The Netflix TechBlog

AUGUST 29, 2023

A brief history of IPC at Netflix Netflix was early to the cloud, particularly for large-scale companies: we began the migration in 2008, and by 2010, Netflix streaming was fully run on AWS. Today we have a wealth of tools, both OSS and commercial, all designed for cloud-native environments.

Traffic 220

Traffic Latency Cloud C++ 220

All Things Distributed

DECEMBER 13, 2016

In November 2015, Amazon Web Services announced that it would launch a new AWS infrastructure region in the United Kingdom. The British Government is also helping to drive innovation and has embraced a cloud-first policy for technology adoption. Take Peterborough City Council as an example.

AWS 166

AWS Cloud Artificial Intelligence IoT 166

Dynatrace

APRIL 5, 2021

The growth of Azure cloud computing. Azure is a large and growing cloud computing ecosystem that empowers its users to access databases, launch virtual servers, create websites or mobile applications, run a Kubernetes cluster, and train machine learning models, to name a few examples. Making the best use of Azure Functions.

Azure 138

Azure Serverless IoT Lambda 138

Dynatrace

AUGUST 17, 2023

Some years ago, I worked closely with the Spring Framework team as a product manager at Pivotal Software. In 2015, the Spring folks already regarded Dynatrace as the gold standard for performance monitoring.

Metrics 207

Metrics Analytics Speed Java 207

Dynatrace

DECEMBER 22, 2021

With limited visibility, teams have a narrow understanding of how those decisions impact other software components and vice-versa. Observability platforms are becoming essential as the complexity of cloud-native architectures increases. But by 2015, it was more common to split up monolithic applications into distributed systems.

Artificial Intelligence 186

Artificial Intelligence Metrics Architecture DevOps 186

All Things Distributed

JANUARY 6, 2016

The rapidly expanding AWS Partner Network (APN) in Korea includes independent software vendors (ISVs) and systems integrators (SIs) who are building innovative solutions and services around the AWS cloud. Finally, the Seoul Region brings the benefits of the cloud much closer to home for Korean startups.

AWS 110

AWS Cloud Games Latency 110

Dynatrace

APRIL 2, 2020

For nearly fifteen years (~ 2001-2015), network traffic effectively served as a common API for measuring usage, performance, and availability of all applications, links, and clients. Dynatrace PurePath technology enabled application engineers to radically improve the quality of services and software.

Network 167

Network Traffic Monitoring Java 167

All Things Distributed

MARCH 11, 2015

Cloud computing is enabling amazing new innovations both in consumer and enterprise products, as it became the new normal for organizations of all sizes. So many exciting new areas are being empowered by cloud that it is fascinating to watch. Cloud analytics are everywhere. Cloud enables self-service analytics.

Analytics 135

Analytics Cloud Healthcare Retail 135

High Scalability

MARCH 22, 2019

Know anyone who needs cloud? I wrote Explain the Cloud Like I'm 10 just for them. Let them dogfood the software patch. skamille : I worry that the cloud is just moving us back to a world of proprietary software. A satellite image of phytoplankton populations or algae blooms in the Baltic Sea. Debt skyrocketing.

Internet 134

Internet Internet Scalability Wireless 134

Dynatrace

APRIL 30, 2021

Many organizations that have integrated their software development and operations into DevOps practices struggle with efficiency because they’re juggling disparate DevOps tools, or their tools aren’t meeting their needs. In 2011, we only had a few releases a year, but by 2015 we were targeting 25 releases a year.

DevOps 222

DevOps Speed Efficiency Engineering 222

Brendan Gregg

JULY 4, 2021

It's an exciting time for developments in computer performance, not just for the BPF technology (which I often [write about]) but also for processors with 3D stacking and cloud vendor CPUs (e.g., Ford, et al., “TCP on Upcoming Sapphire Rapids CPUs,” [link] Oct 2020 - [Liu 20] Linda Liu, “Samsung QVO vs EVO vs PRO: What’s the Difference?

Performance 140

Performance Latency Hardware Storage 140

All Things Distributed

MAY 15, 2014

This is the promise – and the reality – of cloud computing which is driving tremendous change in the technology industry and transforming how we do business in Europe and around the world. Cloud computing unlocks innovation within organisations of all types and sizes.

Cloud 123

Cloud Innovation AWS Government 123

Dynatrace

APRIL 17, 2019

During our annual Perform event, CEO John Van Siclen explained how several years ago – whilst at a dinner in Linz – we saw the cloud coming, and that it would disrupt everything, meaning monitoring alone would no longer be enough. We’re spearheading the move to the cloud, the disruption, and we want you to continue with us on that journey.

Innovation 140

Innovation Virtualization Cloud Azure 140

Dynatrace

JUNE 2, 2020

Autonomous Cloud Programmability. Many use cases in your software development, delivery, and operations depend on the real-time data that your Dynatrace monitoring environment collects. Our API was first introduced in 2015 and has since led to great success for our customers in automating their IT operations. Dynatrace news.

Metrics 187

Metrics Scalability Tuning Monitoring 187

Brendan Gregg

FEBRUARY 28, 2023

TCP Extensions for Multipath Operation with Multiple Addresses,” [link] Mar 2020 - [Gregg 20] Brendan Gregg, “Systems Performance: Enterprise and the Cloud, Second Edition,” Addison-Wesley, 2020 - [Hruska 20] Joel Hruska, “Intel Demos PCIe 5.0 Ford, et al., “TCP

Performance 110

Performance Latency Cache Virtualization 110

Brendan Gregg

SEPTEMBER 25, 2021

As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI. Software-based clocksources could fix those issues and provide accurate monotonically-increasing time. We ended up setting it in the BaseAMI for all cloud services. But I'm not completely sure.

Speed 126

Speed Java AWS Virtualization 126

The Netflix TechBlog

DECEMBER 23, 2020

Unfortunately, these default namespace boundaries are not sufficient to prevent container escape, as seen in CVEs like CVE-2015–2925. Various pieces of software used elevated capabilities for FUSE, low-level packet monitoring, and performance tracing amongst other use cases. To mitigate this, we run containers as unprivileged users?—?making

Media 286

Media Metrics Systems Processing 286

Brendan Gregg

JULY 2, 2021

This is currently part of our FlameCommander UI, which also runs flame graphs across the cloud. This is thinking like a sysadmin who installs and maintains software, and not like a programmer who codes everything. Second, the BPF software, especially certain kprobe-based tools, require ongoing maintenance. That's the fast way.

Latency 145

Latency Cache Energy Systems 145

All Things Distributed

APRIL 4, 2017

In 2014 and 2015 respectively, AWS opened offices in Stockholm and Espoo, Finland. In making the switch to AWS, WOW air has saved between $30,000 and $45,000 on hardware, and software licensing. AWS Partner Network (APN) Consulting Partners in the Nordics help customers migrate to the cloud.

AWS 116

AWS Airlines Latency Games 116

Brendan Gregg

FEBRUARY 28, 2023

TCP Extensions for Multipath Operation with Multiple Addresses,” [link] , Mar 2020 [Gregg 20] Brendan Gregg, “Systems Performance: Enterprise and the Cloud, Second Edition,” Addison-Wesley, 2020 [Hruska 20] Joel Hruska, “Intel Demos PCIe 5.0 Ford, et al., “TCP

Performance 52

Performance Latency Cache Virtualization 52

Brendan Gregg

JULY 4, 2021

It's an exciting time for developments in computer performance, not just for the BPF technology (which I often [write about]) but also for processors with 3D stacking and cloud vendor CPUs (e.g., Ford, et al., “TCP on Upcoming Sapphire Rapids CPUs,” [link] Oct 2020 - [Liu 20] Linda Liu, “Samsung QVO vs EVO vs PRO: What’s the Difference?

Performance 52

Performance Latency Hardware Storage 52

Testsigma

JUNE 5, 2021

In 2015, 35% of the internet traffic came from mobile devices, 6 years later, the number is 54.8%. Cloud-based online tools generally go with the emulators and simulators on their platform. They are just software running on an operating system. Then, the best way is to opt for a cloud-based device lab.

Mobile 52

Mobile Testing Website Testing Tools 52

Brendan Gregg

NOVEMBER 29, 2017

Hardware virtualization for cloud computing has come a long way, improving performance using technologies such as VT-x, SR-IOV, VT-d, NVMe, and APICv. At Netflix, we've been using these technologies as they've been made available for instance types in the AWS EC2 cloud. Each dimension has progressed through these stages: 1. Impressive!

Virtualization 111

Virtualization AWS Hardware Storage 111

Strategic Tech

FEBRUARY 27, 2021

Recommended Reading: From zero to production in sixty minutes: Building a cloud platform for product development. HMRC , of all places, had an excellent DX for continuously delivering applications all the way back in 2015. Learning & Sharing Community Being a software developer is a very privileged career.

Development 98

Development Strategy Infrastructure Metrics 98

Brendan Gregg

MARCH 16, 2024

To explain this example in more detail: The profiler periodically interrupts software execution, and for those disconnected stacks it happens to be the execution of the kernel software ("vfs*", "ext*", etc.). I spent years as a cloud customer where I couldn't access many HW-level things.) Click here for a longer explanation.

Java 145

Java Cache Google Hardware 145

Testsigma

FEBRUARY 19, 2021

Testsigma is a cloud-based, AI-driven test automation platform that supports Agile and Continuous Delivery teams – for browser as well as mobile testing. TestComplete is an automated UI testing tool which is developed by SmartBear Software. XCUITest is a UI testing framework for iOS apps that was launched by Apple in 2015.

Testing Tools 57

Testing Tools Mobile Testing Java 57

Brendan Gregg

SEPTEMBER 25, 2021

As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI. Software-based clocksources could fix those issues and provide accurate monotonically-increasing time. We ended up setting it in the BaseAMI for all cloud services. But I'm not completely sure.

Speed 40

Speed Java AWS Virtualization 40

The Netflix TechBlog

NOVEMBER 22, 2019

4:45pm-5:45pm NFX 202 A day in the life of a Netflix Engineer Dave Hahn , SRE Engineering Manager Abstract : Netflix is a large, ever-changing ecosystem serving millions of customers across the globe through cloud-based systems and a globally distributed CDN. Wednesday?—?December

AWS 37

AWS Entertainment Open Source Benchmarking 37

ACM Sigarch

APRIL 26, 2018

They introduced the architecture of coarse grain reconfigurable array (CGRA) for statically scheduled data flow computing in HOTCHIPS’17 and its software stack of compiler and linker in ICCAD’17. TPU1 focused on the inference tasks, and has been deployed in the datacenter since 2015.

Hardware 99

Hardware Artificial Intelligence Architecture Google 99

Enprowess

JANUARY 12, 2022

Technology helps companies offer their software services to customers quickly, creating personalized experiences. Internet of things (IoT) – Number of IoT devices 2015-2025 Statista. Serverless architecture is the fastest-growing cloud computing paradigm nowadays. That will share and collect real-time data. Smart cities.

Blockchain 59

Blockchain IoT Development Serverless 59

Brendan Gregg

SEPTEMBER 25, 2021

As a Xen guest, this profile was gathered using perf(1) and the kernel's software cpu-clock soft interrupts, not the hardware NMI. Software-based clocksources could fix those issues and provide accurate monotonically-increasing time. We ended up setting it in the BaseAMI for all cloud services.

Speed 52

Speed Java AWS Virtualization 52

Brendan Gregg

JULY 2, 2021

This is currently part of our FlameCommander UI, which also runs flame graphs across the cloud. They need constant updates to keep working across different software versions. As an extreme example, I wrote cachestat(8) while on vacation in 2014 for use on the Netflix cloud, which was a mix of Linux 3.2 patch to Linux 5.12.

Open Source 40

Open Source Latency Cache Energy 40

Brendan Gregg

NOVEMBER 28, 2017

Hardware virtualization for cloud computing has come a long way, improving performance using technologies such as VT-x, SR-IOV, VT-d, NVMe, and APICv. At Netflix, we've been using these technologies as they've been made available for instance types in the AWS EC2 cloud. Each dimension has progressed through these stages: 1. Impressive!

Virtualization 40

Virtualization AWS Hardware Storage 40

Brendan Gregg

AUGUST 8, 2017

Load averages are an industry-critical metric – my company spends millions auto-scaling cloud instances based on them and other metrics – but on Linux there's some mystery around them. They can be also useful when a single value of demand is desired, such as for a cloud auto scaling rule. I've never seen an explanation.

Latency 111

Latency Metrics C++ Systems 111

Smashing Magazine

JANUARY 6, 2020

In real-life world, most products aren’t even close: an median bundle size today is around 417KB , which is up 42% compared to early 2015. In 2015, Google introduced Brotli , a new open-source lossless data format, which is now supported in all modern browsers. Plus, it’s even supported on Fastly’s edge cloud.

Performance 145

Performance Cache Network Metrics 145

Smashing Magazine

JANUARY 7, 2019

In real-life world, most products aren’t even close: an average bundle size today is around 400KB , which is up 35% compared to late 2015. In 2015, Google introduced Brotli , a new open-source lossless data format, which is now supported in all modern browsers. We could also go beyond the bundle size budget though. Is TLS Fast Yet?

Performance 104

Performance Cache Network Metrics 104

Smashing Magazine

JANUARY 11, 2021

compared to early 2015. Also check DNS Performance comparison and Cloud Peformance Comparison. In 2015, Google introduced Brotli , a new open-source lossless data format, which is now supported in all modern browsers. Plus, it’s even supported on Fastly’s edge cloud. Unfortunately, the data is only from 2019).

Performance 145

Performance Cache Media Metrics 145