You are viewing content from a past/completed QCon Plus - November 2020

Session

It’s Not Your Machine; It’s Your Code.

Can we use information in tweets to decide how and when to trade stocks? Yes. But can we do this efficiently at scale, and on a tight budget? Well, this talk will discuss what such a task entails. We will look at some of the performance issues encountered in a simulated high frequency trading scenario, and how we can solve them with a hardware-conscious approach.    

By peeling back layers of software abstractions, we will learn skills and tools to decide how to make the most of our hardware, and how to circumvent limitations imposed by commonly used software.

Main Takeaways

1 Get to see why the standard Linux kernel can hurt your performance at scale, and can prematurely force you into horizontal scaling.

2 Learn about the dangers of extensive abstractions in high throughput systems, and how to get around them.


What are you working on these days?

Lately, I'm working on software for risk management where we try to predict and mitigate the risks associated with creating content at a given time. One such risk for example is what happens when we cannot meet certain production aspects due to COVID-19 restrictions. Based on such factors, we dynamically and intelligently decide how to proceed with the creation process.

And what is the goal of your presentation?

To examine a real-world problem where we might need to challenge our thinking by bypassing popular abstractions and hence regain otherwise hidden performance.

What would you like attendees to walk out with?

Horizontal scaling should not be the default solution to performance issues. Knowing the limitations of your tools and that those limitations can often be circumvented by putting in a little extra work, can usually save resources, time, and money.


Speaker

Adekunle Adepoju

Senior Software Engineer @Netflix

Adekunle works on the Content Platform Engineering team at Netflix, which is tasked with optimizing and accelerating the process of content creation. This involves using engineering methodologies to turn the complex human processes of content creation, into a more deterministic process in order...

Read more
Find Adekunle Adepoju at:

Date

Wednesday Nov 18 / 12:50PM EST (40 minutes)

Track

Mechanical Sympathy: The Software/Hardware Divide

Add to Calendar

Add to calendar

Share

From the same track

Session

Improving Video Encoding System Efficiency @Netflix

Wednesday Nov 18 / 12:00PM EST

Every show on Netflix is encoded for the device type and bit rate that is optimal for the customers. For any one show that can be tens of different encodes, generated by a large-scale system that scales up to hundreds of thousands of CPU cores concurrently. As the performance team at Netflix, we...

Susie Xia

Senior Performance Engineer @Netflix

Session

Pragmatic Performance - Tales from the Trenches

Wednesday Nov 18 / 01:40PM EST

In industry, one if often required to retrofit existing systems to extract more performance out of them. These performance optimization efforts are also performed under deadlines that make the "best'' solution, however attractive, often infeasible. In this talk, we would like to...

Ramesh Subramonian

Principal Engineer @TargetNews

PANEL DISCUSSION

Mechanical Sympathy Panel

Wednesday Nov 18 / 02:30PM EST

In this panel, we’ll continue the conversation about mechanical sympathy by bringing our speakers back to discuss where they see future trends and new ideas they have yet to try. We will touch on new tools that can provide even better insights into what is happening in our systems. We will...

Susie Xia

Senior Performance Engineer @Netflix

Adekunle Adepoju

Senior Software Engineer @Netflix

Ramesh Subramonian

Principal Engineer @TargetNews

View full Schedule

Less than

15

weeks until QCon Plus May 2022

Level-up on the emerging software trends and practices you need to know about.

Deep-dive with world-class software leaders at QCon Plus (Nov 1-12, 2021).

Save your spot for $549 before February 7th

Register