PgConf.Russia 2016

Currently, PostgreSQL uses the interpreter to execute SQL-queries. This yields an overhead caused by indirect calls to handler functions and runtime checks, which could be avoided if the query were compiled into the native code "on-the-fly" (i.e. JIT-compiled): at a run time the specific table structure is known as well as data types used in the query. This is especially important for complex queries, which performance is CPU-bound. At the moment there are two major projects that implement JIT-compilation in PostgreSQL: a commercial database Vitesse DB and an open-source project PGStorm. The former uses LLVM JIT to achieve up to 8x speedup on selected TPC-H benchmarks, while the latter JIT-compiles the query using CUDA and executes it on GPU, which allows to speed up execution of specific query types by an order.

Our work is dedicated to adding support for SQL query JIT-compilation to PostgreSQL using LLVM compiler infrastructure. In the presentation we'll discuss how JIT-compilation can be used to speed up various stages of query execution in PostgreSQL, and the specifics of translating an SQL query into LLVM bitcode to achieve good performing native code. Also we'll present preliminary results for our JIT-compiler on TPC-H benchmark.

When new versions of Postgres are released most of the attention is focused on new features. Inevitably a release note claiming speed improvements seems relatively mundane and doesn't provide the compelling argument for upgrading. However the reality is that these speed improvements represent pain points that have been identified and solved.

Reviewing the changes to the sort code in Postgres over the last 10 years clearly shows the kinds of problems users have run into. As usage patterns changed over years, databases scaled up, and hardware changed new problems arose and drove further development to solve them.

Upcoming changes in 9.5 and 9.6 will dramatically change the experience further. Making sorting UTF8 and other encodings less of a problem and handling scaling to larger machines with many processors and memory cache more effectively.

Schema-less is definitely a trend in the data storage nowadays, and it's not only about NoSQL, but also about traditional RDBMS. Many relational databases (e.g. PostgreSQL, Oracle, db2, Mysql) allow to storing data in the schema-less json format and use their own more or less unique way to do that.

This talk contains two parts:

• Comparison of the json support in PostgreSQL and different relational databases, namely Mysql, Oracle, db2, MSSql in terms of supported features, functions and so on.
• Performance benchmarks for databases with the advanced json support, namely PostgreSQL and Mysql, and the MongoDB on different workload types and configurations.

Since its launch in 2008, Zalando has grown with tremendous speed. The road from startup to multinational corporation has been full of challenges, especially for Zalando's technology team. Distributed across Berlin, Helsinki, Dublin and Dortmund — and nearly 900 professionals strong — Zalando Technology still plans to expand by adding 1,000 more developers through the end of 2016. This rapid growth has showed us that we need to be very flexible about developing processes and organizational structures, so we can scale and experiment. In March 2015, our team adopted Radical Agility: a tech management strategy that emphasizes Autonomy, Purpose, and Mastery, with trust as the glue holding it all together. To make autonomy possible, teams can now choose their own technology stacks for the products they own. Microservices, speaking with each other using RESTful APIs, promise to minimize the costs of integration between autonomous teams. Isolated AWS accounts, run on top of our own open-source Platform as a Service (called STUPS.io), give each autonomous team enough hardware to experiment and introduce new features without breaking our entire system.

One small issue with having microservices isolated in their individual AWS accounts: Our teams keep local data for themselves. In this environment, building an ETL process for data analyses, or integrating data from different services, becomes quite challenging. PostgreSQL's new logical replication features, however, now make it possible to stream all the data changes from the isolated databases to the data integration system so that it can collect this data, represent it in different forms, and prepare it for analysis.

In this talk, I will discuss Zalando's open-source data collection prototype, which uses PostgreSQL's logical replication streaming capabilities to collect data from various PostgreSQL databases and recreate it for different formats and systems (Data Lake, Operational Data Store, KPI calculation systems, automatic process monitoring). The audience will come away with new ideas for how to use Postgres streaming replication in a microservices environment.