The Netflix TechBlog

JUNE 14, 2023

By the summer of 2020, many UI engineers were ready to move to GraphQL. The GraphQL shim enabled client engineers to move quickly onto GraphQL, figure out client-side concerns like cache normalization, experiment with different GraphQL clients, and investigate client performance without being blocked by server-side migrations.

Traffic 357

Traffic Latency Metrics Cache 357

The Netflix TechBlog

JUNE 4, 2019

Because microprocessors are so fast, computer architecture design has evolved towards adding various levels of caching between compute units and the main memory, in order to hide the latency of bringing the bits to the brains. This avoids thrashing caches too much for B and evens out the pressure on the L3 caches of the machine.

Cache 258

Cache Latency Airlines Logistics 258

Scalegrid

MAY 11, 2024

MongoDB offers several storage engines that cater to various use cases. The default storage engine in earlier versions was MMAPv1, which utilized memory-mapped files and document-level locking. The newer, pluggable storage engine, WiredTiger, addresses this by using prefix compression, collection-level locking, and row-based storage.

Storage 130

Storage Engineering Cache Database 130

Percona

APRIL 14, 2023

A shared characteristic in most (if not all) databases, be them traditional relational databases like Oracle, MySQL, and PostgreSQL or some kind of NoSQL-style database like MongoDB, is the use of a caching mechanism to keep (a copy of) part of the data in memory. How do you know if your MySQL database caching is operating efficiently?

Cache 107

Cache Efficiency Database Monitoring 107

Dynatrace

JANUARY 31, 2024

The RAG process begins by summarizing and converting user prompts into queries that are sent to a search platform that uses semantic similarities to find relevant data in vector databases, semantic caches, or other online data sources.

Cache 276

Cache Azure Infrastructure Monitoring 276

The Netflix TechBlog

SEPTEMBER 18, 2024

Additionally, the tight coupling with multiple native database APIs — APIs that continually evolve and sometimes introduce backward-incompatible changes — resulted in org-wide engineering efforts to maintain and optimize our microservice’s data access. Either or both may be required by backing storage engines to de-duplicate mutations.

Latency 260

Latency Storage Cache Servers 260

High Scalability

JANUARY 11, 2022

Machine Learning Engineer at Amazon and has led several machine-learning initiatives across the Amazon ecosystem. FUN FACT : In this talk , Rodrigo Schmidt, director of engineering at Instagram talks about the different challenges they have faced in scaling the data infrastructure at Instagram. This is a guest post by Ankit Sirmorya.

Design 334

Design Media Storage Logistics 334

Alex Russell

MARCH 31, 2022

Browsers will cache tools popular among vocal, leading-edge developers. There's plenty of space for caching most popular frameworks. The best available proxy data also suggests that shared caches would have a minimal positive effect on performance. Suppose a user has only downloaded part of the cache. None of this holds.

Cache 89

Cache Government Traffic Network 89

Dynatrace

JANUARY 16, 2023

Most Kubernetes clusters in the cloud (73%) are built on top of managed distributions from the hyperscalers like AWS Elastic Kubernetes Service (EKS), Azure Kubernetes Service (AKS), or Google Kubernetes Engine (GKE). Accordingly, the remaining 27% of clusters are self-managed by the customer on cloud virtual machines.

Open Source 358

Open Source Java Operating System Programming 358

The Netflix TechBlog

APRIL 27, 2023

Engineers want their alerting system to be realtime, reliable, and actionable. A few years ago, we were paged by our SRE team due to our Metrics Alerting System falling behind — critical application health alerts reached engineers 45 minutes late! It opens doors to support more exciting use-cases.

Storage 297

Storage Cache Metrics Database 297

Uber Engineering

JANUARY 16, 2023

Uber’s interactive analytics team shares how they integrated Alluxio’s data caching into Presto, the SQL query engine powering thousands of daily active users on petabyte scale at Uber, to dramatically reduce data scan latencies through leveraging Presto on local disks.

Cache 98

Cache Speed Latency Analytics 98

The Netflix TechBlog

JULY 12, 2019

By Drew Koszewnik This is the story about how the Content Setup Engineering team used Hollow, a Netflix OSS technology, to re-architect and simplify an essential component in our content pipeline?—?delivering there is no eviction policy, and there are no cache misses. The Idea We decided to employ a total high-density near cache (i.e.,

Cache 184

Cache Architecture Latency Engineering 184

Dynatrace

DECEMBER 21, 2023

Starting with data center capacity and host rightsizing, it quickly became apparent that optimizing applications and their underlying source code was the responsibility of architects and engineers. Implement appropriate caching layers (for example, read-only cache for static data). Reduce inter-process communications overhead.

Cloud 264

Cloud Energy Best Practices Cache 264

Dynatrace

APRIL 7, 2022

Spring Boot 2 uses Micrometer as its default application metrics collector and automatically registers metrics for a wide variety of technologies, like JVM, CPU Usage, Spring MVC, and WebFlux request latencies, cache utilization, data source utilization, Rabbit MQ connection factories, and more. That’s a large amount of data to handle.

Metrics 246

Metrics Java Latency Cache 246

The Netflix TechBlog

OCTOBER 29, 2020

For these reasons, as a small engineering team, we’ve found that optimizing for reliability and speed of product delivery is required for us to serve our evolving customers’ needs successfully. Disk cache Of course, network connectivity may not always be available so downloaded rule sets need to be cached to disk.

Mobile 279

Mobile Cache Network Technology 279

DZone

OCTOBER 11, 2022

Using MongoDB as a cache store ( Architects Zone – Architectural Design Patterns & Best Practices). Email Reveals Google App Engine Search API About Ready For Preview Release, Charges Planned For Storage, Operations ( TechCrunch). Why haven’t cash-strapped American schools embraced open source? Hacker News). Java EE 7 is Final.

Java 244

Java Best Practices Google Analytics 244

CSS Wizardry

SEPTEMBER 16, 2024

It’s a magical tool that makes life as a performance engineer so much easier (and much more fun). Interestingly, 304 responses are still a form of redirect: the server is redirecting your visitor back to their HTTP cache. Cache Everything If you’re going to do something, try only do it once. Go and sign up.

Latency 234

Latency Cache Transportation Mobile 234

The Morning Paper

MARCH 8, 2020

Building an elastic query engine on disaggregated storage , Vuppalapati, NSDI’20. If all data was read from S3 every time, performance would suffer, so of course Snowflake has a caching layer – a distributed ephemeral storage service shared by all the nodes in a warehouse. joins) during query processing.

Storage 112

Storage Engineering Cache Serverless 112

The Netflix TechBlog

SEPTEMBER 24, 2021

Our previous blog post described how MezzFS addresses the challenges for reads using various techniques, such as adaptive buffering and regional caches, to make the system performant and to lower costs. It downloads the part(s) that contain the referenced, uploaded bytes and keeps them in an LRU active cache. We’re hiring!

Cloud 242

Cloud Media Storage Cache 242

The Netflix TechBlog

MARCH 7, 2024

Without these integrations, projects would be stuck at the prototyping stage, or they would have to be maintained as outliers outside the systems maintained by our engineering teams, incurring unsustainable operational overhead. Importantly, all the use cases were engineered by practitioners themselves.

Systems 235

Systems Media Cache Open Source 235

The Netflix TechBlog

MARCH 10, 2023

Elasticsearch Integration Elasticsearch is one of the best and widely adopted distributed, open source search and analytics engines for all types of data, including textual, numerical, geospatial, structured or unstructured data. It provides simple APIs for creating indices, indexing or searching documents, which makes it easy to integrate.

Strategy 264

Strategy Cache Storage Analytics 264

The Netflix TechBlog

MAY 19, 2023

By sponsoring the project, Netflix was able to help AuthZed prioritize engineering effort and accelerate adding Caveats to SpiceDB. Over time, each node caches a subset of subproblems to support a distributed cache, reduce the datastore load, and achieve SpiceDB’s horizontal scalability.

Cache 255

Cache Google Open Source Systems 255

The Netflix TechBlog

JULY 1, 2019

As UI engineers we are excited about delivering creative and engaging experiences that help members choose the content they will love so we are always trying to push the limits of our UI. Our UI runs on top of a custom rendering engine which uses what we call a “surface cache” to optimize our use of graphics memory.

Cache 167

Cache Design Testing Development 167

Dynatrace

NOVEMBER 28, 2022

Lambda then takes a snapshot of the memory and disk state of the initialized execution environment, persists the encrypted snapshot, and caches it for low-latency access. Saving your cloud operations and site reliability engineering teams hours of guesswork and manual tagging, the Davis AI engine analyzes billions of events in real time.

Lambda 246

Lambda AWS Serverless Latency 246

Dynatrace

OCTOBER 21, 2020

Our Cluster Performance Engineering Team in collaboration with our Autonomous Cloud Enablement (ACE) and development teams quickly identified the root cause and fixed the problem in no time! One of them being a small cache that would have brought the initial startup time down by about 95%. Step 4: Fixing the issue.

Code 246

Code Cloud Engineering Java 246

The Netflix TechBlog

MARCH 28, 2025

Key insights from this shiftinclude: A Data-Centric Approach : Shifting focus from model-centric strategies, which heavily rely on feature engineering, to a data-centric one. At inference time, when multi-step decoding is needed, we can deploy KV caching to efficiently reuse past computations and maintain lowlatency.

Tuning 165

Tuning Efficiency Latency Strategy 165

The Netflix TechBlog

MARCH 6, 2019

Mounting object storage in Netflix’s media processing platform By Barak Alon (on behalf of Netflix’s Media Cloud Engineering team) MezzFS (short for “Mezzanine File System”) is a tool we’ve developed at Netflix that mounts cloud objects as local files via FUSE. Disk Caching? — ? Regional caching? —?Netflix Replays? —?More

Media 218

Media Storage Processing Cache 218

The Netflix TechBlog

MARCH 8, 2021

As an engineer, I can work anywhere with a standard laptop as long as I have an IDE and access to Stack Overflow. Instead, we created a service to take the most popular configurations and cache them. To meet this need, the Studio Infrastructure team has created Netflix Workstations. Now, artists can get a new workstation in seconds.

Entertainment 307

Entertainment Storage Open Source Hardware 307

The Netflix TechBlog

JULY 21, 2022

Since memory management is not something one usually associates with classification problems, this blog focuses on formulating the problem as an ML problem and the data engineering that goes along with it. Some nuances while creating this dataset come from the on-field domain knowledge of our engineers. of the time (False Positives).

Big Data 188

Big Data Cache Engineering Data Engineering 188

All Things Distributed

SEPTEMBER 3, 2013

Amazon ElastiCache is a fully managed, in-memory caching service for customers to optimize the latency, performance and cost of their read workloads. Similar to how we offer multiple engines in Amazon RDS, starting today, we are supporting Redis as a new engine choice in Amazon ElastiCache, in addition to Memcached.

Cache 99

Cache Cloud Performance Retail 99

The Netflix TechBlog

SEPTEMBER 8, 2020

This allowed Android engineers to have much more control and observability over how we get our data. This allows the app to query a list of “paths” in each HTTP request, and get specially formatted JSON (jsonGraph) that we use to cache the data and hydrate the UI. This meant that data that was static (e.g.

Latency 241

Latency Cache Java Traffic 241

Dynatrace

MAY 13, 2022

You can also analyze table metrics, such as cache hits and misses. Rather than processing simple time-series data, Dynatrace Davis® , our AI causation engine, maps data to a unified entity model using metrics, traces, logs, and real user data. Precise AI-powered answers for Azure Managed Instance for Apache Cassandra.

Azure 246

Azure Latency Metrics Infrastructure 246

ACM Sigarch

DECEMBER 19, 2022

We assume a base multi-core processor four-way-issue load/store machine with 64-bit integer/address registers Rx, 128-bit (16-byte) data registers Vx, and an L1 D-cache that can do two operations per cycle, each reading or writing an aligned 16-byte memory word. Cache pollution is addressed in a section below.). Cache Underpinning.

Design 145

Design Systems Cache Network 145

Dynatrace

OCTOBER 7, 2021

AWS Fargate: Fargate is a serverless compute engine designed for containers that work with Amazon’s Elastic Kubernetes Service (EKS) and the Amazon Elastic Container Service (ECS). Lambda functions can be written in the language of your choice, and the service also supports container tools. Data Store.

Serverless 325

Serverless AWS Lambda Storage 325

The Netflix TechBlog

SEPTEMBER 10, 2024

The folks on the Cloud Data Engineering (CDE) team, the ones building the paved path for internal data at Netflix, graciously helped us scale it up and make adjustments, but it ended up being an involved process as we kept growing. For these requests where caching removed KeyValue from the hot path, we were able to greatly speed things up.

Latency 234

Latency Cache Tuning Efficiency 234

Dynatrace

OCTOBER 29, 2019

Increased stability of CMDB synchronization through identification engine (IRE). Increased stability of CMDB synchronization through the identification engine (IRE). The Dynatrace integration has used the identification and reconciliation engine (IRE) for two years now to correctly import CIs into the ServiceNow CMDB.

Cache 34

Cache Strategy Monitoring Engineering 34

The Netflix TechBlog

MARCH 5, 2019

Netflix’s engineering culture is predicated on Freedom & Responsibility, the idea that everyone (and every team) at Netflix is entrusted with a core responsibility and they are free to operate with freedom to satisfy their mission. All these micro-services are currently operated in AWS cloud infrastructure.

Infrastructure 185

Infrastructure Cloud Scalability AWS 185