It is essential to understand how your system performs at different workloads to measure the impacts of changes and growth and to understand how those impacts will manifest. Measuring the performance of current workloads is not trivial and the creation of a staging environment where different workloads need to be tested has it's own set of challenges. Performing capacity planning, exploring concerns about scalability and response time and evaluating new hardware or software configurations are all operations requiring measurement and analysis in an environment appropriate to your production set up. To find bottlenecks, performance needs to be measured both at the OS layer and at the MySQL layer: an analysis of OS and MySQL benchmarking and monitoring/measuring tools will be presented, ranging from vmstat and iostat to oprofile and Poor Man Profiler, from mysqlslap to sysbench and dbt2, from INFORMATION_SCHEMA to PERFORMANCE_SCHEMA , from the analysis of query workloads with pt-query-digest to tests with pt-log-player . Various benchmark strategies will be presented for real-life scenarios, as well as tips on how to avoid common mistakes.
1 October 09:00 - 12:00 @
Senior Operational DBA, PalominoDB
René has 10 years of working experience as System, Network and Database Administrator mainly on Linux/Unix platform. In the last 4-5 years his experience was focused mainly on MySQL, working as Senior MySQL Support Engineer at Sun/Oracle and now as Senior Operational DBA at PaolominoDB. In this period he build an analytic and problem solving mindset and he is always eager to take on new challenges, especially if they are related to high performance.