DDSketch: a fast and fully-mergeable quantile sketch with relative-error guarantees

DDSketch: a fast and fully-mergeable quantile sketch with relative-error guarantees Masson et al., VLDB’19

Datadog handles a ton of metrics – some customers have endpoints generating over 10M points per second! For response times (latencies) reporting a simple metric such as ‘average’ is next to useless. Instead we want to understand what’s happening at different latency percentiles (e.g p99).

The ability to compute quantiles over aggregated metrics has been recognized to be an essential feature of any monitoring system… Given how expensive calculating exact quantiles can be for both storage and network bandwidth, most monitoring system will compress the data into sketches and compute approximate quantiles.

Fortunately there are plenty of quantile sketching algorithms available including the GK-sketch, the t-digest, the HDR histogram, and the Moments sketch that we looked at last year. For reasons we’ll see shortly though, none of those were good enough for Datadog, so they developed their own sketching data structure, DDSketch. Officially in the paper DDSketch stands for ‘Distributed Distribution Sketch’ but that seems a bit of a stretch… surely it’s the ‘Datadog Sketch’ ! A glance at the code repository for the Python implementation confirms my suspicion: there are several references to Continue reading

HPE’s vision for the intelligent edge

It’s not just speeds and feeds anymore, it's intelligent software, integrated security and automation that will drive the networks of the future.That about sums up the networking areas that Keerti Melkote, HPE's President, Intelligent Edge, thinks are ripe for innovation in the next few years.He has a broad perspective because his role puts him in charge of the company's networking products, both wired and wireless.Now see how AI can boost data-center availability and efficiency “On the wired side, we are seeing an evolution in terms of manageability," said Melkote, who founded Aruba, now part of HPE. "I think the last couple of decades of wired networking have been about faster connectivity. How do you go from a 10G to 100G Ethernet inside data centers? That will continue, but the bigger picture that we’re beginning to see is really around automation.” To read this article in full, please click here

HPE’s vision for the intelligent edge

It’s not just speeds and feeds anymore, it's intelligent software, integrated security and automation that will drive the networks of the future.That about sums up the networking areas that Keerti Melkote, HPE's President, Intelligent Edge, thinks are ripe for innovation in the next few years.He has a broad perspective because his role puts him in charge of the company's networking products, both wired and wireless.Now see how AI can boost data-center availability and efficiency “On the wired side, we are seeing an evolution in terms of manageability," said Melkote, who founded Aruba, now part of HPE. "I think the last couple of decades of wired networking have been about faster connectivity. How do you go from a 10G to 100G Ethernet inside data centers? That will continue, but the bigger picture that we’re beginning to see is really around automation.” To read this article in full, please click here

HPE’s vision for the intelligent edge

It’s not just speeds and feeds anymore, it's intelligent software, integrated security and automation that will drive the networks of the future.That about sums up the networking areas that Keerti Melkote, HPE's President, Intelligent Edge, thinks are ripe for innovation in the next few years.He has a broad perspective because his role puts him in charge of the company's networking products, both wired and wireless.Now see how AI can boost data-center availability and efficiency “On the wired side, we are seeing an evolution in terms of manageability," said Melkote, who founded Aruba, now part of HPE. "I think the last couple of decades of wired networking have been about faster connectivity. How do you go from a 10G to 100G Ethernet inside data centers? That will continue, but the bigger picture that we’re beginning to see is really around automation.” To read this article in full, please click here

Weak Chinese Switch Market Quashes Global Growth, Says Dell’Oro

Q&A: HPE’s networking chief opens up about intelligent edge, Cisco and micro data centers

Since founding Aruba Networks in 2002 and then staying on when Hewlett Packard bought the firm in 2013,  Keerti Melkote has seen firsthand the evolution of the wireless industry.From the initial rush to bring laptops using Wi-Fi to the enterprise and the advent of Apple iPad – which Melkote says was a defining moment for enterprise mobility because of the device’s popularity and its need for pervasive enterprise Wi-Fi connectivity – the wireless world has changed dramatically. More about edge networking How edge networking and IoT will reshape data centers Edge computing best practices How edge computing can help secure the IoT And as HPE's President, Intelligent Edge, Melkote is in a position to set the future course for the company’s wired and wireless strategy.  He recently talked with Network World Senior Editor Michael Cooney to lay out HPE’s networking challenges and strategies as it negotiates one of the most technologically and competitively challenging markets.To read this article in full, please click here

Introducing Docker Hub’s New & Improved Tag User Experience

One of Docker’s core missions is delivering choice and flexibility across different application languages and frameworks, operating systems, and infrastructure. When it comes to modern applications, the choice of infrastructure is not just whether the application is run on-premises, on virtual machines or bare metal, or in the cloud. It can also be a choice of which architecture – x86, Arm, or GPU. 

Today, we’re happy to share some updates in Docker Hub that make it easier to access multi-architecture images and scanning results through the Tag UX. 

Navigating to Image Tags

In this example, we’re looking at a listing for a Docker Official Image that supports x86, PowerPC and IBMz as listed in the labels. When you land on the image page on Docker Hub, you can quickly identify if an image supports multiple architectures in the labels underneath the image name. For further details, you can click on ‘Tags’:

In this section, you can now view the different architectures separately to easily identify the right image for the architecture you need, complete with image size and operating system information:

If you click on the digest for a particular architecture, you will now also be able to Continue reading

StreamSets Reaches for the Sky With Cloud Service Launch

Prevent DNS (and other) spoofing with Calico

AquaSec’s Daniel Sagi recently authored a blog post about DNS spoofing in Kubernetes. TLDR is that if you use default networking in Kubernetes you might be vulnerable to ARP spoofing which can allow pods to spoof (impersonate) the IP addresses of other pods. Since so much traffic is dialed via domain names rather than IPs, spoofing DNS can allow you to redirect lots of traffic inside the cluster for nefarious purposes.

So this is bad, right? Fortunately, Calico already prevents ARP spoofing out of the box. Furthermore, Calico’s design prevents other classes of spoofing attacks. In this post we’ll discuss how Calico keeps you safe from IP address spoofing, and how to go above and beyond for extra security.

ARP Spoofing

ARP spoofing is an attack that allows a malicious pod or network endpoint to receive IP traffic that isn’t meant for it. Sagi’s post already describes this well, so I won’t repeat the details here. An important thing to note, however, is that ARP spoofing only works if the malicious entity and the target share the same layer 2 segment (e.g. have direct Ethernet connectivity). In Calico, the network is fully routed at layer 3, meaning that Continue reading

Fast Reroute, Fast Convergence, WRED and WFQ

Fast Reroute , Fast Convergence , WRED and WFQ. You may think that why Orhan is putting all these mechanisms together. I will give you an analogy. Those who participate my talks., know that I love using analogies.  Before we try to understand how these mechanisms are related with each other, let me explain what …

Continue reading "Fast Reroute, Fast Convergence, WRED and WFQ"

The post Fast Reroute, Fast Convergence, WRED and WFQ appeared first on Cisco Network Design and Architecture | CCDE Bootcamp | orhanergun.net.

FTC fines YouTube, but do fines really encourage change? | TECH(feed)

The FTC hit yet another tech company with a seemingly massive fine for mishandling user data. This time, YouTube, owned by Google, is forced to pay $170 million for collecting data about children under 13 without parental consent. The Federal Trade Commission slapped Facebook with a $5 billion fine just a few months ago. In this episode of TECH(feed), Juliet asks whether or not these fines are effective in regulating the tech industry.

Sally Floyd, Who Helped Things Run Smoothly Online, Dies at 69 – The New York Times

best known as one of the inventors of Random Early Detection

The post Sally Floyd, Who Helped Things Run Smoothly Online, Dies at 69 – The New York Times appeared first on EtherealMind.

An MNO’s Guide to Buying a 5G-Ready Next-Generation Firewall

Pureport’s Multicloud Fabric Now Supports AWS Transit Gateway

Sprint and T-Mobile US Coordinate 5G Strategies

USB4 gets final approval, offers Ethernet-like speed

The USB Implementers Forum (USB-IF), the industry consortium behind the development of the Universal Serial Bus (USB) specification, announced this week it has finalized the technical specifications for USB4, the next generation of the spec.One of the most important aspects of USB4 (they have dispensed with the space between the acronym and the version number with this release) is that it merges USB with Thunderbolt 3, an Intel-designed interface that hasn’t really caught on outside of laptops despite its potential. For that reason, Intel gave the Thunderbolt spec to the USB consortium.Unfortunately, Thunderbolt 3 is listed as an option for USB4 devices, so some will have it and some won’t. This will undoubtedly cause headaches, and hopefully all device makers will include Thunderbolt 3.To read this article in full, please click here

AnsibleFest Atlanta – Culture and Collaboration

Now that AnsibleFest is right around the corner, we wanted to take a closer look at each of the tracks that we will offer. We talked with Track Lead Brian Coursen and asked him a few questions about the Culture and Collaboration Track and sessions within the track.  

Who is this track best for? 

This track is best for attendees that want to see how Ansible is used and how it brings people and teams together in the workplace.

What topics will this track cover? 

Topics will include how to create an automation culture as well as highlight some automation use cases. This will include minimizing business unit conflict with patch automation, how to build an open source network service orchestrator using Ansible at the core, and why automation isn't just a passing fad but a necessity in today's enterprise.

What should attendees expect to learn from this track? 

Attendees will learn about DevOps culture and automation. They will also learn about how places like National Weather Service Southern Region; Datacom; and the British financial institution, RBS, are all using Ansible to create a culture of collaboration. 

Where would you Continue reading

Data center cooling: Electricity-free system sends excess building heat into space

We all know that blocking incoming sunlight helps cool buildings and that indoor thermal conditions can be improved with the added shade. More recently, though, scientists have been experimenting with ways to augment that passive cooling by capturing any superfluous, unwanted solar heat and expelling it, preferably into outer space, where it can’t add to global warming.Difficulties in getting that kind of radiative cooling to work are two-fold. First, directing the heat optimally is hard.“Normally, thermal emissions travel in all directions,” says Qiaoqiang Gan, an associate professor of electrical engineering at University at Buffalo, in a news release. The school is working on radiative concepts. That’s bad for heat spill-over and can send the thermal energy where it’s not wanted—like into other buildings.To read this article in full, please click here

Data center cooling: Electricity-free system sends excess building heat into space

We all know that blocking incoming sunlight helps cool buildings and that indoor thermal conditions can be improved with the added shade. More recently, though, scientists have been experimenting with ways to augment that passive cooling by capturing any superfluous, unwanted solar heat and expelling it, preferably into outer space, where it can’t add to global warming.Difficulties in getting that kind of radiative cooling to work are two-fold. First, directing the heat optimally is hard.“Normally, thermal emissions travel in all directions,” says Qiaoqiang Gan, an associate professor of electrical engineering at University at Buffalo, in a news release. The school is working on radiative concepts. That’s bad for heat spill-over and can send the thermal energy where it’s not wanted—like into other buildings.To read this article in full, please click here

The Inevitable Slowdown In Server Spending

It had to happen sooner or later, and really, the wonder is that it hasn’t already happened, given the nature of the infrastructure buildouts at hyperscalers and cloud builders, the skittishness of enterprises due to the trade war between the United States and China, the uncertainty in Europe over the British exit, and general concern with macroeconomic issues because it has now been almost twelve years since the last recession. …

The Inevitable Slowdown In Server Spending was written by Timothy Prickett Morgan at The Next Platform.