The Netflix TechBlog

OCTOBER 19, 2020

Kevin Lew , Narayanan Arunachalam , Elizabeth Carretto , Dustin Haffner , Andrei Ushakov, Seth Katz , Greg Burrell , Ram Vaithilingam , Mike Smith and Maulik Pandey “ @Netflixhelps Why doesn’t Tiger King play on my phone?”?—?a We needed to increase engineering productivity via distributed request tracing.

Infrastructure 233

Infrastructure Transportation Storage Open Source 233

Percona

MAY 10, 2023

I have seen many Linux Performance engineers looking at the “IOWait” portion of CPU usage as something to indicate whenever the system is I/O-bound. In this blog post, I will explain why this approach is unreliable and what better indicators you can use.

Cache 143

Cache Monitoring Open Source Processing 143

Dynatrace

JUNE 25, 2021

I lead a dedicated Dynatrace engineering team which has contributed to the OpenTelemetry project since its inception. I also serve as co-chair of the W3C Distributed Tracing working group , which works on standards like W3C Trace Context. Why is everyone talking about OpenTelemetry? Dynatrace news. Distributed tracing.

Open Source 199

Open Source Monitoring Google Systems 199

Dynatrace

SEPTEMBER 18, 2020

Sure, cloud infrastructure requires comprehensive performance visibility, as Dynatrace provides , but the services that leverage cloud infrastructures also require close attention. Well-defined APIs are required for managing such microservices and tracking changes in their performance. Stalled I/O of the underlying message bus.

Infrastructure 191

Infrastructure Latency Metrics Analytics 191

O'Reilly

OCTOBER 24, 2023

Generative AI output became more like itself over time, with less variation. I don’t have the resources to recursively train large models, but I thought of a simple experiment that might be analogous. In many respects, a generative model is a correlation engine. This is unavoidable.

Programming 89

Programming Code Processing Artificial Intelligence 89

Brendan Gregg

MAY 1, 2022

I'm thrilled to be joining Intel to work on the performance of everything, apps to metal, with a focus on cloud computing. My dream is to turn computer performance analysis into a science, one where we can completely understand the performance of everything: of applications, libraries, kernels, hypervisors, firmware, and hardware.

Wireless 52

Wireless Hardware Open Source Cloud 52

Randon ASCII

JANUARY 12, 2022

In 2004 I was working for Microsoft in the Xbox group, and a new console was being created. I got a copy of the detailed descriptions of the Xbox 360 CPU and I read it through multiple times and suddenly I’d learned enough to become the official CPU expert. register files? arithmetic units?) but I’ve long since forgotten.

Cache 126

Cache Latency Benchmarking Hardware 126

Testsigma

JULY 22, 2021

You try to break anything you try new, you are skeptical and perform some testing yourself to see if anything new works fine! You try to break anything you try new, you are skeptical and perform some testing yourself to see if anything new works fine! As mentioned, I love to learn. I thrive on thinking about the what if’s.

Software 97

Software Software Testing Energy 97

Tasktop

MAY 27, 2021

This time, I spoke to Jeff McCollum, our Product Value Stream Lead for Tasktop Hub , who told me how he used Tasktop Viz and Flow Metrics to perfectly time a major application replatforming. . “I I started thinking about application replatforming a while back, mostly based on intuition and drawing on my professional experience,” Jeff begins.

Metrics 69

Metrics Games Engineering Efficiency 69

Brendan Gregg

MAY 28, 2021

I've moved from the San Francisco Bay Area to Sydney, Australia, where I will continue the best job so far of my career: Performance engineering at Netflix. I'm grateful for the support of Netflix engineering management, Netflix HRBPs, and others for helping to make this happen. Why Australia?

Google 40

Google Engineering Open Source AWS 40

O'Reilly

OCTOBER 12, 2021

Kevlin Henney and I were riffing on some ideas about GitHub Copilot , the tool for automatically generating code base on GPT-3’s language model, trained on the body of code that’s in GitHub. If I write something in C and compile it with gcc, realistically I’m never going to look at the compiler’s output.

Code 120

Code Programming C++ Testing 120

The Agile Manager

DECEMBER 31, 2021

An extension of this argument is that an omnichannel strategy doesn’t distinguish among channels, so separating the two - and thereby creating a distinction between them - is solely an act of financial engineering. I first wrote about this almost nine years ago. brand) value.

Ecommerce 52

Ecommerce Retail Strategy Engineering 52

SQL Performance

JULY 3, 2019

As we started to dig into the issues being experienced, it became clear that from a SQL Server standpoint, the problem revolved around sessions in a Sleeping status that were holding locks inside of the Engine. So, we had to dig in further. Understanding Session Status.

Servers 64

Servers Hardware Code Virtualization 64

Alex Russell

AUGUST 30, 2021

Particularly since last winter, when it finally (albeit haltingly and eventually ) became possible to set a browser other than Safari as the default? The decision to ban competing browser engines is as old as iOS, but Apple has only attempted to explain itself in recent years. If no, please explain why not. Apple's Arguments #.

Engineering 98

Engineering Open Source Website Operating System 98

The Morning Paper

OCTOBER 8, 2019

I hope you enjoy it as much as I did! New models are tested online through an A/B testing framework to compare their performance to previous generations. There were many successful iterations of that approach to follow, but eventually performance saturated and it was hard to make any further improvements. Is it worth it?

Network 82

Network Architecture Tuning Traffic 82

Alex Russell

MARCH 31, 2022

When you work on a browser, you will often hear remarks along the lines of, Why don't you just put [popular framework] in the browser? The best available proxy data also suggests that shared caches would have a minimal positive effect on performance. Removal also creates a performance cliff for content that assumes cache availability.

Cache 82

Cache Government Traffic Network 82

Testsigma

FEBRUARY 27, 2022

These include Shanmugam Krishnasamy, co-founder and CTO of Freshworks; Kiran Darisi, co-founder and VP of engineering at Freshworks; Parsuram Vijayasankar, co-founder and principal engineer at Freshworks; Vetri Vellore, CEO of Ally.io; Nitesh Banta, CEO at B12; Ioann Fainsilber, Co-Founder at Pintek, among others.

Testing 52

Testing Open Source Scalability Engineering 52

Brendan Gregg

MAY 16, 2017

I previously wrote about Netflix in [2015] and [2016], and if you are interested in what it's like to work here, I already covered much in those posts. When I joined Netflix in April 2014, we had over 40 million subscribers in 41 countries. Getting frame pointer support in Java was another project I did a while ago.

Java 75

Java Entertainment Engineering Scalability 75

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. The latest AWS hypervisor, Nitro, uses everything to provide a new hardware-assisted hypervisor that is easy to use and has near bare-metal performance.

Virtualization 111

Virtualization AWS Hardware Storage 111

Randon ASCII

AUGUST 16, 2018

I wasn’t looking for trouble. I wasn’t trying to compile a huge project in the background ( 24-core CPU and I can’t move my mouse ), I was just engaging in that most mundane of 21st century tasks, writing an email at 10:30 am. I kept typing but for several seconds but no characters were appearing on screen.

Programming 75

Programming Virtualization Code Processing 75

Rigor

SEPTEMBER 11, 2019

Reading time 16 min Whether you’re a web performance expert, an evangelist for the culture of performance, a web engineer incorporating performance into your process, or someone new to the web performance entirely, you probably identify as curious, excited about new ideas, and always learning. Rachel Andrew.

Performance 89

Performance Education Google Website 89

CSS - Tricks

JULY 25, 2019

This article is from my friend Ben who runs Calibre , a tool for monitoring the performance of websites. In fact, I just popped over there to take a look and was notified of some little mistakes that slipped by, and I fixed them. We use Calibre here on CSS-Tricks to keep an eye on things. Recommended! PageSpeed 5.0

Google 71

Google Engineering Speed Mobile 71

Alex Russell

MARCH 6, 2021

Back in 2016, I gave a talk outlining the causes and effects of the terrible performance of web apps built using popular tools on the fastest-growing device segment: low-end to mid-range Android phones. Poor performance has a compound effect on user expectations at an ecosystem level. Live by the link, die by the link.

Performance 124

Performance Network Cache Metrics 124

ACM Sigarch

FEBRUARY 23, 2018

Engineers, like economists, deal with large amounts of data and pride ourselves on our clinical ability to analyze and solve complex problems. One of the premises expounded upon ( link ) is that engineering/computer science does not appeal to young women and they choose other careers. Discounting the Past.

Architecture 47

Architecture Cache Hardware Virtualization 47

Smashing Magazine

APRIL 9, 2019

As browsers became more capable and net connections got fatter, we started to use more and more JavaScript, and eventually, reusable JavaScript libraries began to spring up. With these added libraries and subsequent plugins came added page weight, and before long we were starting to think seriously about front-end performance.

Website 57

Website Servers Code Best Practices 57

Sutter's Mill

MARCH 11, 2024

To talk about C++’s current safety problems and solutions well, I need to include the context of the broad landscape of security and safety threats facing all software. When I say “safety” unqualified here, I mean programming language safety, which benefits both software security and software safety.

C++ 139

C++ Programming Code Java 139

Smashing Magazine

OCTOBER 29, 2019

Even if you resize your images to the exact specifications of your website and run them through a compressor, they can still put a strain on performance and run up bandwidth usage. (This is a sponsored post.) As well it should. Worse, all of that image manipulation can compromise the resulting quality. So, what’s the solution? What is WebP?

Website 72

Website Speed Cache Google 72

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. The latest AWS hypervisor, Nitro, uses everything to provide a new hardware-assisted hypervisor that is easy to use and has near bare-metal performance.

Virtualization 40

Virtualization AWS Hardware Storage 40

The Netflix TechBlog

MAY 19, 2023

This post discusses why Netflix wanted ABAC support in SpiceDB, how Netflix collaborated with AuthZed, the end result– SpiceDB Caveats , and how Netflix may leverage this new feature. Why did Netflix Want Caveated Relationships? Netflix required attribute support in SpiceDB to support core Netflix application identity constructs.

Cache 249

Cache Google Open Source Systems 249

Alex Russell

FEBRUARY 3, 2023

For most of the past decade, I have spent a considerable fraction of my professional life consulting with teams building on the web. Not only are new services being built to a self-defeatingly low UX and performance standard, existing experiences are pervasively re-developed on unspeakably slow, JS-taxed stacks. It is not going well.

Social Media 119

Social Media Website Technology Technology 119

Tim Kadlec

JANUARY 4, 2018

I spent a lot less time this year on social media. So I dialed it back. At first, I had to trick myself, hiding my Twitter icon several pages deep on my phone so it was very inconvenient while making sure my Kindle app was up front and center. As time went on I didn’t have to do that anymore.

BioTech 45

BioTech Social Media Entertainment Media 45

The Netflix TechBlog

FEBRUARY 13, 2023

Why should members care about any particular show that we recommend? Even after gaining access, one needed to deal with the challenges of homogeneity across different assets in terms of decoding performance, size, metadata, and general formatting. Trailers and artworks provide a glimpse of what to expect in that show.

Media 290

Media Storage Infrastructure Systems 290

O'Reilly

SEPTEMBER 19, 2023

I am wired to constantly ask “what’s next?” ” Most recently, I’ve been thinking about this in terms of the space we currently call “AI.” Enough time has passed; I think we can now be honest with ourselves. ” Sometimes, the answer is: “more of the same.”

Hardware 99

Hardware Storage Big Data Blockchain 99

O'Reilly

JUNE 20, 2023

According to Gillman, whose clients often face life and death situations that are being decided by AI, “I’ve been in hearings where no one in the room can describe for me, how does the algorithm work? Understanding AI’s mysterious “opaque box” is paramount to creating explainable AI. What factors does it weigh?

Blockchain 79

Blockchain Network Government Programming 79

Smashing Magazine

JULY 2, 2021

Their purpose, sending method, and performance vary, and so should the testing flow. That’s why there is a list of aspects that you should test for any kind of email. We spend a lot of time and effort crafting emails with a specific purpose: to make their recipients read them and take the desired actions. Display issues. Engagement.

Testing 109

Testing Servers Social Media Automotive 109

Smashing Magazine

OCTOBER 22, 2021

As the pandemic lingered, the suddenly-remote team I work with became increasingly foosball -deprived. I thought about how to play foosball in a remote setting, but it was clear that simply reconstructing the rules of foosball on a screen would not be a lot of fun. How To Build A Real-Time Multi-User Game From Scratch.

Games 94

Games Servers Database Virtualization 94

All Things Distributed

MARCH 11, 2016

Looking back over the past 10 years, there are hundreds of lessons that we’ve learned about building and operating services that need to be secure, reliable, scalable, with predictable performance at the lowest possible cost. I have picked a few of these lessons to share with you in the hope that they may be of use for you as well.

AWS 144

AWS Hardware Retail Virtualization 144