The Netflix TechBlog

OCTOBER 26, 2021

Subsequent posts will go into more details on experimentation across Netflix, how Netflix has invested in infrastructure to support and scale experimentation, and the importance of the culture of experimentation within Netflix. In this post, we’ll do the same for false negatives and the related concept of statistical power.

Testing 202

Testing Latency Metrics Innovation 202

The Netflix TechBlog

SEPTEMBER 8, 2020

Over the course of this post, we will talk about our approach to this migration, the strategies that we employed, and the tools we built to support this. The big difference from the monolith, though, is that this is now a standalone service deployed as a separate “application” (service) in our cloud infrastructure.

Latency 233

Latency Cache Java Traffic 233

Scalegrid

APRIL 16, 2020

In this post, we compare ScaleGrid’s Bring Your Own Cloud (BYOC) plan vs. the standard Dedicated Hosting model to help you determine the best strategy for your MySQL, PostgreSQL, Redis™ and MongoDB® database deployment. Are you comfortable setting up your own cloud infrastructure through AWS or Azure? Expert Tip. No problem.

Cloud 242

Cloud Azure AWS Database 242

The Morning Paper

NOVEMBER 14, 2019

Taiji’s routing table is a materialized representation of how user traffic at various edge nodes ought to be distributed over available data centers to balance data center utilization and minimize latency. This outcome at our deployment scale means a reduction of our infrastructure footprint by more than one data center.

Traffic 42

Traffic Internet Internet Latency 42

The Morning Paper

JANUARY 23, 2020

1:18pm a key observation was made that an API call to populate the homepage sidebar saw a huge jump in latency. " Five infrastructure engineers and 3 product engineers were involved in the incident. " Five infrastructure engineers and 3 product engineers were involved in the incident.

Internet 53

Internet Internet Cache Engineering 53

Adrian Cockcroft

NOVEMBER 11, 2019

There are many possible failure modes, and each exercises a different aspect of resilience. Collecting some critical metrics at one second intervals, with a total observability latency of ten seconds or less matches the human attention span much better. A resilient system continues to operate successfully in the presence of failures.

Latency 52

Latency Engineering Systems Hardware 52

Adrian Cockcroft

NOVEMBER 11, 2019

There are many possible failure modes, and each exercises a different aspect of resilience. Collecting some critical metrics at one second intervals, with a total observability latency of ten seconds or less matches the human attention span much better. A resilient system continues to operate successfully in the presence of failures.

Latency 53

Latency Engineering Systems Hardware 53