PostgreSQL Scalability

The talk describes performance benchmarking results of PostgreSQL on modern Hi-End servers. The main attention was paid to the locks for shared data access and associated bottlenecks. The testing propose was to test the linear read scalability limits with an increase of cores number allocated for PostgreSQL. Testing was performed for different postgres versions (9.4, 9.5, 9.6) to check new features designed to increase performance on multiprocessing architectures.

Speeding up query execution in PostgreSQL using LLVM JIT compiler

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.

New B-tree features

B-tree is the most widely used index type in PostgreSQL. This data structure and concerned algorithms are developed about forty years ago. But there is still an area for optimisations. In this presentation I'm going to talk about B-tree data structure, and its features important for the optimal index usage. Furthermore, I'll present a couple of new features which are expected to be included in PostgreSQL 9.6 release.

PostgreSQL in Korea

The Korean PostgreSQL User Group has been relatively small and inactive for many years. However, recently things are changing in Korea. Companies are seeking to alternatives for their expensive proprietary RDBMS in order to cut their TCO. And the government institutes also participate in this trend. We, Bitnine, are leading these changes in Korea. We launched the first version of our PostgreSQL solution, Agens SQL in 2015. We are translating the PostgreSQL documentation into Korean and operating the PostgreSQL User Group. And we are trying to contribute the PostgreSQL Global Development Group. Also, the first Korean PostgreSQL Conference will be hold in 2016. We will lead the organization of this conference. In this talk, we will present the current status of the Korean PostgreSQL User Group and the PostgreSQL DBMS market in Korea. And we also present our activities in Korea and introduce our successful migration cases of the proprietary RDBMS into PostgreSQL.