

✅ L2 is intra-subnet, L3 is inter-subnet

📥 Intra-subnet

To define terms, when I say 'intra-subnet', that is L2 traffic transferred between nodes in the same subnet.

📤 Inter-subnet

'Inter-subnet' refers to a traffic flow that traverses subnet boundaries.

☎️ The Centralized IP L3 Gateways of Old

With VXLAN networks in the past, inter-subnet communication was often performed by a centralized, IP only, gateway on behalf of the rest of the network.
Traffic from customer-side networks would need to be sent to this central device for routing, which often created inefficient traffic flows, and possibly a bandwidth choke-point.
Imagine Continue reading

Beware of Vendors Bringing White Papers

A few weeks ago I wrote about tradeoffs vendors have to make when designing data center switching ASICs, followed by another blog post discussing how to select the ASICs for various roles in data center fabrics.

You REALLY SHOULD read the two blog posts before moving on; here’s the buffer-related TL&DR for those of you ignoring my advice ;)

Beware of Vendors Bringing White Papers

You REALLY SHOULD read the two blog posts before moving on; here’s the buffer-related TL&DR for those of you ignoring my advice ;)

Chip Roadmaps Unfold, Crisscrossing And Interconnecting, At AMD

After its acquisitions of ATI in 2006 and the maturation of its discrete GPUs with the Instinct line from the past few years and the acquisitions of Xilinx and Pensando here in 2022, AMD is not just a second source of X86 processors. …

Chip Roadmaps Unfold, Crisscrossing And Interconnecting, At AMD was written by Timothy Prickett Morgan at The Next Platform.

Digital infrastructure outages get more costly

Digital infrastructure outages have gotten more and more expensive over the course of the past several years, according to a report from the Uptime Institute. Meanwhile, the total number of major outages has remained the same—meaning that, on average, an increasingly large amount of money is getting spent on recovering from each disruption.The proportion of individual outages resulting in losses of over $100,000 is increasing, according to the report, up to 47% of all outages in 2021 from 40% in the previous year. The institute said that, while it doesn't calculate an average overall cost per outage, overall trends are toward more costs being incurred by the average outage.To read this article in full, please click here

AMD ups its supercomputer components

AMD is working on an accelerated processing unit that will outperform its current top APU that powers the world’s first exascale supercomputer.At its recent analyst day, the company introduced a new high-end accelerator, the Instinct MI300, an APU that combines Zen 4 CPUs, the latest generation of GPU technology, plus AMD’s Infinity Cache and Infinity architecture in one package. It will deliver eight times the AI performance of AMD’s current high-end ACU, the MI250, and will be available next year.A pool of high-bandwidth memory on the ACU is shared between the CPU and the GPU allowing them to communicate freely without the performance or energy overhead of redundant memory copies.To read this article in full, please click here

AMD ups its supercomputer components

« Previous 1 … 540 541 542 543 544 … 3,895 Next »