Agenda:

6.00-6.30: Networking & Snacks

6.30-7.30: Talks

Richard Artoul (WarpStream) -- Beyond Tiered Storage: Zero Disk Architectures for Kafka

Yingjun Wu (RisingWave) -- S3 as the state store for stream processing systems

Yang Yang (Uber) and Zhifeng Chen (Uber) – Real-time message delivery with uForwarder

Matthew Penaroza (PingCAP) -- How to choose a database: an overview of major databases

7.30-8.00: Q&A

Abstracts and Speaker Bios

Richard Artoul -- Beyond Tiered Storage: Zero Disk Architectures for Kafka

Abstract: In this talk, Richard Artoul will discuss some of the limitations of tiered storage in Apache Kafka. He'll then present a different approach, WarpStream's "zero disk" architecture which separates storage and compute entirely, with zero local disks, while still providing the full semantics of Kafka.

Bio: Richard Artoul is the co-founder and CEO of WarpStream, a drop-in replacement for Apache Kafka built directly on top of object storage with zero disks. Before WarpStream, he developed Datadog's columnar event store Husky.

Yingjun Wu - S3 as the state store for stream processing systems

Abstract: S3 is cheap; but S3 is slow. Stream processing systems want to maintain internal states at low cost but cannot tolerate high latency. How could we build a stream processing system on top of S3? I'll tell you what we learned over the last three years.

Bio: Yingjun Wu is the founder and CEO of RisingWave Labs. Before starting the company, Yingjun was a software engineer at the Redshift team, Amazon Web Services, and a researcher at the Database group, IBM Almaden Research Center. Yingjun received his PhD degree from National University of Singapore, and was a visiting PhD at Carnegie Mellon University. He has been working in the field of stream processing and database systems for over a decade.

Yang Yang and Zhifeng Chen – Real-time message delivery with uForwarder

Abstract: uForwarder is a proxy that transfers messages from Kafka to consumer services through RPC protocol, and aims to reliably deliver fresh data in real-time at scale.

Bio: Yang Yang is a Sr Staff Software Engineer at Uber, and she leads Uber's Streaming Data (Kafka) and Flink team. She focuses on building a highly scalable and reliable real-time data system at scale for thousands of engineers and data scientists at Uber.
Zhifeng Chen is a Sr Staff Engineer and Tech Lead Manager on Kafka Messaging Platform Team at Uber, also co-authors uForwarder.

Matthew Penaroza -- How to choose a database: an overview of major databases

Abstract: Large enterprises like LinkedIn, Databricks, and Pinterest are building fault-tolerant applications that can process hundreds of TBs of data for real-time data serving. This talk simplifies the database landscape from SQL and NoSQL to Distributed SQL, discussing how/why these enterprises picked TiDB to power their production workloads.

Bio: Before becoming a software engineer, Matthew Penaroza was a professional Dota 2 player. Now, he is a Senior Solutions Architect who works with large companies like AirBnb and LinkedIn to design their data infrastructure.