Brendan Gregg

FEBRUARY 28, 2023

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Ford, et al., “TCP

Performance 110

Performance Latency Cache Virtualization 110

Brendan Gregg

MARCH 16, 2024

2014: Java in Flames Broken Java Stacks (2014) When I joined Netflix in 2014, I found Java's lack of frame pointer support broke all application stacks (pictured in my 2014 Surge talk on the right). Back-end servers. I spent years as a cloud customer where I couldn't access many HW-level things.)

Java 145

Java Cache Google Hardware 145

Brendan Gregg

FEBRUARY 28, 2023

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Ford, et al., “TCP

Performance 52

Performance Latency Cache Virtualization 52

High Scalability

JUNE 22, 2018

And if you know anyone looking for a simple book that uses lots of pictures and lots of examples to explain the cloud, then please recommend my new book: Explain the Cloud Like I'm 10. 40 million : Netflix monthly spend on cloud services; 5% : retention increase can increase profits 25%; 50+% : Facebook's IPv6 traffic from the U.S,

Internet 113

Internet Internet Scalability Artificial Intelligence 113

Brendan Gregg

SEPTEMBER 25, 2021

These strange questions came to the fore back in 2014 when Netflix was switching services from CentOS Linux to Ubuntu, and I helped debug several weird performance issues including one I'll describe here. This server is spending about a third of its CPU cycles just checking the time! How long does it take to read the time?

Speed 126

Speed Java AWS Virtualization 126

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

Brendan Gregg

JULY 2, 2021

The architecture is: While the bpftrace binary is installed on all the target systems, the bpftrace tools (text files) live on a web server and are pushed out when needed. This is currently part of our FlameCommander UI, which also runs flame graphs across the cloud. at the time.

Latency 145

Latency Cache Energy Systems 145

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. This recommendation quickly became out of date. Impressive!

Virtualization 111

Virtualization AWS Hardware Storage 111

The Netflix TechBlog

APRIL 17, 2019

Netflix headquarters circa 2014. Scalable Video Technology (SVT) is Intel’s open source framework that provides high-performance software video encoding libraries for developers of visual cloud technologies. In August 2018, Netflix’s Video Algorithms team and Intel’s Visual Cloud team decided to join forces on SVT-AV1 development.

Open Source 166

Open Source Scalability Speed Efficiency 166

Brendan Gregg

SEPTEMBER 25, 2021

These strange questions came to the fore back in 2014 when Netflix was switching services from CentOS Linux to Ubuntu, and I helped debug several weird performance issues including one I'll describe here. This server is spending about a third of its CPU cycles just checking the time! How long does it take to read the time?

Speed 40

Speed Java AWS Virtualization 40

Brendan Gregg

SEPTEMBER 25, 2021

These strange questions came to the fore back in 2014 when Netflix was switching services from CentOS Linux to Ubuntu, and I helped debug several weird performance issues including one I'll describe here. This server is spending about a third of its CPU cycles just checking the time! How long does it take to read the time?

Speed 52

Speed Java AWS Virtualization 52

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. This recommendation quickly became out of date. Impressive!

Virtualization 40

Virtualization AWS Hardware Storage 40

Brendan Gregg

JULY 2, 2021

The architecture is: While the bpftrace binary is installed on all the target systems, the bpftrace tools (text files) live on a web server and are pushed out when needed. This is currently part of our FlameCommander UI, which also runs flame graphs across the cloud. It depends on the tool. at the time.

Open Source 40

Open Source Latency Cache Energy 40

KeyCDN

OCTOBER 10, 2018

Although a beta version was released in 2014, the first stable release of Kubernetes was just made available in September 2018. A Kubernetes cluster typically consists of: The Master Server The master server is the primary machine responsible for facilitating communication between the cluster’s different components.

Virtualization 47

Virtualization Open Source Network Architecture 47

Brendan Gregg

SEPTEMBER 5, 2017

Oracle VM Server is based on Xen. Xen's biggest user is the Amazon EC2 cloud, which has over one million customers, and appears to be a custom version (it self identifies as version "3.4.3.amazon"). The way the cloud is used helps with security: most instances at my employer have only been up for one or two days.

Virtualization 76

Virtualization AWS Engineering Hardware 76

All Things Distributed

OCTOBER 25, 2018

Expanding the AWS Cloud—An AWS Region is coming to South Africa! Many of our startup customers in Africa are leveraging the AWS Cloud to grow into successful global businesses. Since it launched in 2014, more than 9 million people have saved or borrowed on the JUMO platform. AWS is committed to South Africa's transformation.

AWS 167

AWS Cloud Education Programming 167

Alex Russell

MARCH 6, 2021

Devices and networks have evolved too: Alex Russell @slightlylate An update on mobile CPUs and the Performance Inequality Gap: Mid-tier Android devices (~$300) now get the single-core performance of a 2014 iPhone and the multi-core perf of a 2015 iPhone. mid-priced Androids were slightly faster than 2014's iPhone 6.

Performance 124

Performance Network Cache Metrics 124

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

All Things Distributed

APRIL 4, 2017

In 2014 and 2015 respectively, AWS opened offices in Stockholm and Espoo, Finland. Icelandic low-cost airline carrier WOW air is using AWS for its Internet-facing IT infrastructure, including its booking engine, development platforms, and web servers.

AWS 116

AWS Airlines Latency Games 116

Abhishek Tiwari

NOVEMBER 3, 2018

Although some vendors have added support for APIs and cloud services most have not even bothered to adapt with changing technology landscape. In addition, traditional CMS solutions lack integration with modern software stack, cloud services, and software delivery pipelines. There is hardly any innovation from traditional CMS vendors.

Systems 63

Systems Cache Website Network 63

High Scalability

NOVEMBER 16, 2018

Unwelcome Gaze is a triptych visualizing the publicly reachable web server infrastructure of Google, Facebook, Amazon and the routing graph(s) leading to them. Know anyone looking for a simple book explaining the cloud? book: Explain the Cloud Like I'm 10. The infrastructure is typically consumed on public clouds.

Internet 28

Internet Internet Scalability Energy 28