performance

HiKey: A high-performance ARM 64-bit developing platform for Linaro

November 11, 2019

David Mandala offers an overview of HiKey. With HiKey, developers can easily use the latest Google AOSP SDK to create and debug new and existing peripheral drivers and perform kernel development and other tasks with fewer OEM encumbrances. HiKey can also be used to make VR applications with OSVR, robotic applications with ROS, and secure applications with ARM TrustZone.

HTTP/2: Protocol overview, use cases, and benchmarks

November 10, 2019

After 16 years of solid use, the HTTP protocol finally got a major update. HTTP/2based on SPDYintroduces new, major performance enhancements and features. Nick Shadrin offers a detailed overview of the protocol, outlines some cases when it significantly helps your website performance, and explains why, in some cases, the older version of the protocol performs better.

Keynote performance by Sammus

November 9, 2019

Rapper, singer, producer, and songwriter Sammus balances her music career with her PhD studies and teaching work at Cornell. Her love of tech, music, and video games comes together in the form of dense and intense lyrics that have wowed fans of nerdcore nationwide. She's joining us at OSCON to share a few songs and a few thoughts about how she got here and where she's going.

Lessons from writing HTraced: A high-performance network daemon in Go

November 8, 2019

HTraced is a new trace collection daemon for the Apache HTrace project, written in Golang. Colin McCabe shares his experiences with the Go programming language and explains the design of HTraced. Colin explores libraries, frameworks, and build systems and discusses what was fun, what was tricky, and how the team optimized overall system performance.

Monitoring in motion: Monitoring containers and dynamic infrastructure

November 8, 2019

We rely on our monitoring to tell us when our services, applications, or infrastructure diverge from "normal." Ilan Rabinovitch takes a deep dive into techniques for leveraging service discovery into your monitoring workflow and explains how to instrument your code in your containers and track the performance and availability of your applications as they move around.

Practical performance tips to make your cross-platform mobile apps faster

November 6, 2019

Apache Cordova is one of the most popular frameworks for cross-platform mobile development. To build Cordova apps that perform well, its important to understand how to use the technologies in the most efficient ways. Doris Chen outlines what impacts "native performance," demonstrates how to measure mobile app performance, and shares practical tips for building faster Cordova apps.

Rethinking security from the ground up with a microservices mindset

November 6, 2019

Recent high-profile data breaches have made it clear that traditional security based on n-tier application partitioning is broken. As we move into the container era, there is a huge opportunity to revolutionize security by rendering developer intent directly into the network fabric. Andrew Randall presents an open source approach to this problem, leveraging proven IP networking and Linux concepts.

The bare-metal hypervisor as a platform for innovation

October 29, 2019

Some workloads work better on a hypervisor hosted within an existing operating system, while others work better on a hypervisor run directly on bare metal with no operating system host. Russell Pavlicek explores a growing breed of solutions that specifically leverage the architecture of a bare-metal hypervisor to address new concepts.

Building DistributedLog, a high-performance replicated log service

October 27, 2019

DistributedLog is a high-performance replicated log service built on top of Apache BookKeeper that is the foundation of publish-subscribe at Twitter, serving traffic from transactional databases to real-time data analytic pipelines. Sijie Guo offers an overview of DistributedLog, detailing the technical decisions and challenges behind its creation and how it is used at Twitter.

Developing a big data business strategy

October 25, 2019

Organizations do not need a big data strategy. They need a business strategy that incorporates big data. Most organizations lack a roadmap for using big data to uncover new business opportunities. Bill Schmarzo explains how to explore, justify, and plan big data projects with business management.

Faster conclusions using in-memory columnar SQL and machine learning

October 25, 2019

Hadoops traditional batch technologies are quickly being supplanted by in-memory columnar execution to drive faster data-to-value. Wes McKinney and Jacques Nadeau provide an overview of in-memory columnar execution, survey key related technologies, including Kudu, Ibis, Impala, and Drill, and cover a sample use case using Ibis in conjunction with Apache Drill to deliver real-time conclusions.

Hadoop in the cloud: Good fit or round peg in a square hole?

October 25, 2019

Thomas Phelan and Joel Baxter investigate the advantages and disadvantages of running specific Hadoop workloads in different infrastructure environments. Thomas and Joel then provide a set of rules to help users evaluate big data runtime environments and deployment options to determine which is best suited for a given application.

High-performance clickstream analytics with Apache Phoenix and HBase

October 25, 2019

Traditional data-warehousing techniques are sometimes limited by the scalability of the implementation tools themselves. Arun Thangamani explains how the advanced architectural approaches by tools like Apache Phoenix and HBase allow new, highly scalable live-analytics solutions using the same traditional techniques and showcases a successful implementation at CDK.

How to turn your house into a robot: An adaptive-learning algorithm for the Internet of Things

October 24, 2019

Modern houses and robots have a lot in common. Both have a lot of sensors and have to make a lot of decisions. However, unlike houses, robots adapt and perform helpful tasks. Brandon Rohrer details an algorithm specifically designed to help houses, buildings, roads, and stores learn to actively help the people that use them.

How to use your data science team: Becoming a data-driven organization

October 24, 2019

Youve decided you need data scientists. You know who to hire. Now, what do you do with them? Yael Garten offers examples of how companies like LinkedIn use data to make business and product decisions. Yael reviews the spectrum of data science, and discusses the culture, process and tools needed to transform companies into data-driven organizations.

Putting Kafka into overdrive

October 22, 2019

Apache Kafka lies at the heart of the largest data pipelines, handling trillions of messages and petabytes of data every day. Learn the right approach for getting the most out of Kafka from the experts at LinkedIn and Confluent. Todd Palino and Gwen Shapira explore how to monitor, optimize, and troubleshoot performance of your data pipelinesfrom producer to consumer, development to production.

Python scalability: A convenient truth

October 21, 2019

Despite Python's popularity throughout the data-engineering and data science workflow, the principles behind its performance and scaling behavior are less understood. Travis Oliphant explains best practices and modern tools to scale Python to larger-than-memory and distributed workloads without sacrificing its ease of use or being forced to adopt heavyweight frameworks.

Real-time Hadoop: What an ideal messaging system should bring to Hadoop

October 21, 2019

Application messaging isnt newsolutions include IBM MQ, RabbitMQ, and ActiveMQ. Apache Kafka is a high-performance, high-scalability alternative that integrates well with Hadoop. Can modern distributed messaging systems like Kafka be considered a legacy replacement or is it purely complementary? Ted Dunning outlines Kafka's architectural benefits and tradeoffs to find the answer.

Scala and the JVM as a big data platform: Lessons from Apache Spark

October 21, 2019

The success of Apache Spark is bringing developers to Scala. For big data, the JVM uses memory inefficiently, causing significant GC challenges. Spark's Project Tungsten fixes these problems with custom data layouts and code generation. Dean Wampler gives an overview of Spark, explaining ongoing improvements and what we should do to improve Scala and the JVM for big data.

Toppling the mainframe: Enterprise-grade streaming under 2 ms on Hadoop

October 19, 2019

What if we have reached the point where open source can handle massively difficult streaming problems with enterprise-grade durability? Ilya Ganelin presents Capital Ones novel solution for real-time decisioning on Apache Apex. Ilya shows how Apex provides unique capabilities that ensure less than 2 ms latency in an enterprise-grade solution on Hadoop.

Virtualizing big data: Effective approaches from real-world deployments

October 18, 2019

Martin Yip and Justin Murray explore the benefits of virtualization of Hadoop on vSphere and delve into three different examples of real-world deploymentsat small, medium, and large scalesto demonstrate how enterprises are currently deploying Hadoop differently on virtual machines.

High performance in the critical rendering path

October 16, 2019

Nicolas Bevacqua explores the past, present, and future of web performance. Nicolas quickly covers what you're already doingminifying, bundling, and using progressive enhancementbefore moving on to what you should be doingoptimizing TCP, inlining the important stuff, and deferring the rest so that you don't block the rendering path. Nicolas also explores what HTTP/2 has in store for the future.

How slow load times hurt the user experience (and ultimately your bottom line)

October 16, 2019

There are compelling arguments why companies need to care about serving faster pages to their users. Countless studies have found an irrefutable connection between load times and key performance indicators, ranging from page views to revenue. Tammy Everts outlines research-based reasons why you need to care about web performance and what you can do to make your pages faster.

HTTP/2 vs. HTTP/1.1: A performance analysis

October 16, 2019

The new HTTP/2 protocol is mostly focused on web performance, but what kind of performance improvement can you expect by switching to HTTP/2? Ragnar Lnn explains the key improvements within HTTP/2 and demos a new application developers can use to see how their applications will function on the new protocol.

The rise of async JavaScript

October 14, 2019

As JavaScript has evolved over the past several years, so have the patterns for handling its asynchronous nature. Through callbacks, Promises, and now async functions, JavaScript has made asynchronous control flow easier to tackle. Jeremy Fairbank dives into the new async functions landing in ES7 and investigates various use cases and gotchas along the way.

Using Julia and D3 to analyze web performance data

October 13, 2019

If you've always wanted to play around with D3 or Julia, Philip Tellis will bring you up to speed very quickly. Philip explores both Julia and D3 to demonstrate how to extract meaningful information from web-performance data and guides participants through some fun visualizations that are possible only when using these tools together.