title

text

Fabio Telles Rodriguez
Fabio Telles Rodriguez Timbira
18:00 04 February
45 мин

High Concurrency with Postgres: the Bank of Brazil in real life

Challenges and solutions found in documents dematerialization and bank cheque processing system used in the Bank of Brazil.

Слайды

Видео

Другие доклады

  • Дмитрий Воронин
    Дмитрий Воронин ОАО "НПО РусБИТех"
    22 мин

    The base version of DBMS PostgreSQL can register events bellow: - connect and disconnect - denial of access with date, time and user's name.

    Requirements guidelines for audit subsystem is much wider possibilities basic version of database PostgreSQL.

    The RusBITech company holds the necessary improvements PostgreSQL database to enhance it's functionality.

    A result of improvements audit subsystem of PostgreSQL database as part of the operating system «Astra Linux Special Edition» further enables registration:

    • The creation and destruction of database objects;
    • Changes to the rules of access control;
    • Both failures and successful attempts to access the database objects;
    • Changes to the powers and status of subjects access objects access.

    For all events are specified: - date and time; - The user performing the action of the registrant; - The object on which the action is carried out; - Type of event; - The result of the operation.

    Audit subsystem of modified PostgreSQL is integrated into a centralized audit system OS «Astra Linux Special Edition». Provided the rules setting without stopping the logging (restarting) database.

  • Илья Космодемьянский
    Илья Космодемьянский Data Egret
    180 мин
  • Ivan Goncharov
    Ivan Goncharov IBM
    45 мин

    Why IBM Power 8 is optimal platform for PostgreSQL

    Architecture features of IBM Power 8 allowing to gain high performance in comparison with x86_64. CPU, memory, IO etc. Experience of real benchmarking.

  • D
    Dmitry Melnik ИСП РАН
    22 мин

    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.