The future of HCI

You may have noticed already but HCI has been on our minds lately. We’ve talked about it in-depth in our recent white paper and JR Rivers, Cumulus Networks co-founder & CTO, has shared more about it in relation to a network of pods in his on-demand webinar. JR will share more about his take in an upcoming Kernel of Truth podcast episode but in the meantime, we’ll get Naveen Chhabra’s, a senior industry analyst at Forrester, opinion on the future of HCI.

We sat down with him recently to discuss this and here’s what he had to say.

Question: Why is the network such a critical consideration in any hyperconverged infrastructure (HCI) deployment?

Let’s look at the major transformational projects the organizations globally are working on. One project that spans all organizations, verticals, and geographies is digital transformation. IT leaders upgrade or acquire new technologies to support these projects. One pertinent issue across a large percentage of projects is that these are still focused on technology silos.

Specific to HCI, organizations have successfully collapsed the compute and storage silo. Network infrastructure is still not integrated to the extent that it could and should be. Firms have the capability, via HCI, Continue reading

NGINX structural enhancements for HTTP/2 performance

NGINX structural enhancements for HTTP/2 performance
NGINX structural enhancements for HTTP/2 performance

Introduction

My team: the Cloudflare PROTOCOLS team is responsible for termination of HTTP traffic at the edge of the Cloudflare network. We deal with features related to: TCP, QUIC, TLS and Secure Certificate management, HTTP/1 and HTTP/2. Over Q1, we were responsible for implementing the Enhanced HTTP/2 Prioritization product that Cloudflare announced during Speed Week.

This is a very exciting project to be part of, and doubly exciting to see the results of, but during the course of the project, we had a number of interesting realisations about NGINX: the HTTP oriented server onto which Cloudflare currently deploys its software infrastructure. We quickly became certain that our Enhanced HTTP/2 Prioritization project could not achieve even moderate success if the internal workings of NGINX were not changed.

Due to these realisations we embarked upon a number of significant changes to the internal structure of NGINX in parallel to the work on the core prioritization product. This blog post describes the motivation behind the structural changes, how we approached them, and what impact they had. We also identify additional changes that we plan to add to our roadmap, which we hope will improve performance further.

Background

Enhanced HTTP/2 Prioritization aims to do Continue reading

meeting madness, ONUG, and software defined

Jordan, Eyvonne, and I sit down for a conversation that begins with meetings, and ends with talking about software defined everything (including meetings??).

Outro Music:
Danger Storm Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 3.0 License
http://creativecommons.org/licenses/by/3.0/

French IT giant Atos enters the edge-computing business

French IT giant Atos is the latest to jump into the edge computing business with a small device called BullSequana Edge. Unlike devices from its competitors that are the size of a shipping container, including those from Vapor IO and Schneider Electronics, Atos' edge device can sit in a closet.Atos says the device uses artificial intelligence (AI) applications to offer fast response times that are needed in areas such as manufacturing 4.0, autonomous vehicles, healthcare and retail/airport security – where data needs to be processed and analyzed at the edge in real time.[ Also see: What is edge computing? and How edge networking and IoT will reshape data centers.] The BullSequana Edge can be purchased as standalone infrastructure or bundled with Atos’ software edge software, and that software is pretty impressive. Atos says the BullSequana Edge supports three main categories of use cases:To read this article in full, please click here

French IT giant Atos enters the edge-computing business

French IT giant Atos is the latest to jump into the edge computing business with a small device called BullSequana Edge. Unlike devices from its competitors that are the size of a shipping container, including those from Vapor IO and Schneider Electronics, Atos' edge device can sit in a closet.Atos says the device uses artificial intelligence (AI) applications to offer fast response times that are needed in areas such as manufacturing 4.0, autonomous vehicles, healthcare and retail/airport security – where data needs to be processed and analyzed at the edge in real time.[ Also see: What is edge computing? and How edge networking and IoT will reshape data centers.] The BullSequana Edge can be purchased as standalone infrastructure or bundled with Atos’ software edge software, and that software is pretty impressive. Atos says the BullSequana Edge supports three main categories of use cases:To read this article in full, please click here

Atos is the latest to enter the edge computing business

French IT giant Atos is the latest to jump into the edge computing business with a small device called BullSequana Edge. Unlike devices from its competitors that are the size of a shipping container, including those from Vapor IO and Schneider Electronics, Atos' edge device can sit in a closet.Atos says the device uses artificial intelligence (AI) applications to offer fast response times that are needed in areas such as manufacturing 4.0, autonomous vehicles, healthcare and retail/airport security – where data needs to be processed and analyzed at the edge in real time.[ Also see: What is edge computing? and How edge networking and IoT will reshape data centers.] The BullSequana Edge can be purchased as standalone infrastructure or bundled with Atos’ software edge software, and that software is pretty impressive. Atos says the BullSequana Edge supports three main categories of use cases:To read this article in full, please click here

History Of The Internet From An Asian Perspective – Kilnam Chon

Kilnam Chon is credited as being largely responsible for bringing the Internet to Asia. In this episode we talk with Professor Chon about his experiences in the early days of the Internet and about his role in bringing the second country in the world, South Korea, onto the global network.
Kilnam Chon
Guest
Russ White
Host
Donald Sharp
Host

Outro Music:
Danger Storm Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 3.0 License
http://creativecommons.org/licenses/by/3.0/

The post History Of The Internet From An Asian Perspective – Kilnam Chon appeared first on Network Collective.

The Traffic Jam Whopper project may be the coolest/dumbest IoT idea ever

People love to eat in their cars. That’s why we invented the drive-in and the drive-thru.But despite a fast-food outlet on the corner of every major intersection, it turns out we were only scratching the surface of this idea. Burger King is taking this concept to the next logical step with its new IoT-powered Traffic Jam Whopper project.I have to admit, when I first heard about this, I thought it was a joke, but apparently the Traffic Jam Whopper project is totally real and has already passed a month-long test in Mexico City. While the company hasn’t specified a timeline, it plans to roll out the Traffic Jam Whopper project in Los Angeles (where else?) and other traffic-plagued megacities such as São Paulo and Shanghai.To read this article in full, please click here

Improving Routing Security: Microsoft Joins MANRS

In November, a routing incident in Nigeria caused Internet traffic to be rerouted through Russia and China. It lasted for just over an hour, but during that time, it significantly affected some cloud and search services globally, including Spotify and Google’s Search. It was one of more than 10,000 incidents, such as route hijacking and leaks, that occurred in 2018. Past events have led to large-scale Denial of Service attacks, stolen data, and financial losses.

The global routing system is the backbone of the Internet. It determines how everything – from email messages to videoconferences to website content – moves from network to network. The November event, caused by a configuration mistake with a small ISP in Nigeria, shows that routing incidents can have significant global effects – impacting the security of the Internet itself.

A number of network operators around the world – including Oracle, GÉANT, and Comcast – have joined MANRS to address these types of routing threats. The Mutually Agreed Norms for Routing Security (MANRS) initiative, supported by the Internet Society, does this through technical and collaborative action across the Internet. Those who join agree to take meaningful action to keep the Internet safe for everyone – Continue reading

Don’t Base Your Design on Vendor Marketing

Remember how Arista promoted VXLAN coupled with deep buffer switches as the perfect DCI solution a few years ago? Someone took Arista’s marketing too literally, ran with the idea and combined VXLAN-based DCI with traditional MLAG+STP data center fabric.

While I love that they wrote a blog post documenting their experience (if only more people would do that), it doesn’t change the fact that the design contains the worst of both worlds.

Here are just a few things that went wrong:

Read more ...

Software-defined far memory in warehouse scale computers

Software-defined far memory in warehouse-scale computers Lagar-Cavilla et al., ASPLOS’19

Memory (DRAM) remains comparatively expensive, while in-memory computing demands are growing rapidly. This makes memory a critical factor in the total cost of ownership (TCO) of large compute clusters, or as Google like to call them “Warehouse-scale computers (WSCs).”

This paper describes a “far memory” system that has been in production deployment at Google since 2016. Far memory sits in-between DRAM and flash and colder in-memory data can be migrated to it:

Our software-defined far memory is significantly cheaper (67% or higher memory cost reduction) at relatively good access speeds (6µs) and allows us to store a significant fraction of infrequently accessed data (on average, 20%), translating to significant TCO savings at warehouse scale.

With a far memory tier in place operators can choose between packing more jobs onto each machine, or reducing the DRAM capacity, both of which lead to TCO reductions. Google were able to bring about a 4-5% reduction in memory TCO (worth millions of dollars!) while having negligible impact on applications.

In introducing far memory Google faced a number of challenges: workloads are very diverse and change all the time, both in job Continue reading

1 … 1,256 1,257 1,258 1,259 1,260 … 3,869