Our site uses cookies to provide functionality and performance as well as for social media and advertising purposes. Social media and advertising cookies of third parties are used to offer you social media functionalities and personalized ads for NGINX content and offers. To get more information about these cookies and how we process personal data, check our Privacy Policy. Do you accept the use of cookies and the processing of personal data involved?
Developer, NGINX
Roman is a member of the core development team at NGINX. He contributes to a variety of open source and commercial features including HTTP and TCP/UDP proxying, caching, and video streaming. He manages several open source third-party NGINX modules, including the RTMP streaming module. Prior to NGINX, Roman was developing distributed storage systems and video streaming solutions.
Presentation: Developing NGINX Modules
Developing NGINX Modules is a hands-on class that will give you the foundation you need to begin extending NGINX functionality with NGINX modules. The class will begin with a discussion of when and why a new NGINX module might be the best solution for you. We'll then guide you through the development process from the point of view of a first time developer: obstacles encountered and how they were overcome, with particular attention to the sites, blogs, and queries that were most helpful. Next, you'll dive into NGINX internals – the code that is NGINX. You'll get an architectural overview, deep dives into how connections are handled, data types and structures, memory, module structure, and NGINX coding best-practices. You'll then write a simple hello_world module, exploring the build process, dynamic vs static modules, and how to specify its directives. You'll then write and execute tests for your module. Following the hello_world module, you'll write simple access, header filter, and body filter modules. We'll discuss the NGINX Certified Module program, best practices for module development, and the resources we've made available to you. The class wraps up with a panel discussion with our instructors – Valentin Bartenev, Roman Arutyunyan, and Aidan Carson.
Objectives After completing this class you will be able to:
Audience Developing NGINX Modules is for architects and developers who are interested in extending NGINX core functionality for specific business purposes.
Prerequisites Developing NGINX Modules is intended for developers and advanced administrators with prior development experience. C/C++ and systems programing is recommended. Basic knowledge of configuring, troubleshooting and administering NGINX is highly advised. Although not a requirement, it's ideal for attendees to have taken the NGINX Core course before attending Developing NGINX Modules.
Developer, NGINX
Valentin was already experienced with developing NGINX modules when he joined NGINX, Inc. just a few months after the company was established. Since then, he has worked on implementing new features and fixing bugs in open source NGINX and NGINX Plus for almost six years now. He is mostly known for his work on SPDY and HTTP/2 modules, thread pools, and various improvements on Linux.
Presentation: Developing NGINX Modules
Developing NGINX Modules is a hands-on class that will give you the foundation you need to begin extending NGINX functionality with NGINX modules. The class will begin with a discussion of when and why a new NGINX module might be the best solution for you. We'll then guide you through the development process from the point of view of a first time developer: obstacles encountered and how they were overcome, with particular attention to the sites, blogs, and queries that were most helpful. Next, you'll dive into NGINX internals – the code that is NGINX. You'll get an architectural overview, deep dives into how connections are handled, data types and structures, memory, module structure, and NGINX coding best-practices. You'll then write a simple hello_world module, exploring the build process, dynamic vs static modules, and how to specify its directives. You'll then write and execute tests for your module. Following the hello_world module, you'll write simple access, header filter, and body filter modules. We'll discuss the NGINX Certified Module program, best practices for module development, and the resources we've made available to you. The class wraps up with a panel discussion with our instructors – Valentin Bartenev, Roman Arutyunyan, and Aidan Carson.
Objectives After completing this class you will be able to:
Audience Developing NGINX Modules is for architects and developers who are interested in extending NGINX core functionality for specific business purposes.
Prerequisites Developing NGINX Modules is intended for developers and advanced administrators with prior development experience. C/C++ and systems programing is recommended. Basic knowledge of configuring, troubleshooting and administering NGINX is highly advised. Although not a requirement, it's ideal for attendees to have taken the NGINX Core course before attending Developing NGINX Modules.
Sr. Solutions Architect, Verizon
Mohamad is a Sr. Solutions Architect at Verizon with 14 years of academic and industrial experience in software development, project management, and people management. He has worked and consulted for several Fortune 100 companies architecting, designing, and developing software systems. In the last four years, he has been involved in different digital transformation programs, influencing key technology strategies and focusing on modernizing application architecture including microservices, event-driven architecture, cloud computing, serverless computing, APIs, containers, and DevOps.
Mohamad holds a PhD in Computer Science from the University of Texas at Dallas and had served as adjunct faculty at the University of North Texas at Dallas where he delivered undergraduate computer science courses in topics including computer security, ecommerce security, computer networks, and wireless communications. He is TOGAF 9 Certified and AWS Certified Solutions Architect – Associate.
Presentation: Service Mesh for Microservices 2.0
In the past few years, the microservices architecture became more mainstream, as large enterprises have started adopting it for its promise to enable them to deliver software faster, innovate and embrace newer technologies more easily, and have the freedom to react and make informed decisions. However, most adopters have ended up with a “distributed monolith”, unable to realize the true benefits of architectures like polyglot microservices.
In this session, Mohamad shares his experience working with microservices at Verizon. He reviews his team's journey to their Microservices 2.0 solution, including the challenges they faced along the way as different teams adopted different technology stacks to build microservices. With Microservices 2.0, the strategy is to leverage the “platform” (Kubernetes + service mesh) as the "outer architecture" in order to build business‑focused polyglot services that are decoupled from it.
Sales Engineer, NGINX
Amanda is a Technical Solutions Architect and has spent 2 years with NGINX. She came from a sales background and has successfully transitioned into a technical role. She now works with the sales team on technical training, and works with customers on solutions around NGINX.
Presentation: Demo: How to Configure Unit for a Production Application
Come and learn about how the newest Multilingual and Dynamic App Server NGINX Unit can fit into your environment.
Sr. Network Engineer, AppNexus
Ernesto is a Senior Network Engineer at AppNexus, a multinational technology company based in New York. Its cloud-based software platform enables and optimizes programmatic online advertising.
Presentation: Migrating Load-Balanced Services from F5 to NGINX Plus
In this session Ernesto describes how AppNexus replaced all of the F5 hardware load balancers in its global data centers with NGINX Plus, detailing the motivations for the migration, the pitfalls, and the successes. Major concerns with the F5 load balancers were SSL capacity limitations and the lack of scalability and flexibility. The workaround offered by F5 was cost-prohibitive, unrealistic, and didn't address all the issues. Ernesto also covers in detail the steps and challenges his team went through, from the proof of concept through to the implementation and operation phases. After presenting HTTP and HTTPS benchmark performance data, he discusses some improvements and fixes to NGINX that he thinks would make it a more complete and robust alternative to other hardware-based load balancing solutions.
Manager, Software Engineering, Verizon Digital Media Services
Seungyeob is Manager of Software Engineering for the CDN Streaming team at Verizon Digital Media in Los Angeles, California. He has worked on building and optimizing infrastructure for video delivery on various platforms and protocols. During recent years, his primary focus has been on transmuxing live and VOD videos for HLS and DASH streaming using NGINX.
Presentation: NGINX for Commercial-Quality Streaming Services
NGINX Plus and the NGINX RTMP module offer many streaming features. In this session, Seungyeob talks about challenges his team encountered while developing streaming services based on NGINX, and shares their experiences solving problems. He explains how to encrypt HLS, handle non-standard MP4 files published by customers, and deliver high-bitrate content (UHD videos), and do live low-latency streaming, topics which are now attracting attention from the streaming industry.
API and Platform Evangelist, Telstra
An established international speaker and respected technologist Steven has covered some half million kilometers as a speaker and mentor at over 100 tech and developer events. Among his activities in the international community Steven has helped run the acclaimed BattleHack series for PayPal/Braintree all over the world.
Representing global technology companies such as PayPal, Braintree and Xero Steven has worked closely with developer communities as a Tech Evangelist and industry thought leader to develop and nurture the healthy start-up and developer culture that continues to flourish.
Over the last 20 years, Steven has worked as a senior developer/tech lead for a host of start-ups and as a developer analyst for more than 10 years with Sensis. He has configured and spec’d technology for the likes of Samsung, Virgin, Coca-Cola, Pepsi, Visa, St. George and Westpac.
Presentation: Using NGINX with IoT: Ingress to the Edge and Beyond
In the internet-of-things (IoT) nobody knows you are a fridge. Add a couple of trillion more connected devices and DevOps teams are facing a new challenge. As IoT connectivity utilizing LTE CAT1/CAT M1 and narrowband continues to become more prevalent globally, it presents new challenges in building for speed, scale, and flexibility in the DevOps space.
Building infrastructure to deal with millions of low bandwidth devices has become even more critical, requiring that you ultimately move the power of NGINX ever closer to the edge -- and soon beyond.
In this session we'll look closely at how tiny IoT compute devices work, delve into the connectivity challenges of the IoT world, and explore some of the ways to deal with building out scale with help from NGINX. We'll bring all together with a demo of IoT devices and NGINX in action.
Director, Product Management, NGINX
Liam Crilly, Director of Product Management at NGINX, Inc., wrote his first web app 25 years ago and has enjoyed working with Internet software ever since. Liam has held various product management roles from startups to multinational organizations. When he's not typing arbitrary command into curl(1), Liam can be found behind the wheel (or more likely underneath) his race car.
Presentation: 10 Tips for Deploying NGINX as an API Gateway
At the heart of modern application architectures is the HTTP API. They enable applications to be built rapidly, maintained easily, and scaled at will. API gateways are typically deployed as an additional layer in the application delivery environment, bringing additional complexity and points of failure. In this session, Liam will demonstrate how to use the API gateway you already have - NGINX!
This session will provide actionable tips, configuration snippets and live demos of NGINX deployed as an API gateway. We will look at best practice configuration for delivering REST/JSON and gRPC APIs with NGINX.
Presentation: NGINX and NGINX Plus Update and Demo
In this keynote session we will share the NGINX roadmap and how it is influenced by the technology trends affecting our customers and the open source community. We will take a look at the latest enhancements to NGINX and NGINX Plus, including a demonstration of new capabilities just released with NGINX Plus R16.
Presentation: Wrap Up on the NGINX Application Platform and Ecosystem
The NGINX Application Platform is made up of a portfolio of NGINX products and extended by our rich ecosystem of technology partners. In this keynote, we'll cover some of the more interesting ecosystem solutions including Kubernetes, ModSecurity, Red Hat OpenShift, and others. We'll also discuss how we're evolving our API gateway capabilities.
Technical Manager, Business Development, NGINX
Presentation: Scaling your web app to new heights with AWS and NGINX
In this session we will discuss how AWS and NGINX can complement each other to create highly scalable, high performance and secure web applications. We will cover the different ways that NGINX can integrate with AWS services such as NLB, Route53 and PrivateLink to add new layers of security and functionality to your high traffic website, streaming service or IOT system.
VP, Products and Technologies, Red Hat
Margaret Dawson is a frequent author and speaker on cloud computing, emerging technologies, open source, and digital disruption. A 20-year tech industry veteran, Margaret is the vice president of Portfolio Product Marketing at Red Hat. A proven entrepreneur and intrapreneur, Margaret has led successful initiatives and teams at several startups and Fortune 500 companies, including Amazon, Microsoft, and HP. Prior to Red Hat, she was Vice President of Product Marketing and Cloud Evangelist for HP Helion, the cloud computing division of Hewlett-Packard Enterprise. Ranked as one of the top Women in Cloud Computing, Margaret is an advisor to Cloud Connect and the Cloud Network of Women (CloudNOW) as well as to multiple early-stage companies and CEOs. She is an active mentor for men and women in technology and was recently named Business Role Model of the Year for Women in IT, and Mentor and Coach of the Year in the Stevie Business Awards.
Presentation: How to Survive and Thrive on Your Journey Through Digital Disruption
Every organization is undergoing a transformation. In this journey, the technology choices we make, our architectural decisions, and the pace at which we deliver IT services determine whether we make the business impact required to succeed. No one escapes digital disruption, but we can get ahead of it or even create our own waves of disruption in our market. Margaret Dawson, who works with enterprises and governments worldwide, will cut through the hype of digital transformation and focus on how organizations are thinking and moving into next-generation architectures, agile processes, and collaborative cultures. Through real-world examples, she will discuss the market dynamics and what it takes to be a digital leader. Whether you’re a digital laggard or in the middle of a major transformation, this session will give you ideas and new perspectives.
Sr. Full Stack Developer, The Atlantic
Frankie Dintino is a Senior Full Stack Developer at The Atlantic, where he has worked for the past 8 years. During his time at The Atlantic Frankie has had a hand in all facets of the publication’s web presence. He has created interactives for editorial features, written much of the python code that powers the Django frontend and CMS of theatlantic.com, and built the NGINX/uWSGI stack that delivers the site to readers. He manages several open-source projects, including the NGINX Upload module. He lives in Washington, DC with his wife, Ashley, and a Coton de Tuléar pup named Virgil.
Presentation: Using NGINX for release automation at The Atlantic
At The Atlantic we create a new beta environment for every pull request. This allows developers and the people doing QA to review site changes quickly while keeping costs low. To facilitate this we use a combination of Github, Jenkins, NGINX (with uWSGI cheaper subsystem for Python applications/Passenger for Node) and a few Python scripts. The result is a server configuration that can handle a large number of environments because it only uses resources as necessary. This talk will be valuable to anyone interested in release automation or maximizing server resource usage with NGINX (+uWSGI/Passenger).
Developer, NGINX
Maxim Dounin is a core NGINX developer. He started working with NGINX very early on, and was an active contributor and author of various modules. Maxim joined NGINX, Inc. when it was founded, and now maintains NGINX sources.
Presentation: Reading nginx CHANGES Together
What's new in NGINX recently? While this question is easily answered with a simple "try reading CHANGES", in some cases just reading might not be enough – and nobody tries to read it anyway. Even those who have actually read it might benefit from some background on why the changes were introduced and from more details on how to use them properly.
In this session Maxim summarizes various new features and changes in the NGINX 1.13.x branch (now available in the stable 1.14.x branch). In particular, he discusses:
ngx_http_grpc_module)ngx_http_mirror_module)He also covers what is being developed in the current mainline branch (1.15.x), including:
ssl directiveThe session concludes as everyone reads through CHANGES together (and with expression!) and takes a look at some examples on how to use new features properly.
To get the most from this session, review CHANGES beforehand at nginx.org/en/CHANGES
Director, Integration & Tokenization Architecture, Capital One
Mike Dunn is a Director, Integration & Tokenization Architecture at Capital One. He leads architecture planning for Integration, Tokenization and Secrets management and platforms.
He has more than 15 years experience architecting and developing large-scale systems in financial services, manufacturing, and factory / nuclear power control systems. He works with business leaders and delivery teams to ensure that systems meet business objectives while also being scalable, performant, resilient and easy to use. He enjoys building systems in Lua, Go, NodeJS and architecting resilient AWS, GCP and Kubernetes runtime platforms.
Presentation: NGINX Powers 12 Billion Transactions per day at Capital One
Capital One uses NGINX for our highest throughput, lowest latency applications. Follow our journey as we started with our API Gateway as our first NGINX application, and then based on that success, rolled our several other applications. NGINX's single threaded event loop with OpenResty module for writing custom Lua code has enabled us to scale our applications to 12 Billion operations per day, a peak of 2 million operations per second and being able to hold our latency to 10-30 milliseconds.
Director, Project Management, NGINX
Jason Feldt is an experienced product leader with a demonstrated history of successful creation and growth of a variety of innovative products. He joined NGINX just in time to bring the NGINX Controller product to market. Before NGINX, he was most recently leading software-defined networking and WAN-optimization load balancing products at Riverbed Technology. In his off-time, he enjoys photography, scotch whiskey, and retro computing.
Presentation: Demo: Tips for Managing NGINX at Scale with NGINX Controller
Help us shape the Controller roadmap! We will start with an interactive demonstration of NGINX Controller where audience questions are expected and welcomed as we demonstrate Controller functionality, peppered with stories of the responses from our customers and prospects so far. We will end with a Q&A session on our upcoming Controller roadmap, let us know what you would like to see and what you think of the product so far!
Presentation: NGINX Controller Update and Demo
Hear about NGINX Controller: The history behind its creation, the vision of where we are taking the product and how it fits into the overall product and corporate strategies, a brief demonstration of our current release, and a high-level roadmap of upcoming functionality.
Sr. Director, Product Management, NGINX
Owen Garrett leads the product and go-to-market strategy for NGINX’s web acceleration and delivery technologies. He has over 15 years of experience in software engineering and product leadership at companies such as Riverbed. Today, Owen uses his technical and management expertise to optimize NGINX products and customer satisfaction.
Presentation: Running NGINX and NGINX Plus in Clusters
In this session Owen and Vladimir share strategies for running multiple NGINX and NGINX Plus instances in a cluster. They look in depth at methods for sharing traffic across instances, and at the zone‑synchronization module provided in NGINX Plus for sharing run‑time state.
Presentation: Product Strategy & Announcements
Hear a recap of all the product announcements we're making a NGINX Conf 2018, as well as a preview of our roadmap and key ecosystem integrations. Owen will also cover key enhancements to our open source projects, as well as tee-up the deep-dives and demos you'll see across all aspects of the NGINX Application Platform.
Presentation: Wrap Up on the NGINX Application Platform and Ecosystem
The NGINX Application Platform is made up of a portfolio of NGINX products and extended by our rich ecosystem of technology partners. In this keynote, we'll cover some of the more interesting ecosystem solutions including Kubernetes, ModSecurity, Red Hat OpenShift, and others. We'll also discuss how we're evolving our API gateway capabilities.
Technical Solutions Architect, NGINX
A 20+ year technology professional, Brian has worked at NGINX for the past year and as a Sales Engineer in the software ADC space for 6 years before that. Previous roles include professional services engineer, architect for a hardware manufacturer, and IT operations at not-for-profit companies, all of which have given him a unique perspective on the high-tech field. Brian has written numerous technical articles and holds two patents in networking and network architecture.
Presentation: NGINX Plus, Kubernetes & Prometheus - Gain insights into your Ingress Controller
Are you using the Kubernetes Ingress Controller and want to monitor the traffic flowing through it? How do you measure the health and performance of all your microservices in a Kubernetes environment? Look no further than NGINX Plus and Prometheus (with a little bit of Grafana for some good looking dashboards). In this session we will cover the NGINX Plus API and Status, the NGINX Prometheus Exporter, and accessing the rich data in Prometheus and through Grafana.
CTO, Qrator Labs CZ
Artyom is CTO at Qrator Labs, a DDoS mitigation and network monitoring company. He graduated from the faculty of Computational Mathematics and Cybernetics at Moscow State University, and has been working in the area of IT networking and monitoring for a decade. He previously presented at numerous conferences, including BlackHat USA, RIPE Meeting, APNIC/APRICOT, and ICANN EE DNS Forum.
Presentation: DDoS Beasts and How to Fight Them Part 1
DDoS threats have been evolving rapidly in recent years, to the point where they have become a community-wide problem. The past two years have seen the spawning of numerous IoT-related working groups, mostly in response to the infamous 1.1-Tbps, IoT-based DDoS attack in autumn 2016. Fast-forward a year and half, and we see even more disastrous attacks.
In this session Artyom aims to dissect the DDoS threat. He describes the ISO/OSI layers, offering a mutually exclusive and collectively exhaustive classification of DoS attacks, a description of what makes them possible, and a set of possible ways to mitigate attacks of any kind.
The session is based on apersonal experience. It is vendor-agnostic and doesn't cover or promote any solutions available on the market. Attendees are welcome to use the information to guide them in building their own solution.
Presentation: DDoS Beasts and How to Fight Them Part 2
DDoS threat has been rapidly evolving recently, up to the point when it started to be a community-wide problem. Numerous IoT-related working groups were spawned throughout the last 2 years mostly due to the infamous 1,1 Tbps IoT DDoS attack in autumn 2016. Fast-forward 1,5 years, and we see attacks even more disastrous.
This workshop aims at dissecting the DDoS threat. It goes over the ISO/OSI layers, offering a mutually exclusive and collectively exhaustive classification of denial-of-service attacks, a description of what makes them possible, and a set of possible ways to mitigate attacks of any kind.
The tutorial is based on a personal experience. It is vendor-agnostic and doesn't cover or promote any solutions available on the market, an attendee is welcome to use this as a guide to build their own.
SRE, Traffic-team, Dropbox
Oleg Guba is a Site Reliability Engineer on the Traffic Team at Dropbox's offices in Mountain View, California. He is leading the effort to further scale the Dropbox edge network and continuously improve the edge traffic stack at Dropbox points of presence. The main components of the traffic stack are DNS, Layer 4 load balancers, NGINX, and other traffic-management components. Oleg previously worked at Yandex in Moscow, Russia.
Presentation: An In-Depth Look at the Dropbox EDGE Network
In this session Oleg describes the internal architecture of the EDGE network at Dropbox, including the data centers, PoP locations, and traffic transit patterns. He covers the traffic management approaches in detail for several flows: ingress, internal, and egress.
Systems Engineer, SysEleven GmbH
Roland has worked as a Systems Engineer for SysEleven since 2015. He currently supports the service operation center, which means he directly works with customers taking care of their needs – from critical incidents to changes and more. For this objective he is provided with a deep knowledge of all the customers' setups as well as all the technologies in use.
Presentation: NGINX in a managed hosting environment
When you use NGINX as a load balancer and/or application server, what challenges and problems will you face? As a managed hosting provider from Berlin, we (SysEleven) use NGINX in almost every setup within our virtual environment. We will show you how we deal with NGINX within our own stack and how we manage to easily configure a NGINX server with puppet.
Systems Engineer, SysEleven GmbH
Dimitri has been a Linux Systems Engineer at SysEleven since 2017. After having worked in the service operation center, he moved to the customer operations team where he creates performant open source solutions for applications in a managed hosting environment. His main technological focus is on web-based applications powered by technologies like PHP, Apache, Nginx, Percona SQL, the Elastic Stack and Puppet.
Presentation: NGINX in a managed hosting environment
When you use NGINX as a load balancer and/or application server, what challenges and problems will you face? As a managed hosting provider from Berlin, we (SysEleven) use NGINX in almost every setup within our virtual environment. We will show you how we deal with NGINX within our own stack and how we manage to easily configure a NGINX server with puppet.
VP of Marketing and Strategic Development, Solarflare
Ahmet Houssein is responsible for establishing marketing strategies and implementing programs to drive revenue growth, enter new markets and expand brand awareness to support Solarflare’s continuous development and global expansion. He has over twenty-five years of experience in the server, storage, data center and networking industry, and held senior level executive positions in product development, marketing and business development at Intel and Honeywell. Most recently Houssein was SVP/GM at QLogic where he successfully delivered first to market with 25Gb Ethernet products securing design wins at HP and Dell. One of the key leaders in the creation of the INFINIBAND and PCI-Express industry standard, Houssein is a recipient of the Intel Achievement Award and was a founding board member of the Storage Network Industry Association (SNIA), a global organization of 400 companies in the storage market. He has been educated in London, UK and holds an Electrical Engineering Degree equivalent.
Presentation: Turbocharge Your NGINX Deployment
The modern-day data center is a scale-out, software-defined infrastructure where generic servers are used with software applications to create compute servers, storage servers and various appliance solutions. Today software load balancers are replacing purpose-built hardware/software appliances in order to distribute data around the scale-out environment.
Join Ahmet Houssein as he discusses how Solarflare’s XtremeScale technology with Universal Kernel Bypass accelerates NGINX performance, increasing QPS up to 4X compared to a kernel solution using a standard NIC and Linux kernel driver, while linearly scaling performance.
DevOps Lead, The Atlantic
Mike Howsden designs and automates infrastructure for The Atlantic. He's currently most interested in improving the lives of developers and keeping things running smoothly. He previously worked with PBS Digital and a number of small Internet and media companies.
Presentation: Using NGINX for release automation at The Atlantic
At The Atlantic we create a new beta environment for every pull request. This allows developers and the people doing QA to review site changes quickly while keeping costs low. To facilitate this we use a combination of Github, Jenkins, NGINX (with uWSGI cheaper subsystem for Python applications/Passenger for Node) and a few Python scripts. The result is a server configuration that can handle a large number of environments because it only uses resources as necessary. This talk will be valuable to anyone interested in release automation or maximizing server resource usage with NGINX (+uWSGI/Passenger).
Software Developer, NGINX
Grant Hulegaard is an engineer on the NGINX Controller team. He joined NGINX three years ago in the NGINX Amplify core group. He has helped build tools that work with and around NGINX and NGINX Plus. Prior to NGINX, Grant was a Technical Lead on software solutions for the aviation industry, including the Department of Defense.
Presentation: How to Analyze NGINX Configs Using NGINX Controller
In this session Grant makes a technical deep dive into NGINX configuration files: examining their structure, talking about how to use an NGINX open source project to create a JSON representation of them, and how NGINX Controller uses this structure to analyze your configuration to check for common errors and "gotchas".
Principal Cloud Engineer, Priceline.com
Michael studied astronomy and physics in college and grad school, and ended up in computers. During his 13 years at Priceline.com, he's progressed through Java infrastructure coding, application development, API work, and NodeJS frontend development to DevOps. He now works to make the development process better and faster for application teams by leveraging the new tools and techniques available.
Presentation: Increase Developer Throughput with Unlimited User Testing Environments
Michael explains how developers can use NGINX and Docker to show business users their progress easily without running into the resource constraints imposed by limited testing environments. His team overlays its development version of an application on top of the current production systems, enabling them to see just the new changes and how they interact with the rest of the site. The team uses NGINX to manage the routing for the over 20 separate small applications that make up the user experience, even as each application iterates quickly on multiple features. In combination with Docker, this gives them the benefits of instant environments despite having old, difficult-to-manage monolithic applications in the stack.
Global Product Specialist, NGINX
Kevin is a Global Product Specialist at NGINX Software, Inc. where he specializes in application delivery, routing, monitoring, and load balancing. Kevin has passion for technology and art. He previously worked as a Site Reliability Engineer and Production Manager for Yellowpages.com and most recently as a Technical Solutions Architect and Product Specialist for NGINX Software Inc.
Presentation: Best Practices for Caching
We all know that performance is a critical factor in the success of applications and websites, but it's not always clear how to improve it. Code quality and infrastructure are of course important, but in many cases, you can vastly improve the end-user experience of your application by focusing on some very basic application-delivery techniques. One such technique is implementing and optimizing caching in your application stack.
In this session, Kevin offers an introduction to the basic principles of content caching and outlines how NGINX caches responses, describing NGINX’s unique management process and how the cache metadata is stored on disk. Along the way, Kevin shares techniques for using NGINX's web cache features that can help both novice and advanced users improve performance. He reviews and analyzes all of the available caching directives and parameters, showcases a working example that enables basic caching functionality, and explores various advanced caching implementations from the perspectives of both NGINX configuration and architectural implementation .
Director, Software Engineering, Capital One
Rohit Joshi is a Director, Software Engineering at Capital One. He leads the DevExchange API Gateway, Digital Payments, and PCI Tokenization platforms. The payment token vault is the platform behind the Capital One Eno enabled virtual cards. He has more than 15 years experience developing and operating large-scale customer-focused products, platforms, and services in finance and telecom domains. He enjoys building innovative high-performance platforms. He is passionate about cultivating a culture of creativity, collaboration, and excellence within his teams.
Presentation: NGINX Powers 12 Billion Transactions per day at Capital One
Capital One uses NGINX for our highest throughput, lowest latency applications. Follow our journey as we started with our API Gateway as our first NGINX application, and then based on that success, rolled our several other applications. NGINX's single threaded event loop with OpenResty module for writing custom Lua code has enabled us to scale our applications to 12 Billion operations per day, a peak of 2 million operations per second and being able to hold our latency to 10-30 milliseconds.
Developer, NGINX
Vladimir has been a member of the core development team at NGINX since 2012. He spends most of his time developing commercial features for NGINX Plus, but is always glad to contribute to the open source version. He is the author of such features as session affinity, the Least Time load‑balancing algorithm, and various improvements to the upstream module.
Before joining NGINX, he worked as an RTOS kernel developer, developing the user‑space networking stack and porting NIC drivers.
Presentation: Running NGINX and NGINX Plus in Clusters
In this session Owen and Vladimir share strategies for running multiple NGINX and NGINX Plus instances in a cluster. They look in depth at methods for sharing traffic across instances, and at the zone‑synchronization module provided in NGINX Plus for sharing run‑time state.
Sr. Product Marketing Manager, NGINX
Karthik is Senior Product Marketing Manager at NGINX responsible for driving marketing initiatives for NGINX Controller, our flagship product for managing NGINX Plus instances. He is an experienced product marketer with a proven track record of developing and commercializing IT management & troubleshooting products. Prior to NGINX, Karthik held similar positions at Fluke Networks, Cisco Systems and Nimble Storage, a Hewlett Packard Enterprise company.
Presentation: The TCO of the NGINX Application Platform
What is the total cost of ownership (TCO) of the NGINX Application Platform? In this session, Karthik explains how the NGINX Application Platform has enabled a large B2C enterprise to reduce costs and realize operational efficiencies by simplifying its app‑delivery tool set from 13 distinct solutions down to just 3. Based on feedback from both traditional infrastructure and operations (I&O) and DevOps teams, he describes how NGINX customers have leveraged the NGINX Application Platform's features to maximize ROI.
Director, Cloud Application Platforms, Comcast
Christopher graduated college and immediately asked the question: “What am I going to do with this degree in English?” Starting off in an entry-level customer support role, he moved into various development and engineering roles before settling into roles focusing on the intersection of infrastructure and code. After years of resisting suggestions that he try out management, Christopher agreed to take on a leadership role and quickly discovered that building teams is still building things. He's been focused on how to effectively lead engineering teams since. Christopher is currently Director, Cloud Application Platforms at Comcast Cable.
Presentation: Help Yourself! A Tale of Adoption, DevOps,and the Challenge of Delivering Self-Service for a High-Growth Service
Back in 2015, a small, scrappy group of engineers set out to replace a commercial API management gateway with an in-house solution based on NGINX. A year later they emerged, singed but triumphant, with hundreds of existing services transparently migrated to the new platform. Latencies were reduced and acclaim rang out: “The old 50th percentile is the new 99th!” clients said with glee.
The improvements drove unforeseen growth. Over two years, the number of services hosted more than doubled. Data centers came and went. Thousands of new credentials were added to the system. Transaction rates that once peaked at 2,000 RPS grew to 33,000. The small DevOps team, in its rush to stop paying for a commercial solution, had made a strategic decision to hold off on delivering self-service. Now they had no choice but to prioritize the manual labor required to add services and credentials while working towards self service, before eventually delivering self-service to its consumers.
In this case study, Christopher unpacks events as they unfolded, looks at the decisions that were made, and describes the lessons learned from the challenges his team faced.
Architect, Intel
Gordon McFadden studied Computer Science at the Technical University of Nova Scotia - now part of Dalhousie University - in Halifax, Nova Scotia. After graduation he moved to Vancouver, British Columbia to work in the thriving software and firmware industry. In 2000, he joined Intel. His passions at work include the details of compression and creating solutions around Intel® QuickAssist Technology that allow accelerated compression to be used in massively scalable solutions. Gordon et al. hold a patent relating to self-testing of processors (US9612930).
Presentation: OpenSSL(PKE) + Payload Compression integrated into NGINX
Sr. Director, Charter Communications
Jamie Panagos is currently a Senior Director at Charter Communications where he runs an Operations Engineering team responsible for the delivery of video content to next-generation devices over IP. Before Charter, Jamie focused on networking while working at Juniper Networks, where he was a lead within their Professional Services' service provider and large enterprise practice. He also worked at BBN/GTEi/Genuity/Level(3) Communications, where he was a Senior Engineer concentrating on backbone and MPLS engineering. Jamie holds a JNCIE-M/T (#445) and a JNCIE-ER (#50) and authored "This Week: Deploying MPLS" as well as "JUNOS Day One: Monitoring and Troubleshooting”.
Presentation: The Imperative to Modernize
Every company must learn plan and execute like a technology company. Products, services, and distribution mechanisms are all going digital at breakneck speeds. To win customers and provide a compelling digital experience, organizations must deploy technology that enables them to optimize digital delivery, as well as react quickly to ever-changing business and consumer needs. In this opening keynote, NGINX CEO Gus Robertson will talk about the major trends impacting enterprises in the digital era, how companies can master the transition, and how the NGINX Application Platform helps.
Presentation: Leveraging IPv6 Routing For Resource Reachability
To date, CDNs have largely been deployed as overlay systems exploiting DNS or redirects to guide clients to the best cache. While this has served the industry well, delivery systems will need to adapt and integrate into the network rather than simply riding on top of it if forecasts are accurate. This talk discusses a concept which attempts to converge resources and routing to provide more efficient delivery, more control of resource reachability and easier sharing of delivery infrastructure.
Platform Integration Engineer, NGINX
Michael is a Platform Integration Engineer at NGINX, Inc. in Cambridge UK. He develops NGINX integration solutions for various modern platforms, such as Kubernetes or AWS, assists technology partners with NGINX expertise, and writes technical blog posts and deployment guides.
Presentation: Using NGINX as a Kubernetes Ingress Controller
The Ingress controller is one of the most critical parts of Kubernetes platform, acting as the entry point for all incoming traffic to applications running on Kubernetes. That’s why it must be built on top of a proven and reliable load‑balancing technology, such as NGINX. The NGINX Ingress controller combines the benefits of using the Kubernetes control plane to manage load‑balancing configuration with the performance, reliability, and advanced features of NGINX or NGINX Plus. Additionally, the NGINX Ingress controller integrates NGINX with cloud‑native tools such as Helm and Prometheus, which are rapidly gaining adoption in production Kubernetes environments.
This session is for beginning or intermediate Kubernetes users who are looking to deliver applications on Kubernetes in production. Michael shows how to successfully load balance HTTP as well as TCP/UDP applications on Kubernetes with NGINX Ingress controller. Topics include:
Technical Architect, Professional Services, NGINX
Charles has served as an architect and lead engineer for a wide range of companies, with a focus on high-volume online retailers. He is now Technical Architect at NGINX, Inc. and is leading the launch of the NGINX Microservices Reference Architecture.
Presentation: A Pragmatic Maturity Model for Adopting Microservices
In this session, Charles discusses different architectures for adopting microservices, including the NGINX Microservices Network Architectures. These architectures will be placed in the context of both migration of existing monolithic applications and "green field" applications. After the session, attendess will understand best practices for determining how microservices should be coupled, as well as how to use NGINX to ensure that the microservices are loosely coupled. In addition, we'll look at some of the advanced features of NGINX Plus within a microservices architecture, with a focus on service discovery, load balancing, health monitoring, and security.
VP, Product Management, NGINX
Sidney Rabsatt is Vice President of Product Management at NGINX responsible for leading product strategy. Sidney is an experienced leader with a proven track record of building winning Enterprise products across a variety of markets. Sidney has also held leadership roles at Riverbed Technology and Packeteer and technical roles at Hewlett-Packard and IBM.
Presentation: A Pragmatic Journey to Modernize
Learn about the exciting technology coming from NGINX and how our solutions give organizations the freedom of choice and enable the agility they need to modernize faster.
Technical Marketing Engineer, NGINX
Amir is a Technical Marketing Engineer at NGINX. He started his career as a programmer, then moved to reproducing live customer networks in data centers and building software automation tools accelerating IT operations. Amir has a degree in Computer Engineering and hands-on experience with performance-tuning open source technologies on the Linux operating system.
Presentation: Performance-Tuning NGINX Open Source and NGINX Plus
Speed is key for most users. Slow performance in optimization models can in some cases be solved with parameter tuning. In this session, Amir explains how to maximize NGINX performance and covers important aspects of performance tuning in an infrastructure.
Technical Trainer, NGINX
Gretchen is a technical instructor and instructional designer with 15+ years in technical training and technical sales. She holds MCSE certification, an MBA, and a Master’s in Data Science. She recently traveled all over the world training students on GE Digital’s Predix platform. A glutton for information, she likes to read, play the piano, travel, and watch action and scifi movies. She’s married with two amazing children, one cat, and two obnoxious dogs.
Presentation: NGINX Core
NGINX Core is an eight-hour course that provides the foundation you need to administer, configure, and manage NGINX. Through lecture and hands-on activities you implement NGINX as a web server, load balancer, and reverse proxy. You'll secure your site with SSL/TLS and improve site performance with caching and compression. And you'll learn how to monitor and troubleshoot your site with live activity monitoring, custom logging, and dynamic server configuration. Whether you are new to NGINX, starting your first NGINX project, or refining your DevOps skills, NGINX Core gives you a grounding to build on. NGINX Core is also your gateway to more advanced training topics like Microservices Network Architectures with NGINX, and others.
If you're new to NGINX, NGINX Core is the place to start. If you’re self-taught, or have some working experience with NGINX, NGINX Core will help you solidify your understanding. In NGINX Core, you will implement the most common use cases for NGINX – web server, proxy server, and load balancer – in a secure, scalable way. As you do, you'll build a solid foundation for moving on to advanced topics, including more complex security considerations and microservices implementation and architecture.
NGINX Core combines lecture, instructor demos, and hands-on activities. Each lecture and instructor demo in NGINX Core is followed by hands-on activities in which you implement the use case in a preconfigured, personal training environment. For example, following the lesson on serving static content, you'll implement a basic web server that serves static content in your environment. In later modules you'll add a simple proxy server, enable security (HTTPS), implement variables and maps, route connections, rewrite and redirect requests, implement a variety of load balancing models, and configure caching.
Objectives
After completing this course you will know how to:
Audience NGINX Core is intended for admins, architects, and DevOps professionals who are self-taught or new to NGINX.
Prerequisites No prior knowledge of or experience with NGINX is required. Participants should have a basic understanding of web servers and the Unix command line. Required skills include running Unix commands, navigating the file system, and creating and editing text files.
CEO, NGINX
Gus Robertson serves as Chief Executive Officer of NGINX and is a seasoned leader in the technology industry, including companies such as Microsoft, Visio, Lexmark, and Red Hat. Gus has a proven track record of building successful commercial offerings, strengthening open source communities, and driving customer loyalty.
Presentation: The Imperative to Modernize
Every company must learn plan and execute like a technology company. Products, services, and distribution mechanisms are all going digital at breakneck speeds. To win customers and provide a compelling digital experience, organizations must deploy technology that enables them to optimize digital delivery, as well as react quickly to ever-changing business and consumer needs. In this opening keynote, NGINX CEO Gus Robertson will talk about the major trends impacting enterprises in the digital era, how companies can master the transition, and how the NGINX Application Platform helps.
VP Network and Cybersecurity Engineering and Operations, AppNexus
Josh Ryder is a member of the Technical Operations team at Xandr (nee AppNexus) where he is VP Cybersecurity and Network Engineering & Ops. His main responsibilities include building out the Cybersecurity program and supporting some amazingly skilled engineers and architects as we tackle scaling for our global customer base. Among his teams' recent accomplishments is the complete removal of traditional hardware load balancers in favor of NGINX Plus.
Presentation: The Imperative to Modernize
Every company must learn plan and execute like a technology company. Products, services, and distribution mechanisms are all going digital at breakneck speeds. To win customers and provide a compelling digital experience, organizations must deploy technology that enables them to optimize digital delivery, as well as react quickly to ever-changing business and consumer needs. In this opening keynote, NGINX CEO Gus Robertson will talk about the major trends impacting enterprises in the digital era, how companies can master the transition, and how the NGINX Application Platform helps.
Sr. Product Manager, NGINX
Nick is a Product Manager at NGINX, the company behind the most popular web server technology among high‑performance web sites. Nick has helped many top websites to get to the next step in application delivery through the use of cutting‑edge architectural approaches and solutions. He enjoys hands‑on work with Linux systems, networking, HTTP as well as solving challenging technical problems on a fundamental level. Prior to NGINX, Nick worked at Citrix and ZScaler, helping their users to make the web experience faster and more secure.
Presentation: NGINX Unit Update
NGINX Unit is the new dynamic web and application server, announced last year. It's open source and is now available for production use. Unit supports PHP, Python, Go, Ruby, and Perl.
In this keynote session we will discuss the latest news and update everyone on the progress. We will also discuss the role of where code can be executed in your infrastructure -- as part of your app server or in the delivery infrastructure using something like NGINX JavaScript.
Presentation: Reading the NGINX Unit Changelog Together
NGINX Unit is different from NGINX in terms of its architecture, use cases, and its place in the application stack, but it's very similar in its development culture. As in his session about the NGINX changelog, in this session Nick describes the new features and other changes introduced in NGINX Unit over the past year. He starts with general topics like how to receive announcements on the open source changes, the different code branches, and the version numbering scheme.
He continues with a deep dive into features completed during the beta period:
timeout parameter for applicationshome parameter for Python virtual environmentsatexit handlerprocesses object with prefork and dynamic process managementHe concludes with a review of changes made after the GA release of version 1.0:
access_log parameter for basic access loggingenvironment object for setting environment variablesoptions object for managing php.ini configuration variablessettings object for global configuration optionsTo get the most from this session, review the changelog beforehand at unit.nginx.org/CHANGES.txt
Head of Product Management, Networking, Google Cloud, Google
Lakshmi Sharma leads the networking product management team at Google Cloud. Her team oversees Google Cloud’s network, the largest of any cloud provider in terms of network infrastructure. She has been involved with the networking community for more than a decade and holds a patent in segment routing. Prior to Google, Lakshmi held product management positions at Target, Brocade, RIFT.io, Cisco, and Juniper. Lakshmi also believes in giving back to the community by mentoring and volunteering with several programs, including Project Cornerstone and the Silicon Valley Young Coders Club. She holds an MBA from the University of Santa Clara, as well as a Masters in Computer Applications from Delhi University.
Presentation: Migrate, Manage and Operate Services Securely and at scale in Hybrid Cloud
In this talk we would discuss common patterns on Hybrid and Multi-Clouds application deployments and some tools and technologies that are enabling application deployment and management at scale.
Hosting & Streaming Engineer, NPO
Dick is a Unix/Linux sysadmin who loves all things open-source. Over the last fifteen years, he helped the Dutch Public Broadcasting (NPO) grow its web hosting and video streaming to a platform that can deliver content to the entire Dutch audience while using a minimum of the taxpayer's money.
Presentation: How NPO Achieved High-Throughput, Secure Video Streaming Running NGINX on Modest, Off-The-Shelf Hardware
When the demand for a video streaming platform grows from tens to hundreds of Gigabit, some scaling issues are likely to crop up. In this talk I will zoom in on 3 topics:
At the NPO we host the video streaming platform for the largest Dutch news & sports network. At peak times -- e.g. during important soccer matches or main news events -- the NPO platform serves approximately 450,000 concurrent viewers which translates to 450Gbit of network traffic.
Head of Development Group, Mail.Ru Group
Vasiliy's experience includes more than eight years developing server applications for high workloads. Alongside commercial software development, Vasiliy has taken part in open source projects that include Tarantool, Nkit, and Centrefugo. He is the author of several commercial modules for NGINX and two open source modules. Since 2015, he's been an active conference speaker and article writer.
Presentation: Why Make Your Own NGINX Modules? Theory and Practice
Sometimes you have business goals which can be reached by developing your own modules for NGINX. NGINX modules can be business oriented and contain some business logic as well. However, how do you decide for certain that a module should be developed? How might NGINX help you with development?
In this session, Vasiliy provides the detailed knowledge you need to build your own NGINX modules, including details about NGINX's core, its module architecture, and guiding principles for NGINX code development. Using real‑world case studies and business scenarios, he answers the question, "Why and when do you need to develop your own modules?"
This session will be quite technical. To get the most out of it, attendees need at least intermediate‑level experience with NGINX code.
Webdeveloper and Web Solution Architect, Audi
Timo Stark (5/28/91). Programming since 15 years now.
Started at Audi in 2010 as an SAP ABAP Developer. Since 2014, Timo has been an Enterprise Solution Architect for on-prem hosted web applications and its infrastructure (Loadbalancer, Web-Application-Firewalls, Application-Server, Databases, and much more).
Presentation: Audi Cockpit Project: A microservices web dashboard built using NGINX Plus as an API gateway on AWS
This is a true microservices journey. Almost a year ago we started with nothing more than a vision. Build a web application hosted on AWS and driven by APIs. Make it secure, lightweight, and fast. It needed to be stable and flexible. And have fun while doing it!
We will start our Journey at the very beginning. From a concept over the first AWS Infrastructure setup in dev to the production ecosystem with NGINX Plus as in important component at the end.
Specifically, this talk will discuss the concept behind the API gateway and the traffic routing to Microservices running with Kubernetes in AWS.
CTO and Co-Founder, NGINX
Igor Sysoev’s passion for solving the C10k problem led him to become the author of NGINX, which was initially released in 2004. NGINX’s popularity and use became so widespread that Igor co-founded NGINX, Inc. in 2011. He has 16 years of experience in deeply technical roles and is currently the Chief Technology Officer.
Presentation: NGINX Unit Update
NGINX Unit is the new dynamic web and application server, announced last year. It's open source and is now available for production use. Unit supports PHP, Python, Go, Ruby, and Perl.
In this keynote session we will discuss the latest news and update everyone on the progress. We will also discuss the role of where code can be executed in your infrastructure -- as part of your app server or in the delivery infrastructure using something like NGINX JavaScript.
Technical Trainer, NGINX
James has been teaching folks about software since 2012 and has developed training for the NGINX brand since 2015. He works with our training department to ensure customers and partners understand how to leverage the power of NGINX to achieve enterprise‑level performance.
Presentation: Securing Applications with NGINX
Securing Applications with NGINX is an eight‑hour course for individuals who want a deep understanding of NGINX and NGINX Plus's security features. In this course you'll identify and administer client‑side and upstream encryption (SSL/TLS), configure access control (limit rates, blacklisting/whitelisting), set up authentication (HTTP Basic Auth, OAuth 2.0), and tune the NGINX proxy to have reliable, persistent, fast, and secure connections. The second half of the course explores using NGINX Plus to secure API traffic, authenticate users with OpenID Connect, and block malicious traffic with the NGINX WAF dynamic module based on ModSecurity 3.0.
Objectives
After completing this course you will know how to:
Audience Securing Applications with NGINX is intended for NGINX developers, DevOps, and administrators who want to make sure their solutions are a secure as they can be.
Prerequisites Completion of the NGINX Core course, or comparable experience.
Presentation: NGINX Advanced Load Balancing
NGINX Advanced Load Balancing is a four‑hour class for system administrators, DevOps engineers, and architects who want to deepen their understanding of NGINX load balancing.
Presentation: NGINX Advanced Caching
NGINX Advanced Caching is an four-hour course that builds on the discussion of caching in the NGINX Core course. It's a deep dive into how caching works, tools to managing your cache, techniques for tuning your cache, and methods for scaling your cache.
Director, Productivity & Quality Engineering, CloudBees
Isa started her career as a developer, but has managed Quality Engineering teams for the last nine years. She has helped companies to reach continuous delivery by improving their development, testing, and release processes through automation and risk analysis, including Spain's largest social network, Tuenti, a Rakuten video-on-demand service, the JIRA Cloud, and Infrastructure Services divisions at Atlassian and currently CloudBees. She believes in giving back to the community and is therefore a frequent speaker at testing meetups like After Test and Agile Barcelona, and she has also spoken at international conferences such as Jenkins World, UKStars, devopsdays, itSMF, and expoQA where she has also served on the selection committee.
Presentation: Testing in the Hundred Microservices World, when the Pyramid Becomes an Hourglass
Isa describes how her team went from testing monolithic applications (with its challenges) to testing integrations of hundreds of microservices. They found that a microservices architecture comes at a price: brittle, slow, and infra-dependent tests. In this session, she answers questions like: how can you have robust, fast, reliable and well-scoped tests? How can you be the first one to know about problems in production? And how can you guarantee a rollout plan that affects the fewest customers possible if something goes wrong? This session is about Isa's journey at Atlassian and CloudBees to develop a testing strategy that protected customers in the face of dozens of releases per day of different services at the same time.
Solutions Architect, AWS
Juan is a Solutions Architect on the AWS Partner Team who supports a wide range of Partners across the United States, as well as some Partners in Canada and LATAM. He has deep expertise in Media and Entertainment, Internet of Things, Mobile, Machine Learning, and Software Development. When he’s not working with Partners, he’s tinkering with hardware devices and building cool new software projects.
Presentation: Scaling your web app to new heights with AWS and NGINX
In this session we will discuss how AWS and NGINX can complement each other to create highly scalable, high performance and secure web applications. We will cover the different ways that NGINX can integrate with AWS services such as NLB, Route53 and PrivateLink to add new layers of security and functionality to your high traffic website, streaming service or IOT system.
Developer, NGINX
Dmitry is a member of the core development team at NGINX. He contributed to a variety of open source and commercial features of Nginx. Since 2017 he leads njs project (embeddable javascript interpreter). Prior to NGINX, Dmitry was developing video streaming solutions.
Presentation: NGINX JavaScript in Your Web Server Configuration
In this session Dmitry covers njs (the NGINX JavaScript module, formerly called nginScript) in depth. He explains why we created a different implementation of JavaScript and why NGINX needs a different kind of VM. He goes into detail on the execution model and interpreter. Dmitry describes how users of NGINX and NGINX Plus are using njs to solve real solve real‑world problems, but also use cases where njs might not be the best solution. He concludes with a sneak preview of future plans for njs.
Founder & CEO, OpenResty Inc.
Yichun is founder and CEO of OpenResty Inc, creator of the OpenResty open source web platform, and a contributor to the NGINX, LuaJIT, and SystemTap open source projects. He previously worked on large distributed software systems based on NGINX and OpenResty at Cloudflare, Taobao, and Yahoo! China.
Presentation: Tracing and Troubleshooting NGINX, OpenResty, and Their Backends
Got some online nginx processes eating too much memory, CPU time, or disk I/O resources? Got some very slow requests that occur randomly online, but cannot be reproduced offline? Seen some mysterious NGINX error log messages but have no clues about the actual causes? Bothered by some random nginx process crashes and core dumps in production? In this session, Yichun investigates various real‑world performance and other behavioral issues in the context of NGINX and OpenResty, and explains how to use dynamic tracing and other advanced postmortem debugging technologies to quickly pinpoint the causes online without disrupting production services.
Yichun describes and compares the advantages and disadvantages of various open source debugging frameworks like GDB, SystemTap, and BCC/eBPF, with a brief discussion of the unique challenges of tracing Docker containers in production. He then introduces the new OpenResty Trace platform which unifies these debugging technologies and improves their usability, scalability, and extensibility to a new level, especially in the context of distributed online systems like a microservices mesh or traffic gateway clusters as in a CDN network. He includes examples of writing custom tracing tools using the universal debugging languages provided by OpenResty Trace.
Yichun also uses real examples to demonstrate the use of advanced tracing tools atop OpenResty Trace for the NGINX core and the OpenResty core with LuaJIT. He covers tracing other traditional backend services running behind NGINX or OpenResty via FastCGI, uWSGI, or NGINX Unit, like PHP, Python, Perl, and Ruby. He concludes with examples of tracing data services like PostgreSQL, Memcached, and Redis accessed by NGINX, OpenResty, or their backend applications.