Google Injects Network Intelligence Center Into GCP

The cloud giant's Network Intelligence Center packs four tools aimed at helping customers monitor,...

Read More »

© SDxCentral, LLC. Use of this feed is limited to personal, non-commercial use and is governed by SDxCentral's Terms of Use (https://www.sdxcentral.com/legal/terms-of-service/). Publishing this feed for public or commercial use and/or misrepresentation by a third party is prohibited.

Docker’s Next Chapter: Advancing Developer Workflows for Modern Apps

Today we start the next chapter in the Docker story, one that’s focused on developers. That we have the opportunity to write this next chapter is thanks to you, our community, for without you we wouldn’t be here. And while our focus on developers builds on recent history, it’s a focus also grounded in Docker’s beginning.

In The Beginning

When Solomon Hykes, Docker’s founder, unveiled the Docker project in 2013, he succinctly stated the problem Docker aimed to solve as, “for a developer, shipping code to the server is hard.” To address, Docker abstracted out OS kernels’ complex container primitives, provided a developer-friendly, CLI-based workflow and defined an immutable, portable image format. The result transformed how developers work, making it much easier to build, ship and run their apps on any server. So while container primitives had existed for decades, Docker democratized them and made them as easy to use as

docker run hello-world

The rest is history. Over the last six years, Docker containerization catalyzed the growth of microservices-based applications, enabled development teams to ship apps many times faster and accelerated the migration of apps from the data center to the cloud. Far from a Docker-only effort, a Continue reading

What is edge computing and why it matters

Edge computing is transforming the way data is being handled, processed, and delivered from millions of devices around the world. The explosive growth of internet-connected devices – the IoT – along with new applications that require real-time computing power, continues to drive edge-computing systems.Faster networking technologies, such as 5G wireless, are allowing for edge computing systems to accelerate the creation or support of real-time applications, such as video processing and analytics, self-driving cars, artificial intelligence and robotics, to name a few.To read this article in full, please click here

Liqid Scores $28M Series B, CEO Touts ‘Record Profit’

Companies including Inspur and Dell Technologies sell Liqid’s switch and software inside their...

Read More »

© SDxCentral, LLC. Use of this feed is limited to personal, non-commercial use and is governed by SDxCentral's Terms of Use (https://www.sdxcentral.com/legal/terms-of-service/). Publishing this feed for public or commercial use and/or misrepresentation by a third party is prohibited.

TIP Plugs Critical Mass, Expands Community Labs

Technology prototypes tested and validated by the group are now commercially available and being...

Read More »

© SDxCentral, LLC. Use of this feed is limited to personal, non-commercial use and is governed by SDxCentral's Terms of Use (https://www.sdxcentral.com/legal/terms-of-service/). Publishing this feed for public or commercial use and/or misrepresentation by a third party is prohibited.

Can We Really Use Millions of VXLAN Segments?

One of my readers sent me a question along these lines…

VXLAN Network Identifier is 24 bit long, giving 16 us million separate segments. However, we have to map VNI into VLANs on most switches. How can we scale up to 16 million segments when we have run out of VLAN IDs? Can we create a separate VTEP on the same switch?

VXLAN is just an encapsulation format and does not imply any particular switch architecture. What really matters in this particular case is the implementation of the MAC forwarding table in switching ASIC.

Read more ...

Scaling symbolic evaluation for automated verification of systems code with Serval

Scaling symbolic evaluation for automated verification of systems code with Serval Nelson et al., SOSP’19

Serval is a framework for developing automated verifiers of systems software. It makes an interesting juxtaposition to the approach Google took with Snap that we looked at last time out. I’m sure that Google engineers do indeed take extreme care when building the low level networking code that powers Google’s datacenters, but their fundamental design point was to enable frequent releases for fast iteration, feedback on their designs, and yes, early detection of problems.

Formal verification is at the other end of the spectrum. In theory it enables you to eliminate whole classes of problems and vulnerabilities entirely (in practice perfection is still hard to come by), and so it can be especially valuable in security sensitive situations. But it comes with a very high price tag:

Writing proofs requires a time investment that is usually measured in person-years, and the size of the proofs can be several times or even more that an order of magnitude larger than that of implementation code.

That’s both very expensive and an incredibly long wait for feedback. To invest in formally modelling something, you really Continue reading