The Netflix TechBlog

SEPTEMBER 24, 2021

Virtual Assembly Figure 3 describes how a virtual assembly of the encoded chunks replaces the physical assembly used in our previous architecture. Doing so has the added advantage of being able to design and tune the enhancement to suit the requirements of packager and our other encoding applications.

Cloud 242

Cloud Media Storage Cache 242

Brendan Gregg

DECEMBER 31, 2017

My last talk for 2017 was at AWS re:Invent, on "How Netflix Tunes EC2 Instances for Performance," an updated version of my [2014] talk. Our team looks after the BaseAMI, kernel tuning, OS performance tools and profilers, and self-service tools like Vector. Virtual Memory. We help where we can. schedtool –B PID.

Tuning 53

Tuning AWS Best Practices Network 53

Brendan Gregg

DECEMBER 30, 2017

My last talk for 2017 was at AWS re:Invent, on "How Netflix Tunes EC2 Instances for Performance," an updated version of my [2014] talk. Our team looks after the BaseAMI, kernel tuning, OS performance tools and profilers, and self-service tools like Vector. Virtual Memory. We help where we can. schedtool –B PID.

Tuning 52

Tuning AWS Best Practices Network 52

The Netflix TechBlog

SEPTEMBER 10, 2024

The first was voice control, where you can play a title or search using your virtual assistant with a voice command like “Show me Stranger Things on Netflix.” (See Where aws ends and the internet begins is an exercise left to the reader. We’ll be writing about those new features as well — stay tuned for future posts.

Latency 234

Latency Cache Tuning Efficiency 234

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. The abstractions that Eureka provides for this are Virtual IPs (VIPs) for insecure communication, and Secure VIPs (SVIPs) for secure.

Traffic 229

Traffic Latency Cloud C++ 229

All Things Distributed

OCTOBER 2, 2017

As we began growing the AWS business, we realized that external customers might find our Dynamo database just as useful as we found it within Amazon.com. So, we set out to build a fully hosted AWS database service based upon the original Dynamo design.

Internet 110

Internet Internet AWS Performance 110

Dynatrace

NOVEMBER 10, 2022

Cloud platforms are fully virtualized and, consequently, highly automated. Infrastructure is provisioned and modified in code, eliminating much of the need for manual installation and tuning. This adds up to a significant productivity boost for developers. What are the benefits of cloud-native architecture?

Cloud 162

Cloud Architecture Serverless Infrastructure 162

Brendan Gregg

SEPTEMBER 25, 2021

CLI tools The Cassandra systems were EC2 virtual machine (Xen) instances. Note that Ubuntu also has a frame to show entry into vDSO (virtual dynamic shared object). Aftermath I provided details to AWS and Canonical, and then moved onto the other performance issues as part of the migration.

Speed 103

Speed Java AWS Virtualization 103

Percona

DECEMBER 20, 2018

Now that Database-as-a-service (DBaaS) is in high demand, there is one question regarding AWS services that cannot always be answered easily : When should I use Aurora and when RDS MySQL ? Linux OS Tuning for MySQL Database Performance. Tuning PostgreSQL Database Parameters to Optimize Performance. Tuning InnoDB Primary Keys.

Database 51

Database Tuning Performance AWS 51

Adrian Cockcroft

AUGUST 1, 2022

photo by Adrian I gave a talk at Monitorama in Portland Oregon in June, which set out the idea that carbon is just another metric to monitor, and that in a few years most of the monitoring and performance tuning tools are going to be reporting and optimizing for carbon alongside latency, throughput, availability and cost.

AWS 52

AWS Virtualization DevOps Latency 52

Brendan Gregg

SEPTEMBER 5, 2017

I've suggested adding a command to docker to make listing at least the top-level PIDs in containers easier. ## Virtual Machines The two main technologies on Linux are Xen and KVM (and there's Bhyve for BSD). What happens if processes really do try to populate all that virtual memory?

Virtualization 75

Virtualization AWS Engineering Hardware 75

HammerDB

APRIL 19, 2023

Regardless of whether the computing platform to be evaluated is on-prem, containerized, virtualized, or in the cloud, it is crucial to consider several essential factors. For example, if you are buying the latest Amazon memory-optimized EC2 instance (R7iz), the AWS page ( [link] ) tells us the following: Up to 3.9

Performance 55

Performance Benchmarking Cache Storage 55

Percona

APRIL 12, 2023

So if they can’t beat ‘em in the DBaaS space, they often feel like they have to join ‘em — to the tune of total stack sharing or some proprietary arrangement. The effects have hit cloud vendors who can’t possibly compete with MongoDB. Is MongoDB free for commercial use? Is MongoDB an open source NoSQL database?

Open Source 98

Open Source Programming Database Servers 98

Dotcom-Montior

NOVEMBER 11, 2020

those resources now belong to cloud providers, such as AWS Lambda, Google Cloud Platform, Microsoft Azure, and others. Again, the benefit being that the code within your containers or virtual machines is managed by the cloud provider. No more having to worry about maintenance, patching, or scaling. Focus on Application Development.

Serverless 57

Serverless Monitoring Lambda Latency 57

Percona

APRIL 17, 2023

The main objective of this post is to share my experience over the past years tuning MongoDB and centralize the diverse sources that I crossed in this journey in a unique place. systemctl stop tuned $ systemctl disable tuned Dirty ratio The dirty_ratio is the percentage of total system memory that can hold dirty pages.

Best Practices 52

Best Practices Design Tuning Database 52

O'Reilly

NOVEMBER 28, 2023

Even with cloud-based foundation models like GPT-4, which eliminate the need to develop your own model or provide your own infrastructure, fine-tuning a model for any particular use case is still a major undertaking. How will AI adopters react when the cost of renting infrastructure from AWS, Microsoft, or Google rises?

Open Source 135

Open Source Google Artificial Intelligence Infrastructure 135

Brendan Gregg

SEPTEMBER 25, 2021

CLI tools The Cassandra systems were EC2 virtual machine (Xen) instances. Note that Ubuntu also has a frame to show entry into vDSO (virtual dynamic shared object). Aftermath I provided details to AWS and Canonical, and then moved onto the other performance issues as part of the migration.

Speed 40

Speed Java AWS Virtualization 40

HammerDB

JANUARY 5, 2019

“ Scalability” is a product of both the benchmarking application itself (See the post on HammerDB Architecture to see how it scales implementing multiple virtual users as threads) as well as the benchmarking workload (The TPC benchmarks that HammerDB uses have been designed specifically for this purpose and proven over decades to scale).

Benchmarking 40

Benchmarking Database Social Media Scalability 40

Adrian Cockcroft

NOVEMBER 13, 2023

However if you have a containerized workload that you are measuring with Kepler , or a cloud instance based workload that is running in virtual machines, you measure your carbon footprint based on how many and how big the containers and instances are, and how busy their CPUs are. I’ve written before about how to tune out retry storms.

Energy 52

Energy Cloud Traffic Transportation 52

Adrian Cockcroft

JUNE 21, 2022

I was mostly coding in C, tuning FORTRAN, and when I needed to do a lot of data analysis of benchmark results used the S-PLUS statistics language, that is the predecessor to R. I saw Erik Fisher last time I was in Budapest, and Constantin Gonzalez later became one of the first AWS solutions architects in Germany, too many names to mention.

Tuning 52

Tuning Benchmarking Engineering C++ 52