PgConf.Russia 2016

Enterprises need enterprise-level databases. The existing Postgres clustering solutions are not supported by the community. Postgres needs a community-supported cluster solution. There have been multiple attempts like Postgres-XC/XL, but they are still being developed separately and have low chance to be accepted by the community. Other solutions, like pg_shard, plproxy, FDW-based, etc. lack the notion of global transactions. We developed a Distributed Transaction Manager (DTM) as a Postgres extension to achieve global consistency over a number of Postgres instances. To demonstrate the capabilities of the DTM we present examples of distributed transaction processing using pg_shard and postgres_fdw. We hope that the proposed approach will be included into Postgres 9.6. This will make the development of the clustering solutions easier for all interested parties.

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.

PostgreSQL includes several index types: GiST, SP-GiST, GIN, and of course, the regular B-tree. DBAs are familiar with using each of these for specific use cases, GIN for full-text search, GiST for geometrical data, and so on, but how do they work internally? What makes them suitable for the cases they're typically used for?

In this presentation, I will walk through the internal structure of each of these index types, explaining what strengths and weaknesses each one of them have.

We'll discuss how does Linux work with virtual memory. The following topics will be covered: * x86-64 page table, context switch and page fault; * internals of virtual memory management (VMM) in Linux; * page eviction methods in Linux, page cache and anonymous pages; * huge and gigantic pages, transparent huge pages; * how mmap(2) works and what madvise(2), msync(2) etc. provide; * why large databases don't use mmap(2), but rather implement buffer pool on their own; * ans surely how to tune Linux VMM using sysctl.