Azure HorizonDB is a new PostgreSQL service that improves the OLTP performance and reliability of upstream PostgreSQL through co‑design. By evolving both Azure’s infrastructure and PostgreSQL itself, HorizonDB enables the two to work together more efficiently. This talk introduces the architecture of HorizonDB and explores several key design and implementation decisions that enable more scalable, reliable PostgreSQL in Azure. Read More

TopK is a search engine built from the ground up for unstructured retrieval. It combines dense/sparse/multi-vector search, lexical search, powerful filtering, and customizable scoring capabilities in a single, cloud-native system that scales to billions of documents with high ingest throughput and O(10ms) p99 query latencies. In this talk, I'll focus on how TopK is designed on a high-level, including our... Read More

Amazon Aurora DSQL is a distributed SQL database, designed to make it easier to build reliable, scalable, and resilient applications in the cloud, from small prototypes to massive global applications. In this talk, we'll dive into the architecture of Aurora DSQL, looking at how we handle reads, writes, and commits, and talking through the design decisions we made along the... Read More

In this talk, we'll first give an overview of the Oxla analytical database and how it fits into what we do at Redpanda. Then we'll dive into one of the more interesting aspects of Oxla internals: combating memory bandwidth performance bottlenecks in GROUP BY and JOIN via a specialized, custom hashmap implementation. Read More

Modern database management systems (DBMSs) have evolved to support increasingly sophisticated data-intensive applications, at the cost of substantial complexity to configure them for two reasons. First, DBMSs expose a vast configuration space with trillions of possibilities that encompass system knobs, physical design (e.g., indexes), and query options, amongst others. Second, these applications are constantly evolving with changes in data access... Read More

Database management systems (DBMSs) are the foundation of modern data-intensive applications. But as more features are developed to support new workloads, they become increasingly complex and difficult to configure. Thus, researchers have invested decades of effort into autonomous DBMS configuration. Recent advances in machine learning (ML) have produced tools that outperform unassisted experts in real-world deployments. However, these tools are... Read More

Modern data lakehouses promise unified batch and streaming processing, yet their storage layer remains inherently batch-oriented—optimized for large, immutable files. This mismatch forces streaming workloads to rely on external systems (e.g., Kafka), while analytical queries operate on stale snapshots, breaking end-to-end freshness. In this talk, I’ll present Apache Fluss (incubating), a lakehouse-native streaming storage system designed to bridge this gap.... Read More

As organizations build their data lakehouses on Apache Iceberg, the primary challenge shifts from managing individual files to orchestrating a cohesive ecosystem of tables. How can you guarantee consistency and enable complex operations when multiple data engines—like Spark, Trino, and Flink—need to interact with the same data concurrently? The answer lies in a standardized service layer, defined by the Iceberg... Read More

XTDB is a SQL database that challenges long held assumptions about how data mutates in databases. Instead of UPDATEs and DELETEs destroying information, or forcing developers to implement archival strategies, XTDB preserves history automatically without leaving such decisions to developers. Additionally XTDB implements a variation of the SQL:2011 syntax to simplify time-travel queries across two dimensions of time: system-time (what... Read More

In this presentation, we are going to talk about Lakebase, a vision for the next generation of cloud-based agent-enabled OLTP systems. After the dramatic transformation of analytics (OLAP) platforms over the past one to two decades—with innovations such as columnar storage, vectorized execution, streaming, and the Lakehouse architecture—we argue that databases (OLTP) are now at an inflection point. We will... Read More